mlsanityData to 14 Oct 2026

ReactionMamba: Generating Short & Long Human Reaction Sequences

arXiv 2512.00208 ↗First posted 28 Nov 2025cs.CVcited by 0

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

Abstract (arXiv)

We present ReactionMamba, a novel framework for generating long 3D human reaction motions. Reaction-Mamba integrates a motion VAE for efficient motion encoding with Mamba-based state-space models to decode temporally consistent reactions. This design enables ReactionMamba to generate both short sequences of simple motions and long sequences of complex motions, such as dance and martial arts. We evaluate ReactionMamba on three datasets--NTU120-AS, Lindy Hop, and InterX--and demonstrate competitive performance in terms of realism, diversity, and long-sequence generation compared to previous methods, including InterFormer, ReMoS, and Ready-to-React, while achieving substantial improvements in inference speed.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 49 of its 71 references that are in the map. First posted on arXiv 28 Nov 2025.

Builds on

49 of 71 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Spatial-Temporal Graph Mamba for Music-Guided Dance Video Synthesis9 Jul
  2. 2025Dyadic Mamba: Long-term Dyadic Human Motion Synthesis14 May
  3. 2024Motion Mamba: Efficient and Long Sequence Motion Generation12 Mar
  4. 2023Selective Structured State-Spaces for Long-Form Video Understanding25 Mar

Other references · 45

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  6. 2017Neural Discrete Representation Learningcited by 4,712
  7. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  8. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  9. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  10. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,336
  11. 2022Human Motion Diffusion Modelcited by 1,080
  12. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 608
33 more
  1. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 575
  2. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 533
  3. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 492
  4. 2024U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentationcited by 419
  5. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  6. 2020MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformerscited by 355
  7. 2017On human motion prediction using recurrent neural networkscited by 338
  8. 2022EDGE: Editable Dance Generation From Musiccited by 287
  9. 2024VM-UNet: Vision Mamba UNet for Medical Image Segmentationcited by 287
  10. 2021Video Transformer Networkcited by 272
  11. 2024SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentationcited by 266
  12. 2021TransBTS: Multimodal Brain Tumor Segmentation Using Transformercited by 265
  13. 2022MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesiscited by 218
  14. 2023TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesiscited by 198
  15. 2024Swin-UMamba: Mamba-based UNet with ImageNet-based pretrainingcited by 179
  16. 2020Learning Joint Spatial-Temporal Transformations for Video Inpaintingcited by 163
  17. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  18. 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
  19. 2018Robots Learn Social Skills: End-to-End Learning of Co-Speech Gesture Generation for Humanoid Robotscited by 110
  20. 2022Long Movie Clip Classification with State-Space Video Modelscited by 106
  21. 2023Inter-X: Towards Versatile Human-Human Interaction Analysiscited by 98
  22. 2021Multi-Person Extreme Motion Predictioncited by 75
  23. 2022UDE: A Unified Driving Engine for Human Motion Generationcited by 67
  24. 2023ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactionscited by 62
  25. 2022AO2-DETR: Arbitrary-Oriented Object Detection Transformercited by 55
  26. 2024ReGenNet: Towards Human Action-Reaction Synthesiscited by 53
  27. 2022Efficient Movie Scene Detection using State-Space Transformerscited by 51
  28. 2022Interaction Transformer for Human Reaction Generationcited by 42
  29. 2025Ready-to-React: Online Reaction Policy for Two-Character Interaction Generationcited by 28
  30. 2025A Survey on Human Interaction Motion Generationcited by 25
  31. 2025MambaIC: State Space Models for High-Performance Learned Image Compressioncited by 20
  32. 2021AniFormer: Data-driven 3D Animation with Transformercited by 10
  33. 2021Geometry-Contrastive Transformer for Generalized 3D Pose Transfercited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Think-Then-React: Towards Unconstrained Human Action-to-Reaction Generation
  2. 2025ReactDance: Hierarchical Representation for High-Fidelity and Coherent Long-Form Reactive Dance Generation
  3. 2026Contact Matrix: Enhancing Dance Motion Synthesis with Precise Interaction Modeling
  4. 2026Not Like Transformers: Drop the Beat Representation for Dance Generation with Mamba-Based Diffusion Model
  5. 2024FTMoMamba: Motion Generation with Frequency and Text State Space Models
  6. 2025InterMamba: Efficient Human-Human Interaction Generation with Adaptive Spatio-Temporal Mamba
  7. 2026Listen to Rhythm, Choose Movements: Autoregressive Multimodal Dance Generation via Diffusion and Mamba with Decoupled Dance Dataset
  8. 2026Diffusion Path Alignment for Long-Range Motion Generation and Domain Transitions