mlsanityData to 7 Oct 2026

Motion Mamba: Efficient and Long Sequence Motion Generation

arXiv 2403.07487 ↗First posted 12 Mar 2024cs.CVcited by 111

On the map: State-space sequence models (S4, Mamba) → Video, motion and generative Mamba models

Abstract (arXiv)

Human motion generation stands as a significant pursuit in generative computer vision, while achieving long-sequence and efficient motion generation remains challenging. Recent advancements in state space models (SSMs), notably Mamba, have showcased considerable promise in long sequence modeling with an efficient hardware-aware design, which appears to be a promising direction to build motion generation model upon it. Nevertheless, adapting SSMs to motion generation faces hurdles since the lack of a specialized design architecture to model motion sequence. To address these challenges, we propose Motion Mamba, a simple and efficient approach that presents the pioneering motion generation model utilized SSMs. Specifically, we design a Hierarchical Temporal Mamba (HTM) block to process temporal data by ensemble varying numbers of isolated SSM modules across a symmetric U-Net architecture aimed at preserving motion consistency between frames. We also design a Bidirectional Spatial Mamba (BSM) block to bidirectionally process latent poses, to enhance accurate motion generation within a temporal frame. Our proposed method achieves up to 50% FID improvement and up to 4 times faster on the HumanML3D and KIT-ML datasets compared to the previous best diffusion-based method, which demonstrates strong capabilities of high-quality long sequence motion modeling and real-time human motion generation. See project website https://steve-zeyu-zhang.github.io/MotionMamba/

Key facts. Cited by 111 papers in the map (data through 7 Oct 2026). Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 47 of its 61 references that are in the map. First posted on arXiv 12 Mar 2024.

Builds on

47 of 61 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  9. 2017Neural Discrete Representation Learningcited by 4,650
  10. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  11. 2022A ConvNet for the 2020scited by 3,545
  12. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
35 more
  1. 2017Improved Training of Wasserstein GANscited by 2,223
  2. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  3. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  4. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  5. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  6. 2022Human Motion Diffusion Modelcited by 1,062
  7. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,051
  8. 2024VMamba: Visual State Space Modelcited by 955
  9. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
  10. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 607
  11. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 567
  12. 2023MotionGPT: Human Motion as a Foreign Languagecited by 521
  13. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  14. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 486
  15. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 438
  16. 2022On the Parameterization and Initialization of Diagonal State Space Modelscited by 418
  17. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 406
  18. 2022Diagonal State Spaces are as Effective as Structured State Spacescited by 350
  19. 2016The KIT Motion-Language Datasetcited by 334
  20. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  21. 2021Robust Motion In-betweeningcited by 223
  22. 2021Synthesis of Compositional Animations from Textual Descriptionscited by 177
  23. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  24. 2023AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanismcited by 116
  25. 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
  26. 2021Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agentscited by 106
  27. 2022What Makes Convolutional Models Great on Long Sequence Modeling?cited by 86
  28. 2024Mamba-ND: Selective State Space Modeling for Multi-Dimensional Datacited by 84
  29. 2023TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integrationcited by 76
  30. 2023Diffusion Models Without Attentioncited by 75
  31. 2017Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networkscited by 61
  32. 2022Pretraining Without Attentioncited by 51
  33. 2018Human Motion Modeling using DVGANscited by 45
  34. 2023Convolutional State Space Models for Long-Range Spatiotemporal Modelingcited by 19
  35. 20232-D SSM: A General Spatial Layer for Visual Transformerscited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 43; 2025: 44; 2026: 24.

111 papers.

Sort:

By area:

  1. 2024DRAMA: An Efficient End-to-end Motion Planner for Autonomous Driving with Mambacited by 87
  2. 2024ZigMa: A DiT-style Zigzag Mamba Diffusion Modelcited by 84
  3. 2024Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregressioncited by 78
  4. 2024Vision Mamba: A Comprehensive Survey and Taxonomycited by 53
  5. 2024A Survey on Visual Mambacited by 50
  6. 2024Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separationcited by 45
  7. 2024Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mambacited by 45
  8. 2024Visual Mamba: A Survey and New Outlookscited by 41
  9. 2024MoGenTS: Motion Generation based on Spatial-Temporal Joint Modelingcited by 40
  10. 2025Motion Anything: Any to Motion Generationcited by 40
  11. 2024A Survey of Mambacited by 39
  12. 2025Muon Outperforms Adam in Tail-End Associative Memory Learningcited by 38
38 more
  1. 2024EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Spacecited by 30
  2. 2024Unimotion: Unifying 3D Human Motion Synthesis and Understandingcited by 29
  3. 2025Absolute Coordinates Make Motion Generation Easycited by 27
  4. 2024InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion Generationcited by 23
  5. 2024Light-T2M: A Lightweight and Fast Model for Text-to-motion Generationcited by 21
  6. 2024Motion Avatar: Generate Human and Animal Avatars with Arbitrary Motioncited by 19
  7. 2024Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sportscited by 19
  8. 2024Mamba in Vision: A Comprehensive Survey of Techniques and Applicationscited by 18
  9. 2024QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Modelcited by 18
  10. 2024RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion Mambacited by 17
  11. 2025Trajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSMcited by 17
  12. 2024Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motioncited by 16
  13. 2024A Comprehensive Survey of Mamba Architectures for Medical Image Analysis: Classification, Segmentation, Restoration and Beyondcited by 16
  14. 2024KMM: Key Frame Mask Mamba for Extended Motion Generationcited by 16
  15. 2024SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimizationcited by 14
  16. 2024ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attentioncited by 13
  17. 2024InfiniDreamer: Arbitrarily Long Human Motion Generation via Segment Score Distillationcited by 12
  18. 2025Auto-Regressive Diffusion for Generating 3D Human-Object Interactionscited by 12
  19. 2024HARMamba: Efficient and Lightweight Wearable Sensor Human Activity Recognition Based on Bidirectional Mambacited by 11
  20. 2024MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Modelscited by 11
  21. 2024MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mambacited by 11
  22. 2025Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motionscited by 11
  23. 2025CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objectscited by 10
  24. 2024MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Trainingcited by 9
  25. 2024Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generationscited by 9
  26. 2025Align Your Rhythm: Generating Highly Aligned Dance Poses with Gating-Enhanced Rhythm-Aware Feature Representationcited by 8
  27. 2025Motion Generation: A Survey of Generative Approaches and Benchmarkscited by 8
  28. 2024Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?cited by 7
  29. 2024Deformable Mamba for Wide Field of View Segmentationcited by 7
  30. 2026FrankenMotion: Part-level Human Motion Generation and Compositioncited by 7
  31. 2024MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimizationcited by 6
  32. 2024BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesiscited by 6
  33. 2026SafeMo: Linguistically Grounded Unlearning for Trustworthy Text-to-Motion Generationcited by 6
  34. 2024Medical Artificial Intelligence for Early Detection of Lung Cancer: A Surveycited by 5
  35. 2024Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-trainingcited by 5
  36. 2025GenM3: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generationcited by 5
  37. 2026Temporal Consistency-Aware Text-to-Motion Generationcited by 5
  38. 2025FDG-Diff: Frequency-Domain-Guided Diffusion Framework for Compressed Hazy Image Restorationcited by 4

50 most cited of 111 All 111 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Learning Human Motion with Temporally Conditional Mamba
  2. 2024Scalable Autoregressive Image Generation with Mamba
  3. 2024Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding
  4. 2025MSF-Mamba: Motion-aware State Fusion Mamba for Efficient Micro-Gesture Recognition
  5. 2024PoseMamba: Monocular 3D Human Pose Estimation with Bidirectional Global-Local Spatio-Temporal State Space Model
  6. 2026Mamba-Enhanced Implicit Motion Learning for Audio-Driven Portrait Animation
  7. 2025Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing
  8. 2024MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models