Diffusion Models for Motion Generation

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, with none the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 38

All topics

From Digital Human Interactions to Physics-Based Humanoid Skills: Physics-Grounded Post-Training of Interaction Generators
Oct 7, 2026Kerui Chen, Jianrong Zhang, Kai Lv +1Physics-Informed Generative Modeling Diffusion Models for Motion Generation
College of Artificial Intelligence, Zhejiang University. · School of Computer Science and Technology, Beijing Jiaotong University.
SuperMotion: Source-Preserving Denoising for Text-Driven Human Motion Editing
Oct 1, 2026Fa-Ting Hong, Peter WonkaHuman Motion Generation Diffusion Models for Motion Generation
King Abdullah University of Science and Technology
World2Motion: Turning Video World Models into 3D Human Motion Generators
Sep 29, 2026Fangyuan Tu, Xiangyue Zhang, Yiyi Cai +8Human Motion Generation Diffusion Models for Motion Generation
Japan Advanced Institute of Science and Technology · The University of Tokyo · Institute of Science Tokyo +1
BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusion
Sep 28, 2026Wanjiang Weng, Yongliang Wu, Xiaofeng Tan +3Masked Diffusion Models Text-to-Motion Generation
Department of Computer Science and Engineering, Southeast University, Nanjing, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China · National University of Singapore +1
Triangular Resampling for Long-Horizon Motion Generation
Sep 28, 2026Kunhang Li, Yiyi Cai, Xiangyue Zhang +5Motion Diffusion Models Human Motion Generation
The University of Tokyo · Alaya Lab · Japan Advanced Institute of Science and Technology
MotionSpaceFlow: Representation-Aware Flow Matching in Direct Motion Space
Sep 28, 2026Qing Yu, Kent FujiwaraFlow Matching Text-to-Motion Generation
LY Corporation, Tokyo, Japan
FloodDiffusion 2: Efficient and Path Controllable Streaming Motion Generation
Sep 27, 2026Yiyi Cai, Yuhan Wu, Kunhang Li +6Motion Diffusion Models Human Motion Generation
Alaya Lab · The University of Tokyo · Japan Advanced Institute of Science and Technology +1
VISTA: Video-Injected Stylized Text-to-Animation
Sep 20, 2026Monseej Purkayastha, Anindita Ghosh, Philipp SlusallekText-to-Motion Generation Human Motion Generation
Saarland Informatics Campus & German Research Centre for Artificial Intelligence (DFKI), Saarbrücken, Germany · Max Planck Institute for Informatics (MPII), Saarbrücken, Germany
Flexible Motion Generation from Language and Style References
Sep 7, 2026Kai Weixian Lan, Bodie Criswell, Briana Fedkiw +3Text-to-Motion Generation Motion Diffusion Models
University of California, Davis, USA · University of Utah, USA · Epic Games, USA +1
EquiFusion: Kinematics-Agnostic Human Motion Prediction via Equivariant Latent Diffusion
Jul 13, 2026Cecilia Curreli, Florian Hofherr, Dominik Muhle +3Equivariant Neural Networks Human Motion Prediction
Technical University of Munich, Munich, Germany · Munich Center for Machine Learning, Munich, Germany
Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation
Jul 7, 2026Sakuya Ota, Qing Yu, Kent Fujiwara +2Diffusion Model Alignment Text-to-Motion Generation
Institute of Science Tokyo, Tokyo, Japan · LY Corporation, Tokyo, Japan · National Institute of Informatics (NII), Tokyo, Japan
MobileWan: Closing the Quality Gap for Mobile Video Diffusion
Jul 7, 2026Mohsen Ghafoorian, Denis Korzhenkov, Adil Karjauv +9Video Diffusion Models Video Generation
Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc.
Track the Noise, Move the World:3D-Grounded Motion-Consistent Noise for Controllable Video Generation
Jul 2, 2026Long Vu, Tan Ngo, Animesh Karnewar +5Camera-Controlled Video Generation Video Diffusion Models
Qualcomm AI Research · Trinity College Dublin, Ireland
Training-free Controllable Human Motion Generation under Heterogeneous Constraints
Jul 2, 2026Xiaofei Hui, Bo Yan, Haoxuan Qu +2Constrained Generative Modeling Human Motion Generation
Lancaster University, United Kingdom · Shenzhen International Graduate School, Tsinghua University, China
SICAGE: Speaker-Independent Culture-Aware Gesture Generation using TED4C-L Dataset
Jun 29, 2026Ariel Gjaci, Antonio Sgorbissa, Vittorio MurinoCo-Speech Gesture Generation Diffusion Models for Motion Generation
Italian Institute of Technology, Genoa, Italy · University of Genoa, Genoa, Italy
SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models
Jun 26, 2026Ruoyu Wang, Jialun Liu, Huayang Huang +5Physical Consistency in Video Generation Video Diffusion Models
School of Computer Science, Wuhan University · Institute of Artificial Intelligence, China Telecom (TeleAI) · School of Artificial Intelligence, Wuhan University
IMAGIN-4D: Image-Guided Controllable Interaction Generation
Jun 22, 2026Sai Kumar Dwivedi, Federica Bogo, Buğra Tekin +6HOI Generation Human Motion Generation
Meta, Switzerland · Max Planck Institute for Intelligent Systems, Tübingen, Germany · University of Amsterdam, Netherlands +1
Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motion
Jun 19, 2026Dongseok Shim, Julian Tanke, Kengo Uchida +5Unified Multimodal Models Text-to-Motion Generation
Sony Group Corporation · Sony AI
Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them
Jun 4, 2026Woojung Han, Seil Kang, Youngjun Jun +3Physical Consistency in Video Generation Image-to-Video Generation
1Yonsei University, South Korea · 2NVIDIA, Taiwan.
Bionic Human-Motion Style Transfer for Physically Executable Whole-Body Control of Humanoid Robots
Jun 2, 2026Tianchen Huang, Mingkuan Zhao, Yang Gao +8Humanoid Robot Control Human Motion Generation
Institute of Humanoid Robots, Department of Precision Machinery and Precision Instrumentation, University of Science and Technology of China, Hefei, Anhui, 230026, China. · School of Computer Science and Technology, Faculty of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi, 710049, China. · School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, 730000, China.
Steady-Forcing: Balancing Spatial Persistence and Motion Continuity in Long-Horizon Nature Video Diffusion
Jun 2, 2026Matiur Rahman Minar, Seunghun Oh, GangHyeon Jeong +1Physical Consistency in Video Generation Long-Horizon Video Generation
Department of Computer Science and Engineering Sogang University Seoul, Korea · Department of Artifical Intelligence Sogang University Seoul, Korea
DC-Motion: Decoupling Structure and Details via Discrete-Continuous Tokens for Human Motion Generation
May 28, 2026Hequan Wang, Xuean Chen, Jiaxu Zhang +2Text-to-Motion Generation Human Motion Generation
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, China · Geophysical Exploration Brigade of Hubei Provincial Geological Bureau, Wuhan 430058, China · Information Systems Technology and Design Pillar, Singapore University of Technology and Design, 487372, Singapore
Φ-Noise: Training-Free Temporal Video Conditioning via Phase-Based Noise Manipulation
May 23, 2026Ofir Abramovich, Nadav Z. Cohen, Adi Rosenthal +1Video Diffusion Models Diffusion Models for Motion Generation
Canvas-Lab Department of Computer Science Reichman University
LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation
May 22, 2026Bo Jiang, Depu Meng, Yihan Hu +3Physical Consistency in Video Generation Diffusion Model Guidance
Applied Intuition · University of California, Berkeley
CoMoGen: COntrollable MOtion Dynamics and Interactions with Mask-Guided Video GENeration
May 21, 2026Adil Meric, Lin Geng Foo, Mert Kiray +3HOI Generation Image-to-Video Generation
Technical University of Munich · Max Planck Institute for Informatics, Saarland Informatics Campus · Munich Center for Machine Learning (MCML) +1
DrawMotion: Generating 3D Human Motions by Freehand Drawing
May 20, 2026Tao Wang, Lei Jin, Zhihua Wu +7Text-to-Motion Generation Human Motion Generation
Beijing University of Posts and Telecommunications · University of Science and Technology of China · 3NLP Lab, School of Computer Science and Engineering, Northeastern University, Shenyang, China +4
TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion
May 13, 2026Nurislam Tursynbek, Zhiqiang Lao, Heather Yu +2Video Diffusion Models Diffusion Transformer
UNC Chapel Hill1 · Futurewei Technologies Inc2 · UCSD3
Generative Motion In-betweening by Diffusion over Continuous Implicit Representations
May 12, 2026Shiyu Fan, Paul Henderson, Edmond S. L. HoImplicit Neural Representations Latent Diffusion Models
School of Computing Science, University of Glasgow, United Kingdom.
Towards Highly-Constrained Human Motion Generation with Retrieval-Guided Diffusion Noise Optimization
May 8, 2026Hanchao Liu, Fang-Lue Zhang, Shining Zhang +2Constrained Generative Modeling Retrieval-Augmented Generation
Tsinghua University · University of New South Wales
Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency
May 7, 2026Thong Nguyen, Khoi M. Le, Cong-Duy Nguyen +3Image-to-Video Generation Diffusion Models for Motion Generation
National University of Singapore, Singapore · Centre for AI Research, VinUniversity, Vietnam · Nanyang Technological University, Singapore

Oct 7, 2026, cs.CVJ/K move · Enter open · S save

From Digital Human Interactions to Physics-Based Humanoid Skills: Physics-Grounded Post-Training of Interaction Generators

Kerui Chen, Jianrong Zhang, Kai Lv, Hehe Fan

College of Artificial Intelligence, Zhejiang University. · School of Computer Science and Technology, Beijing Jiaotong University.

Physics-Informed Generative Modeling Diffusion Models for Motion Generation Humanoid Motion Tracking

Open paper AskPDF arXiv

Recent methods have made promising progress in generating interactions between two humanoids, largely relying on physics-based tracking policies to convert digital reference motions into executable trajectories. However, limited tracking capabilities restrict the range of reference motions that can be successfully executed, reducing data utilization. Moreover, even successful tracking does not guarantee physically plausible responses or faithful realization of the intended interactions. In this paper, we introduce DIGHT, a co-adaptive framework that couples a Digital human Interaction Generator with a Humanoid Tracking policy. Our DIGHT first executes multiple text-conditioned interaction candidates in simulation using a fixed tracker. It then constructs physics-grounded preferences from the resulting rollouts, covering both general executability and interaction fidelity. Rather than collapsing these signals into a single scalar reward for candidate ranking, we align the pretrained generator using physics-decoupled diffusion direct preference optimization (DPO), preserving criterion-specific supervision without differentiating through the simulator. To improve executability, preference pairs are derived from tracking error, friction, and floating. Additionally, to improve interaction fidelity, we propose to incorporate force feedback from simulator as a measure of contact fidelity and construct preferences over contact occurrence, location, duration, and force magnitude. The aligned generator then supplies reference motions for fine-tuning the tracker, improving compatibility between generation and physical execution. Extensive experiments demonstrate that our approach not only improves the physical plausibility of generated motions but also enables more reliable and faithful humanoid interactions in simulation.

Momentum

Related topics

Latest papers 38