{"total":94,"rows":[{"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":"2312.02256","title":"EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation","created":"2023-12-04","cited_by_count":89,"area":"diffusion"},{"id":"2411.16575","title":"Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression","created":"2024-11-25","cited_by_count":85,"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":"2403.13900","title":"CoMo: Controllable Motion Generation through Language Guided Pose Code Editing","created":"2024-03-20","cited_by_count":67,"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":"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":"2405.17013","title":"Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs","created":"2024-05-27","cited_by_count":47,"area":"agents"},{"id":"2503.13836","title":"SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing","created":"2025-03-18","cited_by_count":39,"area":"diffusion"},{"id":"2410.10780","title":"MaskControl: Spatio-Temporal Control for Masked Motion Synthesis","created":"2024-10-14","cited_by_count":38,"area":"diffusion"},{"id":"2407.12783","title":"SMooDi: Stylized Motion Diffusion Model","created":"2024-07-17","cited_by_count":37,"area":"diffusion"},{"id":"2603.15546","title":"Kimodo: Scaling Controllable Human Motion Generation","created":"2026-03-16","cited_by_count":37,"area":null},{"id":"2410.00464","title":"Enabling Synergistic Full-Body Control in Prompt-Based Co-Speech Motion Generation","created":"2024-10-01","cited_by_count":35,"area":null},{"id":"2312.05295","title":"Disentangled Clothed Avatar Generation from Text Descriptions","created":"2023-12-08","cited_by_count":33,"area":null},{"id":"2505.19377","title":"Absolute Coordinates Make Motion Generation Easy","created":"2025-05-26","cited_by_count":29,"area":null},{"id":"2503.18211","title":"SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction","created":"2025-03-23","cited_by_count":27,"area":null},{"id":"2504.12540","title":"UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Control","created":"2025-04-17","cited_by_count":25,"area":null},{"id":"2404.19722","title":"PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios","created":"2024-04-30","cited_by_count":24,"area":null},{"id":"2411.15472","title":"KinMo: Kinematic-aware Human Motion Understanding and Generation","created":"2024-11-23","cited_by_count":21,"area":null},{"id":"2502.05534","title":"Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation","created":"2025-02-08","cited_by_count":21,"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":"2504.08449","title":"Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input","created":"2025-04-11","cited_by_count":17,"area":null},{"id":"2504.19189","title":"Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation","created":"2025-04-27","cited_by_count":17,"area":null},{"id":"2503.01291","title":"SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance","created":"2025-03-03","cited_by_count":16,"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":"2504.01019","title":"MixerMDM: Learnable Composition of Human Motion Diffusion Models","created":"2025-04-01","cited_by_count":13,"area":"diffusion"},{"id":"2411.19921","title":"SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation","created":"2024-11-29","cited_by_count":12,"area":"rag"},{"id":"2505.21437","title":"CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects","created":"2025-05-27","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":"2507.20220","title":"Motion-example-controlled Co-speech Gesture Generation Leveraging Large Language Models","created":"2025-07-27","cited_by_count":11,"area":null},{"id":"2510.06504","title":"Text2Interact: High-Fidelity and Diverse Text-to-Two-Person Interaction Generation","created":"2025-10-07","cited_by_count":11,"area":null},{"id":"2403.11469","title":"Generative Motion Stylization of Cross-structure Characters within Canonical Motion Space","created":"2024-03-18","cited_by_count":10,"area":null},{"id":"2406.17988","title":"DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Image","created":"2024-06-26","cited_by_count":9,"area":null},{"id":"2503.15557","title":"Motion Synthesis with Sparse and Flexible Keyjoint Control","created":"2025-03-18","cited_by_count":9,"area":null},{"id":"2403.11111","title":"Diffusion Models are Efficient Data Generators for Human Mesh Recovery","created":"2024-03-17","cited_by_count":8,"area":"diffusion"},{"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":"2507.05419","title":"Motion Generation: A Survey of Generative Approaches and Benchmarks","created":"2025-07-07","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":"2502.14140","title":"ModSkill: Physical Character Skill Modularization","created":"2025-02-19","cited_by_count":7,"area":"offlinerl"},{"id":"2503.21775","title":"StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion","created":"2025-03-27","cited_by_count":7,"area":"diffusion"},{"id":"2512.22808","title":"EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation","created":"2025-12-28","cited_by_count":7,"area":null},{"id":"2607.08741","title":"ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation","created":"2026-07-09","cited_by_count":7,"area":null},{"id":"2503.07597","title":"HumanMM: Global Human Motion Recovery from Multi-shot Videos","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2505.11013","title":"Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusion","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2511.07409","title":"DIMO: Diverse 3D Motion Generation for Arbitrary Objects","created":"2025-11-10","cited_by_count":6,"area":null},{"id":"2602.22742","title":"ProjFlow: Projection Sampling with Flow Matching for Zero-Shot Exact Spatial Motion Control","created":"2026-02-26","cited_by_count":5,"area":"diffusion"},{"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":"2603.15975","title":"UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors","created":"2026-03-16","cited_by_count":5,"area":null},{"id":"2504.00234","title":"CBIL: Collective Behavior Imitation Learning for Fish from Real Videos","created":"2025-03-31","cited_by_count":4,"area":"offlinerl"},{"id":"2508.08179","title":"PP-Motion: Physical-Perceptual Fidelity Evaluation for Human Motion Generation","created":"2025-08-11","cited_by_count":4,"area":null},{"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":"2412.08685","title":"ChatDyn: Language-Driven Multi-Actor Dynamics Generation in Street Scenes","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2502.11563","title":"Leader and Follower: Interactive Motion Generation under Trajectory Constraints","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2507.06590","title":"MOST: Motion Diffusion Model for Rare Text via Temporal Clip Banzhaf Interaction","created":"2025-07-09","cited_by_count":3,"area":"diffusion"},{"id":"2508.08991","title":"Spatial-Temporal Multi-Scale Quantization for Flexible Motion Generation","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2412.09901","title":"MulSMo: Multimodal Stylized Motion Generation by Bidirectional Control Flow","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2503.07323","title":"Navigating Motion Agents in Dynamic and Cluttered Environments through LLM Reasoning","created":"2025-03-10","cited_by_count":2,"area":"lr"},{"id":"2508.12176","title":"Scalable RF Simulation in Generative 4D Worlds","created":"2025-08-16","cited_by_count":2,"area":null},{"id":"2512.13840","title":"MoLingo: Motion-Language Alignment for Text-to-Human Motion Generation","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2604.08509","title":"Visually-grounded Humanoid Agents","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2605.28272","title":"EchoAvatar: Real-time Generative Avatar Animation from Audio Streams","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2409.14692","title":"Dynamic Realms: 4D Content Analysis, Recovery and Generation with Geometric, Topological and Physical Priors","created":"2024-09-23","cited_by_count":1,"area":null},{"id":"2507.20117","title":"RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2512.02453","title":"ClusterStyle: Modeling Intra-Style Diversity with Prototypical Clustering for Stylized Motion Generation","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2601.14258","title":"SOSControl: Enhancing Human Motion Generation through Saliency-Aware Symbolic Orientation and Timing Control","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2603.02190","title":"Sketch2Colab: Sketch-Conditioned Multi-Human Animation via Controllable Flow Distillation","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.11605","title":"LaMoGen: Language to Motion Generation Through LLM-Guided Symbolic Inference","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2605.29488","title":"AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.05624","title":"KV-Control: Parameter-Efficient K/V Injection for Trajectory-Controlled Text-to-Motion","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2609.05415","title":"UniMate: One Unified Model to Animate Diverse Skeletons","created":"2026-09-04","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":"2509.24469","title":"LaMoGen: Laban Movement-Guided Diffusion for Text-to-Motion Generation","created":"2025-09-29","cited_by_count":0,"area":"diffusion"},{"id":"2603.19795","title":"Controllable Text-to-Motion Generation via Modular Body-Part Phase Control","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.27040","title":"Unified Number-Free Text-to-Motion Generation Via Flow Matching","created":"2026-03-27","cited_by_count":0,"area":"diffusion"},{"id":"2604.02973","title":"Exploring Motion-Language Alignment for Text-driven Motion Generation","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.10199","title":"FatigueFusion: Latent Space Fusion for Fatigue-Driven Motion Synthesis","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2604.13581","title":"SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.08054","title":"Towards Highly-Constrained Human Motion Generation with Retrieval-Guided Diffusion Noise Optimization","created":"2026-05-08","cited_by_count":0,"area":"diffusion"},{"id":"2605.10376","title":"SleepWalk: A Three-Tier Benchmark for Stress-Testing Instruction-Guided Vision-Language Navigation","created":"2026-05-11","cited_by_count":0,"area":"mllm"},{"id":"2605.13041","title":"EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcing","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.14716","title":"SCAMP: Sparse-anchor Control is One Small Projection","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.14935","title":"Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.20209","title":"NaP-Control: Navigating Diffusion Prior for Versatile and Fast Character Control","created":"2026-04-15","cited_by_count":0,"area":"diffusion"},{"id":"2606.05162","title":"Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.23675","title":"IMAGIN-4D: Image-Guided Controllable Interaction Generation","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2608.15230","title":"PersonaDrive: Controllable Trajectory Prediction with Multi-Dimensional Driving Personas","created":"2026-08-15","cited_by_count":0,"area":"driving"},{"id":"2608.23258","title":"Progressively Learning Heterogeneous Skills in a Unified Latent Space","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.34799","title":"STRIDE: Automated Evaluation of Text-to-Trajectory Alignment across Diverse Contexts","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.16252","title":"MFlowHOI: Whole-Body Human-Object Interaction Generation via Part-Aware MeanFlow","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}