Overview

Human motion generation studies how to synthesize or edit body movement for animation, avatars, interaction, and humanoid robots. Common approaches use diffusion or flow-matching models, autoregressive and masked motion tokens, and structured representations of body parts or joint trajectories; retrieval, planning, and physics-based refinement can add control. Text-to-motion is often tested on HumanML3D and KIT-ML, while dance and speech-driven gestures use benchmarks such as AIST++ and BEAT. A central challenge is balancing semantic accuracy, natural and diverse motion, physical plausibility, and precise control—especially for long or real-time sequences, where evaluation metrics may not reflect human judgments or successful execution.

Latest papers

CardsList

309 papers20 papers in the last four weeks, down 47% on the four weeks before. 0.2% of all new papers.

  1. SemPhys: Semantic-Physical Co-Learning for Humanoid Motion Generation via Differentiable World Models

    Nov 18, 2026Zejian Kang, Yeqiang Wang, Zekai Chen +9Human Motion GenerationRobot Motion Generation

  2. Learning Martial Arts Motion Skills for Animating Opponents in VR Sparring Games

    Nov 18, 2026Jiqing Wen, Qixuan Shi, Robert LiKamWa +1Human Motion GenerationAgent Skill Learning

  3. From a Single RGB Image to Robot Execution: Metric Scene Alignment and Contact-Guided Retargeting

    Nov 11, 2026Zhenxuan Ding, Yu Huang, Xinmiao Wang +3Human Motion GenerationMotion Retargeting

  4. EgoHMP: Achieving Precise Human Motion Prediction in 3D Scenes via Egocentric Cues

    Nov 10, 2026Xin Zhao, Pengzhan Zhou, Ziyi Li +3Human Motion PredictionHuman Motion Generation

  5. FlashMotion: Ultra-Fast Long-Term 3D Motion Generation

    Nov 10, 2026Kaixing Yang, Xulong Tang, Ronghui Li +10Human Motion GenerationText-to-Motion Generation

  6. AHEADance: Anticipatory Humanoid Dance from Streaming Audio

    Nov 9, 2026Tianhu Peng, Yukun Wang, Lingfan Bao +2Robot Motion GenerationHuman Motion Generation

  7. Kimodo-Policy: Learning Kinematic Action Models for Humanoid Loco-Manipulation

    Nov 8, 2026Yunheng Wang, Jiaxi Zhang, Wei Lu +12Humanoid Loco-ManipulationWhole-Body Humanoid Control

  8. MV-Sign: Multi-View 3D Motion Integration and Enhanced Text-to-Motion Conditioning for Sign Language Production

    Nov 5, 2026Singyu Muk, Kaustubh Kundu, Kunyuan Xie +2Sign Language GenerationHuman Motion Generation

  9. FFMT: Frequency-Factorized Multi-Rate Tokenization for Music-to-Dance Generation

    Nov 5, 2026Qirong Guo, Ruijie Li, Zeyan Li +3Autoregressive Motion GenerationHuman Motion Generation

  10. Semantic Residual Vector Quantization for Sign Language Generation

    Nov 4, 2026Chang Liu, Ke Han, Niccolò Biondi +4Sign Language GenerationHuman Motion Generation

  11. Möbius: A Unified Motion-Language Model Bridging Understanding and Generation

    Nov 3, 2026Jiazhi Shu, Chengfeng Zhao, Jinyi Wang +7Human Motion GenerationText-to-Motion Generation

  12. Movens-Zero: Scaling Humanoid Motion Foundation Models with Large-Scale Human Videos

    Oct 30, 2026Wendong Bu, Tinghong Ye, Qizhou Wang +21Human Motion GenerationMultimodal Generation

  13. TalkFlow: Structured Latent Flow Matching for Speech Driven Holistic Motion Generation

    Oct 29, 2026Xinmu Wang, Fumi Honda, Xiang Gao +3Human Motion GenerationCo-Speech Gesture Generation

  14. StepControl: Long-Horizon Human Motion Generation from Foot-Contact Schedules

    Oct 28, 2026Hojun Jang, Jinseok Bae, Donggeun Lim +5Autoregressive Motion GenerationHuman Motion Generation

  15. TopX: Text-to-Motion for Unseen Skeletons from the Skeleton File Alone

    Oct 25, 2026Tengjiao Sun, Pengcheng Fang, Xiaoyu Zhan +3Text-to-Motion GenerationHuman Motion Generation

  16. ChoreoStudio: Planning What, When, and Who in Music-Driven Group Choreography

    Oct 23, 2026Jing Xu, Cunjian Chen, Qiuhong KeHuman Motion Generation

  17. PhysibleMDM: Enforcing Inference-Time Physical Feasibility Constraints on Motion Diffusion Models via Noise Optimization

    Oct 21, 2026Maximilian Stölzle, David Müller, Agon Serifi +3Motion Diffusion ModelsHuman Motion Generation

  18. SP-HLM: Sparse-Pose-Driven Motion Generation and Whole-Body Control for Humanoid Loco-Manipulation

    Oct 21, 2026Zhaohui Yang, Quanbao Lin, Chengqi Shi +9Whole-Body Humanoid ControlHumanoid Loco-Manipulation

  19. Learn to Modify: Self-evolving Multi-agent Refinement Framework for Conversational Text-to-Motion Generation

    Oct 20, 2026Jianan Li, Jiawei Zhao, Yangtao Zhou +6Text-to-Motion GenerationHuman Motion Generation

  20. BUMP: Body-driven Unified Multi-object Physics for HOI Synthesis

    Oct 19, 2026Wonjung Woo, Hyeonwoo Kim, Hanbyul JooHOI GenerationHuman Motion Generation

  21. MOMO: Human Motion from Moving Sounds

    Oct 17, 2026Deli Cai, Shuyang Xu, Zhiyang Dou +4Human Motion GenerationSpatial Audio

  22. ULIFLOW: Unified Latent Human-Object Interaction Flow

    Oct 16, 2026Wenqi Cai, Chunzhi Gu, Weichen Zhou +5HOI GenerationHuman Motion Generation

  23. SynerGest: Temporal-Spatial Synergistic Gesture Generation for Dyadic Conversations

    Oct 16, 2026Chengxiang Guo, Jian Wang, Lanmiao Liu +3Contrastive Flow MatchingCo-Speech Gesture Generation

  24. OmniPoser: Flexible Human Motion Recovery in the Wild with Masked Flow Matching

    Oct 14, 2026Minghao Liu, Tutian Tang3D Human Reconstruction3D Human Pose Estimation

  25. Walk Like This: Stylized Locomotion for Physics-Based Characters through Example-Driven Diffusion

    Oct 13, 2026Joshua Aurand, Agon Serifi, Sammy Christen +4Style-Conditioned Motion GenerationRobot Locomotion

  26. Learning Dynamic Grasping

    Oct 10, 2026Nga Kiu Kelly Ho, Yilin Liu, Hao Xu +1HOI GenerationHuman Motion Generation

  27. ELMA: Benchmarking Anaphoric Compositions for Long-Term Text-to-Motion Generation

    Oct 9, 2026Shun Kato, Dixin Yang, Kotaro Amaya +5Human Motion GenerationText-to-Motion Generation

  28. PartiGen: Part-Aware Representations for Language-Conditioned Humanoid Motion Generation

    Oct 9, 2026Chuxuan Huang, Zhanxiang Cao, Tianyue Zhan +14Text-to-Motion GenerationHuman Motion Generation