{"total":196,"rows":[{"id":"2503.06669","title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","created":"2025-03-09","cited_by_count":405,"area":null},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228,"area":null},{"id":"2505.11709","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","created":"2025-05-16","cited_by_count":211,"area":null},{"id":"2503.00200","title":"Unified Video Action Model","created":"2025-02-28","cited_by_count":205,"area":null},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189,"area":null},{"id":"2503.06800","title":"VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation","created":"2025-03-09","cited_by_count":149,"area":null},{"id":"2503.19325","title":"Long-Context Autoregressive Video Modeling with Next-Frame Prediction","created":"2025-03-25","cited_by_count":123,"area":null},{"id":"2506.18903","title":"VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory","created":"2025-06-23","cited_by_count":109,"area":null},{"id":"2502.12894","title":"CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image","created":"2025-02-18","cited_by_count":106,"area":null},{"id":"2506.09350","title":"Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation","created":"2025-06-11","cited_by_count":90,"area":null},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87,"area":null},{"id":"2501.10105","title":"Universal Actions for Enhanced Embodied Foundation Models","created":"2025-01-17","cited_by_count":82,"area":null},{"id":"2411.02038","title":"Addressing Representation Collapse in Vector Quantized Models with One Linear Layer","created":"2024-11-04","cited_by_count":80,"area":null},{"id":"2412.03568","title":"The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control","created":"2024-12-04","cited_by_count":80,"area":null},{"id":"2511.01266","title":"MotionStream: Real-Time Video Generation with Interactive Motion Controls","created":"2025-11-03","cited_by_count":76,"area":null},{"id":"2412.04445","title":"Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos","created":"2024-12-05","cited_by_count":69,"area":null},{"id":"2603.04379","title":"Helios: Real Real-Time Long Video Generation Model","created":"2026-03-04","cited_by_count":65,"area":null},{"id":"2509.09677","title":"The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs","created":"2025-09-11","cited_by_count":64,"area":null},{"id":"2503.24361","title":"Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation","created":"2025-03-31","cited_by_count":46,"area":null},{"id":"2410.23208","title":"Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks","created":"2024-10-30","cited_by_count":45,"area":null},{"id":"2505.18151","title":"WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions","created":"2025-05-23","cited_by_count":45,"area":null},{"id":"2502.00379","title":"Latent Action Learning Requires Supervision in the Presence of Distractors","created":"2025-02-01","cited_by_count":44,"area":null},{"id":"2502.07825","title":"Pre-Trained Video Generative Models as World Simulators","created":"2025-02-10","cited_by_count":44,"area":null},{"id":"2501.09781","title":"VideoWorld: Exploring Knowledge Learning from Unlabeled Videos","created":"2025-01-16","cited_by_count":43,"area":null},{"id":"2405.13570","title":"MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation","created":"2024-05-22","cited_by_count":42,"area":null},{"id":"2512.04519","title":"VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory","created":"2025-12-04","cited_by_count":42,"area":null},{"id":"2505.04999","title":"CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations","created":"2025-05-08","cited_by_count":41,"area":null},{"id":"2505.17006","title":"CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning","created":"2025-05-22","cited_by_count":40,"area":null},{"id":"2512.15716","title":"Spatia: Video Generation with Updatable Spatial Memory","created":"2025-12-17","cited_by_count":40,"area":null},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2512.11047","title":"WholeBodyVLA: Towards Unified Latent VLA for Whole-Body Loco-Manipulation Control","created":"2025-12-11","cited_by_count":36,"area":null},{"id":"2607.08639","title":"Native Video-Action Pretraining for Generalizable Robot Control","created":"2026-07-09","cited_by_count":36,"area":null},{"id":"2406.19370","title":"Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2505.08787","title":"UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations","created":"2025-05-13","cited_by_count":35,"area":null},{"id":"2601.15282","title":"Rethinking Video Generation Model for the Embodied World","created":"2026-01-21","cited_by_count":33,"area":null},{"id":"2503.17076","title":"Halton Scheduler For Masked Generative Image Transformer","created":"2025-03-21","cited_by_count":32,"area":null},{"id":"2506.15691","title":"What Do Latent Action Models Actually Learn?","created":"2025-05-27","cited_by_count":32,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2501.12389","title":"Taming Teacher Forcing for Masked Autoregressive Video Generation","created":"2025-01-21","cited_by_count":30,"area":null},{"id":"2603.25746","title":"ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling","created":"2026-03-26","cited_by_count":28,"area":null},{"id":"2405.10674","title":"From Sora What We Can See: A Survey of Text-to-Video Generation","created":"2024-05-17","cited_by_count":27,"area":null},{"id":"2411.07223","title":"Grounding Video Models to Actions through Goal Conditioned Exploration","created":"2024-11-11","cited_by_count":26,"area":null},{"id":"2412.00887","title":"Playable Game Generation","created":"2024-12-01","cited_by_count":26,"area":null},{"id":"2502.07737","title":"Next Block Prediction: Video Generation via Semi-Autoregressive Modeling","created":"2025-02-11","cited_by_count":26,"area":null},{"id":"2404.08706","title":"Game Generation via Large Language Models","created":"2024-04-11","cited_by_count":25,"area":null},{"id":"2405.04682","title":"TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generation","created":"2024-05-07","cited_by_count":25,"area":null},{"id":"2410.10076","title":"VideoAgent: Self-Improving Video Generation","created":"2024-10-14","cited_by_count":25,"area":null},{"id":"2512.24766","title":"Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow","created":"2025-12-31","cited_by_count":25,"area":null},{"id":"2501.10928","title":"Generative Physical AI in Vision: A Survey","created":"2025-01-19","cited_by_count":24,"area":null},{"id":"2504.21853","title":"A Survey of Interactive Generative Video","created":"2025-04-30","cited_by_count":23,"area":null},{"id":"2510.15352","title":"GaussGym: An open-source real-to-sim framework for learning locomotion from pixels","created":"2025-10-17","cited_by_count":22,"area":null},{"id":"2603.05449","title":"RealWonder: Real-Time Physical Action-Conditioned Video Generation","created":"2026-03-05","cited_by_count":22,"area":null},{"id":"2507.06219","title":"Is Diversity All You Need for Scalable Robotic Manipulation?","created":"2025-07-08","cited_by_count":20,"area":null},{"id":"2507.08800","title":"NeuralOS: Towards Simulating Operating Systems via Neural Generative Models","created":"2025-07-11","cited_by_count":19,"area":null},{"id":"2405.06686","title":"Word2World: Generating Stories and Worlds through Large Language Models","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2506.14168","title":"VideoMAR: Autoregressive Video Generatio with Continuous Tokens","created":"2025-06-17","cited_by_count":16,"area":null},{"id":"2508.15720","title":"WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception","created":"2025-08-21","cited_by_count":16,"area":null},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2503.04641","title":"Simulating the Real World: A Unified Survey of Multimodal Generative Models","created":"2025-03-06","cited_by_count":15,"area":null},{"id":"2508.08601","title":"Yan: Foundational Interactive Video Generation","created":"2025-08-12","cited_by_count":15,"area":null},{"id":"2508.13104","title":"Precise Action-to-Video Generation Through Visual Action Prompts","created":"2025-08-18","cited_by_count":15,"area":null},{"id":"2511.20186","title":"Exo2EgoSyn: Unlocking Foundation Video Generation Models for Exocentric-to-Egocentric Video Synthesis","created":"2025-11-25","cited_by_count":15,"area":null},{"id":"2511.20351","title":"Thinking in 360{\\deg}: Humanoid Visual Search in the Wild","created":"2025-11-25","cited_by_count":15,"area":null},{"id":"2602.14941","title":"AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories","created":"2026-02-16","cited_by_count":15,"area":null},{"id":"2605.23458","title":"One-Forcing: Towards Stable One-Step Autoregressive Video Generation","created":"2026-05-22","cited_by_count":15,"area":null},{"id":"2502.07600","title":"PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning","created":"2025-02-11","cited_by_count":14,"area":null},{"id":"2604.01001","title":"EgoSim: Egocentric World Simulator for Embodied Interaction Generation","created":"2026-04-01","cited_by_count":14,"area":null},{"id":"2410.15536","title":"GRS: Generating Robotic Simulation Tasks from Real-World Images","created":"2024-10-20","cited_by_count":13,"area":null},{"id":"2503.17359","title":"Position: Interactive Generative Video as Next-Generation Game Engine","created":"2025-03-21","cited_by_count":13,"area":null},{"id":"2601.15281","title":"StableWorld: Towards Stable and Consistent Long Interactive Video Generation","created":"2026-01-21","cited_by_count":12,"area":null},{"id":"2602.10102","title":"VideoWorld 2: Learning Transferable Knowledge from Real-world Videos","created":"2026-02-10","cited_by_count":12,"area":null},{"id":"2605.04128","title":"JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation","created":"2026-05-05","cited_by_count":12,"area":null},{"id":"2403.00729","title":"Can Transformers Capture Spatial Relations between Objects?","created":"2024-03-01","cited_by_count":11,"area":null},{"id":"2504.08125","title":"Gen3DEval: Using vLLMs for Automatic Evaluation of Generated 3D Objects","created":"2025-04-10","cited_by_count":11,"area":null},{"id":"2603.15381","title":"Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science","created":"2026-03-16","cited_by_count":11,"area":null},{"id":"2409.17652","title":"FactorSim: Generative Simulation via Factorized Representation","created":"2024-09-26","cited_by_count":10,"area":null},{"id":"2410.01791","title":"DreamGarden: A Designer Assistant for Growing Games from a Single Prompt","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2603.13528","title":"Learning Actionable Manipulation Recovery via Counterfactual Failure Synthesis","created":"2026-03-13","cited_by_count":10,"area":null},{"id":"2605.12496","title":"CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives","created":"2026-05-12","cited_by_count":10,"area":null},{"id":"2606.28128","title":"PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation","created":"2026-06-26","cited_by_count":10,"area":null},{"id":"2411.16619","title":"Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation Metric","created":"2024-11-25","cited_by_count":9,"area":null},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2502.09680","title":"Object-Centric Latent Action Learning","created":"2025-02-13","cited_by_count":9,"area":null},{"id":"2506.07886","title":"EgoM2P: Egocentric Multimodal Multitask Pretraining","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2506.18901","title":"From Virtual Games to Real-World Play","created":"2025-06-23","cited_by_count":9,"area":null},{"id":"2512.10571","title":"AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner","created":"2025-12-11","cited_by_count":9,"area":null},{"id":"2407.09502","title":"From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models","created":"2024-06-14","cited_by_count":8,"area":null},{"id":"2510.04236","title":"Scaling Sequence-to-Sequence Generative Neural Rendering","created":"2025-10-05","cited_by_count":8,"area":null},{"id":"2605.07061","title":"Do Joint Audio-Video Generation Models Understand Physics?","created":"2026-05-08","cited_by_count":8,"area":null},{"id":"2504.01014","title":"AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction","created":"2025-04-01","cited_by_count":7,"area":null},{"id":"2603.05923","title":"Learning Next Action Predictors from Human-Computer Interaction","created":"2026-03-06","cited_by_count":7,"area":null},{"id":"2604.03340","title":"Learning Additively Compositional Latent Actions for Embodied AI","created":"2026-04-03","cited_by_count":7,"area":null},{"id":"2604.18215","title":"Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation","created":"2026-04-20","cited_by_count":7,"area":null},{"id":"2605.15188","title":"FutureSim: Replaying World Events to Evaluate Adaptive Agents","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2602.02259","title":"Segment to Focus: Guiding Latent Action Models in the Presence of Distractors","created":"2026-02-02","cited_by_count":6,"area":null},{"id":"2603.26285","title":"PhysVid: Physics Aware Local Conditioning for Generative Video Models","created":"2026-03-27","cited_by_count":6,"area":null},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2503.21383","title":"Controlling Large Language Model with Latent Actions","created":"2025-03-27","cited_by_count":5,"area":null},{"id":"2510.02110","title":"SoundReactor: Frame-level Online Video-to-Audio Generation","created":"2025-10-02","cited_by_count":5,"area":null}],"next_cursor":"100"}