| 2026-11-19 | 2611.24830 | A Foundation Model to Measure and Predict Human Behaviour | Haoran Ye et al. | arXiv | 2 | |
| 2026-11-18 | 2611.19857 | PanDWM: Panoramic 4D Driving World Models | Jiajun Sun et al. | arXiv | 1 | |
| 2026-11-17 | 2611.19771 | JEPA4R: Embodied JEPA World Models with 4D Point Planning | Jiarui Dong et al. | arXiv | 5 | |
| 2026-11-13 | W4416236439 | Emergent long-tailed dynamics in spin ice | Chenyue Guo et al. | Proceedings of the National Academy of Sciences | | |
| 2026-11-03 | 2610.40293 | MAServeBench: Benchmarking Multi-Agent LLM Serving Systems with Hierarchical Collaboration Workloads | Shengxuan Qiu et al. | arXiv | 9 | |
| 2026-11-03 | W7133615810 | Helios: Real Real-Time Long Video Generation Model | Shenghai Yuan et al. | IEEE Transactions on Pattern Analysis and Machine Intelligence | | |
| 2026-10-27 | 2610.37341 | CodeCap-Bench: Can Code Serve as a Good Video Caption? | Jiafu Tang et al. | arXiv | 52 |  |
| 2026-10-27 | 2610.33079 | Rethinking Video Storage for AI Training: Breaking Cross-Frame Dependencies for Efficient Random Access | Zetian Song et al. | arXiv | 12 | |
| 2026-10-20 | 2609.22332 | AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation | Jiadi You et al. | arXiv | 20 | |
| 2026-10-19 | 2610.26659 | SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes? | Zhaoxi Zhang et al. | arXiv | 120 | |
| 2026-10-16 | 2610.22240 | MMSearch-OPD: Easy Made Hard, Hard Made Learnable for Long-Horizon Multimodal Search Agents | Huanyao Zhang et al. | arXiv | 6 | |
| 2026-10-16 | 2610.06598 | SimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World Models | Xiaodong Wang et al. | arXiv | 2 | |
| 2026-10-14 | 2610.17656 | Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence | Jiahao Meng et al. | arXiv | 24 | |
| 2026-10-14 | 2602.05758 | LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards | Qize Yu et al. | arXiv | 21 | |
| 2026-10-14 | 2610.15357 | UniForge3D: Joint 3D Reconstruction and Generation in a Shared Anchor-Guided Space | Wenjue Chen et al. | arXiv | 4 | |
| 2026-10-12 | W4415137648 | Antiferromagnetism and tightly bound Cooper pairs induced by kinetic frustration | Yixin Zhang et al. | Proceedings of the National Academy of Sciences | | |
| 2026-10-08 | 2610.10047 | AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation | Zhifei Yang et al. | arXiv | 7 | |
| 2026-10-06 | 2610.05033 | Code2Games: Enabling Coding Agents for Gaming World Generation | Wei Wu et al. | arXiv | 5 | |
| 2026-10-05 | 2610.02388 | Octrees as an Explicit 3D Language | Ran Dan et al. | arXiv | 11 | |
| 2026-10-02 | 2610.00360 | DexPolicy: Scheduled Exploration for Trajectory-Guided Dexterous Manipulation | Haoyu Wang et al. | arXiv | 2 | |
| 2026-09-30 | 2609.35932 | Same Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection | Yan Zhan et al. | arXiv | 5 | |
| 2026-09-29 | 2609.29233 | Post-Training Leaves Behavioral Shadows on Unrelated Decisions | Ziyang Zhang et al. | arXiv | 48 | |
| 2026-09-29 | 2609.31948 | Duplex-MPE: Benchmarking Multi-Party Interaction in Full-Duplex Dialogue | Chengqian Ma et al. | arXiv | 43 | |
| 2026-09-28 | 2609.18703 | RayOrch: Programming and Executing Lineage-Controlled Multi-Grain Dataflows for Foundation-Model Data Preparation | Xiaochen Ma et al. | arXiv | 53 | |
| 2026-09-25 | 2609.28811 | DeltaWAM: Delta World Action Models for Bimanual Manipulation | Han Yan et al. | arXiv | 17 | |
| 2026-09-22 | 2609.23088 | OmniEdu: Open Foundation Models for Learning and Teaching | Hao Liang et al. | arXiv | 69 | |
| 2026-09-22 | 2609.24974 | Harness-Zero: Harness Distillation via Agent-as-Harness | Haoran Ye et al. | arXiv | 34 | |
| 2026-09-14 | 2609.06107 | DataFlex-RL: An Evaluation Platform for RLVR Data Policies | Hao Liang et al. | arXiv | 66 | |
| 2026-09-14 | 2609.06251 | MobileVLA-R1 2.0: RL-Enhanced Reasoning for Mobile Robot Control | Ting Huang et al. | arXiv | 6 | |
| 2026-09-14 | 2609.08365 | ReMoMask-2: Latent Retrieval-Augmented Masked Motion Generation | Yiran Wang et al. | arXiv | 1 | |
| 2026-09-10 | 2609.02771 | From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution | Yuzhang Luo et al. | arXiv | 4 | |
| 2026-09-07 | 2609.04250 | Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue | Chengqian Ma et al. | arXiv | 43 | |
| 2026-08-26 | 2608.22274 | Length-Adaptive Decoding for Masked Diffusion Machine Translation | Yan Zhan et al. | arXiv | 3 | |
| 2026-08-25 | 2608.23252 | The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search | Peiyang Liu et al. | arXiv | 4 | |
| 2026-08-17 | 2608.00220 | Verifier-Induced Support Reshaping in On-Policy Optimization | Shaohang Wei et al. | arXiv | 6 | |
| 2026-08-13 | 2608.11878 | ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents | Yutao Mou et al. | arXiv | 13 | |
| 2026-08-05 | 2608.01127 | MiniWorld: Democratizing the Training of Video World Models from Scratch | Yian Zhao et al. | arXiv | 16 | |
| 2026-08-05 | 2608.03971 | UniWorld-Design: From Pixel Generation to Layer-Native Design | Zongjian Li et al. | arXiv | 13 | |
| 2026-08-05 | 2608.03874 | ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities? | Tianyi Guan et al. | arXiv | 10 | |
| 2026-08-04 | 2608.01827 | DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agents | Huanyao Zhang et al. | arXiv | 13 | |
| 2026-08-04 | 2608.00574 | Relax Within, Balance Across: Geometry-Guided Load Balancing for Vision-Language Mixture-of-Experts | Ziang Wu et al. | arXiv | 3 | |
| 2026-07-31 | 2607.28022 | Flux-OPD: On-Policy Distillation with Evolving Contexts | Yuran Wang et al. | arXiv | 45 | |
| 2026-07-28 | 2607.24744 | Data Pyramid for Embodied Manipulation | Yifan Ye et al. | arXiv | 36 | |
| 2026-07-27 | 2607.20465 | DataPrep-Bench: Benchmarking LLMs as Training Data Preparators | Hao Liang et al. | arXiv | 53 | |
| 2026-07-24 | 2605.09635 | K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs | Hao Liang et al. | arXiv | 55 | |
| 2026-07-22 | 2607.16617 | DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines | Runming He et al. | arXiv | 87 | |
| 2026-07-22 | 2607.18091 | SciForma: Structure-Faithful Generation of Scientific Diagrams | Yuxuan Luo et al. | arXiv | 24 | |
| 2026-07-13 | 2607.06374 | VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery | Jiazi Wang et al. | arXiv | 4 | |
| 2026-06-29 | 2606.27978 | Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation | Jiayi Xu et al. | arXiv | 5 | |
| 2026-06-22 | 2606.17480 | GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning | Haoyu Wang et al. | arXiv | 3 | |
| 2026-06-19 | 2606.15133 | DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects | Tianshan Zhang et al. | arXiv | 33 | |
| 2026-06-17 | 2606.15142 | MotionVLA: Vision-Language-Action Model for Humanoid Motion | Nonghai Zhang et al. | arXiv | 4 | |
| 2026-06-08 | 2606.07433 | Watch, Remember, Reason: Human-View Video Understanding with MLLMs | Jiahao Meng et al. | arXiv | 20 | |
| 2026-06-05 | 2606.06042 | LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing | Jianzong Wu et al. | arXiv | 24 | |
| 2026-06-05 | 2606.06155 | AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding | Qize Yu et al. | arXiv | 18 | |
| 2026-06-05 | 2606.03092 | The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs | Xu Wan et al. | arXiv | 7 | |
| 2026-05-28 | 2605.28691 | OSP-Next: Efficient High-Quality Video Generation with Sparse Sequence Parallelism, HiF8 Quantization, and Reinforcement Learning | Yunyang Ge et al. | arXiv | 21 | |
| 2026-05-21 | 2605.14747 | Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining | Weimin Xiong et al. | arXiv | 46 | |
| 2026-05-20 | 2605.18263 | RT-Splatting: Joint Reflection-Transmission Modeling with Gaussian Splatting | Ji Shi et al. | arXiv | 7 | |
| 2026-05-19 | 2605.18287 | StableVLA: Towards Robust Vision-Language-Action Models without Extra Data | Yiyang Fu et al. | arXiv | 14 | |
| 2026-05-18 | 2605.15250 | GQLA: Group-Query Latent Attention for Hardware-Adaptive Large Language Model Decoding | Fanxu Meng | arXiv | 12 | |
| 2026-05-15 | 2605.15186 | VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction | Kaixin Zhu et al. | arXiv | 24 | |
| 2026-05-14 | 2605.11363 | PresentAgent-2: Towards Generalist Multimodal Presentation Agents | Wei Wu et al. | arXiv | 8 | |
| 2026-05-13 | 2605.10365 | Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values | Haonan Dong et al. | arXiv | 9 | |
| 2026-05-13 | 2605.11354 | Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction | Haoyu Zhang et al. | arXiv | 2 | |
| 2026-05-11 | 2605.07363 | MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference | Ruijie Zhou et al. | arXiv | 11 | |
| 2026-05-04 | 2604.24026 | From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills | Qiliang Liang et al. | arXiv | 21 | |