Papyrus

Discovery

Fresh from arXiv + Hugging Face, matched to tags in your library. Papers you've already added are filtered out; un-acted items age out after 30 days.

Today · Jul 9, 202649

HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better

huggingface ▲ 4 Published 2026-07-05 · Gengluo Li, Xingyu Wan, Shangpin Peng et al.
#pretraining
🏢 Tencent
Open ↗

RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules

huggingface ▲ 1 Published 2026-06-30 · Ádám Kovács, Nadia Verdha, Gábor Recski
#nlp
🎓 KR Labs
Open ↗

The Poisoned Chalice of LLM Evaluation Report

arxiv Published 2026-07-08 · Jonathan Katzy, Ali Al-Kaswan, Razvan Mihai Popescu et al.
#pretraining
Open ↗

GIFT: Geometry-Informed Low-precision Gradient Communication for LLM Pretraining

arxiv Published 2026-07-08 · Jieying Wang, Shuyuan Fan, Mingkai Zheng et al.
#pretraining
Open ↗

TimEE: End-to-end Time Series Classification via In-Context Learning

arxiv Published 2026-07-08 · Jaris Küken, Shi Bin Hoo, Martin Mráz et al.
#pretraining
Open ↗

Infinite Worlds with Versatile Interactions

huggingface ▲ 18 Published 2026-07-08 · Zelin Gao, Qiuyu Wang, Jiapeng Zhu et al.
#pretraining
Open ↗

SonoRank: Towards Calibration-Free Real-Time Finger Flexion Detection from Forearm Ultrasound Sequences

arxiv Published 2026-07-08 · Dean Zadok, Alon Wolf, Alex M. Bronstein et al.
#pretraining
Open ↗

Embedded Blockchain Infrastructure Management (eBIM): A RISC-V-Empowered Hardware--Software Co-Design Framework Towards Trustworthy Blockchain

arxiv Published 2026-07-08 · Qinglin Yang, Yuan Liu, Yaoyao Zhang et al.
#foundational
Open ↗

RL Post-Training Builds Compositional Reasoning Strategies

arxiv Published 2026-07-08 · Azwar Abdulsalam, Nishil Patel, Andrew Saxe
#pretraining
Open ↗

DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation

arxiv Published 2026-07-08 · Jordan Painter, Dipankar Srirag, Adarsh Kappiyath et al.
#pretraining
Open ↗

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

huggingface ▲ 32 Published 2026-07-08 · Shuailei Ma, Jiaqi Liao, Xinyang Wang et al.
#pretraining
Open ↗

How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization

arxiv Published 2026-07-08 · Xinyi Wu, Siyuan Liu, Ali Jadbabaie
#transformers
Open ↗

Any-Dimensional Learning by Sampling

arxiv Published 2026-07-08 · Eitan Levin, Venkat Chandrasekaran
#transformers
Open ↗

Co-LMLM: Continuous-Query Limited Memory Language Models

arxiv Published 2026-07-08 · Yair Feldman, Linxi Zhao, Nathan Godey et al.
#pretraining
Open ↗

Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning

huggingface ▲ 59 Published 2026-07-08 · Chen Tang, Yizhou Wang, Jianyu Wu et al.
#foundational
🎓 shanghai ailab
Open ↗

Bibby AI: An Editor-Native Agentic Platform for Academic Research, Writing, and Publishing

huggingface ▲ 1 Published 2026-07-02 · Nilesh Jain
🎓 Bibby Research Labs
Open ↗

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration

huggingface ▲ 9 Published 2026-07-05 · Hairui Zhu, Yiying Yang, Tengjin Weng et al.
Open ↗

Where to cut, how deep: BPE and Unigram-LM on chemistry SMILES

huggingface ▲ 2 Published 2026-07-05 · Hunter Heidenreich
Open ↗

SiamJEPA: On the Role of Siamese Student Encoders in JEPA

huggingface ▲ 0 Published 2026-07-03 · Makoto Yamada
Open ↗

Rank-Then-Act: Reward-Free Control from Frame-Order Progress

huggingface ▲ 6 Published 2026-07-01 · Yuriy Maksyuta, George Bredis, Ruslan Rakhimov et al.
🏢 T-Tech
Open ↗

SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review

huggingface ▲ 4 Published 2026-07-06 · Ruoyu Wang, Jierun Chen, Shaowei Wang et al.
🏢 SWE-Lego
Open ↗

Attending to Multimodal Generation One Token at a Time

huggingface ▲ 6 Published 2026-07-03 · Varun Gupta, Vineet Gandhi, Makarand Tapaswi
🎓 Katha AI Lab @ IIIT Hyderabad
Open ↗

SceneFrom3D: Geometry-Conditioned Outdoor 3D Scene Generation via View Scheduling with Object-Level Control

huggingface ▲ 2 Published 2026-07-04 · Geonung Kim, Jeongeun Park, Nuri Ryu et al.
🎓 POSTECH Computer Graphics Lab
Open ↗

VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech

huggingface ▲ 0 Published 2026-07-02 · Yi-Cheng Lin, Yusuke Hirota, Sung-Feng Huang et al.
Open ↗

Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training

huggingface ▲ 3 Published 2026-07-01 · Zijian Zhang, Rizhen Hu, Athanasios Glentis et al.
Open ↗

LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL

huggingface ▲ 18 Published 2026-07-04 · Yujin Kim, Namgyu Ho, Sangmin Hwang et al.
🎓 KAIST AI
Open ↗

Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers

huggingface ▲ 1 Published 2026-06-29 · Anh Nguyen, Ngan Nguyen, Duc Vu et al.
Open ↗

JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications

huggingface ▲ 13 Published 2026-06-28 · Oxygen AIIC, Chan Long, Chao Liu et al.
Open ↗

WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence

huggingface ▲ 4 Published 2026-07-06 · Xiangyu Han, Mengyu Yang, Jiaqi Li et al.
🏢 NVIDIA
Open ↗

Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation

huggingface ▲ 37 Published 2026-07-07 · Hongyu Qu, Jianzhe Gao, Xiaobin Hu et al.
Open ↗

RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies

huggingface ▲ 4 Published 2026-07-06 · Tianxing Chen, Yue Chen, Zixuan Li et al.
🏢 RoboDojo-Benchmark
Open ↗

Teaching LLMs a Low-Resource Language: Enhancing Code Completion in Pharo

huggingface ▲ 1 Published 2026-07-05 · Kilian Kier, Alessandro Giagnorio, Omar AbedelKader et al.
Open ↗

FedMark-FM: Auditable, Risk-Adjusted Data Markets for Federated Foundation-Model Adaptation

arxiv Published 2026-07-08 · Phat T. Tran-Truong, Xuan-Bach Le, Minh Nhat Nguyen
Open ↗

Generating Personalized Lower-Limb Kinematics Across Walking Speeds Using Subject-Conditioned Diffusion

arxiv Published 2026-07-08 · Diya Dinesh, Adrian Krieger, Changseob Song et al.
Open ↗

An analytical solution of a quantum system with non-Markovian behavior: The Bixon-Jortner system in time domain

arxiv Published 2026-07-08 · Osman Cevheroğlu, Arkadaş Özakın
Open ↗

AA-ViT: Anatomically Aware Vision Transformer with Structural and Frequency Guidance for Contrast Enhanced Brain MRI Synthesis

arxiv Published 2026-07-08 · Talha Meraj, Tom Flannery, Charlie Cummins et al.
Open ↗

PALS: Percentile-Aware Layerwise Sparsity for LLM Pruning

arxiv Published 2026-07-08 · Yazdan Jamshidi, Alexey Shvets
Open ↗

On Computing Minimum Wheeler DFA From Their Language

arxiv Published 2026-07-08 · Ruben Becker, Davide Cenzato, Nicola Prezza et al.
Open ↗

Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning

arxiv Published 2026-07-08 · Maximilian Andreas Hoefler, Karsten Mueller, Wojciech Samek
Open ↗

On the Robustness in Data-Driven Nonlinear Optimal Control: From Stability to Optimality

arxiv Published 2026-07-08 · Yicheng Lin, Zhisheng Duan, Tianzhi Li et al.
Open ↗

Multi-Class vs. Multi-Label BERT for CVE-to-CWE Mapping: How Taxonomy Structure Shapes the Errors

arxiv Published 2026-07-08 · Ana Schwengber Kelm, Christian Bockermann, Jörg Frochte
Open ↗

Vacuum polarization and renormalized stress-energy tensor of spherical thin shells

arxiv Published 2026-07-08 · Julio Arrechea, Cormac Breen, Adrian Ottewill et al.
Open ↗

MLIP Studio: An Open Platform for Interactive Benchmarking and Atomistic Simulations Using Machine Learning Interatomic Potentials

arxiv Published 2026-07-08 · Manas Sharma, Sudeep Punnathanam, Ananth Govind Rajan
Open ↗

Analysis of polarization drift of optical signals over deployed aerial-inground fiber connections

arxiv Published 2026-07-08 · Aneesh Ramaswamy, Nageswara S. V. Rao, Joseph C. Chapman et al.
Open ↗

ATLAS: Automated HLS for DL-Optimized FPGAs

arxiv Published 2026-07-08 · Ruthwik Reddy Sunketa, Aman Arora
Open ↗

Six-Pole Dual-band Bandpass Filter for WiMAX Applications

arxiv Published 2026-07-08 · Halimat Olamide Yusuf, Augustine O. Nwajana
Open ↗

MedPMC: A Systematic Framework for Scaling High-Fidelity Medical Multimodal Data for Foundation Models

arxiv Published 2026-07-08 · Hyunjae Kim, Dain Kim, Pan Xiao et al.
Open ↗

The Key to Going Linear: Analysis-Driven Transformer Linearization

arxiv Published 2026-07-08 · Anna Kuzina, Paul N. Whatmough, Babak Ehteshami Bejnordi
Open ↗

Yesterday · Jul 8, 202657

From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models

arxiv Published 2026-07-07 · Zanyi Wang, Xin Lin, Haodong Li et al.
#pretraining
Open ↗

Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion

arxiv Published 2026-07-07 · Shervin Khalafi, Igor Krawczuk, Sergio Rozada et al.
#transformers
Open ↗

Rethinking Indic AI from a Lens of Cultural Heritage Preservation

arxiv Published 2026-07-07 · Aparna Madva, Sharath Srivatsa, Srinath Srinivasa et al.
#nlp
Open ↗

Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs

arxiv Published 2026-07-07 · Zhenyu Liu, Yunxin Li, Xuanyu Zhang et al.
#nlp
Open ↗

XRFormer: Multiscale Tokenization for XRF Representation Learning

arxiv Published 2026-07-07 · Sofiane Daimellah, Sylvie Le Hégarat-Mascle, Clotilde Boust
#pretraining
Open ↗

From Foundation to Application: Improving VLA Models in Practice

huggingface ▲ 12 Published 2026-07-06 · Wei Wu, Fangjing Wang, Fan Lu et al.
#pretraining
🏢 Robbyant
Open ↗

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

huggingface ▲ 21 Published 2026-07-02 · Xiang Hu, Xinyu Wei, Hao Gu et al.
#pretraining
🏢 Tencent Hunyuan
Open ↗

ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation

arxiv Published 2026-07-07 · Tianjiao Yu, Xinzhuo Li, Yifan Shen et al.
Open ↗

Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation

arxiv Published 2026-07-07 · Jiaming Liu, Qingpo Wuwu, Nuowei Han et al.
Open ↗

Vision as Unified Multimodal Generation

huggingface ▲ 22 Published 2026-07-07 · Xiaoyang Han, Jianhua Li, Kewang Deng et al.
🏢 SenseNova
Open ↗

RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation

huggingface ▲ 7 Published 2026-07-07 · Haoyu Zhao, Xingyue Zhao, Hangyu Li et al.
Open ↗

Quantum Channel Polynomial Processing

arxiv Published 2026-07-07 · Tianhan Liu, Fedor Simkovic, Martin Leib
Open ↗

Unsupervised Domain Adaptation for Calcification Classification in Mammography Across Multi-Site Datasets

arxiv Published 2026-07-07 · Xuan Liu, Derek L. Nguyen, Emily C. Barre et al.
Open ↗

The Right Space for Dynamics: Numerics with Diffeomorphism Equivariance

arxiv Published 2026-07-07 · Wolf-Juergen Beyn, Michail E. Kavousanakis, Yannis G. Kevrekidis
Open ↗

CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models

arxiv Published 2026-07-07 · He Liang, Chenyang Ma, Yiming Zhang et al.
Open ↗

DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression

arxiv Published 2026-07-07 · Anna Cordoba, Adam Puente Tercero, Nerea Angulo Hijo et al.
Open ↗

RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models

arxiv Published 2026-07-07 · Qian Sun, Yong-Ming Tian, Jia-Wei Huang et al.
Open ↗

Hypothesis-driven Model Expansion under Uncertainty for Open-World Robot Planning

arxiv Published 2026-07-07 · Anxing Xiao, Hanbo Zhang, Tianrun Hu et al.
Open ↗

Constrained Capacity Analysis for Faster-than-Nyquist Signaling

arxiv Published 2026-07-07 · Zichao Zhang, Melda Yuksel, Gokhan M. Guvensen et al.
Open ↗

Holographic Tests of the $μ$ Ensemble

arxiv Published 2026-07-07 · Nikolay Bobev, Fridrik Freyr Gautason, Jesse van Muiden
Open ↗

Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation

arxiv Published 2026-07-07 · Anna Córdoba, Adam Puente Tercero, Nerea Angulo Hijo et al.
Open ↗

EgoPolice: A Benchmark for Egocentric Video Understanding in High-Stakes Police Body-Worn Camera Footage

arxiv Published 2026-07-07 · Max Gonzalez Saez-Diez, Jihoon Chung, Adam D. Wolsky et al.
Open ↗

WordVoice: Explicit and Decoupled Multi-Dimensional Word-Level Control for LLM-Based TTS

arxiv Published 2026-07-07 · Sihang Nie, Jinxin Ji, Xiaofen Xing et al.
Open ↗

TILDE: TILt-based Distributional Erasure for Concept Unlearning

arxiv Published 2026-07-07 · Naveen George, Naoki Murata, Yuhta Takida et al.
Open ↗

Understanding Small-Signal Impedance Matrices in Different Reference Frames

arxiv Published 2026-07-07 · J. Pedra
Open ↗

Economised path integrals

arxiv Published 2026-07-07 · Zezhu Zeng, David E. Manolopoulos
Open ↗

Asymptotic analysis of N-elliptic localized solutions for the Fokas--Lenells equation

arxiv Published 2026-07-07 · Wang Tang, Guo-Fu Yu
Open ↗

Precise Video-to-Audio Generation with Cross-Modal Alignment in Latent Space

arxiv Published 2026-07-07 · Thanh V. T. Tran, Ngoc-Son Nguyen, Luong Tran et al.
Open ↗

Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator

huggingface ▲ 0 Published 2026-07-06 · Zihan Wang, Seungjun Lee, Yinghao Xu et al.
🎓 National University of Singapore
Open ↗

PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages

huggingface ▲ 5 Published 2026-07-06 · Daryna Dementieva, Nikolay Babakov, Kathy Hämmerl et al.
🏢 Natural Language Processing @ TUM
Open ↗

Gemma 4 Technical Report

huggingface ▲ 36 Published 2026-07-01 · Gemma Team, Sherif El Abd, Vaibhav Aggarwal et al.
🏢 Google
Open ↗

When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers

huggingface ▲ 4 Published 2026-06-30 · Yushi Sun, Bowen Cao, Wai Lam
🏢 Tencent
Open ↗

TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

huggingface ▲ 10 Published 2026-07-06 · Yuhang Zhou, Kai Zheng, Haoling Li et al.
🏢 Tencent Hunyuan
Open ↗

3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance

huggingface ▲ 4 Published 2026-06-29 · Dongyoon Hwang, Byungkun Lee, Dongjin Kim et al.
🎓 KAIST AI
Open ↗

MentalThink: Shaping Thoughts in Mental SVG World

huggingface ▲ 9 Published 2026-07-02 · Kangheng Lin, Jisheng Yin, Dingming Li et al.
Open ↗

CGGS: Consistency-Augmented Geometric Gaussian Splatting for Ego-centric 3D Scene Generation

huggingface ▲ 1 Published 2026-07-03 · Zhenyu Sun, Xiaohan Zhang, Qi Liu et al.
Open ↗

Layer-wise Cross-Lingual Depression Detection from Speech: Analysis with Contrastive Alignment

huggingface ▲ 1 Published 2026-07-02 · Anisha Pattanayak, Hanie Kang, Huang-Cheng Chou et al.
Open ↗

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

huggingface ▲ 7 Published 2026-07-05 · Xin Cheng, Xingkai Yu, Chenze Shao et al.
🏢 DeepSeek
Open ↗

MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs

huggingface ▲ 2 Published 2026-06-28 · Yuxuan Fan, Gyusik Seo, Jing Hao et al.
🎓 Nanyang Technological University Singapore
Open ↗

Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model

huggingface ▲ 2 Published 2026-07-02 · Xinyin Ma, Julius Berner, Chao Liu et al.
🏢 NVIDIA
Open ↗

Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning

huggingface ▲ 16 Published 2026-07-02 · Wenzheng Zeng, Siyi Jiao, Chen Gao et al.
🎓 National University of Singapore
Open ↗

Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models

huggingface ▲ 2 Published 2026-07-06 · Julian Killingback, Varad Ingale, Hamed Zamani et al.
🎓 University of Massachusetts Amherst
Open ↗

TREK: Distill to Explore, Reinforce to Refine

huggingface ▲ 6 Published 2026-07-05 · Yuanda Xu, Zhengze Zhou, Kayhan Behdin et al.
Open ↗

SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models

huggingface ▲ 1 Published 2026-07-06 · Changti Wu, Bin Yu, Zhaolong Shen et al.
🎓 Zhongguancun Academy
Open ↗

SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe

huggingface ▲ 14 Published 2026-07-02 · Yifei Shen, Bo Li, Xinjie Zhang
🎓 LMMs-Lab
Open ↗

AlayaWorld: Long-Horizon and Playable Video World Generation

huggingface ▲ 49 Published 2026-07-06 · AlayaWorld Team, Kaipeng Zhang, Chuanhao Li et al.
Open ↗

Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding

huggingface ▲ 5 Published 2026-07-06 · Yonggan Fu, Lexington Whalen, Abhinav Garg et al.
🏢 NVIDIA
Open ↗

RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

huggingface ▲ 7 Published 2026-07-06 · Haoyu Zhao, Xingyue Zhao, Siteng Huang et al.
Open ↗

Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory

huggingface ▲ 18 Published 2026-07-05 · Chang Nie, Jiaju Wei, Junlan Feng et al.
🎓 Nanjing University
Open ↗

GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks

huggingface ▲ 4 Published 2026-07-05 · Kaiyuan Chen, Shuangyu Xie, Letian Fu et al.
🏢 UC Berkeley
Open ↗

ACID: Action Consistency via Inverse Dynamics for Planning with World Models

huggingface ▲ 13 Published 2026-07-01 · Gawon Seo, Dongwon Kim, Suha Kwak
🎓 Pohang University of Science and Technology
Open ↗

SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference

huggingface ▲ 7 Published 2026-06-29 · Amirhossein Abaskohi, Giuseppe Carenini, Peter West et al.
🏢 Microsoft
Open ↗

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

huggingface ▲ 2 Published 2026-06-26 · Zixin Ding, Shaghayegh Emami, Giovanna Salvi et al.
🎓 University of Chicago
Open ↗

Jul 7, 202657

GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation

huggingface ▲ 28 Published 2026-07-01 · GigaWorld Team, Angyuan Ma, Boyuan Wang et al.
#pretraining
🏢 GigaAI
Open ↗

OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers

huggingface ▲ 27 Published 2026-07-03 · Siyuan Li, Jiabao Pan, Yumou Liu et al.
#pretraining
🎓 OpenDataLab
Open ↗

EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments

huggingface ▲ 5 Published 2026-07-06 · Deyao Zhu, Xin Zhou, Shengling Qin et al.
#pretraining
🏢 ByteDance Seed
Open ↗

ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization

arxiv Published 2026-07-06 · Mahnoor Shahid, Hannes Rothe
#foundational
Open ↗

Probing Geospatial SSL Representations with Environmental Signals

arxiv Published 2026-07-06 · Rohita Mocharla, Vishal M. Patel
#pretraining
Open ↗

Vision Pretraining for Dense Spatial Perception

huggingface ▲ 21 Published 2026-07-06 · Zelin Fu, Bin Tan, Changjiang Sun et al.
#pretraining
🏢 Robbyant
Open ↗

SalAngaBhava: A Sinhala Market Dataset for Aspect-based Sentiment Analysis

arxiv Published 2026-07-06 · Lakshani Galwatta, Nisansa de Silva, Sarangi Aththanayake et al.
#nlp
Open ↗

How Much is Left? LLMs Linearly Encode Their Remaining Output Length

arxiv Published 2026-07-06 · Mohamed Amine Merzouk, Dmitri Carpov, Mirko Bronzi et al.
#transformers
Open ↗

Generated Contents Enrichment

huggingface ▲ 1 Published 2026-06-29 · Mahdi Naseri, Jiayan Qiu, Zhou Wang
🎓 University of Waterloo
Open ↗

Measuring the Gap Between Human and LLM Research Ideas

huggingface ▲ 8 Published 2026-06-30 · Ziyu Chen, Yilun Zhao, Arman Cohan
🎓 Yale NLP Lab
Open ↗

Teaching LLMs to Recommend and Defer in Underrepresented Epilepsy Care

huggingface ▲ 2 Published 2026-06-29 · Shreyas Rajesh, Kartik Sharma, Tonmoy Monsoor et al.
🎓 University of California, Los Angeles
Open ↗

Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction

huggingface ▲ 3 Published 2026-07-01 · Mingzhe Du, Luu Anh Tuan, Tianyi Wu et al.
Open ↗

ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes

huggingface ▲ 33 Published 2026-07-04 · Qihao Zhao, Yangyu Huang, Yalun Dai et al.
🏢 Microsoft
Open ↗

Wan-Streamer v0.2: Higher Resolution, Same Latency

huggingface ▲ 17 Published 2026-07-04 · Lianghua Huang, Zhi-Fan Wu, Yupeng Shi et al.
🏢 Wan-AI
Open ↗

Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification

huggingface ▲ 3 Published 2026-07-03 · Yunhao Feng, Ruixiao Lin, Ming Wen et al.
🏢 Ant Group
Open ↗

ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog

huggingface ▲ 36 Published 2026-07-04 · Lingao Xiao, Yalun Dai, Yangyu Huang et al.
🏢 Microsoft
Open ↗

PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction

huggingface ▲ 2 Published 2026-07-02 · Zhuoqun Li, Boxi Cao, Jiawei Chen et al.
Open ↗

Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization

huggingface ▲ 0 Published 2026-07-04 · Ryota Komatsu, Kota Kawakita, Takuma Okamoto et al.
Open ↗

UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning

huggingface ▲ 41 Published 2026-07-04 · Niu Lian, Alan Chen, Zhehao Yu et al.
Open ↗

Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models

huggingface ▲ 1 Published 2026-07-05 · Hongyu Li, Wanjia Fu, Xiaoyan Cong et al.
🎓 Brown University
Open ↗

PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation

huggingface ▲ 0 Published 2026-07-02 · Ebenezer Tarubinga
🏢 Ebenworks Systems
Open ↗

Multiplayer Interactive World Models with Representation Autoencoders

huggingface ▲ 4 Published 2026-07-05 · Anthony Hu, Václav Volhejn, Adrien Ramanana Rahary et al.
Open ↗

LLM-as-a-Verifier: A General-Purpose Verification Framework

huggingface ▲ 5 Published 2026-07-05 · Jacky Kwok, Shulu Li, Pranav Atreya et al.
Open ↗

EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots

huggingface ▲ 20 Published 2026-07-01 · Heqing Yang, Yang Yi, Liyao Wang et al.
Open ↗

InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization

huggingface ▲ 13 Published 2026-07-05 · Haoxiang Ma, Junhao Cai, Xiaoxu Xu et al.
Open ↗

GORGO: Online Tuning for Cross-Region Network-Aware LLM Serving

huggingface ▲ 2 Published 2026-06-29 · Alessio Ricci Toniolo, Rome Thorstenson, Abinaya Dinesh
Open ↗

dOPSD: On-Policy Self-Distillation for Diffusion Language Models

huggingface ▲ 9 Published 2026-07-04 · Phuong Tuan Dat, Qi Li, Xinchao Wang
Open ↗

Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval

huggingface ▲ 10 Published 2026-07-05 · Suhyeong Park, Junha Jung, Jungwoo Park et al.
Open ↗

Perceptual Flow Matching for Few-Step Generative Modeling

huggingface ▲ 7 Published 2026-07-02 · Chuyang Zhao, Yifei Song, Hongfa Wang et al.
🏢 jingdong
Open ↗

CONFLUX: A Latent Diusion Model for 3D Chest-CT Synthesis with RL Post-Training

huggingface ▲ 1 Published 2026-07-02 · Max Van Puyvelde, Halil Ibrahim Gulluk, Wim Van Criekinge et al.
🎓 Gevaert Lab
Open ↗

MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing

huggingface ▲ 3 Published 2026-07-05 · Gal Fiebelman, Hadar Averbuch-Elor, Sagie Benaim
Open ↗

KVpop -- Key-Value Cache Compression with Predictive Online Pruning

huggingface ▲ 8 Published 2026-07-05 · Lukas Hauzenberger, Niklas Schmidinger, Anamaria-Roberta Hartl et al.
🏢 NX-AI
Open ↗

Multi-Turn Agentic Scientific Literature Search via Workflow Induction

huggingface ▲ 5 Published 2026-06-30 · Jisen Li, Bingxuan Li, Nanyi Jiang et al.
🎓 University of Illinois at Urbana-Champaign
Open ↗

Intent-Based Mutation Testing: From Naturally Written Programming Intents to Mutants

arxiv Published 2026-07-06 · Asma Hamidi, Ahmed Khanfir, Mike Papadakis
Open ↗

The Changing Role of Symbolic Methods in Artificial Intelligence

arxiv Published 2026-07-06 · Jun Sun
Open ↗

FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small Object Detection

arxiv Published 2026-07-06 · Aiwen Liu, Chengguang Zhu, Gang Wang et al.
Open ↗

$\mathrm{L}^p$ bounds for parabolic Riesz transforms with rough coefficients: The case $1<p \leq 2$

arxiv Published 2026-07-06 · Khalid Baadi, Moritz Egert, Benjamin W. Kosmala
Open ↗

Spectral-topology-induced criticality in non-Hermitian fermionic metals

arxiv Published 2026-07-06 · Ayan Banerjee, Julius T. Gohsrich, Flore K. Kunst
Open ↗

cQED-iCIPT2: A Near-Exact Method for Polaritonic Chemistry

arxiv Published 2026-07-06 · Ning Zhang, Wenjian Liu
Open ↗

Unified Audio Intelligence Without Regressing on Text Intelligence

arxiv Published 2026-07-06 · Zhifeng Kong, Sang-gil Lee, Jaehyeon Kim et al.
Open ↗

Finfluencers on TikTok: A Longitudinal Analysis of Content, Engagement, and Disclaimer Practices

arxiv Published 2026-07-06 · Essam Ghadafi, Panagiotis Andriotis
Open ↗

Quasi-holonomy in non-adiabatic quantum evolution

arxiv Published 2026-07-06 · Erik Sjöqvist, Adam Fredriksson
Open ↗

A Transform Pair for Doubly Connected Domains

arxiv Published 2026-07-06 · Jesse J. Hulse
Open ↗

FlowMark: Mask-Guided Video Watermarking

arxiv Published 2026-07-06 · Vishal Asnani, Shruti Agarwal, John Collomosse
Open ↗

Wavelet Scattering Transform for Interpretable Schizophrenia Biomarker Discovery and Classification from Resting-State EEG

arxiv Published 2026-07-06 · Md. Taksimul Ahsan Tawhid, Nasif Ahmed Rafe, Alif Tahmid Priyom et al.
Open ↗

Air Quality Downscaling with Station-Guided Pseudo-Supervision

arxiv Published 2026-07-06 · Guorun Wang, Simone Foti, Andreas D. Demou et al.
Open ↗

Polynomial Initial-State Jumps and Christoffel Transforms in Krylov Complexity

arxiv Published 2026-07-06 · Abhishek Chowdhury, Ajit Prasad Mahapatra
Open ↗

Topological Shape Representation for Aneurysm -- Bifurcation Detection

arxiv Published 2026-07-06 · Akshay Gokhale, Mansi Dhamne
Open ↗

PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

huggingface ▲ 31 Published 2026-07-06 · Sensen Gao, Zhaoqing Wang, Qihang Cao et al.
Open ↗

Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation

arxiv Published 2026-07-06 · Haozhe Wang, Weijia Feng, Jinpeng Yu et al.
Open ↗

CATs: Secure Blockchain Interoperability with Cross-chain Atomic Transactions

arxiv Published 2026-07-06 · Andreas Penzkofer, Franck Cassez
Open ↗

From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model

arxiv Published 2026-07-06 · Wenhao Li, Xueying Jiang, Quanhao Qian et al.
Open ↗

Jul 6, 20266

DataComp-VLM: Improved Open Datasets for Vision-Language Models

huggingface ▲ 7 Published 2026-06-25 · Matteo Farina, Vishaal Udandarao, Thao Nguyen et al.
Open ↗

MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering

huggingface ▲ 3 Published 2026-06-30 · Dang Quang Thien Tran, Quang V. Dang, Vinamra Tyagi et al.
Open ↗

VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon

huggingface ▲ 17 Published 2026-07-01 · Yi Pan, Miao Pan, Qi Lu et al.
🏢 ZJU-OmniAI
Open ↗

Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming

huggingface ▲ 6 Published 2026-06-29 · Yong Yang, Xing Zheng, Huiyu Wu et al.
🏢 Tencent
Open ↗

AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation

huggingface ▲ 3 Published 2026-06-29 · Bao Long Nguyen Huu, Atsushi Hashimoto
🏢 OMRON SINIC X Corp.
Open ↗

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

huggingface ▲ 46 Published 2026-06-27 · Jing Liang, Hongyao Tang, Yi Ma et al.
Open ↗

Jul 4, 202633

Towards Robustness against Typographic Attack with Training-free Concept Localization

arxiv Published 2026-07-02 · Bohan Liu, Wenqian Ye, Guangzhi Xiong et al.
#foundational#pretraining
Open ↗

LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning

arxiv Published 2026-07-02 · Matteo Boglioni, Thibault Rousset, Siva Reddy et al.
#pretraining
Open ↗

VT-WAM: Visual-Tactile World Action Model for Contact-Rich Manipulation

arxiv Published 2026-07-02 · Shuai Tian, Yupeng Zheng, Yuhang Zheng et al.
#transformers
Open ↗

OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers

huggingface ▲ 11 Published 2026-07-02 · Donghyun Lee, Jitesh Chavan, Duy Nguyen et al.
#transformers
🏢 Cantina, Inc.
Open ↗

Language Models as Measurement Apparatus for Culture

arxiv Published 2026-07-02 · Kent K. Chang
#nlp
Open ↗

HTTP REST API Structure Learning

arxiv Published 2026-07-02 · Ran Dubin, Amit Dvir
#foundational
Open ↗

Directed univalence for simplicial objects in an $\infty$-topos

arxiv Published 2026-07-02 · Evan Cavallo, Emily Riehl, Christian Sattler
#foundational
Open ↗

Transformer Geometry Observatory TGO-II: Representational Similarity Observatory

arxiv Published 2026-07-02 · Kaustubh Kapil, Kishor P. Upla
#transformers
Open ↗

Generative Autonomous Grid Control: Integrating Decision Transformers with a Two-Stage Safety Stack

arxiv Published 2026-07-02 · Mohamed Shamseldein
#transformers
Open ↗

AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition

huggingface ▲ 14 Published 2026-07-01 · Haiyang Li, Yuming Fu, Qun Song et al.
#transformers
🎓 Chongqing Technology and Business University
Open ↗

PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation

huggingface ▲ 9 Published 2026-07-02 · Haofei Xu, Rundi Wu, Philipp Henzler et al.
🏢 Google
Open ↗

A Probabilistic Sign Rule for Quotients of Positive Series and Integral Transforms

arxiv Published 2026-07-02 · Zakaria Derbazi
Open ↗

Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots

huggingface ▲ 15 Published 2026-07-02 · Ling Xu, Chuyu Han, Borui Li et al.
🎓 PhysicalAI System Group @ SAIL Lab, Southeast University
Open ↗

The Merger-Driven Origin of the Vast Extended Stellar Disc Around the Andromeda Galaxy

arxiv Published 2026-07-02 · C. Tsakonas, M. Arnaboldi, F. Hammer et al.
Open ↗

QuadRocket: An Aerial Robotic Testbed for Adaptive Thrust-Vector Control of Rocket-Like Vehicles

arxiv Published 2026-07-02 · Pedro Santos, Joel Reis, Paulo Oliveira et al.
Open ↗

Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment

huggingface ▲ 2 Published 2026-07-02 · Ziyao Wang, Maonan Wang, Yucheng He et al.
🎓 Chinese University of Hong Kong, Shenzhen
Open ↗

TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution

arxiv Published 2026-07-02 · Jiale Amber Wang, Kaiyuan Wang, Pengyu Nie
Open ↗

Will Scaling Improve Social Simulation with LLMs?

arxiv Published 2026-07-02 · Caleb Ziems, William Held, Su Doga Karaca et al.
Open ↗

A Quantum-Walk Representation of Color-Ordered MHV Scattering Amplitudes

arxiv Published 2026-07-02 · Anirudh Verma, C. M. Chandrashekar
Open ↗

Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data

arxiv Published 2026-07-02 · Xuanyu Chen, Nan Yang, Shuai Wang et al.
Open ↗

Improved Approximation Algorithms for n-Pairs Shortest Paths

arxiv Published 2026-07-02 · Avi Kadria, Liam Roditty, Virginia Vassilevska Williams
Open ↗

Extreme Adaptive Transformer for Time Series Forecasting

arxiv Published 2026-07-02 · Sanjeev Shrestha, Hui Liu, Yifan Zhang
Open ↗

Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs

arxiv Published 2026-07-02 · Francesca Pistilli, Simone Alberto Peirone, Giuseppe Averta
Open ↗

Complex dynamics in the Sherrington-Kirkpatrick game

arxiv Published 2026-07-02 · Desmond Chan, Tobias Galla
Open ↗

Masked complex non-decimated wavelet features for patient-level classification of contrast-enhanced mammography

arxiv Published 2026-07-02 · Sara Antonijevic, Brani Vidakovic
Open ↗

Ultra-Low-Cost Hybrid Beamforming: A New Static-Connection Architecture with Sparse Phase-Shifter Sharing

arxiv Published 2026-07-02 · Honghao Wang, Qingqing Wu, Yifei Wu et al.
Open ↗

Scaling Laws for Grid-Based Approximate Nearest Neighbor Search in High Dimensions

huggingface ▲ 2 Published 2026-06-30 · Matthew J Liu, Wei Hang Zheng, Vidhan Purohit et al.
🎓 University of California, Berkeley
Open ↗

Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting

huggingface ▲ 4 Published 2026-06-25 · Kuo-Chung Peng, Jiun-Cheng Jiang, Chun-Hua Lin et al.
Open ↗

WARP: Weight-Space Analysis for Recovering Training Data Portfolios

huggingface ▲ 7 Published 2026-07-01 · Tzu-Heng Huang, Aditya Goyal, John Cooper et al.
🎓 sprocket-lab
Open ↗

AutoMem: Automated Learning of Memory as a Cognitive Skill

huggingface ▲ 17 Published 2026-06-30 · Shengguang Wu, Hao Zhu, Yuhui Zhang et al.
Open ↗

DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation

huggingface ▲ 9 Published 2026-06-28 · Peyman Hosseini, Ondrej Bohdal, Ahmed Alajrami et al.
Open ↗

Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads

huggingface ▲ 17 Published 2026-06-30 · Aryo Pradipta Gema, Beatrice Alex, Pasquale Minervini
Open ↗

Jul 3, 202629

Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs

huggingface ▲ 6 Published 2026-07-01 · Junhao Shi, Siyin Wang, Xiaopeng Yu et al.
#pretraining
Open ↗

PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking

huggingface ▲ 5 Published 2026-06-29 · Dengxian Gong, Yuanzheng Wu, Haobo Yuan et al.
🏢 Wuhan Univeristy
Open ↗

CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion

huggingface ▲ 3 Published 2026-06-28 · Pan Wang, Yihao Hu, Xiujin Liu
Open ↗

SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation

huggingface ▲ 3 Published 2026-06-28 · Zhiyuan Ma, Zhengfeng Shi, Yuning An et al.
🎓 MAIR Lab@HUST
Open ↗

Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation

huggingface ▲ 3 Published 2026-06-27 · Jongoh Jeong, Sun-Kyung Lee, Kuk-Jin Yoon
Open ↗

Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?

huggingface ▲ 5 Published 2026-06-30 · Zhi Chen, Zhensu Sun, Yuling Shi et al.
🎓 Singapore Management University
Open ↗

HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents

huggingface ▲ 2 Published 2026-06-29 · Qianchu Liu, Sheng Zhang, Guanghui Qin et al.
🏢 Microsoft
Open ↗

Building to the Test: Coding Agents Deliver What You Check, Not What You Requested

huggingface ▲ 4 Published 2026-06-25 · Yanuo Ma, Ben Kereopa-Yorke, Ben Schultz
🏢 Microsoft
Open ↗

When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling

huggingface ▲ 4 Published 2026-06-26 · Yong Yi Bay, Kathleen A. Yearick
Open ↗

GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity

huggingface ▲ 5 Published 2026-06-29 · Yong Yi Bay, Kathleen A. Yearick
Open ↗

Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue

huggingface ▲ 4 Published 2026-06-29 · Nan Li, Albert Gatt, Massimo Poesio
🎓 NLP Group at Utrecht University
Open ↗

AgenticDataBench: A Comprehensive Benchmark for Data Agents

huggingface ▲ 26 Published 2026-07-01 · Zhaoyan Sun, Shan Zhong, Daizhou Wen et al.
🎓 Tsinghua University
Open ↗

Optimizing Visual Generative Models via Distribution-wise Rewards

huggingface ▲ 14 Published 2026-07-01 · Ruihang Li, Mengde Xu, Shuyang Gu et al.
🏢 Tencent Hunyuan
Open ↗

Program-as-Weights: A Programming Paradigm for Fuzzy Functions

huggingface ▲ 74 Published 2026-07-01 · Wentao Zhang, Liliana Hotsko, Woojeong Kim et al.
🎓 University of Waterloo
Open ↗

AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models

huggingface ▲ 7 Published 2026-07-01 · Rintaro Otsubo, Ryo Fujii, Reina Ishikawa et al.
Open ↗

Denser neq Better: Limits of On-Policy Self-Distillation for Continual Post-Training

huggingface ▲ 5 Published 2026-07-01 · Meng Wang, Haohan Zhao, Wenzhuo Liu et al.
Open ↗

WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory

huggingface ▲ 21 Published 2026-07-01 · Hanlin Wang, Hao Ouyang, Qiuyu Wang et al.
Open ↗

Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling

huggingface ▲ 33 Published 2026-07-01 · Xingyu Zheng, Xianglong Liu, Yifu Ding et al.
Open ↗

Representation Distribution Matching for One-Step Visual Generation

huggingface ▲ 7 Published 2026-07-01 · Lan Feng, Wuyang Li, Eloi Zablocki et al.
🎓 EPFL VITA Lab
Open ↗

PACE: A Proxy for Agentic Capability Evaluation

huggingface ▲ 9 Published 2026-07-01 · Yueqi Song, Lintang Sutawika, Jiarui Liu et al.
Open ↗

SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use

huggingface ▲ 17 Published 2026-07-01 · Jiayin Zhu, Kelong Mao, Yudong Guo et al.
Open ↗

When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search

huggingface ▲ 11 Published 2026-06-25 · Yiling Tao, Shihan Deng, Meiling Tao et al.
🏢 Tencent Hunyuan
Open ↗

Discrete Diffusion Language Models for Interactive Radiology Report Drafting

huggingface ▲ 5 Published 2026-06-30 · Max Van Puyvelde, Halil Ibrahim Gulluk, Wim Van Criekinge et al.
🎓 Gevaert Lab
Open ↗

From SRA to Self-Flow: Data Augmentation or Self-Supervision?

huggingface ▲ 11 Published 2026-07-01 · Dengyang Jiang, Mengmeng Wang, Harry Yang et al.
Open ↗

AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents

huggingface ▲ 53 Published 2026-07-01 · Xiangchen Cheng, Yunwei Jiang, Jianwen Sun et al.
🏢 Alaya Studio
Open ↗

EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

huggingface ▲ 45 Published 2026-07-01 · Zhilin Wang, Han Song, Runzhe Zhan et al.
Open ↗

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning

huggingface ▲ 20 Published 2026-06-29 · Junha Jung, Minbyul Jeong, Suhyeon Lim et al.
Open ↗

InstanceControl: Controllable Complex Image Generation without Instance Labeling

huggingface ▲ 10 Published 2026-06-29 · Xiaoyu Liu, Huan Wang, Fan Li et al.
Open ↗

Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR

huggingface ▲ 4 Published 2026-06-26 · Yongjin Yang, Jiarui Liu, Yinghui He et al.
🎓 University of Toronto
Open ↗

Jul 2, 202629

The State-Prediction Separation Hypothesis

huggingface ▲ 4 Published 2026-06-30 · Giovanni Monea, Nathan Godey, Kianté Brantley et al.
#transformers#pretraining
🎓 Cornell LIL Lab
Open ↗

ABot-M0.5: Unified Mobility-and-Manipulation World Action Model

huggingface ▲ 6 Published 2026-06-30 · Ronghan Chen, Yandan Yang, Zuojin Tang et al.
#transformers
Open ↗

Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?

huggingface ▲ 10 Published 2026-06-23 · Tyler Ga Wei Lum, Kushal Kedia, C. Karen Liu et al.
#pretraining
🎓 Stanford University
Open ↗

Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination

huggingface ▲ 1 Published 2026-06-30 · Subhadeep Pal, Shashwat Sourav, Tirthankar Ghosal et al.
🎓 Massachusetts Institute of Technology
Open ↗

AI translation of literary texts is "fine", but readers still prefer human translations

huggingface ▲ 0 Published 2026-06-23 · Yves Ferstler, Adam Podoxin, Ty Brassington et al.
Open ↗

Cross-Domain Generalization Failure in Lightweight Intrusion Detection Models for IIoT Networks

huggingface ▲ 3 Published 2026-06-30 · MD Azizul Hakim, Md Shihab Uddin, Talha Ibne Anis
Open ↗

Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising

huggingface ▲ 1 Published 2026-06-30 · Tianci Liu, Zihan Dong, Linjun Zhang et al.
Open ↗

PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

huggingface ▲ 22 Published 2026-06-25 · Yana Wei, Hongbo Peng, Yanlin Lai et al.
🎓 Johns Hopkins University
Open ↗

NoPA: Non-Parametric Online 3D Scene Graph Generation

huggingface ▲ 0 Published 2026-06-30 · Qi Xun Yeo, Seungjun Lee, Yan Li et al.
🎓 National University of Singapore
Open ↗

Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning

huggingface ▲ 12 Published 2026-06-30 · Shijie Li, Yilin Gao, Siyuan Yang et al.
Open ↗

ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving

huggingface ▲ 16 Published 2026-06-30 · Sangjin Choi, Sukmin Cho, Yifan Xiong et al.
🏢 Microsoft Research
Open ↗

Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity

huggingface ▲ 4 Published 2026-06-29 · Bytedance Seed
🏢 ByteDance Seed
Open ↗

ASPIRE: Agentic /Skills Discovery for Robotics

huggingface ▲ 7 Published 2026-06-29 · Runyu Lu, Yubo Wu, Ethan Kou et al.
🏢 NVIDIA
Open ↗

MemSyco-Bench: Benchmarking Sycophancy in Agent Memory

huggingface ▲ 17 Published 2026-06-30 · Zhishang Xiang, Zerui Chen, Yunbo Tang et al.
Open ↗

When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors

huggingface ▲ 3 Published 2026-06-29 · Yuqing Yang, Qi Zhu, Zhen Han et al.
🏢 Amazon Web Services (AWS)
Open ↗

Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning

huggingface ▲ 10 Published 2026-06-30 · Hongxing Li, Xiufeng Huang, Dingming Li et al.
🎓 Zhejiang University
Open ↗

TurboServe: Serving Streaming Video Generation Efficiently and Economically

huggingface ▲ 18 Published 2026-06-16 · Youhe Jiang, Haoxu Wang, Haotong Bao et al.
🎓 Tsinghua University
Open ↗

AutoTrainess: Teaching Language Models to Improve Language Models Autonomously

huggingface ▲ 3 Published 2026-06-29 · Zhaojian Yu, Penghao Yin, Shuzheng Gao et al.
Open ↗

CausalMix: Data Mixture as Causal Inference for Language Model Training

huggingface ▲ 9 Published 2026-06-30 · Zinan Tang, Yukun Zhang, Shaomian Zheng et al.
🎓 Tsinghua University
Open ↗

Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts

huggingface ▲ 15 Published 2026-06-30 · Taewook Kang, Taeheon Kim, Donghyun Shin et al.
🎓 Seoul National University
Open ↗

Valdi: Value Diffusion World Models

huggingface ▲ 3 Published 2026-06-30 · Christopher Lindenberg, Kashyap Chitta
Open ↗

Autonomous Scientific Discovery via Iterative Meta-Reflection

huggingface ▲ 3 Published 2026-06-30 · Bingchen Zhao, Sara Beery, Oisin Mac Aodha
Open ↗

BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery

huggingface ▲ 6 Published 2026-06-18 · Jieyi Wang, Bingxuan Li, Nanyi Jiang et al.
Open ↗

AtomiMed: Hierarchical Atomic Fact-Checking for Universal Clinical-Aware Medical Report Evaluation

huggingface ▲ 3 Published 2026-06-29 · Yuan Wang, Wanxing Chang, Songtao Jiang et al.
🎓 Zhejiang University
Open ↗

VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement

huggingface ▲ 10 Published 2026-06-30 · Seohyun Lee, Seoung Choi, Dohwan Ko et al.
Open ↗

RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue

huggingface ▲ 1 Published 2026-06-30 · Zhihao Lin, Mingyi Zhou, Zhensu Sun et al.
🎓 Beihang University
Open ↗

TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning

huggingface ▲ 6 Published 2026-06-29 · Yuanda Xu, Zhengze Zhou, Hejian Sang et al.
🏢 LinkedIn
Open ↗

SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions

huggingface ▲ 2 Published 2026-06-28 · Mohit Raghavendra, Anisha Gunjal, Aakash Sabharwal et al.
🏢 Scale AI
Open ↗

Hierarchical Experimentalist Agents

huggingface ▲ 1 Published 2026-06-27 · Abhranil Chandra, Sankaran Vaidyanathan, Utsav Dhanuka et al.
🎓 University of Massachusetts Amherst
Open ↗

Jul 1, 202658

PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation

huggingface ▲ 7 Published 2026-06-24 · Chunshi Wang, Haohan Weng, Junliang Ye et al.
#transformers#pretraining
🏢 Tencent Hunyuan
Open ↗

Low-dimensional topology of deep neural networks

arxiv Published 2026-06-30 · Junyu Ren, Lek-Heng Lim
#transformers
Open ↗

Review Residuals: Update-Conditioned Residual Gating for Transformers

arxiv Published 2026-06-30 · Kyle Kramer
#transformers
Open ↗

FlexViT: A Flexible FPGA-based Accelerator for Edge Vision Transformers

arxiv Published 2026-06-30 · Hubert Dymarkowski, Xingjian Fu, Rappy Saha et al.
#transformers
Open ↗

Adapting Generalist Robot Policies with Semantic Reinforcement Learning

arxiv Published 2026-06-30 · Jagdeep Singh Bhatia, Andrew Wagenmaker, William Chen et al.
#pretraining
Open ↗

Signed-Permutation Coordinate Transport for RMSNorm Transformers

arxiv Published 2026-06-30 · John Sweeney
#transformers
Open ↗

Radial Suppression Accelerates Algorithmic Generalization: A Geometric Analysis of Delayed Generalization

arxiv Published 2026-06-30 · Srijan Tiwari, Aditya Chauhan, Manjot Singh
#transformers
Open ↗

SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE

huggingface ▲ 3 Published 2026-06-30 · Or Hirschorn, Aaron Olender, Eli Alshan et al.
#transformers
Open ↗

A Gravitational Interpretation of Fine-Tuning Reversion

huggingface ▲ 1 Published 2026-06-25 · Samuele Poppi, Nils Lukas
🎓 Mohamed Bin Zayed University of Artificial Intelligence
Open ↗

RocketSmith: Agentic Additive Manufacturing of High-Powered Rockets

huggingface ▲ 4 Published 2026-06-25 · Peter Pak, Jesse Barkley, Rumi Loghmani et al.
🎓 Carnegie Mellon University
Open ↗

SWE-Together: Evaluating Coding Agents in Interactive User Sessions

huggingface ▲ 12 Published 2026-06-28 · Yifan Wu, Zhuokai Zhao, Songlin Li et al.
🏢 Meta Research
Open ↗

Mind the Heads: Topological Representation Alignment for Multimodal LLMs

huggingface ▲ 2 Published 2026-06-21 · Davide Caffagni, Alberto Compagnoni, Federico Melis et al.
🎓 AImageLab
Open ↗

LLM Program Optimization via Retrieval Augmented Search

huggingface ▲ 2 Published 2026-06-22 · Sagnik Anupam, Alexander Shypula, Osbert Bastani
🎓 University of Pennsylvania
Open ↗

Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?

huggingface ▲ 2 Published 2026-06-25 · Guoheng Sun, Kaixi Feng, Shwai He et al.
🏢 LLM-Drop
Open ↗

MirrorPPR: Exemplar-Based Portrait Photo Retouching

huggingface ▲ 1 Published 2026-06-27 · Zhihong Liu, Zheng Li, Jiachun Jin et al.
🎓 DENG Lab @ SJTU
Open ↗

LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents

huggingface ▲ 1 Published 2026-06-28 · Yogeswar Reddy Thota
🎓 University of Texas at Dallas
Open ↗

Dockerless: Environment-Free Program Verifier for Coding Agents

huggingface ▲ 77 Published 2026-06-25 · Wenhao Zeng, Yuling Shi, Xiaodong Gu et al.
🏢 ByteDance
Open ↗

DOPD: Dual On-policy Distillation

huggingface ▲ 61 Published 2026-06-28 · Xinlei Yu, Gen Li, Qingyi Si et al.
Open ↗

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

huggingface ▲ 16 Published 2026-06-26 · Young-Jun Lee, Seungone Kim, Minki Kang et al.
🏢 Minnesota NLP
Open ↗

AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation

huggingface ▲ 3 Published 2026-06-28 · Kien T. Pham, I Chieh Chen, Qifeng Chen et al.
Open ↗

MemLearner: Learning to Query Context memory for Video World Models

huggingface ▲ 16 Published 2026-06-29 · Jiwen Yu, Jianxiong Gao, Jianhong Bai et al.
Open ↗

Xiaomi-GUI-0 Technical Report

huggingface ▲ 5 Published 2026-06-29 · Wanxia Cao, Chengzhen Duan, Pei Fu et al.
🏢 Xiaomi Research
Open ↗

BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding

huggingface ▲ 64 Published 2026-06-29 · Hao Zhang, Yiming Hu, Yong Wang et al.
Open ↗

BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language

huggingface ▲ 2 Published 2026-06-28 · Haitao Wu, Qirui Zhang, Zhouheng Yao et al.
Open ↗

PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising

huggingface ▲ 2 Published 2026-06-28 · Koorosh Roohi, Javad Rajabi, Andrew Fleet et al.
🎓 University of Toronto
Open ↗

TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive

huggingface ▲ 1 Published 2026-06-29 · Brian Wei, Srikumar Sastry, Daniel Cher et al.
🎓 Multimodal Vision Research Laboratory @ WashU
Open ↗

Multi-Block Diffusion Language Models

huggingface ▲ 16 Published 2026-06-29 · Yijie Jin, Jiajun Xu, Yuxuan Liu et al.
🎓 DENG Lab @ SJTU
Open ↗

Little Brains, Big Feats: Exploring Compact Language Models

huggingface ▲ 7 Published 2026-06-28 · Dari Baturova, Elena Bruches, Ivan Chernov et al.
🏢 Siberian Neuronets LLC
Open ↗

GEAR: Guided End-to-End AutoRegression for Image Synthesis

huggingface ▲ 21 Published 2026-06-29 · Bin Lin, Zheyuan Liu, Chenguo Lin et al.
🏢 Tencent Hunyuan
Open ↗

RedVox: Safety and Fairness Gaps in Speech Models Across Languages

huggingface ▲ 11 Published 2026-06-24 · Beatrice Savoldi, Sara Papi, Wafa Aissa et al.
🏢 FBK-MT
Open ↗

Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views

huggingface ▲ 10 Published 2026-06-27 · Mijin Yoo, In Cho, Subin Jeon et al.
Open ↗

MuSViT: A Foundation Vision Model for Sheet Music Representation

huggingface ▲ 0 Published 2026-06-29 · Carlos Penarrubia, Antonio Rios-Vila, Eliseo Fuentes-Martinez et al.
🏢 Pattern Recognition and Artificial Intelligence Group
Open ↗

DataEvolver: Self-Evolving Multi-Agent Data Construction for Text-Rich Image Generation

huggingface ▲ 7 Published 2026-06-29 · Siyu Yan, Yizhen Gao, Yilin Wang et al.
Open ↗

SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History

huggingface ▲ 2 Published 2026-06-22 · Zhiwei Li, Yong Hu
🏢 Tencent
Open ↗

An Agentic AI Framework to Accelerate Scientific Discovery in Plant Phenotyping

arxiv Published 2026-06-30 · Renan Souza, Daniel Rosendo, Kelsey Carter et al.
Open ↗

Automatic quantum function parallelization and memory management in Qrisp

arxiv Published 2026-06-30 · Raphael Seidel
Open ↗

Towards Voxel Spacing Consistency for Medical Image Segmentation

arxiv Published 2026-06-30 · Xin You, Runze Yang, Minghui Zhang et al.
Open ↗

An Open-Source Tool for Reproducible Freeway Network Extraction from OpenStreetMap

arxiv Published 2026-06-30 · Drew Miller, Cathy Wu
Open ↗

Belief Contraction in Dynamic Epistemic Logic

arxiv Published 2026-06-30 · Gaia Belardinelli, Snow Zhang
Open ↗

Harnessing Textual Refusal Directions for Multimodal Safety

arxiv Published 2026-06-30 · Moreno D'Incà, Massimiliano Mancini, Nicu Sebe
Open ↗

Attend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM Inference

arxiv Published 2026-06-30 · Zhaoyang Luo, Runmin Dong, Miao Yang et al.
Open ↗

MVP-Nav: Multi-layer Value Map Planner Navigator

arxiv Published 2026-06-30 · Wenyuan Xie, Shaokai Wu, Yijin Zhou et al.
Open ↗

Making Sense of Touch from the Child's View for Contrastive Learning

arxiv Published 2026-06-30 · Max Whitton, Zecheng Wang, Puchen Liu et al.
Open ↗

A Conformal Selection Framework for Individual Treatment Beneficiaries with Auxiliary External Data

arxiv Published 2026-06-30 · Jiajun Liu, Ke Zhu, Xiaofei Wang
Open ↗

DigitalCoach: Communication and Grounding Gaps in Human and Agentic Computer Use Coaching

arxiv Published 2026-06-30 · Meng Chen, Anya Ji, Tsung-Han Wu et al.
Open ↗

LUNA: Learning Universal 3D Human Animation Beyond Skinning

arxiv Published 2026-06-30 · Peng Li, Rawal Khirodkar, Junxuan Li et al.
Open ↗

ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs

arxiv Published 2026-06-30 · Yuhao Wang, Mu Qiao, Haiwen Diao et al.
Open ↗

Joint inference of weak lensing convergence map and cosmology with diffusion models

arxiv Published 2026-06-30 · Benjamin Remy, Chihway Chang, Rebecca Willett
Open ↗

OopsieVerse: A Safety Benchmark with Damage-Aware Simulation for Robot Manipulation

arxiv Published 2026-06-30 · Arnav Balaji, Arpit Bahety, Sriniket Ambatipudi et al.
Open ↗

The geometric bookkeeping guide for $\varepsilon$-factorised differential equations

arxiv Published 2026-06-30 · Antonela Matijašić
Open ↗

FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning

arxiv Published 2026-06-30 · Zekai Chen, Kairui Yang, Xuaner Chen et al.
Open ↗

Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs

huggingface ▲ 6 Published 2026-06-30 · Gabrielle Kaili-May Liu, Avi Caciularu, Gal Yona et al.
🏢 Google
Open ↗

PointSplat: Compact Gaussian Splatting via Human-Centric Prediction

arxiv Published 2026-06-30 · Yujie Guo, Yudong Jin, Lingteng Qiu et al.
Open ↗

FaceMoE: Mixture of Experts for Low-Resolution Face Recognition

arxiv Published 2026-06-30 · Kartik Narayan, Vishal M. Patel
Open ↗

Jun 30, 202659

Reweighting Framewise Attention in Video Transformers for Facial Expression Understanding

arxiv Published 2026-06-29 · Seongro Yoon, Donghyeon Cho, Jinsun Park et al.
#transformers#pretraining
Open ↗

Open-Vocabulary and Referring Segmentation for 3D Gaussians Using 2D Detectors

arxiv Published 2026-06-29 · Jameel Hassan, Yasiru Ranasinghe, Vishal Patel
#pretraining
Open ↗

One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining

arxiv Published 2026-06-29 · Philip Zmushko, Egor Petrov, Nursultan Abdullaev et al.
#pretraining
Open ↗

Teaching Prompt-Based Programming with LLMs: A 45-Minute Lesson with Guided Practice for End-User Programmers

arxiv Published 2026-06-29 · Keith Tran, Samiha Marwan, Thomas Price
#foundational
Open ↗

HASTE: A Framework for Training-Free, Dynamic, and Steerable Compression of Pre-Trained Convolutional Neural Networks

arxiv Published 2026-06-29 · Lukas Meiner, Jens Mehnert, Alexandru Paul Condurache
#transformers
Open ↗

Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark

huggingface ▲ 1 Published 2026-06-28 · Matthias Blaschke, Daniel Kienzle, Zsuzsanna Koczor-Benda et al.
#pretraining
🏢 Chair for Machine Learning & Computer Vision
Open ↗

Learning Transferable Dynamics Priors from Action to World Modeling

huggingface ▲ 1 Published 2026-06-27 · Ze Huang, Jiahui Zhang, Hairuo Liu et al.
#pretraining
Open ↗

DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model

huggingface ▲ 4 Published 2026-06-28 · Daniyel Ayupov, Artur Markov-Tsoy
#foundational
Open ↗

GROW$^2$: Grounding Which and Where for Robot Tool Use

arxiv Published 2026-06-29 · Yuhong Deng, Yuyao Liu, David Hsu
Open ↗

Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models

arxiv Published 2026-06-29 · Subramanyam Sahoo, Aman Chadha, Vinija Jain et al.
Open ↗

PyMETA: A Benchmark Dataset for Hierarchical Student Code Error Classification with Python-Interpreter-Based Labels

arxiv Published 2026-06-29 · Chuyue Li, Ziqi Tang, Jingyi Wang et al.
Open ↗

Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation

arxiv Published 2026-06-29 · Siddhant Bansal, Zhifan Zhu, Shashank Tripathi et al.
Open ↗

Efficient Eccentric Effective-One-Body Dynamics via Near-Identity Averaging Transformations

arxiv Published 2026-06-29 · Philip Lynch, Alessandra Buonanno, Aldo Gamboa et al.
Open ↗

APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms

arxiv Published 2026-06-29 · Juntao Jiang, Jinsheng Bai, Linxuan Fan et al.
Open ↗

Beyond 2D Matching: A Unified Single-Stage Framework for Geometry-Aware Cross-View Object Geo-Localization

arxiv Published 2026-06-29 · Liyao Wang, Ruipu Wu, Haojun Xu et al.
Open ↗

The Fundamental Limits of Valid Transport Map Estimation

arxiv Published 2026-06-29 · Sivaraman Balakrishnan
Open ↗

Revisiting crossed-correlated baths in open quantum systems simulated by HEOM or T-TEDOPA

arxiv Published 2026-06-29 · Brieuc Le Dé, Etienne Mangaud, Alex W. Chin et al.
Open ↗

Morphing into Hybrid Attention Models

huggingface ▲ 42 Published 2026-06-29 · Disen Lan, Jianbin Zheng, Yuxi Ren et al.
🏢 ByteDance Seed
Open ↗

Poller: Are LLMs Suitable for Evaluating the Poetry Understanding Task?

arxiv Published 2026-06-29 · Shanshan Wang, Derek F. Wong, Jingming Yao et al.
Open ↗

SubEdge: A Subscriber-Centric Edge Computing Subsystem in 6G Networks for AI

arxiv Published 2026-06-29 · Abdirazak Ali Asir Rage, Riccardo Pozza, Rahim Tafazolli
Open ↗

Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision

arxiv Published 2026-06-29 · Haoyang Li, Guanlin Li, Youhe Feng et al.
Open ↗

MAS-Lab: A Specification-Driven Validation Framework for Reliable Multi-Agent Systems

arxiv Published 2026-06-29 · Jordan Augé, Giovanna Carofiglio, Giulio Grassi et al.
Open ↗

StereoGS: Sparse-View 3D Gaussian Splatting via Stereo Priors

arxiv Published 2026-06-29 · Wenhao Yuan, Yiyuan Ge, Deli Cai
Open ↗

Learning from Mistakes: Rollout-Retrieval Lifelong Policy Learning for Autonomous Driving

arxiv Published 2026-06-29 · Cheng Gong, Haoyang Wang, Chao Lu et al.
Open ↗

Orca: The World is in Your Mind

huggingface ▲ 161 Published 2026-06-29 · Yihao Wang, Yuheng Ji, Mingyu Cao et al.
Open ↗

Working with measurement-based computations on qudits

arxiv Published 2026-06-29 · Piotr Mitosek, Miriam Backens
Open ↗

3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement

arxiv Published 2026-06-29 · Deyin Liu, Jicheng Xu, Lin Yuanbo Wu et al.
Open ↗

A Field-Theoretic Framework for Work Statistics and Universal Scaling in Non-equilibrium Phase Transitions

arxiv Published 2026-06-29 · Yanbo Qiao, Ruohan Xu, H. T. Quan
Open ↗

SIMAX: A Scalable and Interpretable Framework for Multi-Fidelity and Annotated Clinician-Patient Dialogue Simulation

arxiv Published 2026-06-29 · Zhuhan Bao, Rui Yang, Bohao Yang et al.
Open ↗

Factorizable Normalizing Flows for parameter-dependent density morphing

arxiv Published 2026-06-29 · Davide Valsecchi, Mauro Donegà, Rainer Wallny
Open ↗

Discovering the Kalman-Bucy-Koopman Filter

arxiv Published 2026-06-29 · Umesh Vaidya
Open ↗

Demonstration of unpartible entanglement

arxiv Published 2026-06-29 · Philip Held, Laura Ares, Federico Pegoraro et al.
Open ↗

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

huggingface ▲ 1 Published 2026-06-26 · Han Luo, Bingbing Wen, Lucy Lu Wang
🎓 University of Washington
Open ↗

ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval

huggingface ▲ 3 Published 2026-06-25 · Siqiao Xue, Chunxue Xu
Open ↗

Large-Scale Tunnel Air-Ground Collaboration With FLISP: Fast LiDAR-IMU Synchronized Path Planner

huggingface ▲ 1 Published 2026-06-24 · Fenghe Guo, Runjie Shen, Chenyang Sun et al.
Open ↗

TheoremGraph: Bridging Formal and Informal Mathematics

huggingface ▲ 2 Published 2026-06-23 · Simon Kurgan, Evan Wang, Eric Leonen et al.
🎓 University of Washington Math AI Lab
Open ↗

The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction

huggingface ▲ 2 Published 2026-06-28 · Yuxi Wang, Chengkai Jin, Yufei Liu et al.
🎓 Nanyang Technological University Singapore
Open ↗

Interleaved Speech Language Models Latently Work In Text

huggingface ▲ 9 Published 2026-06-20 · Talia Sternberg, Gallil Maimon, Yossi Adi
🎓 The Hebrew University of Jerusalem
Open ↗

Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning

huggingface ▲ 22 Published 2026-06-25 · Hohin Kwan, Hongyu Li, Ray Zhang et al.
Open ↗

Trimming the Long-Tail of Visual World Modeling Evaluation

huggingface ▲ 30 Published 2026-06-22 · Bingxuan Li, Yining Hong, Cheng Qian et al.
🎓 University of Illinois at Urbana-Champaign
Open ↗

LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing

huggingface ▲ 55 Published 2026-06-24 · Xinyu Wang, Chongbo Zhao, Fangneng Zhan et al.
🎓 Tsinghua University
Open ↗

TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents

huggingface ▲ 35 Published 2026-06-25 · Shoufa Chen, Luyuan Wang, Xuan Yang et al.
🏢 AI at Meta
Open ↗

OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

huggingface ▲ 7 Published 2026-06-27 · Mengqi Yuan, Zilong Zhou, Xinzhuang Xiong et al.
Open ↗

Walking in the Implicit: Interactive World Exploration via Neural Scene Representation

huggingface ▲ 4 Published 2026-06-28 · Zhiqi Li, Chengrui Dong, Zhenhua Du et al.
Open ↗

SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing

huggingface ▲ 1 Published 2026-06-28 · Jiacheng Zhang, Haoyu He, Sen Zhang et al.
🏢 ByteDance
Open ↗

One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding

huggingface ▲ 1 Published 2026-06-28 · Chen Liu, Ling Chen, Hanzhang Zhou et al.
🏢 Tongyi-MAI
Open ↗

PoseShield: Neural Collision Fields for Human Self-Collision Resolution

huggingface ▲ 1 Published 2026-06-28 · Zhengyuan Li, Zeyun Deng, Yifan Shen et al.
Open ↗

ReFreeKV: Towards Threshold-Free KV Cache Compression

huggingface ▲ 18 Published 2026-06-25 · Xuanfan Ni, Liyan Xu, Chenyang Lyu et al.
🏢 Tencent
Open ↗

Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting

huggingface ▲ 14 Published 2026-06-28 · Xiaobiao Du, YuAn Wang, Hao Li et al.
🎓 University of Technology Sydney
Open ↗

Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis

huggingface ▲ 5 Published 2026-06-28 · Shufan Li, Greg Heinrich, Hanrong Ye et al.
🏢 NVIDIA
Open ↗

TACO: Tool-Augmented Credit Optimization for Agentic Tool Use

huggingface ▲ 12 Published 2026-06-28 · Mingkuan Feng, Jinyang Wu, Hao Gu et al.
Open ↗

ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models

huggingface ▲ 2 Published 2026-06-21 · Jun Zhang, Jiasheng Zheng, Boxi Cao et al.
Open ↗

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

huggingface ▲ 54 Published 2026-06-28 · Lei Bai, Zongsheng Cao, Yang Chen et al.
🏢 Intern Science
Open ↗

PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents

huggingface ▲ 4 Published 2026-06-27 · Seongjae Kang, Taehyung Yu, Sung Ju Hwang
🎓 KAIST AI
Open ↗

Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE

huggingface ▲ 3 Published 2026-06-24 · Haoyou Deng, Keyu Yan, Chaojie Mao et al.
🎓 TongyiLab
Open ↗

GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots

huggingface ▲ 4 Published 2026-06-28 · Sunqi Fan, Lingshan Chen, Runqi Yin et al.
🏢 Tencent Hunyuan
Open ↗

Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction

huggingface ▲ 4 Published 2026-06-25 · Chenguang Wang, Ming Li, Xinyue Zeng et al.
Open ↗

Jun 29, 202646

Higher-Order Fourier Neural Operator: Explicit Mode Mixer for Nonlinear PDEs

arxiv Published 2026-06-26 · Alex Colagrande, Paul Caillon, Eva Feillet et al.
#transformers
Open ↗

PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation

huggingface ▲ 29 Published 2026-06-25 · Peiwen Zhang, Yufan Deng, Shangkun Sun et al.
🏢 NVIDIA
Open ↗

SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation

huggingface ▲ 5 Published 2026-06-25 · Nadun Ranawaka, Josiah Wong, Wei-Lin Pai et al.
🏢 NVIDIA
Open ↗

Towards Automating Scientific Review with Google's Paper Assistant Tool

huggingface ▲ 2 Published 2026-06-25 · Rajesh Jayaram, Drew Tyler, David Woodruff et al.
🏢 Google
Open ↗

Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs

huggingface ▲ 11 Published 2026-05-06 · Fahd Seddik, Fatemeh Fard
Open ↗

Qwen-Image-2.0-RL Technical Report

huggingface ▲ 18 Published 2026-06-24 · Yixian Xu, Kaiyuan Gao, Yuxiang Chen et al.
🏢 Qwen
Open ↗

SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning

huggingface ▲ 10 Published 2026-06-21 · SingGuard Team
🏢 inclusionAI
Open ↗

NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning

huggingface ▲ 1 Published 2026-06-25 · Tianlin Pan, Lianyu Pang, Cheng Da et al.
🎓 HKUST
Open ↗

Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents

huggingface ▲ 3 Published 2026-06-24 · Minbyul Jeong
Open ↗

ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering

huggingface ▲ 6 Published 2026-06-25 · ZhengXian Wu, Hangrui Xu, Kai Shi et al.
Open ↗

Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots

huggingface ▲ 26 Published 2026-06-25 · Sijin Chen, Kaixuan Jiang, Haixin Shi et al.
🏢 ByteDance Seed
Open ↗

Boundary-Aware Context Grounding for A Low-Channel EEG Agent

huggingface ▲ 0 Published 2026-06-24 · Zhiyuan Xu, Yueqing Dai, Junling Li et al.
Open ↗

Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)

huggingface ▲ 4 Published 2026-06-24 · Ilia Larchenko
Open ↗

Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement

huggingface ▲ 1 Published 2026-06-16 · Kinam Kim, Namiko Saito, Heecheol Kim et al.
🏢 Microsoft Research
Open ↗

GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems

huggingface ▲ 3 Published 2026-06-25 · Xiaocheng Yang, Abdulrahman Alrabah, Dilek Hakkani-Tür et al.
🎓 University of Illinois at Urbana-Champaign
Open ↗

Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents

huggingface ▲ 3 Published 2026-06-22 · Vidya Srinivas, Zachary Englhardt, Shwetak Patel et al.
Open ↗

The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar

huggingface ▲ 4 Published 2026-06-23 · Ilseyar Alimova, Bogdan Monogov, Artyom Mazur et al.
Open ↗

In-flight calibration of the Wide-field X-ray Telescope on board the Einstein Probe

arxiv Published 2026-06-26 · Huaqing Cheng, Hai-Wu Pan, Yuan Liu et al.
Open ↗

Improved Energy Stable Symmetric Gauss-Seidel Projection Method for Micromagnetics Simulations

arxiv Published 2026-06-26 · Yingxi Miao, Changjian Xie
Open ↗

When One Adapter Speaks for Many: Discovering Low-Rank Redundancy in Continual Fine-Tuning

arxiv Published 2026-06-26 · Tanguy Dieudonné, Giulia Lanzillotta, Enis Simsar et al.
Open ↗

AI-Driven Synthesis for High-Tech System Design: Automating Innovation

arxiv Published 2026-06-26 · Luuk Oerlemans, Steven Westerhof, Theo Hofman
Open ↗

Science of High Resolution X-ray Imaging

arxiv Published 2026-06-26 · H. L. Marshall, K. Weaver, M. Schattenburg et al.
Open ↗

MixTTA: Low-Rank Cross-Channel Mixing for Reliable Test-Time Adaptation

arxiv Published 2026-06-26 · Mansoo Jung, Youngwook Kim, Jungwoo Lee
Open ↗

Spectral densities from Euclidean correlators via integral transforms: theoretical framework

arxiv Published 2026-06-26 · Leonardo Giusti, Matteo Saccardi, Diego Toniolo
Open ↗

Gravitational-wave response functions for space-borne detectors based on multiple geometric time-delay interferometry links

arxiv Published 2026-06-26 · Rui Luo, Pan-Pan Wang, Lin-Lin Yang et al.
Open ↗

Vacuum Fluctuation-Induced State Switching in Degenerate Optical Parametric Oscillators

arxiv Published 2026-06-26 · Yihao Huang, Seou Choi, Rom Simovitch et al.
Open ↗

CPAgents: Agentic Composite Phenotype Generation for Cardiac Disease Association

arxiv Published 2026-06-26 · Zuoou Li, Wenlong Zhao, Kelly Yu et al.
Open ↗

A fast sum-of-Gaussians algorithm for the high-dimensional fractional Fokker-Planck equation

arxiv Published 2026-06-26 · Shidong Jiang, Dong Wang, Qi Zhou
Open ↗

Quantum anomalies from three-point on-shell bootstrap

arxiv Published 2026-06-26 · Hiren Kakkad, Rémy Larue, Alexander Ochirov
Open ↗

COCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-Negatives

arxiv Published 2026-06-26 · David Steinmann, Antonia Wüst, Kristian Kersting et al.
Open ↗

Hybrid quantum-classical neural network for sample-efficient recognition of topological phases

arxiv Published 2026-06-26 · Markus K. Hoffmann, Leon C. Sander, Colin Scarato et al.
Open ↗

Higher dimensional quantum Hall effect and the analog of $W_\infty$-algebra

arxiv Published 2026-06-26 · Dimitra Karabali, V. P. Nair
Open ↗

Faraday Tomography with the SKA: A New Era of Cosmic Magnetism Studies

arxiv Published 2026-06-26 · Miguel Carcamo, Anna M. M. Scaife, Jeroen Stil et al.
Open ↗

Noise-Directed Adaptive Remapping for Integer Optimization: from qubits to (encoded) qudits

arxiv Published 2026-06-26 · Stuart Hadfield, Filip B. Maciejewski, Davide Venturelli
Open ↗

Qudit extension of parameterized IQP circuits: A generative quantum machine learning approach to integer data

arxiv Published 2026-06-26 · Robert J. Banks, Arianna Crippa, Matthias Traube et al.
Open ↗

Affine Option Pricing with Hawkes-Type Endogenous Jump Activity

arxiv Published 2026-06-26 · Ziyang Fang, Shenglan Yuan
Open ↗

Agent-Native Immune System: Architecture, Taxonomy, and Engineering

arxiv Published 2026-06-26 · Bo Shen, Lifeng Chang, Tianyuan Wei et al.
Open ↗

Parameter Efficient Hybrid Transformer (PEHT) for Network Traffic Prediction via Dynamic Urban Congestion Integration

arxiv Published 2026-06-26 · Abdolazim Rezaei, Mehdi Sookhak, Mahboobeh Haghparast
Open ↗

Revealing precision bounds on neutrino oscillation parameters with quantum estimation theory

arxiv Published 2026-06-26 · Jihong Huang, Tommy Ohlsson, Sampsa Vihonen et al.
Open ↗

PAC-Bayesian Certificates for Quadratic Closed-Loop Control

arxiv Published 2026-06-26 · Domagoj Herceg
Open ↗

DexCompose: Reusing Dexterous Policies for Multi-Task Manipulation with a Single Hand

arxiv Published 2026-06-26 · Dihong Huang, Zhenyu Wei, Zhuxiu Xu et al.
Open ↗

Jun 27, 20266

Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments

huggingface ▲ 18 Published 2026-06-24 · Mykola Vysotskyi, Runqi Lin, Grzegorz Biziel et al.
🎓 University of Oxford
Open ↗

LISA: Likelihood Score Alignment for Visual-condition Controllable Generation

huggingface ▲ 13 Published 2026-06-24 · Yanghao Wang, Hongxu Chen, Jiazhen Liu et al.
🎓 HKUST
Open ↗

Information-Aware KV Cache Compression for Long Reasoning

huggingface ▲ 10 Published 2026-06-24 · Jushi Kai, Zhuiri Xiao, Alexandra Birch et al.
Open ↗

Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents

huggingface ▲ 8 Published 2026-06-23 · Changdae Oh, Wendi Li, Seongheon Park et al.
🎓 University of Wisconsin - Madison
Open ↗

ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation

huggingface ▲ 4 Published 2026-06-21 · Anindya Mondal, Sauradip Nag, Anjan Dutta
Open ↗

Jun 26, 202656

Scalable Behavior Cloning with Open Data, Training, and Evaluation

arxiv Published 2026-06-25 · Arthur Allshire, Himanshu Gaurav Singh, Ritvik Singh et al.
#transformers
Open ↗

DnA: Denoising Attention for Visual Tasks

arxiv Published 2026-06-25 · Ron Campos, Subhajit Maity, Xin Li et al.
#transformers
Open ↗

RayPE: Ray-Space Positional Encoding for 3D-Aware Video Generation

arxiv Published 2026-06-25 · Minghao Yin, Jiahao Lu, Wenbo Hu et al.
#transformers
Open ↗

SAM2Matting: Generalized Image and Video Matting

arxiv Published 2026-06-25 · Ruiqi Shen, Guangquan Jie, Chang Liu et al.
#foundational
Open ↗

RoPEMover: Depth-Aware Object Relocation via Positional Embeddings

arxiv Published 2026-06-25 · Ipek Oztas, Duygu Ceylan, Aybars Bugra Aksoy et al.
#transformers
Open ↗

Sculpting NeRF Geometry: Human-Preference Fine-Tuning of a 3D-Aware Face GAN

arxiv Published 2026-06-25 · Archer Moore, Mingming Gong, Liam Hodgkinson
#pretraining
Open ↗

LA4VLA: Learning to Act without Seeing via Language-Action Pretraining

arxiv Published 2026-06-25 · Tao Lin, Yuxin Du, Yiran Mao et al.
#pretraining
Open ↗

How Good Can Linear Models Be for Time-Series Forecasting?

huggingface ▲ 4 Published 2026-06-25 · Lang Huang, Jinglue Xu, Luke Darlow
#transformers
🏢 Sakana AI
Open ↗

RSPC: A Benchmark for Modeling Stress and Psychiatric Conditions in Digitally Mediated Relationships using Psychiatrist Annotations

arxiv Published 2026-06-25 · Parmitha Vangapandu, Sai Ganesh Mokkapati, Sathwik Narkedimilli et al.
#nlp
Open ↗

Evaluating Architectural Trade-offs in CGRAs: The Impact of Scratchpad Memory and Heterogeneity on Compute-Intensive Kernels

arxiv Published 2026-06-25 · María José Belda, Lara Orlandic, Fernando Castro et al.
#transformers
Open ↗

CARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear Attention

arxiv Published 2026-06-25 · Sayak Dutta
#transformers
Open ↗

Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement

arxiv Published 2026-06-25 · Sangwoo Cho, Kushal Chawla, Pengshan Cai et al.
#nlp
Open ↗

World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays

arxiv Published 2026-06-25 · Manish Kumar Govind, Dominick Reilly, Smit Patel et al.
Open ↗

Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models

arxiv Published 2026-06-25 · Shravan Venkatraman, Ritesh Thawkar, Omkar Thawakar et al.
Open ↗

Don't Settle at the Mode! Mitigating Diversity Collapse in Pretrained Flow Models via Feature Self-Guidance

arxiv Published 2026-06-25 · Pradhaan S Bhat, Rishubh Parihar, Abhijnya Bhat et al.
Open ↗

Accessing both electrochemical SEIRA and SERS with ultrasensitive metamaterials for enhanced molecular identification

arxiv Published 2026-06-25 · Nicolas Spiesshofer, Tabitha Jones, Sarah May Sibug Torres et al.
Open ↗

PhysiFormer: Learning to Simulate Mechanics in World Space

huggingface ▲ 9 Published 2026-06-25 · Yiming Chen, Yushi Lan, Andrea Vedaldi
Open ↗

Mapping Political-Elite Networks in Europe with a Multilingual Joint Entity-Relation Extraction Pipeline

arxiv Published 2026-06-25 · Kirill Solovev, Jana Lasser
Open ↗

Hallucination in World Models is Predictable and Preventable

huggingface ▲ 8 Published 2026-06-25 · Nicklas Hansen, Xiaolong Wang
🎓 University of California at San Diego
Open ↗

Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoencoders

arxiv Published 2026-06-25 · Nathanaël Jacquier, Maria Vakalopoulou, Mahdi S. Hosseini
Open ↗

OctoSense: Self-Supervised Learning for Multimodal Robot Perception

arxiv Published 2026-06-25 · Anthony Bisulco, Jeremy Wang, Kostas Daniilidis et al.
Open ↗

ViQ: Text-Aligned Visual Quantized Representations at Any Resolution

huggingface ▲ 38 Published 2026-06-25 · Xumin Yu, Zuyan Liu, Zhenyu Yang et al.
🏢 Tencent Hunyuan
Open ↗

Massive Cosmological Correlators from Flat Space: a Laplace-Space Approach

arxiv Published 2026-06-25 · Nathan Belrhali, Arthur Poisson, Sébastien Renaux-Petel
Open ↗

Laplace Space for Cosmological Correlators

arxiv Published 2026-06-25 · Nathan Belrhali, Arthur Poisson, Sébastien Renaux-Petel
Open ↗

See & Sniff: Learning Visuo-Olfactory Representations

arxiv Published 2026-06-25 · Seongyu Kim, Seungwoo Lee, Hyeonggon Ryu et al.
Open ↗

EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting

huggingface ▲ 2 Published 2026-06-25 · Junwei Luo, Shuai Yuan, Zhenya Yang et al.
Open ↗

The SPOTLIGHT Multibeam Real-Time Transient Detection System

arxiv Published 2026-06-25 · Ujjwal Panda, Jayanta Roy, Kshitij Bane et al.
Open ↗

CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies

huggingface ▲ 9 Published 2026-06-14 · Issa Sugiura, Daichi Hattori, Kazuo Araragi et al.
Open ↗

Discretizing Reward Models

huggingface ▲ 12 Published 2026-06-18 · Vijay Viswanathan, Shiqi Wang, Devamanyu Hazarika et al.
🏢 AI at Meta
Open ↗

JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting

huggingface ▲ 32 Published 2026-06-24 · Lanxiang Hu, Zhaoxiang Feng, Yulun Wu et al.
Open ↗

How Post-Training Shapes Biological Reasoning Models

huggingface ▲ 3 Published 2026-06-14 · Lukas Fesser, Hanlin Zhang, Michelle M. Li et al.
Open ↗

The Verification Horizon: No Silver Bullet for Coding Agent Rewards

huggingface ▲ 42 Published 2026-06-23 · Binghai Wang, Chenlong Zhang, Dayiheng Liu et al.
🏢 Qwen
Open ↗

GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents

huggingface ▲ 28 Published 2026-06-21 · Xiao Zhou, Siyue Zhang, Yilun Zhao et al.
Open ↗

Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

huggingface ▲ 15 Published 2026-06-23 · Yupu Hao, Zhuoran Jin, Huanxuan Liao et al.
🎓 Chinese Academic of Science Institute of Automation
Open ↗

OpenBioRQ: Unsolved Biomedical Research Questions for Agents

huggingface ▲ 3 Published 2026-06-19 · Minbyul Jeong
Open ↗

In-Context World Modeling for Robotic Control

huggingface ▲ 45 Published 2026-06-24 · Siyin Wang, Junhao Shi, Senyu Fei et al.
🏢 OpenMOSS
Open ↗

Confidence-Aware Tool Orchestration for Robust Video Understanding

huggingface ▲ 9 Published 2026-06-24 · Yangfan He, Yujin Choi, Jaehong Yoon
🎓 Nanyang Technological University Singapore
Open ↗

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

huggingface ▲ 40 Published 2026-06-24 · Shuo Yang, Jinyang Wu, Zhengxi Lu et al.
Open ↗

Fast LeWorldModel

huggingface ▲ 22 Published 2026-06-23 · Yuntian Gao, Xiangyu Xu
Open ↗

COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami

huggingface ▲ 4 Published 2026-06-23 · Tom Zahavy, Shaobo Hou, Thomas Tumiel et al.
🏢 GoogleDeepMind
Open ↗

Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation

huggingface ▲ 41 Published 2026-06-24 · Zekai Zhang, Jiahao Li, Jie Zhang et al.
🏢 Qwen
Open ↗

DanceOPD: On-Policy Generative Field Distillation

huggingface ▲ 66 Published 2026-06-24 · Wei Zhou, Xiongwei Zhu, Zelin Xu et al.
🏢 ByteDance Seed
Open ↗

GridVQA-X: A Framework for Evaluating Multimodal Explainability Methods

huggingface ▲ 3 Published 2026-06-01 · Sujay Belsare, Sudarshan Nikhil, Sushant Kumar et al.
🎓 Aikyam Lab
Open ↗

Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation

huggingface ▲ 1 Published 2026-06-23 · Atin Pothiraj, Jaemin Cho, Yue Zhang et al.
Open ↗

Do Thinking Tokens Help with Safety?

huggingface ▲ 1 Published 2026-06-22 · Narutatsu Ri, Abhishek Panigrahi, Sanjeev Arora
🎓 Princeton University
Open ↗

Forecasting Future Behavior as a Learning Task

huggingface ▲ 1 Published 2026-06-08 · Mosh Levy, Yoav Goldberg, Asa Cooper Stickland
Open ↗

Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents

huggingface ▲ 1 Published 2026-06-21 · Aman Mehta, Anupam Datta
🏢 Snowflake
Open ↗

Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach

huggingface ▲ 0 Published 2026-06-18 · Tzu-Chieh Wei, Yi-Cheng Lin, Huang-Cheng Chou et al.
Open ↗

Lite Any Stereo V2: Faster and Stronger Efficient Zero-Shot Stereo Matching

huggingface ▲ 3 Published 2026-06-22 · Junpeng Jing, Ronglai Zuo, Zhelun Shen et al.
🎓 Imperial College London
Open ↗

PrivacyAlign: Contextual Privacy Alignment for LLM Agents

huggingface ▲ 3 Published 2026-06-18 · Manveer Singh Tamber, Abhay Puri, Marc-Etienne Brunet et al.
Open ↗

What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics

huggingface ▲ 3 Published 2026-06-22 · Sofiia Nikolenko, Michele Papucci, Mina Rezaei et al.
Open ↗

Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation

huggingface ▲ 1 Published 2026-06-17 · Hyun-Kurl Jang, Jihun Kim, Hyeokjun Kweon et al.
Open ↗

ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation

huggingface ▲ 5 Published 2026-06-21 · Chen Lin, Kedi Chen, Wei Zhang
🎓 East China Normal University
Open ↗

Jun 25, 202658

Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models

huggingface ▲ 8 Published 2026-06-23 · Kaiwen Zheng, Guande He, Min Zhao et al.
#transformers
🏢 NVIDIA
Open ↗

TacVerse: A Multi-Sensor Dataset and Benchmark for Cross-Sensor Vision-Based Tactile Perception

arxiv Published 2026-06-24 · Lan Wei, Gurmeher Khurana, Sirine Bhouri et al.
#pretraining
Open ↗

SurgAtlas: A Large-Scale Surgical Video-Language Dataset with 2,391 Hours of Open and Minimally Invasive Surgery

arxiv Published 2026-06-24 · Filippos Bellos, Andre S. Gala-Garza, Miaowei Wang et al.
#pretraining
Open ↗

Klein--Gordon Dynamics from Intrinsic Phase Periodicity

arxiv Published 2026-06-24 · Emiliano Puddu
#foundational
Open ↗

Relativity Without Light: Homogeneity, Isotropy, and Determinism Force Quadratic Spacetime Metrics

arxiv Published 2026-06-24 · Deon Nicholas
#foundational
Open ↗

Natural Ungrokking: Asymmetric Control of Which Rules Survive Pretraining

arxiv Published 2026-06-24 · Juliana Li, Diya Sreedhar
#pretraining
Open ↗

ChartWalker: Benchmarking the Cross-Chart RAG Task

huggingface ▲ 2 Published 2026-06-21 · Ning Tang, Chenghan Xie, Hanyang Yuan et al.
🎓 Beijing Academy of Artificial Intelligence
Open ↗

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

huggingface ▲ 0 Published 2026-06-22 · Honglin Guo, Qi Zhang, Yu Zhang et al.
Open ↗

Semantic Browsing: Controllable Diversity for Image Generation

huggingface ▲ 14 Published 2026-06-21 · Sara Dorfman, Maya Vishnevsky, Omer Dahary et al.
Open ↗

Multi4D: High-Fidelity Dynamic Gaussian Splatting via Multi-Level Competitive Allocation

huggingface ▲ 0 Published 2026-06-19 · Rui Wang, Quentin Lohmeyer, Siyu Tang et al.
Open ↗

Critique of Agent Model

huggingface ▲ 16 Published 2026-06-21 · Eric Xing, Mingkai Deng, Jinyu Hou
🎓 SAILING Lab (CMU & MBZUAI)
Open ↗

VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct

huggingface ▲ 4 Published 2026-06-21 · Haoling Li, Kai Zheng, Jie Wu et al.
🏢 Tencent Hunyuan
Open ↗

MEMPROBE: Probing Long-Term Agent Memory via Hidden User-State Recovery

huggingface ▲ 1 Published 2026-06-22 · Enze Ma, Yufan Zhou, Wei-Chieh Huang et al.
🎓 University of California at San Diego
Open ↗

Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models

huggingface ▲ 31 Published 2026-06-22 · Lianghua Huang, Zhifan Wu, Wei Wang et al.
🏢 Wan-AI
Open ↗

Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods

huggingface ▲ 6 Published 2026-06-22 · Xingsong Ye, Yongkun Du, Jiaxin Zhang et al.
🎓 Fudan University
Open ↗

IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation

huggingface ▲ 13 Published 2026-06-22 · Zixuan Li, Haokun Lin, Yicheng Xiao et al.
🏢 Ant Group
Open ↗

Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence

huggingface ▲ 26 Published 2026-06-15 · Xuanle Zhao, Qiushi Sun, Jingyu Xiao et al.
Open ↗

Improved Large Language Diffusion Models

huggingface ▲ 21 Published 2026-06-23 · Shen Nie, Qiyang Min, Shaoxuan Xu et al.
🏢 ByteDance Seed
Open ↗

RoPE-Aware Bit Allocation for KV-Cache Quantization

huggingface ▲ 3 Published 2026-06-22 · Fengfeng Liang, Yuechen Zhang, Jiaya Jia
Open ↗

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

huggingface ▲ 7 Published 2026-06-21 · Haggai Roitman
Open ↗

DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation

huggingface ▲ 46 Published 2026-06-23 · Nan Chen, Yiyang Cai, Rongchang Xie et al.
Open ↗

Autodata: An agentic data scientist to create high quality synthetic data

huggingface ▲ 6 Published 2026-06-23 · Ilia Kulikov, Chenxi Whitehouse, Tianhao Wu et al.
🏢 AI at Meta
Open ↗

Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do

huggingface ▲ 6 Published 2026-06-20 · Zhuoran Jin, Kejian Zhu, Hongbang Yuan et al.
🎓 Chinese Academic of Science Institute of Automation
Open ↗

Are We Ready For An Agent-Native Memory System?

huggingface ▲ 59 Published 2026-06-22 · Wei Zhou, Xuanhe Zhou, Shaokun Han et al.
🎓 Shanghai Jiao Tong University
Open ↗

EBench: Elemental Diagnosis of Generalist Mobile Manipulation Policies

huggingface ▲ 12 Published 2026-06-19 · Ning Gao, Jinliang Zheng, Xing Gao et al.
🏢 Intern Robotics
Open ↗

V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning

huggingface ▲ 15 Published 2026-06-23 · Haoxiang Sun, Zhihang Yi, Langxuan Deng et al.
🎓 Sichuan University Alumni
Open ↗

UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating

huggingface ▲ 8 Published 2026-06-18 · Jiehui Huang, Yuechen Zhang, Bin Xia et al.
🏢 Kling Team
Open ↗

When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents

huggingface ▲ 3 Published 2026-06-17 · Kaiyue Yang, Yuyan Bu, Jingwei Yi et al.
🎓 Beijing Academy of Artificial Intelligence
Open ↗

CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression

huggingface ▲ 3 Published 2026-06-22 · Morayo Danielle Adeyemi, Ryan A. Rossi, Franck Dernoncourt
Open ↗

RL-Index: Reinforcement Learning for Retrieval Index Reasoning

huggingface ▲ 5 Published 2026-06-14 · Yongjia Lei, Nedim Lipka, Zhisheng Qi et al.
Open ↗

ShutterMuse: Capture-Time Photography Guidance with MLLMs

huggingface ▲ 33 Published 2026-06-23 · Jiayu Li, Yixiao Fang, Tianyu Hu et al.
Open ↗

MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation

huggingface ▲ 19 Published 2026-06-23 · JoungBin Lee, Jaewoo Jung, Jongmin Lee et al.
🎓 KAIST AI
Open ↗

Constraint Tax in Open-Weight LLMs: An Empirical Study of Tool Calling Suppression Under Structured Output Constraints

huggingface ▲ 0 Published 2026-06-23 · Fangzheng Li, Aimin Zhang, Chen Lv
Open ↗

Naturalness Predicts but Does Not Cause Transferability in Image Encodings of Real-World Streams

arxiv Published 2026-06-24 · Faruk Alpay, Baris Basaran
Open ↗

Sequential and Generative Models for Vehicular Distributed MIMO Channel Prediction

arxiv Published 2026-06-24 · Malek Abida, Rafik Zayani, Eric Simon et al.
Open ↗

Molexar: A Unified Multimodal Molecular Foundation Model for Drug Design

arxiv Published 2026-06-24 · Haoyu Lin, Yiyan Liao, Jinmei Pan et al.
Open ↗

Euclid Quick Data Release (Q2) -- The Euclid Galactic Bulge Survey

arxiv Published 2026-06-24 · J. -P. Beaulieu, E. Bachelet, M. Gilles et al.
Open ↗

A 3D-Printable Dataset for Fair Testing and Comparisons of Tactile Sensors

arxiv Published 2026-06-24 · Dexter R. Shepherd, Nicolas Herzig, Phil Husbands et al.
Open ↗

From spectral structure to sensing limits in quantum thermometry

arxiv Published 2026-06-24 · Youssef Aiache, Simone Cavazzoni, Abderrahim El Allati et al.
Open ↗

Single-dish HI Intensity Mapping with the SKAO: Precursor Progress with MeerKAT's Large Area Synoptic Survey (MeerKLASS)

arxiv Published 2026-06-24 · Steven Cunnington, Jingying Wang, Mario G. Santos et al.
Open ↗

A Benchmark for Heterogeneous Stereo Deblurring with Physically- and Epipolar-constrained Cross Attention

arxiv Published 2026-06-24 · Hoju Shin, Jiah Kim, Seung-Wook Kim et al.
Open ↗

Radial Perturbations of Black Holes in DHOST Theories

arxiv Published 2026-06-24 · Christos Charmousis, Simon Iteanu, David Langlois et al.
Open ↗

Cosmology with Tully-Fisher HI Galaxy Surveys

arxiv Published 2026-06-24 · Joël Mayor, Anthony Carr, Khaled Said et al.
Open ↗

Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization

arxiv Published 2026-06-24 · Kamar Hibatallah Baghdadi, Kawther Guoual Belhamidi, Sara Belhadj et al.
Open ↗

Dziri Voicebot: An End-to-End Low-Resource Speech-to-Speech Conversational System for Algerian Dialect

arxiv Published 2026-06-24 · Dihia Lanasri, Fairouz Taki, Asma Kemmoum
Open ↗

Spin modulations in the Rashba-Hubbard chain -- a tensor network study

arxiv Published 2026-06-24 · Jozef Genzor, Roman Krčmár, Andrej Gendiar et al.
Open ↗

A Simple Numerical Method for Non-Gaussian Signal Ensembles in Nonlinear Power Amplifiers

arxiv Published 2026-06-24 · Cameron M. Pike, Animesh Yadav
Open ↗

Geometrically convex return risk measures on AM-algebras

arxiv Published 2026-06-24 · Christian Laudagé
Open ↗

RoboAtlas: Contextual Active SLAM

arxiv Published 2026-06-24 · Alexander Schperberg, Shivam K. Panda, Abraham P. Vinod et al.
Open ↗

On the existence problem of regular Gabor frames

arxiv Published 2026-06-24 · Jaume de Dios Pont, Lukas Liehr, Mitchell A. Taylor
Open ↗

Deviance-style normalization for jointly overdispersed counts

arxiv Published 2026-06-24 · Akshay Balsubramani
Open ↗

Many-Body Second Order Green's Function Theory for Ab Initio Molecular Quantum Electrodynamics

arxiv Published 2026-06-24 · Amirhosein Amini, Jaime Cerda, Leopoldo Mejía et al.
Open ↗

Analytic Approach to Quantum Control Using Quantum Signal Processing

arxiv Published 2026-06-24 · Aishwarya Majumdar, John M. Martyn, Yuan Liu et al.
Open ↗

TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy

huggingface ▲ 5 Published 2026-06-24 · Hao Sun, Hao Yan, Mengting Chen et al.
🏢 Alibaba-Inc
Open ↗

Learning Action Priors for Cross-embodiment Robot Manipulation

arxiv Published 2026-06-24 · Dong Jing, Tianqi Zhang, Jiaqi Liu et al.
Open ↗

Jun 24, 202657

L3Cube-MahaPOS: A Marathi Part-of-Speech Tagging Dataset and BERT Models

arxiv Published 2026-06-23 · Hariom Ingle, Ronit Ghode, Ishwari Gondkar et al.
#nlp#foundational
Open ↗

DiffusionBench: On Holistic Evaluation of Diffusion Transformers

huggingface ▲ 3 Published 2026-06-23 · Xingjian Leng, Jaskirat Singh, Zhanhao Liang et al.
#transformers
Open ↗

FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation

huggingface ▲ 0 Published 2026-06-23 · Haorui Ji, Weizhe Liu, Hongdong Li et al.
#transformers
🏢 ByteDance
Open ↗

DDStereo: Efficient Dual Decoder Transformers for Stereo 3D Road Anomaly Detection

arxiv Published 2026-06-23 · Shiyi Mu, Zichong Gu, Zhiqi Ai et al.
#transformers
Open ↗

Paying to Know: Micro-Transaction Markets for Verified Product Information in Agentic E-Commerce

arxiv Published 2026-06-23 · Filippos Ventirozos, Matthew Shardlow
#nlp
Open ↗

Revealing Training Data Exposure in Vision Language Large Models via Parameter Gradients

arxiv Published 2026-06-23 · Zhihao Zhu, Hongyi Tang, Yi Yang et al.
#pretraining
Open ↗

Adaptive Hebbian Memory Routing in Vision Transformers for Few-Shot Learning

arxiv Published 2026-06-23 · Mohammed Yusuf Mujawar, Noorbakhsh Amiri Golilarz
#transformers
Open ↗

EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies

huggingface ▲ 0 Published 2026-06-17 · Ganlin Yang, Zhangzheng Tu, Yuqiang Yang et al.
#foundational
🎓 shanghai ailab
Open ↗

TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization

huggingface ▲ 0 Published 2026-06-21 · Matan Ben-Tov, Mahmood Sharif
#foundational
🎓 Tel Aviv University
Open ↗

InSight: Self-Guided Skill Acquisition via Steerable VLAs

huggingface ▲ 0 Published 2026-06-23 · Maggie Wang, Lars Osterberg, Stephen Tian et al.
🎓 Stanford University
Open ↗

BenchX: Benchmarking AI Models for Cancer Detection and Localization with Demographic and Protocol Biases

arxiv Published 2026-06-23 · Qi Chen, Wenxuan Li, Pedro R. A. S. Bassi et al.
Open ↗

Queues with Correlated Service Times -- the $M/M_D/c$ Model

arxiv Published 2026-06-23 · Qihui Bu, Suman Thapa, Yiqiang Q. Zhao
Open ↗

Stability Checking of Markov Jump Linear Systems via Probabilistic Temporal Logic (Extended Version)

arxiv Published 2026-06-23 · Lena Becker, Holger Hermanns
Open ↗

"Zooming In" on Agentic Web Browsers as Assistive Technologies: A Case Study with a Low-Vision Technology Expert

arxiv Published 2026-06-23 · Laura Colazzo, Giuseppe Anzillotti
Open ↗

Real vs. Complex Spectral Bases for Neural Operators: The Role of Green's Function Alignment

arxiv Published 2026-06-23 · Jason Sulskis, Sathya Ravi
Open ↗

Overview: Extragalactic Continuum Science with the SKAO

arxiv Published 2026-06-23 · Catherine L. Hale, Fatemeh S. Tabatabaei
Open ↗

Exact log-odds representation and mean-field criticality of a growing social group model

arxiv Published 2026-06-23 · Xingfu Ke, Fanyuan Meng
Open ↗

The Bondi--Sachs gauge, BMS frames, and memory in black hole perturbation theory

arxiv Published 2026-06-23 · Andrew Spiers, Adam Pound, Jordan Moxon
Open ↗

DeepBD: A Grounded Agentic Workflow for Variant Prioritization and Diagnosis of Genetic Birth Defects

arxiv Published 2026-06-23 · Shiyu Li, Ziqi Yan, Zhihao Wu et al.
Open ↗

Posterior Refinement: Fast Language Generation via Any-Order Flow Maps

arxiv Published 2026-06-23 · Manan Agarwal, Sheel Shah, Chanhyuk Lee et al.
Open ↗

Autoregressive Processes on Riemannian Manifolds

arxiv Published 2026-06-23 · Meshal Abuqrais, Davide Pigoli
Open ↗

Compact Object-Level Representations with Open-Vocabulary Understanding for Indoor Visual Relocalization

arxiv Published 2026-06-23 · Zhaopeng Cui, Jiarui Hu, Jingbo Liu et al.
Open ↗

UniDrive: A Unified Vision-Language and Grounding Framework for Interpretable Risk Understanding in Autonomous Driving

arxiv Published 2026-06-23 · Xiaowei Gao, Pengxiang Li, Yitai Cheng et al.
Open ↗

Can Scale Save Us From Plasticity Loss in Large Language Models?

arxiv Published 2026-06-23 · J. Fernando Hernandez-Garcia, Tomás Figliolia, Beren Millidge
Open ↗

Unlocking the Full Potential of SKAO Extra-galactic Science with High-multiplex Optical Spectroscopy

arxiv Published 2026-06-23 · Kenneth J Duncan, Natasha Maddox, Daniel J. B Smith et al.
Open ↗

Stellar Wind Driven Alfvén Wing Dynamics in Planetary and Exoplanetary Magnetospheres

arxiv Published 2026-06-23 · Sakshi Gupta, Arnab Basak, Dibyendu Nandy
Open ↗

World Value Models for Robotic Manipulation

huggingface ▲ 1 Published 2026-06-23 · Zhihao Wang, Jianxiong Li, Yu Cui et al.
🏢 ByteDance Seed
Open ↗

BioMedVR: Confusion-Aware Mixture-of-Prompt Experts for Biomedical Visual Reprogramming

arxiv Published 2026-06-23 · Jiaxiang Liu, Tianxiang Hu, Juwei Guan et al.
Open ↗

Metric dimension of $C^{\ast}$-algebras of cocycle twisted transformation groupoids: Growth and dynamical complexity

arxiv Published 2026-06-23 · Arnab Chattopadhyay, Soumalya Joardar
Open ↗

A Grounded Evidence-Retrieval Benchmark and Hybrid RAG Framework for Silicon Pixel Detector R&D

arxiv Published 2026-06-23 · Tianqi Gao, Ruobing Jiang, Dawei Fu et al.
Open ↗

Decentralised AI Training and Inference with BlockTrain

arxiv Published 2026-06-23 · Peter Toth
Open ↗

QG-MIL: A Gated Transformer Aggregator for Domain-Agnostic Multiple Instance Learning in Medical Imaging

huggingface ▲ 1 Published 2026-06-17 · Luca Zedda, Davide Antonio Mura, Cecilia Di Ruberto et al.
Open ↗

LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and Diagnosis

huggingface ▲ 17 Published 2026-06-10 · Shihao Xu, Tiancheng Zhou, Jiatong Ma et al.
🏢 Lyncia
Open ↗

FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation

huggingface ▲ 4 Published 2026-06-22 · Orest Kupyn, Goutam Bhat, Philipp Henzler et al.
🏢 Google
Open ↗

AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction

huggingface ▲ 23 Published 2026-06-21 · Shanhui Zhao, Jiacheng Liu, Guohong Liu et al.
🎓 AIR, Tsinghua University
Open ↗

Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning

huggingface ▲ 6 Published 2026-06-22 · Shiding Zhu, Yudi Qi, Yajie Wang et al.
🎓 Zhejiang University
Open ↗

FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning

huggingface ▲ 1 Published 2026-06-22 · Xirui Li, Zhe Liu, Xiaoqing Ye et al.
Open ↗

An Efficient Method for the Optimal Control of Microgrids Under Uncertainties using Local Reduction

huggingface ▲ 0 Published 2026-06-09 · Edoardo Scaccia, Eric C. Kerrigan, Anna Sadowska
🎓 Zhejiang University
Open ↗

NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?

huggingface ▲ 38 Published 2026-06-22 · Yuru Wang, Lejun Cheng, Yuxin Zuo et al.
🏢 Frontis AI
Open ↗

DREAM: Dense Retrieval Embeddings via Autoregressive Modeling

huggingface ▲ 1 Published 2026-06-22 · Yixuan Tang, Yi Yang
Open ↗

FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs

huggingface ▲ 9 Published 2026-06-21 · Wenlong Cheng, Yuan Gan, Yunqiu Xu et al.
Open ↗

ReMMD: Realistic Multilingual Multi-Image Agentic Verification for Multimodal Misinformation Detection

huggingface ▲ 1 Published 2026-06-22 · Chenhao Dang, Dantong Zhu, Jun Yang et al.
🎓 OpenDataLab
Open ↗

Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning

huggingface ▲ 0 Published 2026-06-22 · Chenhao Dang, Jing Ma, Mingjie Liao
🎓 OpenDataLab
Open ↗

Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning

huggingface ▲ 5 Published 2026-06-22 · Jiayi Lei, Yuandong Pu, Xingyu Han et al.
Open ↗

Qwen-AgentWorld: Language World Models for General Agents

huggingface ▲ 58 Published 2026-06-22 · Yuxin Zuo, Zikai Xiao, Li Sheng et al.
🏢 Qwen
Open ↗

MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management

huggingface ▲ 21 Published 2026-06-17 · Guangyi Liu, Gao Wu, Congxiao Liu et al.
🏢 kwai
Open ↗

OpenThoughts-Agent: Data Recipes for Agentic Models

huggingface ▲ 5 Published 2026-06-22 · Negin Raoof, Richard Zhuang, Marianna Nezhurina et al.
Open ↗

MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization

huggingface ▲ 23 Published 2026-06-17 · Guangyi Liu, Pengxiang Zhao, Gao Wu et al.
🏢 kwai
Open ↗

Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning

huggingface ▲ 3 Published 2026-06-16 · Xiaoyue Xu, Sikui Zhang, Xiaorong Wang et al.
🏢 OpenBMB
Open ↗

Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild

huggingface ▲ 2 Published 2026-06-21 · Yehonathan Litman, Xiaoxuan Ma, Manan Shah et al.
Open ↗

Comparing Linear Probes with Mahalanobis Cosine Similarity

huggingface ▲ 3 Published 2026-06-16 · Zhuofan Josh Ying, Peter Hase, Nikolaus Kriegeskorte
Open ↗

ShotcreteDepth: A Bi-modal Dataset for Robust Robotic Depth Perception in Shotcrete Construction Environments

huggingface ▲ 0 Published 2026-06-21 · Jakub Gregorek, Lars Arnold Dethlefsen, Patrick Schmidt et al.
🏢 DTU - Perception and Cognition for Autonomous Systems
Open ↗

When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents

huggingface ▲ 1 Published 2026-06-21 · Aman Mehta
🏢 Snowflake
Open ↗

Go-with-the-Track: Video Compositing and Motion Control with Point Tracking

huggingface ▲ 2 Published 2026-06-17 · Koichi Namekata, Yash Kant, Zhizheng Liu et al.
🎓 Eyeline Labs
Open ↗

Libretto: Giving LLM Agents a Sense of Musical Structure

huggingface ▲ 1 Published 2026-06-20 · Yichen Xu
🎓 University of California, Berkeley
Open ↗

A Verifiable Search Is Not a Learnable Chain-of-Thought

huggingface ▲ 3 Published 2026-06-19 · Harsh Patel
Open ↗

Jun 23, 202658

PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning

huggingface ▲ 6 Published 2026-06-18 · Youngjoon Jeong, Jihwan Yu, Minsoo Jo et al.
#pretraining
🎓 Seoul National University
Open ↗

UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation

huggingface ▲ 2 Published 2026-06-21 · Yohann Perron, Guillaume Astruc, Nicolas Gonthier et al.
#transformers
Open ↗

Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers

arxiv Published 2026-06-22 · Tianyi Li, Zhiqiang Shen
#transformers
Open ↗

Vera: A Layered Diffusion Model for Content-Preserving Video Editing

arxiv Published 2026-06-22 · Hongkai Zheng, Ta-Ying Cheng, Benjamin Klein et al.
#transformers
Open ↗

Muown Implicitly Performs Angular Step-size Decay

arxiv Published 2026-06-22 · Florian Hübler, Kai Lion, Antonio Orvieto et al.
#transformers
Open ↗

The Table Says Otherwise: Testing LLMs with Counterfactual Relational Data

arxiv Published 2026-06-22 · Xinzhi Wang, Chunwei Liu
#pretraining
Open ↗

Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?

arxiv Published 2026-06-22 · Dingzhi Yu, Hongyi Tao, Yuanyu Wan et al.
#pretraining
Open ↗

HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization

huggingface ▲ 14 Published 2026-06-17 · Zhentao Tan, Wei Chen, Jingyi Shen et al.
Open ↗

World Action Models: A Survey

huggingface ▲ 30 Published 2026-06-17 · Qiuhong Shen, Shihua Zhang, Yue Liao et al.
🎓 National University of Singapore
Open ↗

PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems

huggingface ▲ 52 Published 2026-06-20 · Jiayu Liu, Qihan Lin, Cheng Qian et al.
🎓 University of Illinois at Urbana-Champaign
Open ↗

Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning

huggingface ▲ 4 Published 2026-06-17 · Yanxi Chen, Weijie Shi, Yuexiang Xie et al.
🎓 TongyiLab
Open ↗

Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation

huggingface ▲ 12 Published 2026-06-16 · Zhilin Huang, Hang Gao, Ziqiang Dong et al.
🏢 QwenBusinessUnit-Edu
Open ↗

OpenRath: Session-Centered Runtime State for Agent Systems

huggingface ▲ 11 Published 2026-06-16 · Fukang Wen, Zhijie Wang, Ruilin Xu
Open ↗

Safe Few-Step Generation via Velocity Editing

huggingface ▲ 3 Published 2026-06-21 · Yujin Choi, Jaehong Yoon
🎓 Nanyang Technological University Singapore
Open ↗

PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models

huggingface ▲ 1 Published 2026-06-20 · Xianghui Wang, Feng Chen, Wenbo Zhang et al.
🎓 sichuan university
Open ↗

EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions

huggingface ▲ 51 Published 2026-06-21 · Jincheng Zhong, Weizhi Wang, Che Jiang et al.
🏢 Frontis AI
Open ↗

Causal Discovery in the Era of Agents

huggingface ▲ 3 Published 2026-06-21 · Yujia Zheng, Vishal Verma, Mantej Gill et al.
🎓 Carnegie Mellon University
Open ↗

Self-Compacting Language Model Agents

huggingface ▲ 6 Published 2026-06-21 · Tianjian Li, Jingyu Zhang, William Jurayj et al.
Open ↗

Training Open Models for Agentic Phone Use

huggingface ▲ 4 Published 2026-06-21 · Zhengyang Tang, Xin Lai, Pengyuan Lyu et al.
🏢 Tencent Hunyuan
Open ↗

CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents

huggingface ▲ 21 Published 2026-06-21 · Zhanbo Hua, Yifan Yao, Weihao Xie et al.
🎓 NJU-LINK Lab
Open ↗

Unlimited OCR Works

huggingface ▲ 6 Published 2026-06-21 · Youyang Yin, Huanhuan Liu, YY et al.
🏢 BAIDU
Open ↗

FastMix: Fast Data Mixture Optimization via Gradient Descent

huggingface ▲ 0 Published 2026-06-11 · Haoru Tan, Sitong Wu, Yanfeng Chen et al.
🏢 Tencent Hunyuan
Open ↗

Tmax: A simple recipe for terminal agents

huggingface ▲ 3 Published 2026-06-21 · Hamish Ivison, Junjie Oscar Yin, Rulin Shao et al.
Open ↗

DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams

huggingface ▲ 34 Published 2026-06-18 · Cong Wan, Zeyu Guo, Zijian Cai et al.
Open ↗

HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions

huggingface ▲ 0 Published 2026-06-21 · Yuichi Tateno
🏢 HAKARI-Bench
Open ↗

MeshFlow: Mesh Generation with Equivariant Flow Matching

huggingface ▲ 1 Published 2026-06-21 · Qi Sun, Kiyohiro Nakayama, Jing Nathan Yan et al.
Open ↗

Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents

huggingface ▲ 5 Published 2026-06-21 · Haoran Zhang, Yifu Lu, Boyang Wang et al.
🎓 University of Michigan
Open ↗

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

huggingface ▲ 4 Published 2026-06-19 · Xuanming Zhang, Sining Zhoubian, Yuxuan Chen et al.
🏢 Qwen
Open ↗

Improving Text-to-Music Generation with Human Preference Rewards

huggingface ▲ 0 Published 2026-06-18 · Yonghyun Kim, Junwon Lee, Haiwen Xia et al.
🏢 TuneJury
Open ↗

SkillHarness: Harnessing Safe Skills for Computer-Use Agents

huggingface ▲ 11 Published 2026-06-01 · Yurun Chen, Biao Yi, Keting Yin et al.
🎓 Zhejiang University
Open ↗

BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language

huggingface ▲ 13 Published 2026-06-19 · Qizhi Pei, Zhimeng Zhou, Yi Duan et al.
🎓 shanghai ailab
Open ↗

Notes2Skills: From Lab Notebooks to Certainty-Aware Scientific Agent Skills

huggingface ▲ 5 Published 2026-06-09 · Shi Liu, Jiayao Chen, Chengwei Qin et al.
🎓 Southern university of science and technology
Open ↗

Counsel: A Meta-Evaluation Dataset for Agentic Tasks

huggingface ▲ 2 Published 2026-06-18 · Sashank Pisupati, Henry Broomfield, Eujeong Choi et al.
🏢 Atla
Open ↗

SQLConductor: Search-to-Policy Learning for Step-wise Text-to-SQL Orchestration

arxiv Published 2026-06-22 · Yizhang Zhu, Zhangyang Peng, Boyan Li et al.
Open ↗

HeteroViT: A Versatile Single-Layer Vision Transformer Concept, Co-Designed for Distributed Real-Time Data Reduction on Scientific Detectors

arxiv Published 2026-06-22 · Abhilasha Dave, Weijian Zheng, Antonino Miceli et al.
Open ↗

AwakeForest: An Interactive Geospatial Platform for Large-Scale Forest Imagery

arxiv Published 2026-06-22 · Suraj Prasai, Kangning Cui, Rongkun Zhu et al.
Open ↗

The Energy Consumption of Transformer Fine-Tuning: A Roofline-Inspired Scaling Model

arxiv Published 2026-06-22 · Mansour Zoubeirou a Mayaki
Open ↗

Skewness tunes the small-drift record rate of random walks and Lévy flights

arxiv Published 2026-06-22 · José Ricardo G. Mendonça
Open ↗

Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views

huggingface ▲ 2 Published 2026-06-22 · Jiho Choi, Seonho Lee, Seojeong Park et al.
🎓 KAIST AI
Open ↗

LangMAP: A Language-Adaptive Approach to Tokenization

arxiv Published 2026-06-22 · Clara Meister, Suchir Salhan, Andrzej Szablewski et al.
Open ↗

INCARBench: A Benchmark for Scientific Configuration in VASP INCAR by Large Language Models

arxiv Published 2026-06-22 · Bin Shao, Jixiang Li, Xinyue Zhang et al.
Open ↗

A Generative Model for Closed-Loop Microsimulation of Signalized Intersections

arxiv Published 2026-06-22 · Yash Ranjan, Rahul Sengupta, Anand Rangarajan et al.
Open ↗

The Topology of Ill-Posed Questions: Persistent Homology for Detection and Steering in LLMs

arxiv Published 2026-06-22 · Guangyu Jiang, Sizhe Tang, Mahdi Imani et al.
Open ↗

Random dimension reduction and learning symmetric properties of quantum states

arxiv Published 2026-06-22 · Angus Lowe, Xinyu Tan
Open ↗

Real-Time Multimodal Activity-Aware Error Detection in Robot-Assisted Surgery

arxiv Published 2026-06-22 · Seyed Hamid Reza Roodabeh, Zongyu Li, Homa Alemzadeh
Open ↗

Neural Networks as Linear Regression: An Introduction for Statisticians

arxiv Published 2026-06-22 · Abigail Loe, Susan Murray, Zhenke Wu
Open ↗

Polycepta: Object-Centric Appearance Estimation for Multi-Object Tracking

arxiv Published 2026-06-22 · Mohamed Nagy, Naoufel Werghi, Jorge Dias et al.
Open ↗

One country, multiple portraits: representativeness in GPS-based mobility data is source-specific and spatially dependent

arxiv Published 2026-06-22 · Carmen Cabrera, Francisco Rowe, Miguel González-Leonardo et al.
Open ↗

DiT-Reward: Generative Representations for Text-to-Image Reward Modeling

arxiv Published 2026-06-22 · Yuanming Yang, Guoqing Ma, Bo Wang et al.
Open ↗

Pose Anything Anywhere:Model-free Object Poses from Arbitrary References

arxiv Published 2026-06-22 · Hongli Xu, Jiaqi Hu, Junwen Huang et al.
Open ↗

Learning Process Rewards via Success Visitation Matching for Efficient RL

arxiv Published 2026-06-22 · Raymond Tsao, Andrew Wagenmaker, Sergey Levine
Open ↗

Flatness Preserves Instruction Following in Vision-Language-Action Models

arxiv Published 2026-06-22 · Haochen Zhang, Yonatan Bisk
Open ↗

Tapered Language Models

huggingface ▲ 1 Published 2026-06-22 · Reza Bayat, Ali Behrouz, Aaron Courville
Open ↗

LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models

arxiv Published 2026-06-22 · Rongxu Cui, Zongzheng Zhang, Jingrui Pang et al.
Open ↗

Randomized YaRN Improves Length Generalization for Long-Context Reasoning

arxiv Published 2026-06-22 · Manas Mehta, Fangcong Yin, Greg Durrett
Open ↗

Jun 22, 20269

Distilling Examples into Task Instructions: Enhanced In-Context Learning for Real-World B2B Conversations

huggingface ▲ 1 Published 2026-06-13 · Guy Rotman, Adi Kopilov, Danit Berger Zalmanson et al.
#nlp
Open ↗

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

huggingface ▲ 46 Published 2026-06-16 · Yueyi Sun, Yuhao Wang, Jason Li et al.
#foundational
🏢 ByteDance
Open ↗

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

huggingface ▲ 5 Published 2026-06-14 · Ye Jin, Yangyang Xu, Jun Zhu et al.
Open ↗

Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models

huggingface ▲ 1 Published 2026-06-14 · Yanming Zhang, Yihan Bian, Jingyuan Qi et al.
🎓 Tianyi Lab
Open ↗

GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning

huggingface ▲ 3 Published 2026-06-15 · Haoyu Wang, Guoqing Ma, Zeyu Zhang et al.
🎓 Peking University
Open ↗

SpatialAvatar-0: High-Quality 4D Head Avatar with Multi-Stage Reconstruction

huggingface ▲ 0 Published 2026-06-13 · Yiran Wang, Zeyu Zhang, Yuanming Li et al.
Open ↗

GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents

huggingface ▲ 7 Published 2026-06-16 · Zhe Ren, Yibo Yang, Yimeng Chen et al.
Open ↗

BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation

huggingface ▲ 5 Published 2026-06-16 · Max Van Puyvelde, Ibrahim Gulluk, Wim Van Criekinge et al.
🎓 Gevaert Lab
Open ↗

WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents

huggingface ▲ 3 Published 2026-06-16 · Yehang Zhang, Jianchong Su, Haojian Huang et al.
Open ↗

Jun 20, 20269

LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents

huggingface ▲ 6 Published 2026-06-17 · Md Nayem Uddin, Amir Saeidi, Eduardo Blanco et al.
🎓 Arizona State University
Open ↗

Context-Aware RL for Agentic and Multimodal LLMs

huggingface ▲ 11 Published 2026-06-14 · Peiyang Xu, Bangzheng Li, Sijia Liu et al.
🎓 Princeton University
Open ↗

Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States

huggingface ▲ 6 Published 2026-06-16 · Denis Peskoff, Joe Barrow, Christopher Vu et al.
🏢 LOCUS
Open ↗

ReSyn: A Generalized Recursive Regular Expression Synthesis Framework

huggingface ▲ 2 Published 2026-06-12 · Seongmin Kim, Hyunjoon Cheon, Su-Hyeon Kim et al.
Open ↗

LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI

huggingface ▲ 5 Published 2026-06-15 · Lalit Yadav, Akshaj Gurugubelli
🏢 Independent Research
Open ↗

Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why

huggingface ▲ 5 Published 2026-06-16 · Osman Alperen Çinar-Koraş, Marie Bauer, Sameh Khattab et al.
🏢 IKIM
Open ↗

The Data Manifold under the Microscope

huggingface ▲ 3 Published 2026-06-13 · Marios Koulakis, Constantin Seibold
Open ↗

The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation

huggingface ▲ 5 Published 2026-06-17 · Nicolas Dufour, Alexei A. Efros, Patrick Pérez
🏢 Kyutai
Open ↗

Duration Aware Scheduling for ASR Serving Under Workload Drift

huggingface ▲ 3 Published 2026-03-10 · Darshan Makwana, Yash Jogi, Harsh Kotta et al.
Open ↗

Jun 19, 202656

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

huggingface ▲ 14 Published 2026-06-16 · Yuyang Zhang, Wenyao Zhang, Zekun Qi et al.
#pretraining
🎓 Shanghai Jiao Tong University
Open ↗

Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation

huggingface ▲ 5 Published 2026-06-14 · Zhongzhu Zhou, Qingyang Wu, Junxiong Wang et al.
#pretraining
🏢 Together
Open ↗

Quantum ring all-reduce: communication and privacy advantages for distributed learning

arxiv Published 2026-06-18 · María Gragera Garcés, Lirandë Pira
#foundational
Open ↗

CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges

arxiv Published 2026-06-18 · Helena Bonaldi, Genoveffa Martone, Marco Guerini
#nlp
Open ↗

Rethinking Shrinkage Bias in LLM FP4 Pretraining: Geometric Origin, Systemic Impact, and UFP4 Recipe

huggingface ▲ 7 Published 2026-06-18 · Qian Zhao, Kunlong Chen, Changxin Tian et al.
#pretraining
🏢 inclusionAI
Open ↗

MixProLAP: Mixture-Induced Uncertainty Modeling for Probabilistic Language-Audio Pretraining

arxiv Published 2026-06-18 · Yu Nakagome, Jaesong Lee, Soo-Whan Chung
#pretraining
Open ↗

HEPTv2: End-to-End Efficient Point Transformer for Charged Particle Reconstruction

arxiv Published 2026-06-18 · Siqi Miao, Shitij Govil, Jack P. Rodgers et al.
#transformers
Open ↗

HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining

huggingface ▲ 8 Published 2026-06-18 · Juncheng Ma, Jianxin Bi, Yufan Deng et al.
#pretraining
Open ↗

When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?

huggingface ▲ 3 Published 2026-06-15 · Xuanfei Ren, Tengyang Xie
🎓 University of Wisconsin - Madison
Open ↗

Reinforcement Learning-Guided Retrieval with Soft Fusion for Robust Multimodal Imitation Learning under Missing Modalities

huggingface ▲ 0 Published 2026-06-12 · Hassan Ismkhan, Hamid Bouchahcia
Open ↗

Re-Centering Humans in LLM Personalization

huggingface ▲ 0 Published 2026-06-03 · Lechen Zhang, Jiarui Liu, Tal August
Open ↗

REVES: REvision and VErification--Augmented Training for Test-Time Scaling

huggingface ▲ 2 Published 2026-06-16 · Yuanxin Liu, Ruida Zhou, Xinyan Zhao et al.
Open ↗

Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning

huggingface ▲ 0 Published 2026-06-17 · Sajib Acharjee Dip, Dawei Zhou, Liqing Zhang
🎓 Virginia Polytechnic Institute and State University
Open ↗

LooseControlVideo: Directorial Video Control using Spatial Blocking

huggingface ▲ 0 Published 2026-06-16 · Shariq Farooq Bhat, Niloy J. Mitra, Kalyan Sunkavalli
🏢 Adobe
Open ↗

Thinking with Visual Grounding

huggingface ▲ 4 Published 2026-06-14 · Junkai Zhang, Yihe Deng, Kai-Wei Chang et al.
🎓 University of California, Los Angeles
Open ↗

Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents

huggingface ▲ 17 Published 2026-06-17 · Dhaval C. Patel, Kaoutar El Maghraoui, Shuxin Lin et al.
🏢 IBM
Open ↗

JAMER: Project-Level Code Framework Dataset and Benchmark on Professional Game Engines

huggingface ▲ 3 Published 2026-06-17 · Jianwen Sun, Chuanhao Li, Zizhen Li et al.
Open ↗

Current World Models Lack a Persistent State Core

huggingface ▲ 10 Published 2026-06-17 · Jinpeng Lu, Dexu Zhu, Haoyuan Shi et al.
Open ↗

FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining

huggingface ▲ 25 Published 2026-06-17 · Jinghong Lan, Wei Cheng, Yunuo Chen et al.
🎓 Fudan University
Open ↗

Holo-World: Unified Camera, Object and Weather Control for Video World Model

huggingface ▲ 5 Published 2026-06-17 · Xiangchen Yin, Wenzhang Sun, Jiahui Yuan et al.
Open ↗

ENPIRE: Agentic Robot Policy Self-Improvement in the Real World

huggingface ▲ 10 Published 2026-06-17 · Wenli Xiao, Jia Xie, Tonghe Zhang et al.
🏢 NVIDIA
Open ↗

Adaptive Volumetric Mechanical Property Fields Invariant to Resolution

huggingface ▲ 5 Published 2026-06-15 · Rishit Dagli, Donglai Xiang, Vismay Modi et al.
🏢 NVIDIA
Open ↗

Selective Synergistic Learning for Video Object-Centric Learning

huggingface ▲ 3 Published 2026-06-13 · WonJun Moon, Jae-Pil Heo
🎓 Sungkyunkwan University
Open ↗

FAPO: Fully Autonomous Prompt Optimization of Multi-Step LLM Pipelines

huggingface ▲ 9 Published 2026-06-16 · Paul Kassianik, Baturay Saglam, Huaibo Zhao et al.
🏢 Cisco Foundation AI
Open ↗

Understanding the Behaviors of Environment-aware Information Retrieval

huggingface ▲ 6 Published 2026-06-14 · Ruifeng Yuan, Chaohao Yuan, David Dai et al.
🏢 LCO-Embedding
Open ↗

JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising

huggingface ▲ 19 Published 2026-06-17 · Siang-Ling Zhang, Huai-Hsun Cheng, Tsung-Ju Yang et al.
🎓 National Yang Ming Chiao Tung University
Open ↗

S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence

huggingface ▲ 37 Published 2026-06-17 · Yalun Dai, Hao Li, Shulin Tian et al.
🏢 Ropedia
Open ↗

Playful Agentic Robot Learning

huggingface ▲ 44 Published 2026-06-16 · Junyi Zhang, Jiaxin Ge, Hanjun Yoo et al.
🏢 UC Berkeley
Open ↗

DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis

huggingface ▲ 30 Published 2026-06-17 · Cheng-You Lu, Yi-Shan Hung, Wei-Ling Chi et al.
Open ↗

DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects

huggingface ▲ 69 Published 2026-06-12 · Tianshan Zhang, Yijia Duan, Yanjun Li et al.
🎓 Peking University
Open ↗

FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows

huggingface ▲ 19 Published 2026-06-17 · Daniel Gilo, Sven Elflein, Ido Sobol et al.
🎓 Technion Israel institute of technology
Open ↗

No Resource, No Benchmarks, No Problem? Evaluating and Improving LLMs for Code Generation in No-Resource Languages

huggingface ▲ 3 Published 2026-06-14 · Alessandro Giagnorio, Alberto Martin-Lopez, Gabriele Bavota
Open ↗

A Model-Driven Approach for Developing Families of Reinforcement Learning Environments

arxiv Published 2026-06-18 · Xiaoran Liu, Istvan David
Open ↗

Data dependent Shepard approximation through and adaptive modification of the shape parameter

arxiv Published 2026-06-18 · José Kuruc, Juan Ruiz-Álvarez, Bo Wang et al.
Open ↗

Formalizing Extended Complex Numbers, Mobius Transformations, and Cross Ratio in Lean 4

arxiv Published 2026-06-18 · Fubin Yan, Kenneth W. Shum
Open ↗

Advancing Astrophysics with the SKA II

arxiv Published 2026-06-18 · Anna Bonaldi, Tyler L. Bourke, Philippa Hartley et al.
Open ↗

DataMagic: Transforming Tabular Data into Data Insight Video

arxiv Published 2026-06-18 · Yupeng Xie, Chen Ma, Zhenyang Wang et al.
Open ↗

Geometry-Aware Superpixel Graph Transformer with Metadata for Skin Lesion Classification

arxiv Published 2026-06-18 · Muhammad Azeem, Tanveer Hussain, Amr Ahmed et al.
Open ↗

The Significance of Style Diversity in Annotation-Free Synthetic Data Generation

arxiv Published 2026-06-18 · Zahra Abbasiantaeb, Zeno Belligoli, Omar Essam et al.
Open ↗

On the Redundancy of Timestep Embeddings in Diffusion Models

arxiv Published 2026-06-18 · José A. Chávez
Open ↗

Private Rate-Double-Robust Inference

arxiv Published 2026-06-18 · Máté Kormos, Aad van der Vaart
Open ↗

Shadow Completion in Celestial OPEs

arxiv Published 2026-06-18 · Reiko Liu, Zijian Liu, Wen-Jie Ma
Open ↗

Interpretable Sperm Morphology Classification via Attention-Guided Deep Learning

arxiv Published 2026-06-18 · Zahra Asghari Varzaneh, Reza Khoshkangini, Thomas Ebner et al.
Open ↗

Computing noise-canceling observables via Pauli propagation

arxiv Published 2026-06-18 · Andrew Eddins, Caleb Johnson, Alberto Baiardi et al.
Open ↗

Repurposing a Speech Classifier for Guided Diffusion-Based Speech Generation

arxiv Published 2026-06-18 · Rostislav Makarov, Timo Gerkmann
Open ↗

Fisher-Geometric Sharpness and the Implicit Bias of SGD toward Flat Minima

arxiv Published 2026-06-18 · Md Sakir Ahmed, Kumaresh Sarmah, Hemen Dutta
Open ↗

Many-body chirality of topological stabilizer states

arxiv Published 2026-06-18 · Tyler D. Ellison, Dongjin Lee, Zhi Li et al.
Open ↗

A-COMPASS: Formal Foundations for Anonymity Analysis in Microdata

arxiv Published 2026-06-18 · Tamara Tagliavia, Silvia Ghilezan
Open ↗

Planar constant piecewise smooth vector fields with large hysteresis

arxiv Published 2026-06-18 · Tiago Carvalho, Leonardo Serantola, Bruno de Souza Rangel
Open ↗

Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages

huggingface ▲ 55 Published 2026-06-18 · Maria Ivanova, Pavel Zadorozhny, Rodion Levichev et al.
Open ↗

SARLO-80: Worldwide Slant SAR Language Optic Dataset 80cm

arxiv Published 2026-06-18 · Solène Debuysère, Nicolas Trouvé, Nathan Letheule et al.
Open ↗

DeepSWIP: Quotient-WMC Counterfactuals for Neural Probabilistic Logic Programs

arxiv Published 2026-06-18 · Saimun Habib, Vaishak Belle, Fengxiang He
Open ↗

Multi-Task Bayesian In-Context Learning

arxiv Published 2026-06-18 · Qingyang Zhu, Eric Karl Oermann, Kyunghyun Cho
Open ↗

The Token Is a Group Element: On Lie-Algebra Attention over Matrix Lie Groups

arxiv Published 2026-06-18 · Przemyslaw Musialski
Open ↗

Thinking in Boxes: 3D Editing in Real Images Made Easy

arxiv Published 2026-06-18 · Pradhaan S Bhat, Naveen Chandra R, Rishubh Parihar et al.
Open ↗

UNIEGO: Proxies as Mediators for Unified Egocentric Video Representation Learning

arxiv Published 2026-06-18 · Wenhao Chi, Arkaprava Sinha, Dominick Reilly et al.
Open ↗

Jun 18, 202664

Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection

arxiv Published 2026-06-17 · Jinhan Li, Kexian Tang, Yihan Xu et al.
#foundational#pretraining
Open ↗

EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts

arxiv Published 2026-06-17 · Minseo Kim, Minjae Lee, Seunghyuk Oh et al.
#pretraining
Open ↗

ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection

arxiv Published 2026-06-17 · Jinhao Song, Shan Liang, Yiqun Yue et al.
#foundational
Open ↗

Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training

arxiv Published 2026-06-17 · Ruiqi Lai, Dakai An, Wei Gao et al.
#transformers
Open ↗

Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors

arxiv Published 2026-06-17 · Michael Finkelson, Daniel Segal, Eitan Richardson et al.
#foundational
Open ↗

CollaboratoR: A scalable workflow for collaborative data entry and management

arxiv Published 2026-06-17 · Patrick Bills, Ashwini Ramesh, Lais Petri et al.
#foundational
Open ↗

Patnaik-Pearson intrinsic dimension for internal representations of neural networks

arxiv Published 2026-06-17 · Tom Hadfield
#transformers
Open ↗

Trade-offs in Medical LLM Adaptation: An Empirical Study in French QA

arxiv Published 2026-06-17 · Ikram Belmadani, Oumaima El Khettari, Carlos Ramisch et al.
#pretraining
Open ↗

OneCanvas: 3D Scene Understanding via Panoramic Reprojection

arxiv Published 2026-06-17 · Bartłomiej Baranowski, Dave Zhenyu Chen, Matthias Nießner
#pretraining
Open ↗

Transformer Geometry Observatory TGO-I: Spectral Geometry Observatory

arxiv Published 2026-06-17 · Kaustubh Kapil, Kishor P. Upla
#transformers
Open ↗

When Isolated Quantum Systems Appear Classical

arxiv Published 2026-06-17 · Thiago R. de Oliveira, Pedro S. Correia, Tiago Debarba et al.
#foundational
Open ↗

Dango: A Strictly L1-Only Large Language Model for Studying Second Language Acquisition

arxiv Published 2026-06-17 · Shiho Matta, Yin Jou Huang, Fei Cheng et al.
#pretraining
Open ↗

Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems

huggingface ▲ 1 Published 2026-06-04 · Shaoyang Xu, Jingshen Zhang, Long P. Hoang et al.
#nlp
🎓 iNLP Lab @ SUTD
Open ↗

Kairos: A Native World Model Stack for Physical AI

huggingface ▲ 20 Published 2026-06-15 · Kairos Team, Fei Wang, Shan You et al.
#foundational
Open ↗

Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification

huggingface ▲ 9 Published 2026-06-15 · Wujian Peng, Lingchen Meng, Yuxuan Cai et al.
🏢 Qwen
Open ↗

LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching

huggingface ▲ 31 Published 2026-06-14 · Jaward Sesay, Yue Yu, Siwei Dong et al.
Open ↗

TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs

huggingface ▲ 26 Published 2026-06-07 · Hyeongwon Jang, Gyouk Chu, Changhun Kim et al.
🎓 KAIST AI
Open ↗

Looped World Models

huggingface ▲ 8 Published 2026-06-15 · Hongyuan Adam Lu, Z. L. Victor Wei, Qun Zhang et al.
🏢 FaceMind
Open ↗

ActWorld: From Explorable to Interactive World Model via Action-Aware Memory

huggingface ▲ 5 Published 2026-06-15 · Zhexiao Xiong, Yizhi Song, Hao Kang et al.
🏢 ByteDance
Open ↗

GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?

huggingface ▲ 37 Published 2026-06-15 · Tongxu Luo, Rongsheng Wang, Jiaxi Bi et al.
🎓 Chinese University of Hong Kong, Shenzhen
Open ↗

A Gradient Perspective on RLVR Stability and Winner Advantage Policy Optimization

huggingface ▲ 6 Published 2026-06-14 · Prasanth YSS, Zhichen Ren, Rasa Hosseinzadeh et al.
🏢 Layer 6 AI
Open ↗

Beyond Monolingual Deep Research: Evaluating Agents and Retrievers with Cross-Lingual BrowseComp-Plus

huggingface ▲ 4 Published 2026-06-12 · Yuheng Lu, Qingcheng Zeng, Heli Qi et al.
🎓 UTokyo Yokoya Lab
Open ↗

OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation

huggingface ▲ 22 Published 2026-06-15 · Guibin Zhang, Xun Xu, Yanwei Yue et al.
🎓 National University of Singapore
Open ↗

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

huggingface ▲ 41 Published 2026-06-15 · Byung-Kwan Lee, Ximing Lu, Shizhe Diao et al.
🏢 NVIDIA
Open ↗

Audio-to-Audio via Diffusion Warm Initialization

arxiv Published 2026-06-17 · Cristóbal Andrade, Sebastian J. Schlecht
Open ↗

A Controlled Benchmark of Quantum-Latent GAN Augmentation for Brain MRI

arxiv Published 2026-06-17 · Syed Mujtaba Haider, Silvia Figini
Open ↗

Local Exact Controllability of Landau-Lifshitz-Gilbert Equation

arxiv Published 2026-06-17 · Chunxi Jiao, Ho Man Tai
Open ↗

Not Your Usual FFT: QFT$\rightarrow$FFT via Classical Quantum-Circuit Simulation

arxiv Published 2026-06-17 · Stefano Markidis, Gilbert Netzer, Luca Pennati et al.
Open ↗

Sumi: Open Uniform Diffusion Language Model from Scratch

huggingface ▲ 6 Published 2026-06-17 · Mengyu Ye, Keito Kudo, Wataru Ikeda et al.
Open ↗

Dimension reduction of multivariate densities in Bayes spaces

arxiv Published 2026-06-17 · Adéla Czolková, Karel Hron, Sonja Greven
Open ↗

Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games

huggingface ▲ 34 Published 2026-06-17 · Shengyuan Ding, Xilin Wei, Xinyu Fang et al.
🏢 Intern Large Models
Open ↗

Rigorous analysis for the Dirac system on the quarter-plane

arxiv Published 2026-06-17 · Hassan Babaei, Jerry L. Bona, Andreas Chatziafratis
Open ↗

Explaining Attention with Program Synthesis

arxiv Published 2026-06-17 · Amiri Hayes, Belinda Li, Jacob Andreas
Open ↗

NeuMesh++: Towards Versatile and Efficient Volumetric Editing with Disentangled Neural Mesh-based Implicit Field

arxiv Published 2026-06-17 · Chong Bao, Yuan Li, Bangbang Yang et al.
Open ↗

On two overlooked stick-breaking constructions of the normalized inverse Gaussian process

arxiv Published 2026-06-17 · Annalisa Cerquetti
Open ↗

Confidence is Not Reliability: Rethinking MC Dropout in Brain Tumour Segmentation

arxiv Published 2026-06-17 · Xin Ci Wong, Duygu Sarikaya, Kieran Zucker et al.
Open ↗

Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models

arxiv Published 2026-06-17 · Nikita Kachaev, Andrey Moskalenko, Matvey Skripkin et al.
Open ↗

A Unified Framework for Efficient Remote Sensing Visual Question Answering: Adapting Dual, Hybrid, and Encoder-Decoder Architectures

arxiv Published 2026-06-17 · Timothy Agboada, Shikha Chandel, Yadav Raj Ghimire et al.
Open ↗

Beyond Algorithms: Conceptual Innovation in Medical Imaging AI

arxiv Published 2026-06-17 · Mark A. Anastasio
Open ↗

DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models

arxiv Published 2026-06-17 · Zirui Wu, Lin Zheng, Jiacheng Ye et al.
Open ↗

A Taxonomy of Mental Health and Technology Needs for Alzheimer's and Dementia Caregivers

arxiv Published 2026-06-17 · Keran Wang, Drishti Goel, Jiayue Melissa Shi et al.
Open ↗

Quantum-Classical Auxiliary-Field Quantum Monte Carlo at the Edge of Practicability

arxiv Published 2026-06-17 · Francesco Nappi, Matthew Kiser, Fedor Šimkovic
Open ↗

FineCombo-TTS: Collaborative and Precise Controllable Speech Synthesis Using Text Descriptions and Reference Speech

arxiv Published 2026-06-17 · Shuoyi Zhou, Yixuan Zhou, Peiji Yang et al.
Open ↗

Impact of the Einstein Telescope's duty cycle on the estimation of binary black holes parameters

arxiv Published 2026-06-17 · Luca Negri, Thomas C. K. Ng, Thibeau Wouters et al.
Open ↗

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

huggingface ▲ 36 Published 2026-06-17 · Kangsheng Duan, Ziyang Xu, Wenyu Liu et al.
Open ↗

Learning to Annotate Delayed and False AEB Events: A Practical System for Extreme Class Imbalance and Asymmetric Label Noise

arxiv Published 2026-06-17 · Mengxiang Hao, Xin Jiang, Xinghao Huang et al.
Open ↗

Hardware- and Vision-in-the-Loop Validation of Deep Monocular Pose Estimation for Autonomous Maritime UAV Flight

arxiv Published 2026-06-17 · Maneesha Wickramasuriya, Beomyeol Yu, Jaden Shin et al.
Open ↗

To Gamble, Perchance to Grow

arxiv Published 2026-06-17 · Mark Whitmeyer
Open ↗

Pulse: Training Acceleration for Large Diffusion Models with Automatic Pipeline Parallelism

arxiv Published 2026-06-17 · Boran Sun, Guoyong Jiang, Lin Zhang et al.
Open ↗

SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks

huggingface ▲ 3 Published 2026-06-14 · Jingru Guo, Xiangyuan Xue, Lian Zhang et al.
Open ↗

Native Active Perception as Reasoning for Omni-Modal Understanding

huggingface ▲ 9 Published 2026-06-16 · Zhenghao Xing, Ruiyang Xu, Yuxuan Wang et al.
🏢 Qwen
Open ↗

Reinforcing Dual-Path Reasoning in Spatial Vision Language Models

huggingface ▲ 12 Published 2026-06-15 · Yatai Ji, An-Chieh Cheng, Yang Fu et al.
🎓 University of Hong Kong
Open ↗

SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior

huggingface ▲ 12 Published 2026-06-15 · Mingyue Cui, Linghui Shen, Xingyi Yang
🎓 The Hong Kong Polytechnic University
Open ↗

Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding

huggingface ▲ 12 Published 2026-06-15 · Jingyuan Huang, Zuming Huang, Yucheng Shi et al.
🎓 University of Georgia
Open ↗

IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products

huggingface ▲ 2 Published 2026-06-12 · Haonan Qi, Jin Cao, Yongqi Zhang et al.
🏢 1688 multimodal & industrial AI
Open ↗

Learning User Simulators with Turing Rewards

huggingface ▲ 2 Published 2026-06-16 · Yingshan Susan Wang, Cedegao E. Zhang, Linlu Qiu et al.
🎓 Massachusetts Institute of Technology
Open ↗

PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation

huggingface ▲ 2 Published 2026-06-15 · Yuhang Huang, Xuan Lv, Junyan Xu et al.
Open ↗

Physics-IQ Verified

huggingface ▲ 1 Published 2026-06-16 · Tim Rädsch, Yuki M Asano, Hilde Kuehne et al.
Open ↗

CEO-Bench: Can Agents Play the Long Game?

huggingface ▲ 2 Published 2026-06-15 · Haozhe Chen, Karthik Narasimhan, Zhuang Liu
Open ↗

Externalizing Research Synthesis and Validation in AI Scientists through a Research Harness

huggingface ▲ 2 Published 2026-06-16 · Zijian Wang, Hanqi Li, Ziyue Yang et al.
Open ↗

Guava: An Effective and Universal Harness for Embodied Manipulation

huggingface ▲ 21 Published 2026-06-15 · Haowen Liu, Xirui Li, Shaoxiong Yao et al.
Open ↗

Jun 16, 202620

ARIADNE: Agnostic Routing for Inference-time Adapter DyNamic sElection

arxiv Published 2026-06-17 · Enrico Cassano, Michał Brzozowski, Zuzanna Dubanowska et al.
#nlp
Open ↗

Lifecycle-Aware Dynamic Analysis for Secure ML Model Execution

arxiv Published 2026-06-17 · Gabriele Digregorio, Marco Di Gennaro, Francesco Pastore et al.
#foundational
Open ↗

ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining

huggingface ▲ 40 Published 2026-06-14 · Hao Li, Ganlong Zhao, Yufei Liu et al.
#pretraining
🎓 CUHK
Open ↗

Variable-Width Transformers

huggingface ▲ 5 Published 2026-06-15 · Zhaofeng Wu, Oliver Sieberling, Shawn Tan et al.
#transformers
Open ↗

LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling

huggingface ▲ 116 Published 2026-06-15 · Jian Yang, Shawn Guo, Wei Zhang et al.
#transformers
Open ↗

Smoothness-Based Derandomization of PAC-Bayes Bounds

arxiv Published 2026-06-17 · Alexandre Lemire Paquin, Brahim Chaib-Draa, Philippe Giguère
Open ↗

ART-VS: Adaptive Resolution Tiling for Vision Transformer Visual Servoing

arxiv Published 2026-06-17 · Alessandro Scherl, Bernhard Neuberger, Simon Schwaiger et al.
Open ↗

Retrieval-Based Brain Decoding by Alignment, not Complexity

arxiv Published 2026-06-17 · Matteo Ciferri, Matteo Ferrante, Nicola Toschi
Open ↗

A performance portable fast Ewald summation for Stokes flow

arxiv Published 2026-06-17 · Gabriel Kosmacher, Ziyu Du, Joar Bagge et al.
Open ↗

CHERI-D: Secure and efficient inline object ID for CHERI temporal memory safety

arxiv Published 2026-06-17 · Yuecheng Wang, Jonathan Woodruff, Alfredo Mazzinghi et al.
Open ↗

A Hybrid LSTM--Vision Transformer Architecture for Predicting HRRR Forecast Errors

arxiv Published 2026-06-17 · David Aaron Evans, Jay C. Rothenberger, Kara J. Sulia et al.
Open ↗

On a variational model for phase transformation in SiO2 glass

arxiv Published 2026-06-17 · Sarah Dinkelacker-Steinhoff, Klaus Hackl
Open ↗

Completeness for Probabilistic Boolean Tapes

arxiv Published 2026-06-17 · Filippo Bonchi, Cipriano Junior Cioffo
Open ↗

Text-Vision Co-Instructed Image Editing

huggingface ▲ 13 Published 2026-06-14 · Chenxi Xie, Yuhui Wu, Qiaosi Yi et al.
🎓 VCLab
Open ↗

Learning from the Self-future: On-policy Self-distillation for dLLMs

huggingface ▲ 67 Published 2026-06-15 · Yifu Luo, Zeyu Chen, Haoyu Wang et al.
🎓 Max Planck Institute for Intelligent Systems
Open ↗

Rethinking the Role of Efficient Attention in Hybrid Architectures

huggingface ▲ 12 Published 2026-06-12 · Ziqing Qiao, Yinuo Xu, Chaojun Xiao et al.
🏢 OpenBMB
Open ↗

ChLogic: Evaluating Robustness of Logical Reasoning in Chinese Expressions

huggingface ▲ 6 Published 2026-06-15 · Peixian Zhou, Yuxu Chen, Chaorui Zhang et al.
Open ↗

MotionVLA: Vision-Language-Action Model for Humanoid Motion

huggingface ▲ 2 Published 2026-06-12 · Nonghai Zhang, Siyu Zhai, Yanjun Li et al.
🎓 Peking University
Open ↗

Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion

huggingface ▲ 15 Published 2026-06-15 · Weichen Fan, Haiwen Diao, Penghao Wu et al.
🎓 MMLab@NTU
Open ↗

ProCUA-SFT Technical Report

huggingface ▲ 5 Published 2026-06-14 · Jaehun Jung, Ximing Lu, Brandon Cui et al.
🏢 NVIDIA
Open ↗

Jun 15, 202620

Towards an Agent-First Web: Redesigning the Web for AI Agents

arxiv Published 2026-06-17 · Eranga Bandara, Ross Gore, Ravi Mukkamala et al.
#foundational
Open ↗

Complementary Attention Head Pruning for Efficient Transformers

arxiv Published 2026-06-17 · Yaniv Livertovsky, Shahar Somin, Gonen Singer
#transformers
Open ↗

IndicContextEval: A Benchmark for Evaluating Context Utilisation in Audio Large Language Models Across 8 Indic Languages

arxiv Published 2026-06-17 · Sakshi Joshi, Dhruv Subhash Rathi, Sanskar Singh et al.
#pretraining
Open ↗

RefGC-SR^2: Reference-guided Generated Content Super-Resolution and Refinement

huggingface ▲ 7 Published 2026-06-12 · Jeahun Sung, Dahyeon Kye, Soo Ye Kim et al.
Open ↗

RepSelect: Robust LLM Unlearning via Representation Selectivity

huggingface ▲ 2 Published 2026-06-14 · Filip Sondej, Yushi Yang, Adam Mahdi
🎓 University of Oxford
Open ↗

EgoCS-400K: An Egocentric Gameplay Dataset for World Models

huggingface ▲ 12 Published 2026-06-15 · Rongjin Guo, Dong Liang, Yuhao Liu et al.
🎓 City University of Hong Kong
Open ↗

Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning

huggingface ▲ 3 Published 2026-06-12 · Zhengbo Zhang, Changtao Miao, Jinbo Su et al.
Open ↗

Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion

huggingface ▲ 8 Published 2026-06-11 · Yi Lu, Zhuofeng Li, Ping Nie et al.
🎓 SKY Lab
Open ↗

The Price of Anarchy in Disaggregated Inference

huggingface ▲ 0 Published 2026-06-10 · Athos Georgiou
Open ↗

Self-Evolving Visual Questioner

huggingface ▲ 12 Published 2026-06-10 · Yijun Liang, Hengguang Zhou, Ming Li et al.
🎓 University of Maryland College Park
Open ↗

Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings

huggingface ▲ 2 Published 2026-06-12 · Shubhang Bhatnagar, Dheeraj Baiju, Narendra Ahuja
🎓 University of Illinois at Urbana-Champaign
Open ↗

Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences

huggingface ▲ 2 Published 2026-06-14 · Mingyang Li, Yurou Liu, Jieping Ye et al.
🏢 LOGOS-Hub
Open ↗

Post-Carroll Algebra, Conformal Extensions, and Field Theories

arxiv Published 2026-06-17 · Mojtaba Najafizade
Open ↗

Finite free perpetuities

arxiv Published 2026-06-17 · Julia Le Bihan, Bartosz Kołodziejek
Open ↗

Topology of Bloch Bands from Cauchy Data

arxiv Published 2026-06-17 · Didier Felbacq, Emmanuel Rousseau
Open ↗

Human-AI Coevolution Dynamics: A Formal Theory of Social Intelligence Emergence Through Long-Term Interaction

arxiv Published 2026-06-17 · Jingyi Zhou, Senlin Luo, Haofan Chen
Open ↗

A Symmetry Method for Key Vanishing Lemmas and Optimal $2$-Jet Thresholds for Hyperbolicity

arxiv Published 2026-06-17 · Tao Cui, Lei Hou, Jianjun Liu et al.
Open ↗