{"list":"other","total":160,"rows":[{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"2505.11709","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","created":"2025-05-16","cited_by_count":211},{"id":"2602.06949","title":"DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos","created":"2026-02-06","cited_by_count":135},{"id":"2507.12440","title":"EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos","created":"2025-07-16","cited_by_count":128},{"id":"2507.15597","title":"Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos","created":"2025-07-21","cited_by_count":102},{"id":"2511.07820","title":"SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control","created":"2025-11-11","cited_by_count":101},{"id":"2602.16710","title":"EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data","created":"2026-02-18","cited_by_count":94},{"id":"2506.14770","title":"GMT: General Motion Tracking for Humanoid Whole-Body Control","created":"2025-06-17","cited_by_count":83},{"id":"2506.18866","title":"OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation","created":"2025-06-23","cited_by_count":83},{"id":"2509.14055","title":"Wan-Animate: Unified Character Animation and Replacement with Holistic Replication","created":"2025-09-17","cited_by_count":80},{"id":"2605.00078","title":"Being-H0.7: A Latent World-Action Model from Egocentric Videos","created":"2026-04-30","cited_by_count":75},{"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":"2505.20156","title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters","created":"2025-05-26","cited_by_count":69},{"id":"2604.07607","title":"EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World","created":"2026-04-08","cited_by_count":57},{"id":"2507.09122","title":"SnapMoGen: Human Motion Generation from Expressive Texts","created":"2025-07-12","cited_by_count":47},{"id":"2405.11794","title":"ViViD: Video Virtual Try-on using Diffusion Models","created":"2024-05-20","cited_by_count":42},{"id":"2503.06955","title":"Motion Anything: Any to Motion Generation","created":"2025-03-10","cited_by_count":42},{"id":"2506.22554","title":"Seamless Interaction: Dyadic Audiovisual Motion Modeling and Large-Scale Dataset","created":"2025-06-27","cited_by_count":40},{"id":"2502.04847","title":"HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video Generation","created":"2025-02-07","cited_by_count":39},{"id":"2511.04131","title":"BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning","created":"2025-11-06","cited_by_count":38},{"id":"2510.06219","title":"Human3R: Everyone Everywhere All at Once","created":"2025-10-07","cited_by_count":37},{"id":"2603.15546","title":"Kimodo: Scaling Controllable Human Motion Generation","created":"2026-03-16","cited_by_count":37},{"id":"2512.11047","title":"WholeBodyVLA: Towards Unified Latent VLA for Whole-Body Loco-Manipulation Control","created":"2025-12-11","cited_by_count":36},{"id":"2512.23464","title":"HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation","created":"2025-12-29","cited_by_count":36},{"id":"2501.05098","title":"Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset","created":"2025-01-09","cited_by_count":33},{"id":"2508.19209","title":"OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation","created":"2025-08-26","cited_by_count":32},{"id":"2512.13644","title":"World Models for Learning Dexterous Hand-Object Interactions from Human Videos","created":"2025-12-15","cited_by_count":31},{"id":"2507.09862","title":"SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation","created":"2025-07-14","cited_by_count":30},{"id":"2504.14977","title":"RealisDance-DiT: Simple yet Strong Baseline towards Controllable Character Animation in the Wild","created":"2025-04-21","cited_by_count":29},{"id":"2510.08480","title":"Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools","created":"2025-10-09","cited_by_count":26},{"id":"2511.15704","title":"In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data","created":"2025-11-19","cited_by_count":26},{"id":"2410.03311","title":"Scaling Large Motion Models with Million-Level Human Motions","created":"2024-10-04","cited_by_count":22},{"id":"2506.10568","title":"DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers","created":"2025-06-12","cited_by_count":22},{"id":"2510.26794","title":"The Quest for Generalizable Motion Generation: Data, Model, and Evaluation","created":"2025-10-30","cited_by_count":22},{"id":"2602.12160","title":"DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation","created":"2026-02-12","cited_by_count":20},{"id":"2604.23570","title":"EgoLive: A Large-Scale Egocentric Dataset from Real-World Human Tasks","created":"2026-04-26","cited_by_count":20},{"id":"2510.01607","title":"ActiveUMI: Robotic Manipulation with Active Perception from Robot-Free Human Demonstrations","created":"2025-10-02","cited_by_count":19},{"id":"2510.16258","title":"Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset","created":"2025-10-17","cited_by_count":19},{"id":"2509.21574","title":"X-Streamer: Unified Human World Modeling with Audiovisual Interaction","created":"2025-09-25","cited_by_count":18},{"id":"2510.14952","title":"From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance","created":"2025-10-16","cited_by_count":18},{"id":"2508.02807","title":"DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework","created":"2025-08-04","cited_by_count":17},{"id":"2602.09600","title":"Hand2World: Autoregressive Egocentric Interaction Generation via Free-Space Hand Gestures","created":"2026-02-10","cited_by_count":16},{"id":"2605.24934","title":"HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos","created":"2026-05-24","cited_by_count":16},{"id":"2502.18180","title":"ChatMotion: A Multimodal Multi-Agent for Human Motion Analysis","created":"2025-02-25","cited_by_count":14},{"id":"2604.01001","title":"EgoSim: Egocentric World Simulator for Embodied Interaction Generation","created":"2026-04-01","cited_by_count":14},{"id":"2410.20717","title":"Face-MLLM: A Large Face Perception Model","created":"2024-10-28","cited_by_count":13},{"id":"2509.05513","title":"OpenEgo: A Large-Scale Multimodal Egocentric Dataset for Dexterous Manipulation","created":"2025-09-05","cited_by_count":13},{"id":"2512.13313","title":"KlingAvatar 2.0 Technical Report","created":"2025-12-15","cited_by_count":13},{"id":"2512.18814","title":"EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer","created":"2025-12-21","cited_by_count":13},{"id":"2602.18422","title":"Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control","created":"2026-02-20","cited_by_count":13},{"id":"2603.27449","title":"LOME: Learning Human-Object Manipulation with Action-Conditioned Egocentric World Model","created":"2026-03-28","cited_by_count":13},{"id":"2502.08556","title":"Human-Centric Foundation Models: Perception, Generation and Agentic Modeling","created":"2025-02-12","cited_by_count":12},{"id":"2503.18349","title":"Human-Object Interaction via Automatically Designed VLM-Guided Motion Policy","created":"2025-03-24","cited_by_count":12},{"id":"2603.13615","title":"Egocentric World Model for Photorealistic Hand-Object Interaction Synthesis","created":"2026-03-13","cited_by_count":12},{"id":"2603.20169","title":"EgoForge: Goal-Directed Egocentric World Simulator","created":"2026-03-20","cited_by_count":12},{"id":"2605.06747","title":"HumanNet: Scaling Human-centric Video Learning to One Million Hours","created":"2026-05-07","cited_by_count":11},{"id":"2508.07863","title":"Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model","created":"2025-08-11","cited_by_count":10},{"id":"2512.13674","title":"Towards Interactive Intelligence for Digital Humans","created":"2025-12-15","cited_by_count":10},{"id":"2506.10353","title":"Motion-R1: Enhancing Motion Generation with Decomposed Chain-of-Thought and RL Binding","created":"2025-06-12","cited_by_count":9},{"id":"2506.17896","title":"EgoWorld: Translating Exocentric View to Egocentric View using Rich Exocentric Observations","created":"2025-06-22","cited_by_count":9},{"id":"2601.01222","title":"UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass","created":"2026-01-03","cited_by_count":9},{"id":"2512.16907","title":"Flowing from Reasoning to Motion: Learning 3D Hand Trajectory Prediction from Egocentric Human Interaction Videos","created":"2025-12-18","cited_by_count":8},{"id":"2604.11804","title":"OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation","created":"2026-04-13","cited_by_count":8},{"id":"2208.03775","title":"Video-based Human Action Recognition using Deep Learning: A Review","created":"2022-08-07","cited_by_count":7},{"id":"2503.13120","title":"3D Human Interaction Generation: A Survey","created":"2025-03-17","cited_by_count":7},{"id":"2512.22854","title":"ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learning","created":"2025-12-28","cited_by_count":7},{"id":"2606.04970","title":"Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance","created":"2026-06-03","cited_by_count":7},{"id":"2506.07209","title":"HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance","created":"2025-06-08","cited_by_count":6},{"id":"2507.04909","title":"HumanVideo-MME: Benchmarking MLLMs for Human-Centric Video Understanding","created":"2025-07-07","cited_by_count":6},{"id":"2601.10632","title":"CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos","created":"2026-01-15","cited_by_count":6},{"id":"2604.24833","title":"MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives","created":"2026-04-27","cited_by_count":6},{"id":"2606.06194","title":"ActiveMimic: Egocentric Video Pretraining with Active Perception","created":"2026-06-04","cited_by_count":6},{"id":"2606.24422","title":"EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding","created":"2026-06-23","cited_by_count":6},{"id":"2503.08120","title":"UniF$^2$ace: A Unified Fine-grained Face Understanding and Generation Model","created":"2025-03-11","cited_by_count":5},{"id":"2510.26236","title":"PHUMA: Physically Reliable Humanoid Locomotion Dataset","created":"2025-10-30","cited_by_count":5},{"id":"2603.25892","title":"THFM: A Unified Video Foundation Model for 4D Human Perception and Beyond","created":"2026-03-26","cited_by_count":5},{"id":"2604.19748","title":"Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items","created":"2026-04-21","cited_by_count":5},{"id":"2605.15824","title":"FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization","created":"2026-05-15","cited_by_count":5},{"id":"2605.22894","title":"SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control","created":"2026-05-21","cited_by_count":5},{"id":"2605.24652","title":"AVBench: Human-Aligned and Automated Evaluation Benchmark for Audio-Video Generative Models","created":"2026-05-23","cited_by_count":5},{"id":"2606.03985","title":"Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking","created":"2026-06-02","cited_by_count":5},{"id":"2606.07100","title":"LARA: Latent Action Representation Alignment for Vision-Language-Action Models","created":"2026-06-05","cited_by_count":5},{"id":"2606.17054","title":"Human Universal Grasping","created":"2026-06-15","cited_by_count":5},{"id":"2606.22905","title":"InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars","created":"2026-06-22","cited_by_count":5},{"id":"2608.10915","title":"ComBodied Agents: a New Paradigm of Human-Centric Agentic AI","created":"2026-08-11","cited_by_count":5},{"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},{"id":"2603.26908","title":"FusionAgent: A Multimodal Agent with Dynamic Model Selection for Human Recognition","created":"2026-03-27","cited_by_count":4},{"id":"2604.00267","title":"Omni-MMSI: Toward Identity-attributed Social Interaction Understanding","created":"2026-03-31","cited_by_count":4},{"id":"2604.02908","title":"SentiAvatar: Towards Expressive and Interactive Digital Humans","created":"2026-04-03","cited_by_count":4},{"id":"2604.14944","title":"HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments","created":"2026-04-16","cited_by_count":4},{"id":"2605.10079","title":"SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation","created":"2026-05-11","cited_by_count":4},{"id":"2605.11704","title":"ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation","created":"2026-05-12","cited_by_count":4},{"id":"2605.19846","title":"FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding","created":"2026-05-19","cited_by_count":4},{"id":"2505.10238","title":"MTVCraft: Tokenizing 4D Motion for Arbitrary Character Animation","created":"2025-05-15","cited_by_count":3},{"id":"2601.20835","title":"Open-Vocabulary Functional 3D Human-Scene Interaction Generation","created":"2026-01-28","cited_by_count":3},{"id":"2601.22693","title":"PEAR: Pixel-aligned Expressive humAn mesh Recovery","created":"2026-01-30","cited_by_count":3},{"id":"2603.18003","title":"Universal Skeleton Understanding via Differentiable Rendering and MLLMs","created":"2026-03-18","cited_by_count":3},{"id":"2603.21664","title":"HumanOmni-Speaker: Identifying Who said What and When","created":"2026-03-23","cited_by_count":3},{"id":"2604.18326","title":"OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation","created":"2026-04-20","cited_by_count":3}],"next_cursor":"100"}