| DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation | Robotics | Jusuk Lee +8 | May 28, 2026 | 13 |
| RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains | Reinforcement learning | Haoxiang Jiang +7 | May 27, 2026 | 13 |
| The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages | Robotics | Eric Onyame +4 | May 27, 2026 | 13 |
| Lost in Sampling: Assessing Lexical Reachability in LLMs via the Word Coverage Score (WCS) | Code | Samer Awad +5 | May 26, 2026 | 13 |
| Less is More: Early Stopping Rollout for On-Policy Distillation | Safety & alignment | Zhou Ziheng +4 | May 26, 2026 | 13 |
| Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution | Image & video gen | Zixin Jessie Chen +6 | May 25, 2026 | 13 |
| Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing | Efficiency & systems | Tommaso Cerruti +4 | Jul 8, 2026 | 12 |
| CineMobile: On-Device Image-to-Video Diffusion for Cinematic Camera Motion Generation | Image & video gen | Xuyao Huang +4 | Jul 4, 2026 | 12 |
| PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking | Vision & multimodal | Dengxian Gong +13 | Jun 30, 2026 | 12 |
| QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents | Agents | Sergio Hernández-Gutiérrez +5 | Jun 30, 2026 | 12 |
| TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning | Vision & multimodal | Yuanda Xu +7 | Jun 30, 2026 | 12 |
| PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation | Image & video gen | Chunshi Wang +11 | Jun 25, 2026 | 12 |
| SAM2Matting: Generalized Image and Video Matting | Data & benchmarks | Ruiqi Shen +3 | Jun 25, 2026 | 12 |
| TheoremGraph: Bridging Formal and Informal Mathematics | Data & benchmarks | Simon Kurgan +8 | Jun 24, 2026 | 12 |
| ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering | Vision & multimodal | ZhengXian Wu +10 | Jun 26, 2026 | 12 |
| Track2View: 4D-Consistent Camera-Controlled Video Generation via Paired 3D Point Tracks | Image & video gen | Feng Qiao +4 | Jun 14, 2026 | 12 |
| You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences | Vision & multimodal | Ninad Daithankar +3 | Jun 14, 2026 | 12 |
| PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions | Vision & multimodal | Chenxin Li +20 | Jun 12, 2026 | 12 |
| High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation | Image & video gen | Dongyang Liu +9 | Jun 10, 2026 | 12 |
| Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders | Speech & audio | Nikita Koriagin +3 | Jun 8, 2026 | 12 |
| SlimSearcher: Training Efficiency-Aware Web Agents via Adaptive Reward Gating | Agents | Zequn Xie +6 | Jun 5, 2026 | 12 |
| PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams | Safety & alignment | Fuqiang Wang +10 | Jun 5, 2026 | 12 |
| Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills | Agents | Chuan Xiao +7 | Jun 5, 2026 | 12 |
| Unsupervised Skill Discovery for Agentic Data Analysis | Agents | Zhisong Qiu +6 | Jun 4, 2026 | 12 |
| Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams | Agents | Zewen Liu +9 | Jun 1, 2026 | 12 |
| DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory | Image & video gen | Zhenhao Yang +7 | May 29, 2026 | 12 |
| Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion | Agents | Stine Lyngsø Beltoft +7 | May 29, 2026 | 12 |
| Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)? | Vision & multimodal | Yue Zhang +5 | May 28, 2026 | 12 |
| AdaState: Self-Evolving Anchors for Streaming Video Generation | Image & video gen | Yusuf Dalva +1 | May 28, 2026 | 12 |
| NeuROK: Generative 4D Neural Object Kinematics | Image & video gen | Chen Geng +5 | May 28, 2026 | 12 |
| GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning | Vision & multimodal | Haodong Zhao +4 | May 26, 2026 | 12 |
| Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation | Image & video gen | Shuhong Zheng +4 | May 25, 2026 | 12 |
| Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals | Code | Federico Torrielli +2 | May 25, 2026 | 12 |
| Do Language Models Need Sleep? Offline Recurrence for Improved Online Inference | Efficiency & systems | Sangyun Lee +3 | May 25, 2026 | 12 |
| RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies | Robotics | Tianxing Chen +39 | Jul 7, 2026 | 11 |
| Automating the Design of Embodied Agent Architectures | Robotics | Jian Zhou +5 | Jul 3, 2026 | 11 |
| Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding | Image & video gen | Yonggan Fu +25 | Jul 7, 2026 | 11 |
| CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration | Robotics | Hairui Zhu +7 | Jul 6, 2026 | 11 |
| SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference | Code | Amirhossein Abaskohi +3 | Jun 30, 2026 | 11 |
| Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs | Robotics | Junhao Shi +5 | Jul 2, 2026 | 11 |
| Discrete Diffusion Language Models for Interactive Radiology Report Drafting | Image & video gen | Max Van Puyvelde +3 | Jul 1, 2026 | 11 |
| Cross-Domain Generalization Failure in Lightweight Intrusion Detection Models for IIoT Networks | Vision & multimodal | MD Azizul Hakim +2 | Jul 1, 2026 | 11 |
| Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination | Reinforcement learning | Subhadeep Pal +3 | Jul 1, 2026 | 11 |
| The State-Prediction Separation Hypothesis | LLMs & reasoning | Giovanni Monea +3 | Jul 1, 2026 | 11 |
| Unlocking the Visual Record of Materials Science: A Large-Scale Multimodal Dataset from Scientific Literature | Vision & multimodal | Subham Ghosh +3 | Jun 29, 2026 | 11 |
| Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents | Speech & audio | Vidya Srinivas +4 | Jul 1, 2026 | 11 |
| PhysiFormer: Learning to Simulate Mechanics in World Space | Robotics | Yiming Chen +2 | Jun 25, 2026 | 11 |
| Confidence-Aware Tool Orchestration for Robust Video Understanding | Robotics | Yangfan He +2 | Jun 25, 2026 | 11 |
| Information-Aware KV Cache Compression for Long Reasoning | Code | Jushi Kai +3 | Jun 25, 2026 | 11 |
| Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning | Reinforcement learning | Chenhao Dang +2 | Jun 23, 2026 | 11 |
| Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning | Image & video gen | Jiayi Lei +10 | Jun 23, 2026 | 11 |
| DiffusionBench: On Holistic Evaluation of Diffusion Transformers | Image & video gen | Xingjian Leng +7 | Jun 23, 2026 | 11 |
| FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs | Image & video gen | Wenlong Cheng +3 | Jun 22, 2026 | 11 |
| Vera: A Layered Diffusion Model for Content-Preserving Video Editing | Image & video gen | Hongkai Zheng +4 | Jun 22, 2026 | 11 |
| PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning | Robotics | Youngjoon Jeong +4 | Jun 19, 2026 | 11 |
| Notes2Skills: From Lab Notebooks to Certainty-Aware Scientific Agent Skills | Agents | Shi Liu +5 | Jun 10, 2026 | 11 |
| Thinking with Visual Grounding | Speech & audio | Junkai Zhang +3 | Jun 15, 2026 | 11 |
| Sumi: Open Uniform Diffusion Language Model from Scratch | Image & video gen | Mengyu Ye +5 | Jun 17, 2026 | 11 |
| PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation | Robotics | Yuhang Huang +27 | Jun 16, 2026 | 11 |
| Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion | Agents | Yi Lu +9 | Jun 12, 2026 | 11 |
| MBench: A Comprehensive Benchmark on Memory Capability for Video World Models | Image & video gen | Shengjun Zhang +13 | Jun 8, 2026 | 11 |
| RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling | Image & video gen | Chensheng Dai +5 | Jun 4, 2026 | 11 |
| EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning | Agents | Guhong Chen +8 | Jun 2, 2026 | 11 |
| Policy and World Modeling Co-Training for Language Agents | Image & video gen | Ning Lu +11 | Jun 1, 2026 | 11 |
| MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft | Robotics | Tianjie Ju +9 | May 29, 2026 | 11 |
| Linear Scaling Video VLMs for Long Video Understanding | Vision & multimodal | Cristobal Eyzaguirre +2 | May 29, 2026 | 11 |
| Count Anything | Vision & multimodal | Mengqi Lei +6 | May 29, 2026 | 11 |
| DEMON: Diffusion Engine for Musical Orchestrated Noise | Speech & audio | Ryan Fosdick | May 27, 2026 | 11 |
| PhyGenHOI: Physically-Aware 4D Generation of Dynamic Human-Object Interactions | Image & video gen | Omer Benishu +2 | May 28, 2026 | 11 |
| Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention | LLMs & reasoning | Jing Huang +8 | May 28, 2026 | 11 |
| PhoneWorld: Scaling Phone-Use Agent Environments | Agents | Zhengyang Tang +23 | May 28, 2026 | 11 |
| Parallax: Parameterized Local Linear Attention for Language Modeling | Safety & alignment | Yifei Zuo +5 | May 27, 2026 | 11 |
| PANDO: Efficient Multimodal AI Agents via Online Skill Distillation | Vision & multimodal | Yubo Li +3 | May 24, 2026 | 11 |
| OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration | Speech & audio | Xinchen Zhang +9 | May 27, 2026 | 11 |
| AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation | Agents | Shanghua Gao +2 | May 27, 2026 | 11 |
| Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents | Agents | Yifan Wu +7 | Jul 9, 2026 | 10 |
| Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity | Efficiency & systems | Loïc Cabannes +8 | Jul 8, 2026 | 10 |
| Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models | Efficiency & systems | Julian Killingback +3 | Jul 7, 2026 | 10 |
| MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing | Image & video gen | Gal Fiebelman +2 | Jul 6, 2026 | 10 |
| AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer | Code | Xinyu Hou +3 | Jun 30, 2026 | 10 |
| Representation Distribution Matching for One-Step Visual Generation | Vision & multimodal | Lan Feng +4 | Jul 2, 2026 | 10 |
| Denser neq Better: Limits of On-Policy Self-Distillation for Continual Post-Training | Code | Meng Wang +9 | Jul 2, 2026 | 10 |
| DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation | Robotics | Peyman Hosseini +8 | Jun 29, 2026 | 10 |
| Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising | Vision & multimodal | Tianci Liu +7 | Jul 1, 2026 | 10 |
| BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language | Vision & multimodal | Haitao Wu +10 | Jun 29, 2026 | 10 |
| MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation | Image & video gen | Yang Chen +6 | Jun 24, 2026 | 10 |
| The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar | Vision & multimodal | Ilseyar Alimova +7 | Jun 24, 2026 | 10 |
| Vesta: A Generalist Embodied Reasoning Model | Robotics | Johan Bjorck +31 | Jun 18, 2026 | 10 |
| Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents | Agents | Changdae Oh +5 | Jun 24, 2026 | 10 |
| Exploring the Design Space of Reward Backpropagation for Flow Matching | Image & video gen | Ruoyu Wang +5 | Jun 9, 2026 | 10 |
| BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation | Image & video gen | Max Van Puyvelde +3 | Jun 17, 2026 | 10 |
| Holo-World: Unified Camera, Object and Weather Control for Video World Model | Image & video gen | Xiangchen Yin +8 | Jun 18, 2026 | 10 |
| The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation | Image & video gen | Nicolas Dufour +2 | Jun 18, 2026 | 10 |
| FAPO: Fully Autonomous Prompt Optimization of Multi-Step LLM Pipelines | Code | Paul Kassianik +6 | Jun 17, 2026 | 10 |
| Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems | Agents | Shaoyang Xu +4 | Jun 4, 2026 | 10 |
| Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving | Efficiency & systems | Hyungmin Kim +3 | Jun 15, 2026 | 10 |
| Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes | Robotics | Tongyan Fang +8 | Jun 15, 2026 | 10 |
| No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions | Data & benchmarks | Xu Yang +12 | Jun 11, 2026 | 10 |
| μ_0: A Scalable 3D Interaction-Trace World Model | Robotics | Seungjae Lee +8 | Jun 11, 2026 | 10 |
| TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search | Agents | Zhuofan Shi +10 | Jun 10, 2026 | 10 |