mlsanityData to 14 Oct 2026

InterMoE: Individual-Specific 3D Human Interaction Generation via Dynamic Temporal-Selective MoE

arXiv 2511.13488 ↗First posted 17 Nov 2025cs.CVcited by 1

On the map: Mixture-of-experts → MoE in reinforcement learning and robotics

Abstract (arXiv)

Generating high-quality human interactions holds significant value for applications like virtual reality and robotics. However, existing methods often fail to preserve unique individual characteristics or fully adhere to textual descriptions. To address these challenges, we introduce InterMoE, a novel framework built on a Dynamic Temporal-Selective Mixture of Experts. The core of InterMoE is a routing mechanism that synergistically uses both high-level text semantics and low-level motion context to dispatch temporal motion features to specialized experts. This allows experts to dynamically determine the selection capacity and focus on critical temporal features, thereby preserving specific individual characteristic identities while ensuring high semantic fidelity. Extensive experiments show that InterMoE achieves state-of-the-art performance in individual-specific high-fidelity 3D human interaction generation, reducing FID scores by 9% on the InterHuman dataset and 22% on InterX.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in MoE in reinforcement learning and robotics, one of 12 directions in Mixture-of-experts. Builds on 33 of its 40 references that are in the map. First posted on arXiv 17 Nov 2025.

Builds on

33 of 40 references.

References · 33

  1. 2017Neural Discrete Representation Learningcited by 4,712
  2. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  3. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,631
  4. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  5. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  6. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 780
  7. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 588
  8. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 575
  9. 2023MotionGPT: Human Motion as a Foreign Languagecited by 527
  10. 2023MoMask: Generative Masked Modeling of 3D Human Motionscited by 400
  11. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 359
  12. 2023Human Motion Diffusion as a Generative Priorcited by 357
21 more
  1. 2023InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactionscited by 206
  2. 2025MiniMax-01: Scaling Foundation Models with Lightning Attentioncited by 166
  3. 2023MotionGPT: Finetuned LLMs Are General-Purpose Motion Generatorscited by 145
  4. 2022ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Expertscited by 112
  5. 2023Inter-X: Towards Versatile Human-Human Interaction Analysiscited by 98
  6. 2025MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Spacecited by 86
  7. 2022PoseGPT: Quantization-based 3D Human Motion Generation and Forecastingcited by 78
  8. 2023TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integrationcited by 76
  9. 2023Priority-Centric Human Motion Generation in Discrete Latent Spacecited by 67
  10. 2024Scaling Diffusion Transformers to 16 Billion Parameterscited by 66
  11. 2024InterMask: 3D Human Interaction Generation via Collaborative Masked Modelingcited by 47
  12. 2023Digital Life Project: Autonomous 3D Characters with Social Intelligencecited by 43
  13. 2025SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editingcited by 39
  14. 2023DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusioncited by 37
  15. 2023Multi-Architecture Multi-Expert Diffusion Modelscited by 35
  16. 2024Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budgetcited by 30
  17. 2024EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routingcited by 30
  18. 2024in2IN: Leveraging individual Information to Generate Human INteractionscited by 29
  19. 2024TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generationcited by 27
  20. 2025DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformerscited by 24
  21. 2024Two-in-One: Unified Multi-Person Interactive Motion Generation by Latent Diffusion Transformercited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026InterEdit: Navigating Text-Guided 3D Dyadic Human Motion Editingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction
  2. 2026Hoi3DGen: Generating High-Quality Human-Object-Interactions in 3D
  3. 2026Multimodal Priors-Augmented Text-Driven 3D Human-Object Interaction Generation
  4. 2025InterPose: Learning to Generate Human-Object Interactions from Large-Scale Web Videos
  5. 2024HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects
  6. 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion
  7. 2023GenZI: Zero-Shot 3D Human-Scene Interaction Generation
  8. 2023Controllable Human-Object Interaction Synthesis