{"total":135,"rows":[{"id":"2606.02800","title":"Cosmos 3: Omnimodal World Models for Physical AI","created":"2026-06-01","cited_by_count":165,"area":"wm"},{"id":"2604.05014","title":"StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing","created":"2026-04-06","cited_by_count":112,"area":"wm"},{"id":"2604.08995","title":"Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory","created":"2026-04-10","cited_by_count":100,"area":"wm"},{"id":"2605.15178","title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","created":"2026-05-14","cited_by_count":55,"area":"wm"},{"id":"2606.15768","title":"LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies","created":"2026-06-14","cited_by_count":52,"area":"wm"},{"id":"2605.12090","title":"World Action Models: The Next Frontier in Embodied AI","created":"2026-05-12","cited_by_count":50,"area":"wm"},{"id":"2602.22208","title":"Solaris: Building a Multiplayer Video World Model in Minecraft","created":"2026-02-25","cited_by_count":47,"area":"wm"},{"id":"2605.00080","title":"World Model for Robot Learning: A Comprehensive Survey","created":"2026-04-30","cited_by_count":46,"area":"wm"},{"id":"2606.09811","title":"AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing","created":"2026-06-08","cited_by_count":46,"area":"wm"},{"id":"2603.08546","title":"Interactive World Simulator for Robot Policy Training and Evaluation","created":"2026-03-09","cited_by_count":31,"area":"wm"},{"id":"2606.01027","title":"$\\tau_0$-WM: A Unified Video-Action World Model for Robotic Manipulation","created":"2026-05-31","cited_by_count":27,"area":"wm"},{"id":"2603.26599","title":"VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward","created":"2026-03-27","cited_by_count":24,"area":"diffusion"},{"id":"2607.08436","title":"EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data","created":"2026-07-08","cited_by_count":20,"area":"wm"},{"id":"2604.01985","title":"World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry","created":"2026-04-02","cited_by_count":18,"area":"wm"},{"id":"2608.04404","title":"Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models","created":"2026-08-05","cited_by_count":17,"area":"wm"},{"id":"2605.22718","title":"WorldKV: Efficient World Memory with World Retrieval and Compression","created":"2026-05-21","cited_by_count":15,"area":"diffusion"},{"id":"2605.28816","title":"Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players","created":"2026-05-27","cited_by_count":15,"area":"wm"},{"id":"2607.07675","title":"Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence","created":"2026-07-08","cited_by_count":15,"area":"moe"},{"id":"2604.22748","title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","created":"2026-04-24","cited_by_count":14,"area":"wm"},{"id":"2606.17055","title":"T-Rex: Tactile-Reactive Dexterous Manipulation","created":"2026-06-15","cited_by_count":13,"area":"vla"},{"id":"2603.16669","title":"Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation","created":"2026-03-17","cited_by_count":12,"area":"wm"},{"id":"2604.11689","title":"LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment","created":"2026-04-13","cited_by_count":12,"area":"vla"},{"id":"2606.20781","title":"World Action Models: A Survey","created":"2026-06-18","cited_by_count":12,"area":"wm"},{"id":"2606.12217","title":"Making Foresight Actionable: Repurposing Representation Alignment in World Action Models","created":"2026-06-10","cited_by_count":11,"area":"wm"},{"id":"2608.10860","title":"Flex-$\\pi$: A Multi-Stream World-Action Model with Compute Flexibility","created":"2026-08-11","cited_by_count":11,"area":"wm"},{"id":"2604.26848","title":"STARRY: Spatial-Temporal Action-Centric World Modeling for Robotic Manipulation","created":"2026-04-29","cited_by_count":10,"area":"wm"},{"id":"2605.29360","title":"MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models","created":"2026-05-28","cited_by_count":9,"area":"wm"},{"id":"2607.19343","title":"Masked Visual Actions for Unified World Modeling","created":"2026-07-21","cited_by_count":9,"area":"wm"},{"id":"2608.30237","title":"Motus2: A Self-Evolving General World Model for Dexterous Manipulation","created":"2026-08-31","cited_by_count":9,"area":"wm"},{"id":"2603.10422","title":"World2Act: Latent Action Post-Training from World Model Dynamics","created":"2026-03-11","cited_by_count":8,"area":"wm"},{"id":"2607.14183","title":"Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning","created":"2026-07-15","cited_by_count":8,"area":"wm"},{"id":"2606.04463","title":"OSCAR: Omni-Embodiment Action-Conditioned World Model for Robotics","created":"2026-06-03","cited_by_count":7,"area":"wm"},{"id":"2608.03924","title":"ETA: A New Agentic Paradigm for Embodied Tasks","created":"2026-08-04","cited_by_count":7,"area":"agents"},{"id":"2604.09330","title":"VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis","created":"2026-04-10","cited_by_count":6,"area":"wm"},{"id":"2606.29501","title":"Learning Transferable Dynamics Priors from Action to World Modeling","created":"2026-06-28","cited_by_count":6,"area":"wm"},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2608.10232","title":"FACT: Failure-Aware Causal Training for World-Action Models","created":"2026-08-10","cited_by_count":6,"area":"wm"},{"id":"2609.16074","title":"World-Action Models for Robot Learning and Control: A Survey","created":"2026-09-13","cited_by_count":6,"area":"wm"},{"id":"2603.28489","title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","created":"2026-03-30","cited_by_count":5,"area":"wm"},{"id":"2604.27621","title":"Robot Learning from Human Videos: A Survey","created":"2026-04-30","cited_by_count":5,"area":null},{"id":"2606.11628","title":"LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition","created":"2026-06-10","cited_by_count":5,"area":null},{"id":"2606.17054","title":"Human Universal Grasping","created":"2026-06-15","cited_by_count":5,"area":null},{"id":"2608.12122","title":"HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing","created":"2026-08-12","cited_by_count":5,"area":null},{"id":"2603.11755","title":"Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints","created":"2026-03-12","cited_by_count":4,"area":"wm"},{"id":"2606.05645","title":"Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning","created":"2026-06-04","cited_by_count":4,"area":"wm"},{"id":"2606.12365","title":"Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics","created":"2026-06-10","cited_by_count":4,"area":"diffusion"},{"id":"2607.00836","title":"From World Models to World Action Models: A Concise Tutorial for Robotics","created":"2026-07-01","cited_by_count":4,"area":"wm"},{"id":"2607.01060","title":"RoboWorld: Fast and Reliable Neural Simulators for Generalist Robot Policy Evaluation","created":"2026-07-01","cited_by_count":4,"area":"wm"},{"id":"2608.01397","title":"SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space","created":"2026-08-02","cited_by_count":4,"area":"wm"},{"id":"2608.11671","title":"StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models","created":"2026-08-12","cited_by_count":4,"area":"vla"},{"id":"2608.19613","title":"What Matters for Latent Actions in Robot Learning","created":"2026-08-20","cited_by_count":4,"area":null},{"id":"2609.00188","title":"ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training","created":"2026-08-31","cited_by_count":4,"area":"wm"},{"id":"2603.22286","title":"WorldCache: Content-Aware Caching for Accelerated Video World Models","created":"2026-03-23","cited_by_count":3,"area":"wm"},{"id":"2605.15477","title":"EgoExo-WM: Unlocking Exo Video for Ego World Models","created":"2026-05-14","cited_by_count":3,"area":"wm"},{"id":"2606.02577","title":"RoboDream: Compositional World Models for Scalable Robot Data Synthesis","created":"2026-06-01","cited_by_count":3,"area":"wm"},{"id":"2606.07326","title":"AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization","created":"2026-06-05","cited_by_count":3,"area":"wm"},{"id":"2606.13769","title":"$\\mu_0$: A Scalable 3D Interaction-Trace World Model","created":"2026-06-11","cited_by_count":3,"area":"wm"},{"id":"2606.29908","title":"Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation","created":"2026-06-29","cited_by_count":3,"area":"wm"},{"id":"2607.09185","title":"Causally Debiased Latent Action Model for Embodied Action Conditioned World Models","created":"2026-07-10","cited_by_count":3,"area":"wm"},{"id":"2607.22535","title":"Robot-Factored World Models via Robot Rendering","created":"2026-07-24","cited_by_count":3,"area":"wm"},{"id":"2608.06332","title":"GeniWorld: A Generalizable Interactive World Model for Robotic Manipulation via Visual Actions","created":"2026-08-06","cited_by_count":3,"area":"wm"},{"id":"2608.19583","title":"VGI-Bench: Probing Visual Intelligence in Video Generation Models","created":"2026-08-20","cited_by_count":3,"area":"lr"},{"id":"2608.29242","title":"AnyWorld: Factorized Egocentric World Models for Cross-Embodiment Generalization","created":"2026-08-29","cited_by_count":3,"area":"wm"},{"id":"2604.07348","title":"MoRight: Motion Control Done Right","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2604.26182","title":"Lifting Embodied World Models for Planning and Control","created":"2026-04-28","cited_by_count":2,"area":"wm"},{"id":"2606.09813","title":"iMaC: Translating Actions into Motion and Contact Images for Embodied World Models","created":"2026-06-08","cited_by_count":2,"area":"wm"},{"id":"2606.14981","title":"Inference-time Policy Steering via Vision and Touch","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2606.17598","title":"MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulation","created":"2026-06-16","cited_by_count":2,"area":"vla"},{"id":"2607.14187","title":"RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination","created":"2026-07-15","cited_by_count":2,"area":"lr"},{"id":"2607.25918","title":"DC-WAM: Dynamic-Centric Visual Supervision and Reasoning for World-Action Models","created":"2026-07-28","cited_by_count":2,"area":"wm"},{"id":"2608.01452","title":"DynamicManip: Enabling Dynamic Manipulation from a Single Static Demonstration","created":"2026-08-02","cited_by_count":2,"area":null},{"id":"2608.09298","title":"WorldSimProbe: Diagnosing Simulator Faithfulness in Action-Conditioned World Models for Embodied Manipulation","created":"2026-08-10","cited_by_count":2,"area":"wm"},{"id":"2608.30692","title":"Can Video World Models Track Unobserved World States?","created":"2026-08-31","cited_by_count":2,"area":"wm"},{"id":"2604.08544","title":"SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2604.19741","title":"CityRAG: Stepping Into a City via Spatially-Grounded Video Generation","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.01799","title":"Embody4D: A Generalist Data Engine for Embodied 4D World Modeling","created":"2026-05-03","cited_by_count":1,"area":"wm"},{"id":"2605.11750","title":"DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies","created":"2026-05-12","cited_by_count":1,"area":"vla"},{"id":"2605.13775","title":"RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.16395","title":"OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence","created":"2026-05-12","cited_by_count":1,"area":"wm"},{"id":"2605.16797","title":"EgoKit: Towards Unified Low-Cost Egocentric Data Collection with Heterogeneous Devices","created":"2026-05-16","cited_by_count":1,"area":null},{"id":"2606.03920","title":"Benchmarking Visual State Tracking in Multimodal Video Understanding","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.21562","title":"Compressing History into Memory: Distilling Transformers into Recurrent Transformers","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2606.26095","title":"Learning Action Priors for Cross-embodiment Robot Manipulation","created":"2026-06-24","cited_by_count":1,"area":"mllm"},{"id":"2606.28385","title":"RoboGaze: Evaluating Robot World Models via Structured Vision-Language Analysis","created":"2026-06-22","cited_by_count":1,"area":"wm"},{"id":"2607.16602","title":"PAVXploreRL: Physical-Action-Visual World Model Reinforcement Learning with Action Exploration","created":"2026-07-18","cited_by_count":1,"area":"wm"},{"id":"2608.01127","title":"MiniWorld: Democratizing the Training of Video World Models from Scratch","created":"2026-08-02","cited_by_count":1,"area":"wm"},{"id":"2608.05706","title":"LAWM-3D: Learning 3D-Aware Latent Actions from Human Videos for Generalizable Robot World Models","created":"2026-08-06","cited_by_count":1,"area":"wm"},{"id":"2608.15707","title":"GAINS: Leveraging Inconsistent Human Intervention Signals in Reinforcement Learning","created":"2026-08-16","cited_by_count":1,"area":"deeprl"},{"id":"2608.27406","title":"CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators","created":"2026-08-27","cited_by_count":1,"area":"wm"},{"id":"2609.09155","title":"SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators","created":"2026-09-08","cited_by_count":1,"area":"wm"},{"id":"2609.17372","title":"XPACE: Joint World and Action Modeling from Heterogeneous Experience","created":"2026-09-15","cited_by_count":1,"area":"wm"},{"id":"2609.23184","title":"CausalWM: Causal Chain-of-Thought Reasoning for Embodied World Model","created":"2026-09-19","cited_by_count":1,"area":"wm"},{"id":"2609.26314","title":"TriWorldBench: A Tri-View Consistency Perspective on Embodied World Models","created":"2026-09-22","cited_by_count":1,"area":"wm"},{"id":"2610.02054","title":"UniWAM: Unified World-Action Model","created":"2026-10-01","cited_by_count":1,"area":"wm"},{"id":"2606.03868","title":"Unified Video-Action Joint Denoising for Dexterous Action and Data Generation","created":"2026-06-02","cited_by_count":0,"area":"wm"},{"id":"2606.05960","title":"Towards a Data Flywheel for Embodied Intelligence in Logistics","created":"2026-06-04","cited_by_count":0,"area":"wm"},{"id":"2606.24876","title":"FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation","created":"2026-06-23","cited_by_count":0,"area":"diffusion"},{"id":"2607.02646","title":"EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.03461","title":"WorldBagel: Uncovering the Power of Unified Multimodal Models for Vision-Language-Action-World Modeling","created":"2026-07-03","cited_by_count":0,"area":"wm"},{"id":"2607.18709","title":"RoboInter1.5: A Holistic Intermediate Representation Suite for Embodied World Modeling and Robotic Manipulation","created":"2026-07-21","cited_by_count":0,"area":"wm"}],"next_cursor":"100"}