| Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models? | Robotics | Guoheng Sun +10 | Jun 26, 2026 | 6 |
| Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE | Image & video gen | Haoyou Deng +6 | Jun 25, 2026 | 6 |
| Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement | Agents | Igor Itkin | Jun 25, 2026 | 6 |
| Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation | Image & video gen | Jiayi Xu +2 | Jun 26, 2026 | 6 |
| MemoBench: Benchmarking World Modeling in Dynamically Changing Environments | Image & video gen | Haoyu Chen +13 | Jun 25, 2026 | 6 |
| TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy | Robotics | Hao Sun +9 | Jun 24, 2026 | 6 |
| Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods | Image & video gen | Xingsong Ye +7 | Jun 23, 2026 | 6 |
| RL-Index: Reinforcement Learning for Retrieval Index Reasoning | Agents | Yongjia Lei +7 | Jun 15, 2026 | 6 |
| VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct | Vision & multimodal | Haoling Li +6 | Jun 22, 2026 | 6 |
| EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies | Robotics | Ganlin Yang +12 | Jun 18, 2026 | 6 |
| Counsel: A Meta-Evaluation Dataset for Agentic Tasks | Speech & audio | Sashank Pisupati +7 | Jun 19, 2026 | 6 |
| LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents | Agents | Md Nayem Uddin +3 | Jun 18, 2026 | 6 |
| Externalizing Research Synthesis and Validation in AI Scientists through a Research Harness | Efficiency & systems | Zijian Wang +17 | Jun 17, 2026 | 6 |
| Morpheus: A Morphology-Aware Neural Tokenizer and Word Embedder for Turkish | Code | Tolga Şakar | Jun 17, 2026 | 6 |
| LoSoNA: A Benchmark for Local Social Norm Adaptation in Group Conversations | Agents | Mateusz Winiarek +2 | Jun 12, 2026 | 6 |
| StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning | Agents | Daoyu Wang +6 | Jun 5, 2026 | 6 |
| An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models | Safety & alignment | Mingzhong Sun +3 | May 31, 2026 | 6 |
| Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior | Safety & alignment | Rafal Kocielnik +7 | Jun 10, 2026 | 6 |
| SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling | Reinforcement learning | Haoran Xu +5 | Jun 8, 2026 | 6 |
| RepWAM: World Action Modeling with Representation Visual-Action Tokenizers | Robotics | Junke Wang +7 | Jun 11, 2026 | 6 |
| How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs | Reinforcement learning | Zhichen Dong +11 | Jun 9, 2026 | 6 |
| Next Forcing: Causal World Modeling with Multi-Chunk Prediction | Robotics | Gangwei Xu +6 | Jun 9, 2026 | 6 |
| DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning | Agents | Lingyong Yan +15 | Jun 5, 2026 | 6 |
| Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory | Agents | Ruida Wang +5 | Jun 2, 2026 | 6 |
| HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems | Agents | Mingju Chen +4 | Jun 1, 2026 | 6 |
| SPACENUM: Revisiting Spatial Numerical Understanding in VLMs | Robotics | Jianshu Zhang +6 | May 22, 2026 | 6 |
| Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents | Agents | Ziyan Liu +9 | May 28, 2026 | 6 |
| AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification | Agents | Yan Wang +9 | Jun 2, 2026 | 6 |
| Neural Networks Provably Learn Spectral Representations for Group Composition | Safety & alignment | Jianliang He +4 | Jun 2, 2026 | 6 |
| A Multi-AI-agent Framework Enabling End-to-end Finite Element Analysis for Solid Mechanics Problems | Vision & multimodal | Titu Ranjan Sarker +5 | May 28, 2026 | 6 |
| HakushoBench: A Japanese Chart and Table VQA Benchmark from Governmental White Papers | Vision & multimodal | Issa Sugiura +3 | May 31, 2026 | 6 |
| Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline Distillation | Efficiency & systems | M. Ali Bayram +2 | May 28, 2026 | 6 |
| Not only where, But when: Temporal Scheduling for RLVR | Reinforcement learning | Jinghao Zhang +3 | May 25, 2026 | 6 |
| Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems | Robotics | Barak Or | May 23, 2026 | 6 |
| DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization | Code | Jian Mu +4 | May 29, 2026 | 6 |
| SurGe: Improved Surface Geometry in Point Maps | Data & benchmarks | Karim Knaebel +6 | May 29, 2026 | 6 |
| Convex Low-resource Accent-Robust Language Detection in Speech Recognition | Speech & audio | Miria Feng +2 | May 22, 2026 | 6 |
| Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration | Reinforcement learning | Zili Wang +5 | May 27, 2026 | 6 |
| OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents | Agents | Chenyu Zhou +5 | May 27, 2026 | 6 |
| ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations | Agents | Jie Zhu +7 | May 27, 2026 | 6 |
| Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization | Agents | Anmol Agarwal +8 | May 26, 2026 | 6 |
| AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions | Vision & multimodal | Jingwei Sun +5 | May 25, 2026 | 6 |
| AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning | Agents | Yuyang Hu +7 | May 23, 2026 | 6 |
| CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations | Reinforcement learning | Mike Zhang +2 | May 25, 2026 | 6 |
| Learning High-Frequency Continuous Action Chunks in Latent Space | Robotics | Kunyun Wang +4 | May 24, 2026 | 6 |
| How Far Will They Go? Red-Teaming Online Influence with Large Language Models | Agents | Daniel C. Ruiz +4 | May 20, 2026 | 6 |
| PanoWorld: Real-World Panoramic Generation | Image & video gen | Haoyuan Li +9 | Jul 10, 2026 | 5 |
| A Sparse and Truncated State Vector Simulator for Peaked Circuits | Efficiency & systems | Diogo R. Ferreira | Jul 8, 2026 | 5 |
| RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures | Robotics | Hanan Gani +4 | Jul 7, 2026 | 5 |
| Teaching LLMs a Low-Resource Language: Enhancing Code Completion in Pharo | Code | Kilian Kier +7 | Jul 6, 2026 | 5 |
| OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies | Robotics | Kelin Yu +4 | Jul 4, 2026 | 5 |
| SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models | Robotics | Changti Wu +8 | Jul 7, 2026 | 5 |
| Bibby AI: An Editor-Native Agentic Platform for Academic Research, Writing, and Publishing | Agents | Nilesh Jain | Jul 3, 2026 | 5 |
| GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks | Robotics | Kaiyuan Chen +23 | Jul 6, 2026 | 5 |
| Learning to Trigger: Reinforcement Learning at the Large Hadron Collider | Vision & multimodal | Zixin Ding +9 | Jun 27, 2026 | 5 |
| FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model | Speech & audio | Jiaqi Li +11 | Jun 30, 2026 | 5 |
| Hierarchical Experimentalist Agents | Agents | Abhranil Chandra +4 | Jun 28, 2026 | 5 |
| Learning Transferable Dynamics Priors from Action to World Modeling | Robotics | Ze Huang +5 | Jun 28, 2026 | 5 |
| ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval | Vision & multimodal | Siqiao Xue +1 | Jun 26, 2026 | 5 |
| Mind the Heads: Topological Representation Alignment for Multimodal LLMs | Vision & multimodal | Davide Caffagni +7 | Jun 22, 2026 | 5 |
| Simplified Sparse Attention via Gist Tokens | Code | Yuzhen Mao +2 | Jun 26, 2026 | 5 |
| Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline) | Robotics | Ilia Larchenko | Jun 25, 2026 | 5 |
| COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami | Vision & multimodal | Tom Zahavy +18 | Jun 24, 2026 | 5 |
| ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation | Image & video gen | Anindya Mondal +2 | Jun 22, 2026 | 5 |
| CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression | Code | Morayo Danielle Adeyemi +2 | Jun 23, 2026 | 5 |
| What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics | Safety & alignment | Sofiia Nikolenko +3 | Jun 23, 2026 | 5 |
| ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation | Code | Chen Lin +2 | Jun 22, 2026 | 5 |
| When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents | Agents | Kaiyue Yang +7 | Jun 18, 2026 | 5 |
| Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild | Image & video gen | Yehonathan Litman +6 | Jun 22, 2026 | 5 |
| Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views | Vision & multimodal | Jiho Choi +3 | Jun 22, 2026 | 5 |
| PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models | Robotics | Xianghui Wang +6 | Jun 21, 2026 | 5 |
| WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents | Robotics | Yehang Zhang +9 | Jun 17, 2026 | 5 |
| LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI | Vision & multimodal | Lalit Yadav +1 | Jun 16, 2026 | 5 |
| Adaptive Volumetric Mechanical Property Fields Invariant to Resolution | Efficiency & systems | Rishit Dagli +6 | Jun 16, 2026 | 5 |
| Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation | Safety & alignment | Zhongzhu Zhou +6 | Jun 15, 2026 | 5 |
| Physics-IQ Verified | Image & video gen | Tim Rädsch +6 | Jun 17, 2026 | 5 |
| HiLo-Token: Input-Adaptive High-Low Frequency Token Compression for Efficient Image Editing | Image & video gen | Haoran You +9 | Jun 11, 2026 | 5 |
| MotionVLA: Vision-Language-Action Model for Humanoid Motion | Robotics | Nonghai Zhang +7 | Jun 13, 2026 | 5 |
| PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory | Image & video gen | Shuai Yang +5 | Jun 15, 2026 | 5 |
| ExpRL: Exploratory RL for LLM Mid-Training | Reinforcement learning | Violet Xiang +4 | Jun 15, 2026 | 5 |
| MMDiff: Extending Diffusion Transformers for Multi-Modal Generation | Image & video gen | Yagmur Akarken +2 | Jun 15, 2026 | 5 |
| Artificial Intelligence Index Report 2026 | Safety & alignment | Sha Sajadieh +22 | Apr 14, 2026 | 5 |
| AFFORDANCE20Q: Evaluating Affordance Reasoning from Physical Properties | Code | Yifan Jiang +3 | Jun 12, 2026 | 5 |
| Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation | Vision & multimodal | Guo Yu +5 | Jun 11, 2026 | 5 |
| APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies | Robotics | Kechun Xu +4 | Jun 10, 2026 | 5 |
| Benchmarking AI Agents for Addressing Scientific Challenges Across Scales | Agents | Tianyu Liu +32 | Jun 10, 2026 | 5 |
| P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning | Vision & multimodal | Yikang Yang +7 | Jun 9, 2026 | 5 |
| Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents | Agents | Kushal Raj Bhandari +6 | Jun 10, 2026 | 5 |
| DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models | Robotics | Zhuoming Liu +5 | Jun 4, 2026 | 5 |
| UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors | Safety & alignment | Zhiwen Yang +6 | Jun 9, 2026 | 5 |
| Dynamic Linear Attention | Efficiency & systems | Xin Wang +9 | Jun 9, 2026 | 5 |
| Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking | Vision & multimodal | Fan Zhang +9 | Jun 5, 2026 | 5 |
| Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests | Agents | Thanawat Lodkaew +5 | Jun 5, 2026 | 5 |
| What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems | Agents | Chen Huang +2 | Jun 3, 2026 | 5 |
| Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher | Theory | Arda Uzunoglu +2 | May 31, 2026 | 5 |
| Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction | Vision & multimodal | Tianxiang Jiang +7 | Jun 4, 2026 | 5 |
| SePO: Self-Evolving Prompt Agent for System Prompt Optimization | Agents | Wangcheng Tao +2 | Jun 3, 2026 | 5 |
| AdaCodec: A Predictive Visual Code for Video MLLMs | Vision & multimodal | Haowen Hou +10 | Jun 1, 2026 | 5 |
| Absorbing Complexity: An Interaction-Native Knowledge Harness for Financial LLM Agents | Agents | Ailiya Borjigin +6 | Jun 1, 2026 | 5 |
| The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models | Code | Liuyuan Wen +4 | May 29, 2026 | 5 |