{"list":"other","total":87,"rows":[{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2405.14867","title":"Improved Distribution Matching Distillation for Fast Image Synthesis","created":"2024-05-23","cited_by_count":684},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"id":"2506.08009","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","created":"2025-06-09","cited_by_count":625},{"id":"2405.05941","title":"Evaluating Real-World Robot Manipulation Policies in Simulation","created":"2024-05-09","cited_by_count":495},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2505.06111","title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","created":"2025-05-09","cited_by_count":410},{"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},{"id":"2411.04983","title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","created":"2024-11-07","cited_by_count":386},{"id":"2405.17398","title":"Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability","created":"2024-05-27","cited_by_count":347},{"id":"2410.11758","title":"Latent Action Pretraining from Videos","created":"2024-10-15","cited_by_count":321},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300},{"id":"2408.14837","title":"Diffusion Models Are Real-Time Game Engines","created":"2024-08-27","cited_by_count":296},{"id":"2412.03572","title":"Navigation World Models","created":"2024-12-04","cited_by_count":272},{"id":"1910.11215","title":"RoboNet: Large-Scale Multi-Robot Learning","created":"2019-10-24","cited_by_count":270},{"id":"2509.25161","title":"Rolling Forcing: Autoregressive Long Video Diffusion in Real Time","created":"2025-09-29","cited_by_count":234},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"2210.06407","title":"Interactive Language: Talking to Robots in Real Time","created":"2022-10-12","cited_by_count":218},{"id":"2505.11709","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","created":"2025-05-16","cited_by_count":211},{"id":"2503.00200","title":"Unified Video Action Model","created":"2025-02-28","cited_by_count":205},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200},{"id":"2510.02283","title":"Self-Forcing++: Towards Minute-Scale High-Quality Video Generation","created":"2025-10-02","cited_by_count":192},{"id":"2503.20523","title":"GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving","created":"2025-03-26","cited_by_count":185},{"id":"2512.14614","title":"WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling","created":"2025-12-16","cited_by_count":170},{"id":"2403.07788","title":"DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation","created":"2024-03-12","cited_by_count":160},{"id":"2601.20540","title":"Advancing Open-source World Models","created":"2026-01-28","cited_by_count":154},{"id":"2403.09630","title":"GenAD: Generalized Predictive Model for Autonomous Driving","created":"2024-03-14","cited_by_count":150},{"id":"2509.24527","title":"Training Agents Inside of Scalable World Models","created":"2025-09-29","cited_by_count":136},{"id":"2507.12440","title":"EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos","created":"2025-07-16","cited_by_count":128},{"id":"2104.15060","title":"DriveGAN: Towards a Controllable High-Quality Neural Simulation","created":"2021-04-30","cited_by_count":125},{"id":"2406.09905","title":"Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild","created":"2024-06-14","cited_by_count":114},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","cited_by_count":108},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103},{"id":"2507.15597","title":"Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos","created":"2025-07-21","cited_by_count":102},{"id":"2504.08388","title":"MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft","created":"2025-04-11","cited_by_count":97},{"id":"2512.04040","title":"RELIC: Interactive Video World Model with Long-Horizon Memory","created":"2025-12-03","cited_by_count":96},{"id":"2506.09350","title":"Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation","created":"2025-06-11","cited_by_count":90},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87},{"id":"2005.12126","title":"Learning to Simulate Dynamic Environments with GameGAN","created":"2020-05-25","cited_by_count":86},{"id":"2503.13441","title":"Humanoid Policy ~ Human Policy","created":"2025-03-17","cited_by_count":78},{"id":"2311.18834","title":"ART$\\boldsymbol{\\cdot}$V: Auto-Regressive Text-to-Video Generation with Diffusion Models","created":"2023-11-30","cited_by_count":76},{"id":"2505.14357","title":"Vid2World: Crafting Video Diffusion Models to Interactive World Models","created":"2025-05-20","cited_by_count":76},{"id":"2511.01266","title":"MotionStream: Real-Time Video Generation with Interactive Motion Controls","created":"2025-11-03","cited_by_count":76},{"id":"2510.21571","title":"Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos","created":"2025-10-24","cited_by_count":70},{"id":"2512.15840","title":"Large Video Planner Enables Generalizable Robot Control","created":"2025-12-17","cited_by_count":70},{"id":"2509.07996","title":"3D and 4D World Modeling: A Survey","created":"2025-09-04","cited_by_count":67},{"id":"2502.01828","title":"From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment","created":"2025-02-03","cited_by_count":52},{"id":"2312.15770","title":"A Recipe for Scaling up Text-to-Video Generation with Text-free Videos","created":"2023-12-25","cited_by_count":51},{"id":"2305.18499","title":"Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning","created":"2023-05-29","cited_by_count":45},{"id":"2507.23523","title":"H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulation","created":"2025-07-31","cited_by_count":45},{"id":"2506.09981","title":"ReSim: Reliable World Simulation for Autonomous Driving","created":"2025-06-11","cited_by_count":44},{"id":"2506.13922","title":"DynaGuide: Steering Diffusion Polices with Active Dynamic Guidance","created":"2025-06-16","cited_by_count":44},{"id":"2505.09723","title":"EnerVerse-AC: Envisioning Embodied Environments with Action Condition","created":"2025-05-14","cited_by_count":42},{"id":"2512.22414","title":"Emergence of Human to Robot Transfer in Vision-Language-Action Models","created":"2025-12-27","cited_by_count":42},{"id":"2505.04999","title":"CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations","created":"2025-05-08","cited_by_count":41},{"id":"2505.17006","title":"CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning","created":"2025-05-22","cited_by_count":40},{"id":"2505.20290","title":"EgoZero: Robot Learning from Smart Glasses","created":"2025-05-26","cited_by_count":33},{"id":"2506.15691","title":"What Do Latent Action Models Actually Learn?","created":"2025-05-27","cited_by_count":32},{"id":"2506.21552","title":"Whole-Body Conditioned Egocentric Video Prediction","created":"2025-06-26","cited_by_count":30},{"id":"2502.04296","title":"Learning Real-World Action-Video Dynamics with Heterogeneous Masked Autoregression","created":"2025-02-06","cited_by_count":23},{"id":"2504.21853","title":"A Survey of Interactive Generative Video","created":"2025-04-30","cited_by_count":23},{"id":"2512.08333","title":"Robust Finetuning of Vision-Language-Action Robot Policies via Parameter Merging","created":"2025-12-09","cited_by_count":22},{"id":"2506.05294","title":"A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search","created":"2025-06-05","cited_by_count":17},{"id":"2508.13104","title":"Precise Action-to-Video Generation Through Visual Action Prompts","created":"2025-08-18","cited_by_count":15},{"id":"2508.13013","title":"EgoTwin: Dreaming Body and View in First Person","created":"2025-08-18","cited_by_count":13},{"id":"2506.18901","title":"From Virtual Games to Real-World Play","created":"2025-06-23","cited_by_count":9},{"id":"2510.01068","title":"Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition","created":"2025-10-01","cited_by_count":9},{"id":"2511.18173","title":"EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses","created":"2025-11-22","cited_by_count":8},{"id":"2510.16240","title":"Cosmos-Surg-dVRK: World Foundation Model-based Automated Online Evaluation of Surgical Robot Policy Learning","created":"2025-10-17","cited_by_count":4},{"id":"2512.12430","title":"Endless World: Real-Time 3D-Aware Long Video Generation","created":"2025-12-13","cited_by_count":4}],"next_cursor":null}