| MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation | Code | Jiale Xu +2 | Jun 3, 2026 | 5 |
| BraveGuard: From Open-World Threats to Safer Computer-Use Agents | Vision & multimodal | Yunhao Feng +15 | Jun 2, 2026 | 5 |
| BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution | Code | Yangzhen Wu +12 | May 31, 2026 | 5 |
| Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning | Vision & multimodal | Ciara Rowles +4 | May 28, 2026 | 5 |
| Conditional Hypothesis Generation for LLM-Based Text Analysis with Researcher-Specified Covariates | Safety & alignment | Paiheng Xu +2 | Jun 2, 2026 | 5 |
| Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling | Vision & multimodal | Seojeong Park +5 | Jun 1, 2026 | 5 |
| Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets | Code | Andrea Gurioli +4 | May 27, 2026 | 5 |
| Breaking the Chains of Probability: Neutrosophic Logic as a New Framework for Epistemic Uncertainty in Large Language Models | Data & benchmarks | Maikel Yelandi Leyva-Vázquez +1 | May 22, 2026 | 5 |
| Understanding Data Temporality Impact on Large Language Models Pre-training | Code | Hippolyte Pilchen +4 | May 21, 2026 | 5 |
| Representation over Routing: Diagnosing Temporal Routing Pathologies in Multi-Timescale PPO | Vision & multimodal | Jing Sun | May 30, 2026 | 5 |
| Injecting Image Guidance into Text-Conditioned Diffusion Models at Inference | Image & video gen | Agata Żywot +6 | May 24, 2026 | 5 |
| Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints | Agents | Alexi Canesse +3 | May 20, 2026 | 5 |
| From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models | Image & video gen | Zanyi Wang +4 | Jul 9, 2026 | 4 |
| Trust Region Policy Distillation | Efficiency & systems | Zhengpeng Xie +3 | Jul 6, 2026 | 4 |
| PhyMRI-SR: Toward Physics-Aware MRI Image Super-Resolution | Science & bio | Lihua Wei +6 | Jul 7, 2026 | 4 |
| Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models | Image & video gen | Ruchit Rawal +7 | Jul 5, 2026 | 4 |
| Where to cut, how deep: BPE and Unigram-LM on chemistry SMILES | Vision & multimodal | Hunter Heidenreich | Jul 6, 2026 | 4 |
| Layer-wise Cross-Lingual Depression Detection from Speech: Analysis with Contrastive Alignment | Speech & audio | Anisha Pattanayak +4 | Jul 3, 2026 | 4 |
| SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion | Image & video gen | Paul Engstler +3 | Jul 6, 2026 | 4 |
| Speaker-Aware Temporal Aggregation Strategies on Segment Representations for Depression Detection in Dyadic Interaction: A Benchmark Study | Speech & audio | Anisha Pattanayak +3 | Jul 3, 2026 | 4 |
| Taste-aware music retrieval from audio embeddings | Speech & audio | Matteo Spanio +1 | Jul 3, 2026 | 4 |
| Scaling Laws for Grid-Based Approximate Nearest Neighbor Search in High Dimensions | Code | Matthew J Liu +6 | Jul 1, 2026 | 4 |
| RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue | Agents | Zhihao Lin +6 | Jul 1, 2026 | 4 |
| Lexical Consensus: Grounded Word Learning and Shared Meaning in Artificial Agents | Vision & multimodal | Patricio M. Vera | Jun 20, 2026 | 4 |
| Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation | Image & video gen | Chonghuinan Wang +11 | Jun 29, 2026 | 4 |
| Geometric Stability of Neural Population Codes: Regional Variation, Behavioral Relevance, and Circuit Dependence | Vision & multimodal | Prashant C. Raju | Jun 28, 2026 | 4 |
| One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models | Vision & multimodal | Xiaohao Xu +7 | Jun 28, 2026 | 4 |
| A Gravitational Interpretation of Fine-Tuning Reversion | Safety & alignment | Samuele Poppi +1 | Jun 26, 2026 | 4 |
| Large-Scale Tunnel Air-Ground Collaboration With FLISP: Fast LiDAR-IMU Synchronized Path Planner | Robotics | Fenghe Guo +6 | Jun 25, 2026 | 4 |
| LLM Program Optimization via Retrieval Augmented Search | Code | Sagnik Anupam +2 | Jun 23, 2026 | 4 |
| NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning | Vision & multimodal | Tianlin Pan +6 | Jun 26, 2026 | 4 |
| To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair | Agents | Zhihao Lin +7 | Jun 25, 2026 | 4 |
| Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving | Safety & alignment | Yasmin Moslem +13 | Jun 25, 2026 | 4 |
| CogniRoute: Learning to Route Social Evidence in Omni-Modal Models | Speech & audio | Yifan Shen +10 | Jun 18, 2026 | 4 |
| When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models | Agents | Josef Chen | Jun 25, 2026 | 4 |
| OpenBioRQ: Unsolved Biomedical Research Questions for Agents | Agents | Minbyul Jeong | Jun 20, 2026 | 4 |
| ReMMD: Realistic Multilingual Multi-Image Agentic Verification for Multimodal Misinformation Detection | Robotics | Chenhao Dang +4 | Jun 23, 2026 | 4 |
| AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning | Agents | Honglin Guo +9 | Jun 23, 2026 | 4 |
| Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining | Code | Michael K. Chen +4 | Jun 19, 2026 | 4 |
| CalVerT: Augmenting Agents with Calibrated Verifier Telemetry Improves Action and Learning in Knowledge-Intensive Tasks | Agents | Ashwin Vinod +2 | Jun 19, 2026 | 4 |
| Distilling Examples into Task Instructions: Enhanced In-Context Learning for Real-World B2B Conversations | Safety & alignment | Guy Rotman +3 | Jun 14, 2026 | 4 |
| Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why | Agents | Osman Alperen Çinar-Koraş +9 | Jun 17, 2026 | 4 |
| Selective Synergistic Learning for Video Object-Centric Learning | Code | WonJun Moon +1 | Jun 14, 2026 | 4 |
| Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning | Safety & alignment | Sajib Acharjee Dip +2 | Jun 18, 2026 | 4 |
| RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents | Agents | Ruishan Fang +3 | Jun 17, 2026 | 4 |
| When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning? | Reinforcement learning | Xuanfei Ren +1 | Jun 16, 2026 | 4 |
| IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products | Vision & multimodal | Haonan Qi +11 | Jun 12, 2026 | 4 |
| RepSelect: Robust LLM Unlearning via Representation Selectivity | Efficiency & systems | Filip Sondej +2 | Jun 15, 2026 | 4 |
| Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning | Vision & multimodal | Zhengbo Zhang +12 | Jun 13, 2026 | 4 |
| Aligning Quantum Operators with Large Language Models | LLMs & reasoning | Rogerio Feris +4 | Jun 11, 2026 | 4 |
| LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies | Robotics | Jialei Chen +11 | Jun 14, 2026 | 4 |
| Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs | Science & bio | Nafiseh Nikeghbal +3 | Jun 14, 2026 | 4 |
| AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models | Vision & multimodal | Shouwei Ruan +7 | Jun 8, 2026 | 4 |
| EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge | Agents | Yunhan Wang +4 | Jun 11, 2026 | 4 |
| WEAVER, Better, Faster, Longer: An Effective World Model for Robotic Manipulation | Robotics | Arnav Kumar Jain +4 | Jun 11, 2026 | 4 |
| Surflo: Consistent 3D Surface Flow Model with Global State | Code | Antoine Guédon +5 | Jun 11, 2026 | 4 |
| Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents | Agents | Yujun Zhou +10 | Jun 11, 2026 | 4 |
| Flash-GMM: A Memory-Efficient Kernel for Scalable Soft Clustering | Efficiency & systems | Gal Bloch +4 | Jun 9, 2026 | 4 |
| MaskAlign: Token-Subset Representation Alignment for Efficient Diffusion Training | Image & video gen | Lianyu Pang +7 | Jun 7, 2026 | 4 |
| MuJoCo-Drones-Gym: A GPU-Accelerated Multi-Drone Simulator for Control and Reinforcement Learning | Robotics | Manan Tayal | Jun 6, 2026 | 4 |
| POISE: Position-Aware Undetectable Skill Injection on LLM Agents | Speech & audio | Haochang Hao +6 | Jun 6, 2026 | 4 |
| ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction | Vision & multimodal | Amirhossein Abaskohi +5 | May 11, 2026 | 4 |
| U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training | Code | Zhiwen Yang +6 | Jun 9, 2026 | 4 |
| MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation | Image & video gen | Ishaan Preetam Chandratreya +6 | Jun 8, 2026 | 4 |
| Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating | Safety & alignment | Sicheng Wang +8 | Jun 8, 2026 | 4 |
| IR3DE: A Linear Router for Large Language Models | Code | Eros Fanì +1 | Jun 4, 2026 | 4 |
| Optical Reasoning: Rethinking Images as an Expressive Reasoning Medium Beyond Text | Vision & multimodal | Yutong Bian +4 | Jun 8, 2026 | 4 |
| Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting | Safety & alignment | Avijit Ghosh +39 | Jun 8, 2026 | 4 |
| Robotic Policy Adaptation via Weight-Space Meta-Learning | Robotics | Christian Bianchi +6 | Jun 5, 2026 | 4 |
| AsyncWebRL: Efficient Multi-Step RL for Visual Web Agents | Vision & multimodal | Hao Bai +5 | Jun 4, 2026 | 4 |
| Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors | Vision & multimodal | Hanxun Yu +6 | Jun 5, 2026 | 4 |
| Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development | Speech & audio | Zixi Li +1 | Jun 5, 2026 | 4 |
| Towards Retrieving Interaction Spaces for Agentic Search | Agents | Shengyao Zhuang +4 | Jun 5, 2026 | 4 |
| A Cookbook of 3D Vision: Data, Learning Paradigms, and Application | Image & video gen | Hongyang Du +10 | Jun 2, 2026 | 4 |
| CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning | Reinforcement learning | Linas Nasvytis +5 | May 27, 2026 | 4 |
| Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs | Speech & audio | Gio Paik +2 | Jun 4, 2026 | 4 |
| Benchmark Everything Everywhere All at Once | Vision & multimodal | Shiyun Xiong +7 | Jun 4, 2026 | 4 |
| SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstruction | Robotics | Dan Jacobellis +1 | Jun 2, 2026 | 4 |
| MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding | Vision & multimodal | Qian Kou +6 | May 29, 2026 | 4 |
| DAR: Deontic Reasoning with Agentic Harnesses | Agents | Guangyao Dou +3 | Jun 3, 2026 | 4 |
| Access Sets Matter: Budgeting Expert Reads for Scalable Weight-Space Model Merging | Speech & audio | Yuanyi Wang +7 | May 28, 2026 | 4 |
| GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards | Reinforcement learning | Tej Deep Pala +2 | Jun 3, 2026 | 4 |
| ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree | Vision & multimodal | Vincent Koc +5 | May 31, 2026 | 4 |
| MindZero: Learning Online Mental Reasoning With Zero Annotations | Vision & multimodal | Shunchi Zhang +5 | May 29, 2026 | 4 |
| Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation | Image & video gen | Samson Gourevitch +6 | May 21, 2026 | 4 |
| Unified Panoramic Geometry Estimation via Multi-View Foundation Models | Code | Vukasin Bozic +6 | May 25, 2026 | 4 |
| Can LLMs Introspect? A Reality Check | Robotics | Shashwat Singh +2 | May 25, 2026 | 4 |
| NSF-SciFy: Mining the NSF Awards Database for Scientific Claims | Code | Delip Rao +3 | May 25, 2026 | 4 |
| STREAM: A Data-Centric Framework for Mining High-Value Task-Oriented Dialogues from Streaming Media | Agents | Liang Xue +5 | May 24, 2026 | 4 |
| EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration | Image & video gen | Wuyang Li +6 | May 14, 2026 | 4 |
| Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models | Reinforcement learning | Wenlong Deng +6 | May 24, 2026 | 4 |
| MotiMotion: Motion-Controlled Video Generation with Visual Reasoning | Image & video gen | Lee Hsin-Ying +5 | May 21, 2026 | 4 |
| Broadening Access to Transportation Safety Data with Generative AI: A Schema-Grounded Framework for Spatial Natural Language Queries | Safety & alignment | Mahdi Azhdari +1 | May 20, 2026 | 4 |
| CausalDS: Benchmarking Causal Reasoning in Data-Science Agents | Agents | Andrej Leban +1 | Jul 9, 2026 | 3 |
| A Quantized Native Runtime for On-Device Semantic Audio Generation | Speech & audio | Matteo Spanio +1 | Jul 9, 2026 | 3 |
| Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs | Safety & alignment | Kareem Elozeiri +6 | Jul 4, 2026 | 3 |
| SceneFrom3D: Geometry-Conditioned Outdoor 3D Scene Generation via View Scheduling with Object-Level Control | Other | Geonung Kim +4 | Jul 5, 2026 | 3 |
| RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules | Data & benchmarks | Ádám Kovács +2 | Jul 1, 2026 | 3 |
| Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers | Image & video gen | Anh Nguyen +13 | Jun 30, 2026 | 3 |
| Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization | Speech & audio | Ryota Komatsu +3 | Jul 5, 2026 | 3 |