{"total":104,"rows":[{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929,"area":"wm"},{"id":"2404.19759","title":"MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model","created":"2024-04-30","cited_by_count":168,"area":"diffusion"},{"id":"2507.15597","title":"Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos","created":"2025-07-21","cited_by_count":102,"area":"vla"},{"id":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98,"area":null},{"id":"2405.20340","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","created":"2024-05-30","cited_by_count":90,"area":null},{"id":"2503.15451","title":"MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space","created":"2025-03-19","cited_by_count":86,"area":null},{"id":"2312.04393","title":"PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction","created":"2023-12-07","cited_by_count":76,"area":null},{"id":"2502.20390","title":"InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions","created":"2025-02-27","cited_by_count":72,"area":null},{"id":"2507.07095","title":"Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data","created":"2025-07-09","cited_by_count":68,"area":null},{"id":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65,"area":null},{"id":"2403.19652","title":"InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction","created":"2024-03-28","cited_by_count":64,"area":"diffusion"},{"id":"2410.07093","title":"LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning","created":"2024-10-09","cited_by_count":59,"area":null},{"id":"2410.21747","title":"MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding","created":"2024-10-29","cited_by_count":59,"area":null},{"id":"2412.14559","title":"ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model","created":"2024-12-19","cited_by_count":53,"area":null},{"id":"2503.19901","title":"TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization","created":"2025-03-25","cited_by_count":51,"area":null},{"id":"2403.13042","title":"TAPTR: Tracking Any Point with Transformers as Detection","created":"2024-03-19","cited_by_count":45,"area":null},{"id":"2409.17686","title":"MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling","created":"2024-09-26","cited_by_count":41,"area":null},{"id":"2412.16563","title":"SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis","created":"2024-12-21","cited_by_count":32,"area":null},{"id":"2509.09555","title":"InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation","created":"2025-09-11","cited_by_count":32,"area":null},{"id":"2404.01700","title":"MotionChain: Conversational Motion Controllers via Multimodal Prompts","created":"2024-04-02","cited_by_count":30,"area":null},{"id":"2502.02358","title":"MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm","created":"2025-02-04","cited_by_count":30,"area":null},{"id":"2407.21136","title":"MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls","created":"2024-07-30","cited_by_count":26,"area":null},{"id":"2402.04852","title":"Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning","created":"2024-02-07","cited_by_count":25,"area":null},{"id":"2410.03311","title":"Scaling Large Motion Models with Million-Level Human Motions","created":"2024-10-04","cited_by_count":22,"area":null},{"id":"2410.20389","title":"Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patterns","created":"2024-10-27","cited_by_count":21,"area":null},{"id":"2411.17799","title":"Signs as Tokens: A Retrieval-Enhanced Multilingual Sign Language Generator","created":"2024-11-26","cited_by_count":21,"area":null},{"id":"2503.08507","title":"Referring to Any Person","created":"2025-03-11","cited_by_count":21,"area":null},{"id":"2503.13130","title":"ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation","created":"2025-03-17","cited_by_count":20,"area":null},{"id":"2503.24026","title":"HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation","created":"2025-03-31","cited_by_count":19,"area":null},{"id":"2508.13139","title":"Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence","created":"2025-08-18","cited_by_count":19,"area":null},{"id":"2410.18977","title":"Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing","created":"2024-10-24","cited_by_count":18,"area":"diffusion"},{"id":"2412.00174","title":"SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters","created":"2024-11-29","cited_by_count":18,"area":null},{"id":"2403.15709","title":"Contact-aware Human Motion Generation from Textual Descriptions","created":"2024-03-23","cited_by_count":16,"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":"2503.08270","title":"HERO: Human Reaction Generation from Videos","created":"2025-03-11","cited_by_count":15,"area":null},{"id":"2503.22906","title":"SocialGen: Modeling Multi-Human Social Interaction with Language Models","created":"2025-03-28","cited_by_count":14,"area":null},{"id":"2412.15664","title":"SCENIC: Scene-aware Semantic Navigation with Instruction-guided Control","created":"2024-12-20","cited_by_count":13,"area":"diffusion"},{"id":"2412.20657","title":"Diffgrasp: Whole-Body Grasping Synthesis Guided by Object Motion Using a Diffusion Model","created":"2024-12-30","cited_by_count":13,"area":"diffusion"},{"id":"2508.00599","title":"DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior","created":"2025-08-01","cited_by_count":13,"area":"diffusion"},{"id":"2311.16471","title":"A Unified Framework for Multimodal, Multi-Part Human Motion Synthesis","created":"2023-11-28","cited_by_count":12,"area":null},{"id":"2503.14517","title":"Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained Control","created":"2025-03-14","cited_by_count":12,"area":null},{"id":"2507.11949","title":"MOSPA: Human Motion Generation Driven by Spatial Audio","created":"2025-07-16","cited_by_count":12,"area":null},{"id":"2406.11253","title":"Holistic-Motion2D: Scalable Whole-body Human Motion Generation in 2D Space","created":"2024-06-17","cited_by_count":10,"area":null},{"id":"2410.06513","title":"MotionRL: Align Text-to-Motion Generation to Human Preferences with Multi-Reward Reinforcement Learning","created":"2024-10-09","cited_by_count":10,"area":"alignment"},{"id":"2508.07863","title":"Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model","created":"2025-08-11","cited_by_count":10,"area":null},{"id":"2601.12799","title":"FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions","created":"2026-01-19","cited_by_count":10,"area":"deeprl"},{"id":"2408.11801","title":"Story3D-Agent: Exploring 3D Storytelling Visualization with Large Language Models","created":"2024-08-21","cited_by_count":9,"area":"agents"},{"id":"2504.08959","title":"MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer","created":"2025-04-11","cited_by_count":9,"area":null},{"id":"2404.14745","title":"You Think, You ACT: The New Task of Arbitrary Text to Motion Generation","created":"2024-04-23","cited_by_count":8,"area":null},{"id":"2411.16964","title":"MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning","created":"2024-11-25","cited_by_count":8,"area":"diffusion"},{"id":"2503.13300","title":"Progressive Human Motion Generation Based on Text and Few Motion Frames","created":"2025-03-17","cited_by_count":8,"area":null},{"id":"2403.11237","title":"FORCE: Physics-aware Human-object Interaction","created":"2024-03-17","cited_by_count":7,"area":null},{"id":"2405.15541","title":"Learning Generalizable Human Motion Generator with Reinforcement Learning","created":"2024-05-24","cited_by_count":7,"area":"deeprl"},{"id":"2405.20336","title":"RapVerse: Coherent Vocals and Whole-Body Motions Generations from Text","created":"2024-05-30","cited_by_count":7,"area":null},{"id":"2412.16670","title":"Two-in-One: Unified Multi-Person Interactive Motion Generation by Latent Diffusion Transformer","created":"2024-12-21","cited_by_count":6,"area":"diffusion"},{"id":"2503.07597","title":"HumanMM: Global Human Motion Recovery from Multi-shot Videos","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2603.25734","title":"Unleashing Guidance Without Classifiers for Human-Object Interaction Animation","created":"2026-03-26","cited_by_count":6,"area":null},{"id":"2409.01522","title":"Lagrangian Motion Fields for Long-term Motion Generation","created":"2024-09-03","cited_by_count":5,"area":null},{"id":"2411.01846","title":"KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension","created":"2024-11-04","cited_by_count":5,"area":"mllm"},{"id":"2412.17377","title":"A Plug-and-Play Physical Motion Restoration Approach for In-the-Wild High-Difficulty Motions","created":"2024-12-23","cited_by_count":5,"area":null},{"id":"2509.23635","title":"MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing","created":"2025-09-28","cited_by_count":5,"area":null},{"id":"2512.24321","title":"UniAct: Unified Motion Generation and Action Streaming for Humanoid Robots","created":"2025-12-30","cited_by_count":5,"area":null},{"id":"2603.13500","title":"ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning","created":"2026-03-13","cited_by_count":5,"area":null},{"id":"2312.02772","title":"FG-MDM: Towards Zero-Shot Human Motion Generation via ChatGPT-Refined Descriptions","created":"2023-12-05","cited_by_count":4,"area":"diffusion"},{"id":"2407.06188","title":"CrowdMoGen: Zero-Shot Text-Driven Collective Motion Generation","created":"2024-07-08","cited_by_count":4,"area":null},{"id":"2504.09885","title":"Separate to Collaborate: Dual-Stream Diffusion Model for Coordinated Piano Hand Motion Synthesis","created":"2025-04-14","cited_by_count":4,"area":"diffusion"},{"id":"2506.00958","title":"Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2506.07456","title":"PhysiInter: Integrating Physical Mapping for High-Fidelity Human Interaction Generation","created":"2025-06-09","cited_by_count":4,"area":null},{"id":"2508.05162","title":"X-MoGen: Unified Motion Generation across Humans and Animals","created":"2025-08-07","cited_by_count":4,"area":null},{"id":"2510.19789","title":"OmniMotion-X: Versatile Multimodal Whole-Body Motion Generation","created":"2025-10-22","cited_by_count":4,"area":"diffusion"},{"id":"2603.19227","title":"Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer","created":"2026-03-19","cited_by_count":4,"area":"diffusion"},{"id":"2604.23264","title":"MotionHiFlow: Text-to-motion via hierarchical flow matching","created":"2026-04-25","cited_by_count":4,"area":"diffusion"},{"id":"2409.20502","title":"COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Models","created":"2024-09-30","cited_by_count":3,"area":"diffusion"},{"id":"2503.08714","title":"Versatile Multimodal Controls for Expressive Talking Human Animation","created":"2025-03-10","cited_by_count":3,"area":null},{"id":"2508.06205","title":"PA-HOI: A Physics-Aware Human and Object Interaction Dataset","created":"2025-08-08","cited_by_count":3,"area":null},{"id":"2508.08991","title":"Spatial-Temporal Multi-Scale Quantization for Flexible Motion Generation","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2512.24100","title":"Think Before You Move: Latent Motion Reasoning for Text-to-Motion Generation","created":"2025-12-30","cited_by_count":3,"area":null},{"id":"2603.08590","title":"PRISM: Streaming Human Motion Generation with Per-Joint Latent Decomposition","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2404.12886","title":"MCM: Multi-condition Motion Synthesis Framework","created":"2024-04-19","cited_by_count":2,"area":"diffusion"},{"id":"2509.23911","title":"MoReact: Generating Reactive Motion from Textual Descriptions","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2603.28766","title":"HandX: Scaling Bimanual Motion and Interaction Generation","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2608.01410","title":"GenTrack: Physical Alignment for Robot-Native Motion Generation and Zero-Shot Humanoid Tracking","created":"2026-08-02","cited_by_count":2,"area":null},{"id":"2608.15141","title":"HOIMask: Towards Generative Masked Modeling for Human Object Interaction Generation","created":"2026-08-15","cited_by_count":2,"area":null},{"id":"2506.03191","title":"Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forward","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2506.07460","title":"SIGNER: Temporally Grounded Sign Language Generation via Time-Resolved Conditioning","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2511.15379","title":"Zero-Shot Open-Vocabulary Human Motion Grounding with Test-Time Training","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2607.07880","title":"GIRAF: Towards Generalizable Human Interactions with Articulated Objects","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2608.07993","title":"MRBench: A Comprehensive Benchmark for Human Motion-Text Retrieval","created":"2026-08-08","cited_by_count":1,"area":null},{"id":"2504.16722","title":"PMG: Progressive Motion Generation via Sparse Anchor Postures Curriculum Learning","created":"2025-04-23","cited_by_count":0,"area":null},{"id":"2506.00043","title":"From Motion to Behavior: Hierarchical Modeling of Humanoid Generative Behavior Control","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2507.11102","title":"KptLLM++: Towards Generic Keypoint Comprehension with Large Language Model","created":"2025-07-15","cited_by_count":0,"area":"mllm"},{"id":"2512.01582","title":"RoleMotion: A Large-Scale Dataset towards Robust Scene-Specific Role-Playing Motion Synthesis with Fine-grained Descriptions","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2512.09005","title":"A Survey of Body and Face Motion: Datasets, Performance Evaluation Metrics and Generative Techniques","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2512.21183","title":"Towards Arbitrary Motion Completing via Hierarchical Continuous Representation","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2512.22324","title":"DeMoGen: Towards Decompositional Human Motion Generation with Energy-Based Diffusion Models","created":"2025-12-26","cited_by_count":0,"area":"diffusion"},{"id":"2603.16936","title":"TDMM-LM: Bridging Facial Understanding and Animation via Language Models","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2604.19105","title":"EgoMotion: Hierarchical Reasoning and Diffusion for Egocentric Vision-Language Motion Generation","created":"2026-04-21","cited_by_count":0,"area":"lr"},{"id":"2606.14721","title":"DC-Motion: Decoupling Structure and Details via Discrete-Continuous Tokens for Human Motion Generation","created":"2026-05-28","cited_by_count":0,"area":"diffusion"},{"id":"2607.11644","title":"Motion4Motion: Motion Transfer Across Subjects at Inference","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.20312","title":"Inter-X++: A Comprehensive Benchmark for Multimodal Human-Human Interaction Analysis","created":"2026-08-20","cited_by_count":0,"area":null}],"next_cursor":"100"}