mlsanityData to 7 Oct 2026

ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning

arXiv 2603.13500 ↗First posted 13 Mar 2026cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

We present ActionPlan, a unified motion diffusion framework that bridges real-time streaming with high-quality offline generation within a single model. The core idea is to introduce a per-frame action plan: the model predicts frame-level text latents that act as dense semantic anchors throughout denoising, and uses them to denoise the full motion sequence with combined semantic and motion cues. To support this structured workflow, we design latent-specific diffusion steps, allowing each motion latent to be denoised independently and sampled in flexible orders at inference. As a result, ActionPlan can run in a history-conditioned, future-aware mode for real-time streaming, while also supporting high-quality offline generation. The same mechanism further enables zero-shot motion editing and in-betweening without additional models. Experiments demonstrate that our real-time streaming is 5.25x faster while also achieving 18% motion quality improvement over the best previous method in terms of FID.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 71 of its 78 references that are in the map. First posted on arXiv 13 Mar 2026.

Builds on

71 of 78 references.

References · 71

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2022Classifier-Free Diffusion Guidancecited by 5,717
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  6. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  7. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  8. 2022Human Motion Diffusion Modelcited by 1,062
  9. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
  10. 2024Autoregressive Image Generation without Vector Quantizationcited by 644
  11. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 634
  12. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 577
38 more
  1. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 567
  2. 2023MotionGPT: Human Motion as a Foreign Languagecited by 521
  3. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 486
  4. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 406
  5. 2023MoMask: Generative Masked Modeling of 3D Human Motionscited by 388
  6. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 365
  7. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 357
  8. 2023Human Motion Diffusion as a Generative Priorcited by 354
  9. 2023ReMoDiffuse: Retrieval-Augmented Motion Diffusion Modelcited by 282
  10. 2021BABEL: Bodies, Action and Behavior with English Labelscited by 261
  11. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  12. 2023Guided Motion Diffusion for Controllable Human Motion Synthesiscited by 221
  13. 2022MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesiscited by 218
  14. 2022FLAME: Free-form Language-based Motion Synthesis & Editingcited by 217
  15. 2023InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactionscited by 205
  16. 2023TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesiscited by 194
  17. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 164
  18. 2024Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokenscited by 147
  19. 2023MMM: Generative Masked Motion Modelcited by 129
  20. 2023AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanismcited by 116
  21. 2024Motion Mamba: Efficient and Long Sequence Motion Generationcited by 111
  22. 2023FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editingcited by 105
  23. 2023HumanTOMATO: Text-aligned Whole-body Motion Generationcited by 103
  24. 2024CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character controlcited by 103
  25. 2023TLControl: Trajectory and Language Control for Human Motion Synthesiscited by 93
  26. 2023EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generationcited by 88
  27. 2024Multi-Track Timeline Control for Text-Driven 3D Human Motion Generationcited by 88
  28. 2025MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Spacecited by 82
  29. 2024DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Controlcited by 80
  30. 2024Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregressioncited by 78
  31. 2024Seamless Human Motion Composition with Blended Positional Encodingscited by 77
  32. 2025Go to Zero: Towards Zero-shot Motion Generation with Million-scale Datacited by 67
  33. 2024Large Motion Model for Unified Multi-Modal Motion Generationcited by 65
  34. 2023AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyondcited by 63
  35. 2023Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generationcited by 56
  36. 2024Taming Diffusion Probabilistic Models for Character Controlcited by 56
  37. 2024BAMM: Bidirectional Autoregressive Motion Modelcited by 54
  38. 2023Interactive Character Control with Auto-Regressive Motion Diffusion Modelscited by 52

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026SentiAvatar: Towards Expressive and Interactive Digital Humanscited by 3
  2. 2026UMo: Unified Sparse Motion Modeling for Real-Time Co-Speech Avatarscited by 1
  3. 2026NextMotionQA: Benchmarking and Judging Human Motion Understanding with Vision-Language Modelscited by 0
  4. 2026PAMI: Part Anchored Motion for Text to Human-Object Interaction Generationcited by 0