mlsanityData to 7 Oct 2026

Video, motion and generative Mamba models

209 papers0 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: mamba, motion, temporal, video, modeling

Key facts. Video, motion and generative Mamba models: 209 papers on arXiv since 2023 (data through 7 Oct 2026). 37 of its 209 mapped papers (18%) cite “VideoMamba: State Space Model for Efficient Video Understanding” (2024, arXiv 2403.06977). 23 of its 209 mapped papers (11%) cite “Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces” (2024, arXiv 2402.00789). 3 new papers 18 Sep–7 Oct.

What’s new

18 Sep – 7 Oct 2026

3 new since 18 Sep

  1. PhysMamba: Selective State Space Models as Learned Articulated Body Simulators
  2. Remember What You Did: Action-History Memory with Dual-Expert Denoising for Long-Horizon Vision-Language-Action Policies
  3. Groupwise Selective State-Space Filtering for Accurate and Streaming Action Boundary Detection

Foundations

Most cited by papers here

  1. VideoMamba: State Space Model for Efficient Video Understanding2024cited by 37 here
  2. Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces2024cited by 23 here
  3. Motion Mamba: Efficient and Long Sequence Motion Generation2024cited by 19 here
  4. Graph Mamba: Towards Learning on Graphs with State Space Models2024cited by 15 here
  5. Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding2024cited by 13 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 99 here
  2. 2022Diagonal State Spaces are as Effective as Structured State Spacescited by 27 here
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 151 here
  4. 2024U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentationcited by 16 here
  5. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 63 here
  6. 2024SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentationcited by 12 here
  7. 2024Swin-UMamba: Mamba-based UNet with ImageNet-based pretrainingcited by 12 here
  8. 2024Graph Mamba: Towards Learning on Graphs with State Space Modelscited by 15 here
  9. 2024ZigMa: A DiT-style Zigzag Mamba Diffusion Modelcited by 12 here
  10. 2024A Survey of Mambacited by 9 here
14 more it builds on, not in this chain
  1. 2022Simplified State Space Layers for Sequence Modelingcited by 32 here
  2. 2024Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spacescited by 23 here
  3. 2024Mamba-ND: Selective State Space Modeling for Multi-Dimensional Datacited by 8 here
  4. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 14 here
  5. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 12 here
  6. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 37 here
  7. 2024Motion Mamba: Efficient and Long Sequence Motion Generationcited by 19 here
  8. 2024Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understandingcited by 13 here
  9. 2024STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Modelcited by 9 here
  10. 2024Jamba: A Hybrid Transformer-Mamba Language Modelcited by 19 here
  11. 2024MambaOut: Do We Really Need Mamba for Vision?cited by 9 here
  12. 2024DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesiscited by 9 here
  13. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 38 here
  14. 2024MambaVision: A Hybrid Mamba-Transformer Vision Backbonecited by 12 here

The 24 most cited of 214.

Browse

30 of 209, ranked 6–35

  1. 6ZigMa: A DiT-style Zigzag Mamba Diffusion Model202412
  2. 7STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Model20249
  3. 8DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis20249
  4. 9VideoMamba: Spatio-Temporal Selective State Space Model20247
  5. 10Matten: Video Generation with Mamba-Attention20246
  6. 11Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State Spaces20245
  7. 12Scaling Diffusion Mamba with Bidirectional SSMs for Efficient Image and Video Generation20245
  8. 13SpoT-Mamba: Learning Long-Range Dependency on Spatio-Temporal Graphs with Selective State Spaces20245
  9. 14Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba20245
  10. 15Selective Structured State-Spaces for Long-Form Video Understanding20235
All 30
  1. 16Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion20244
  2. 17RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation20244
  3. 18Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network20244
  4. 19Trajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSM20253
  5. 20VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecasting20243
  6. 21Dimba: Transformer-Mamba Diffusion Models20243
  7. 22Snakes and Ladders: Two Steps Up for VideoMamba20243
  8. 23InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion Generation20243
  9. 24Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models20243
  10. 25DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generation20243
  11. 26Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space20252
  12. 27Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers20252
  13. 28U-Shape Mamba: State Space Model for faster diffusion20252
  14. 29MTIL: Encoding Full History with Mamba for Temporal Imitation Learning20252
  15. 30MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models20242
  16. 31HARMamba: Efficient and Lightweight Wearable Sensor Human Activity Recognition Based on Bidirectional Mamba20242
  17. 32Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos20242
  18. 33ST-MambaSync: The Complement of Mamba and Transformers for Spatial-Temporal in Traffic Flow Prediction20242
  19. 34Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL20242
  20. 35ST-Mamba: Spatial-Temporal Mamba for Traffic Flow Estimation Recovery using Limited Data20242