| AFUN: Towards an Affordance Foundation Model for Functionality Understanding | Robotics | Zhaoning Wang +4 | Jun 1, 2026 | 8 |
| FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search | Agents | James Xu Zhao +3 | May 30, 2026 | 8 |
| SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models | Vision & multimodal | Olaf Dünkel +5 | May 29, 2026 | 8 |
| Measuring the Depth of LLM Unlearning via Activation Patching | Code | Jaeung Lee +2 | May 23, 2026 | 8 |
| ACL-Verbatim: hallucination-free question answering for research | Safety & alignment | Gábor Recski +4 | May 20, 2026 | 8 |
| Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models | Image & video gen | Jiazheng Xing +11 | May 29, 2026 | 8 |
| How can embedding models bind concepts? | Vision & multimodal | Arnas Uselis +2 | May 29, 2026 | 8 |
| SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones? | Speech & audio | Sy-Tuyen Ho +3 | May 28, 2026 | 8 |
| One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation | Vision & multimodal | Sanghyun Jo +6 | May 28, 2026 | 8 |
| OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents | Vision & multimodal | Jiahao Ying +4 | May 22, 2026 | 8 |
| Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection | Vision & multimodal | Travis Lelle | May 28, 2026 | 8 |
| SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Control | Image & video gen | Zhida Zhang +7 | May 27, 2026 | 8 |
| Learning A Unified Risk Map for Autonomous Driving in Partially Observable Environments | Image & video gen | Jie Jia +6 | May 21, 2026 | 8 |
| PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective | Efficiency & systems | Yangyi Huang +6 | May 27, 2026 | 8 |
| Models That Know How Evaluations Are Designed Score Safer | Code | Katharina Deckenbach +3 | May 27, 2026 | 8 |
| AgensFlow: A Coordination-Policy Substrate for Multi-Agent Systems | Agents | Nicole Koenigstein | May 26, 2026 | 8 |
| MRT: Masked Region Transformer for Layered Image Generation and Editing at Scale | Image & video gen | Zhicong Tang +8 | May 26, 2026 | 8 |
| FastKernels: Benchmarking GPU Kernel Generation in Production | Agents | Gabriele Oliaro +7 | May 22, 2026 | 8 |
| ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models | Code | Yujie Lin +4 | May 16, 2026 | 8 |
| UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma | Vision & multimodal | Chongyu Fan +4 | Jul 8, 2026 | 7 |
| AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation | Agents | Andrey Podivilov +6 | Jul 7, 2026 | 7 |
| SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review | Agents | Ruoyu Wang +9 | Jul 7, 2026 | 7 |
| HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better | Vision & multimodal | Gengluo Li +22 | Jul 6, 2026 | 7 |
| Rank-Then-Act: Reward-Free Control from Frame-Order Progress | Vision & multimodal | Yuriy Maksyuta +3 | Jul 2, 2026 | 7 |
| 3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance | Robotics | Dongyoon Hwang +9 | Jun 30, 2026 | 7 |
| AI Wizards at EXIST 2026: Hierarchical Soft-Label Learning for Multimodal Sexism Identification in Memes | Vision & multimodal | Matteo Fasulo +3 | Jul 5, 2026 | 7 |
| Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification | Agents | Yunhao Feng +14 | Jul 4, 2026 | 7 |
| GORGO: Online Tuning for Cross-Region Network-Aware LLM Serving | Code | Alessio Ricci Toniolo +2 | Jun 30, 2026 | 7 |
| Generated Contents Enrichment | Vision & multimodal | Mahdi Naseri +2 | Jun 30, 2026 | 7 |
| Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR | Code | Yongjin Yang +5 | Jun 27, 2026 | 7 |
| Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting | Image & video gen | Kuo-Chung Peng +5 | Jun 26, 2026 | 7 |
| Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue | Robotics | Nan Li +2 | Jun 30, 2026 | 7 |
| HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents | Agents | Qianchu Liu +18 | Jun 30, 2026 | 7 |
| CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion | Vision & multimodal | Pan Wang +2 | Jun 29, 2026 | 7 |
| Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation | Vision & multimodal | Jongoh Jeong +2 | Jun 28, 2026 | 7 |
| SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE | Image & video gen | Or Hirschorn +5 | Jun 30, 2026 | 7 |
| MuSViT: A Foundation Vision Model for Sheet Music Representation | Speech & audio | Carlos Penarrubia +6 | Jun 30, 2026 | 7 |
| SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions | Agents | Mohit Raghavendra +3 | Jun 29, 2026 | 7 |
| LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents | Vision & multimodal | Yogeswar Reddy Thota | Jun 29, 2026 | 7 |
| The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction | Robotics | Yuxi Wang +8 | Jun 29, 2026 | 7 |
| Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark | Safety & alignment | Matthias Blaschke +5 | Jun 29, 2026 | 7 |
| RocketSmith: Agentic Additive Manufacturing of High-Powered Rockets | Agents | Peter Pak +5 | Jun 26, 2026 | 7 |
| ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models | Vision & multimodal | Jun Zhang +7 | Jun 22, 2026 | 7 |
| Towards Automating Scientific Review with Google's Paper Assistant Tool | Agents | Rajesh Jayaram +6 | Jun 26, 2026 | 7 |
| Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement | Robotics | Kinam Kim +5 | Jun 17, 2026 | 7 |
| World Value Models for Robotic Manipulation | Robotics | Zhihao Wang +6 | Jun 23, 2026 | 7 |
| DREAM: Dense Retrieval Embeddings via Autoregressive Modeling | Data & benchmarks | Yixuan Tang +1 | Jun 23, 2026 | 7 |
| Causal Discovery in the Era of Agents | Agents | Yujia Zheng +5 | Jun 22, 2026 | 7 |
| Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs | Safety & alignment | Charbel El Feghali +5 | Jun 19, 2026 | 7 |
| Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning | Agents | Xiaoyue Xu +4 | Jun 17, 2026 | 7 |
| MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents | Agents | Lawrence Keunho Jang +3 | Jun 15, 2026 | 7 |
| Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences | Safety & alignment | Mingyang Li +5 | Jun 15, 2026 | 7 |
| Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning | Vision & multimodal | Haoran Xu +6 | Jun 8, 2026 | 7 |
| Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization | Reinforcement learning | Hao Xiang +10 | Jun 10, 2026 | 7 |
| PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models | Safety & alignment | Gianluca Barmina +9 | Jun 8, 2026 | 7 |
| Bridging the Agent-World Gap: Text World Models for LLM-based Agents | Image & video gen | Yixia Li +15 | Jun 8, 2026 | 7 |
| Trajectory-Refined Distillation | Code | Li Jiang +3 | Jun 7, 2026 | 7 |
| Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evaluation of Vision-Language Models | Vision & multimodal | Mohammad Mahdi Abootorabi +6 | Jun 4, 2026 | 7 |
| Latent Reasoning with Normalizing Flows | Code | Guancheng Tu +7 | Jun 4, 2026 | 7 |
| Towards One-to-Many Temporal Grounding | Vision & multimodal | Qi Xu +7 | Jun 4, 2026 | 7 |
| Flash-WAM: Modality-Aware Distillation for World Action Models | Robotics | Arman Akbari +8 | Jun 3, 2026 | 7 |
| The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs | Efficiency & systems | Xu Wan +6 | Jun 2, 2026 | 7 |
| GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors | Robotics | Tianyi Xie +19 | Jun 3, 2026 | 7 |
| Stateful Visual Encoders for Vision-Language Models | Vision & multimodal | Zirui Wang +5 | Jun 3, 2026 | 7 |
| αDepth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion | Efficiency & systems | Xiang Zhang +5 | May 29, 2026 | 7 |
| Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning | Reinforcement learning | Atoosa Chegini +1 | Jun 1, 2026 | 7 |
| RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models | Robotics | Bin Yu +11 | Jun 1, 2026 | 7 |
| Multi-Agent Computer Use | Vision & multimodal | Jing Yu Koh +2 | Jun 1, 2026 | 7 |
| 3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code | Vision & multimodal | Yipeng Gao +7 | May 31, 2026 | 7 |
| LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning | Code | Mengmeng Ji +3 | May 31, 2026 | 7 |
| SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence | Vision & multimodal | Yulu Pan +6 | May 29, 2026 | 7 |
| Unified Neural Scaling Laws | Vision & multimodal | Ethan Caballero +3 | May 25, 2026 | 7 |
| RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video | Data & benchmarks | Ulrich Prestel +3 | May 29, 2026 | 7 |
| iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning | Vision & multimodal | Chang-Bin Zhang +3 | May 29, 2026 | 7 |
| GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models | Image & video gen | Xiaohang Tang +6 | May 28, 2026 | 7 |
| MAAT: Multi-phase Adapter-Aware Targeted Unlearning | Code | Suryash Yagnik +5 | May 28, 2026 | 7 |
| AlphaTransit: Learning to Design City-scale Transit Routes | Code | Bibek Poudel +2 | May 27, 2026 | 7 |
| FRAPPE: Full Input, Residual Output Autoencoding with Projection Pursuit Encoder | Robotics | Dan Jacobellis +1 | May 27, 2026 | 7 |
| One-Forcing: Towards Stable One-Step Autoregressive Video Generation | Image & video gen | Jiaqi Feng +3 | May 22, 2026 | 7 |
| Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases | Reinforcement learning | Dongyoon Hahm +2 | May 26, 2026 | 7 |
| Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation | Code | Aviral Chharia +1 | May 24, 2026 | 7 |
| LACUNA: Safe Agents as Recursive Program Holes | Agents | Yaoyu Zhao +5 | May 27, 2026 | 7 |
| PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft | Robotics | Yuchen Guo +4 | May 26, 2026 | 7 |
| Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents | Agents | Asaf Yehudai +2 | May 21, 2026 | 7 |
| PRISM: Position-encoded Regressive Inverse Spectral Model for Multilayer Thin-Film Design | Data & benchmarks | Runtian Wang +3 | May 26, 2026 | 7 |
| ECHO: Terminal Agents Learn World Models for Free | Robotics | Vaishnavi Shrivastava +3 | May 23, 2026 | 7 |
| KronQ: LLM Quantization via Kronecker-Factored Hessian | Efficiency & systems | Donghyun Lee +3 | Jul 8, 2026 | 6 |
| ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation | Robotics | Kaifeng Zhao +5 | Jul 9, 2026 | 6 |
| SAM-MT: Real-Time Interactive Multi-Target Video Segmentation | Vision & multimodal | Ruiqi Shen +2 | Jul 9, 2026 | 6 |
| PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages | Safety & alignment | Daryna Dementieva +16 | Jul 7, 2026 | 6 |
| Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training | Agents | Zijian Zhang +6 | Jul 2, 2026 | 6 |
| When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers | Agents | Yushi Sun +2 | Jul 1, 2026 | 6 |
| MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs | Speech & audio | Yuxuan Fan +5 | Jun 29, 2026 | 6 |
| CONFLUX: A Latent Diffusion Model for 3D Chest-CT Synthesis with RL Post-Training | Image & video gen | Max Van Puyvelde +3 | Jul 7, 2026 | 6 |
| Transition-Aware best-of-N sampling for Longitudinal Chest X-ray Reports | Vision & multimodal | Halil Ibrahim Gulluk +3 | Jun 23, 2026 | 6 |
| Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment | Vision & multimodal | Ziyao Wang +7 | Jul 2, 2026 | 6 |
| AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation | Safety & alignment | Bao Long Nguyen Huu +1 | Jun 30, 2026 | 6 |
| TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive | Image & video gen | Brian Wei +4 | Jun 30, 2026 | 6 |
| PoseShield: Neural Collision Fields for Human Self-Collision Resolution | Data & benchmarks | Zhengyuan Li +9 | Jun 29, 2026 | 6 |
| SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing | Safety & alignment | Jiacheng Zhang +7 | Jun 29, 2026 | 6 |