mlsanityData to 14 Oct 2026

Next-Scale Autoregressive Models for Text-to-Motion Generation

arXiv 2604.03799 ↗First posted 4 Apr 2026cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Autoregressive (AR) models offer stable and efficient training, but standard next-token prediction is not well aligned with the temporal structure required for text-conditioned motion generation. We introduce MoScale, a next-scale AR framework that generates motion hierarchically from coarse to fine temporal resolutions. By providing global semantics at the coarsest scale and refining them progressively, MoScale establishes a causal hierarchy better suited for long-range motion structure. To improve robustness under limited text-motion data, we further incorporate cross-scale hierarchical refinement for improving per-scale initial predictions and in-scale temporal refinement for selective bidirectional re-prediction. MoScale achieves SOTA text-to-motion performance with high training efficiency, scales effectively with model size, and generalizes zero-shot to diverse motion generation and editing tasks.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 54 of its 62 references that are in the map. First posted on arXiv 4 Apr 2026.

Builds on

54 of 62 references.

References · 54

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  6. 2017Neural Discrete Representation Learningcited by 4,712
  7. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  8. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  9. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  10. 2022Human Motion Diffusion Modelcited by 1,080
  11. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,023
  12. 2025OpenAI GPT-5 System Cardcited by 989
38 more
  1. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 780
  2. 2019Compressive Transformers for Long-Range Sequence Modellingcited by 726
  3. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 588
  4. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 575
  5. 2023MotionGPT: Human Motion as a Foreign Languagecited by 527
  6. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
  7. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 492
  8. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 441
  9. 2023MoMask: Generative Masked Modeling of 3D Human Motionscited by 400
  10. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 359
  11. 2016The KIT Motion-Language Datasetcited by 338
  12. 2017On human motion prediction using recurrent neural networkscited by 338
  13. 2023ReMoDiffuse: Retrieval-Augmented Motion Diffusion Modelcited by 287
  14. 2022FLAME: Free-form Language-based Motion Synthesis & Editingcited by 217
  15. 2023MMM: Generative Masked Motion Modelcited by 131
  16. 2023AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanismcited by 117
  17. 2018QuaterNet: A Quaternion-based Recurrent Model for Human Motioncited by 109
  18. 2024Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregressioncited by 85
  19. 2024DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Controlcited by 84
  20. 2023Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Modelcited by 79
  21. 2025Diffusion Beats Autoregressive in Data-Constrained Settingscited by 63
  22. 2024MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understandingcited by 59
  23. 2024ParCo: Part-Coordinating Text-to-Motion Synthesiscited by 55
  24. 2024BAMM: Bidirectional Autoregressive Motion Modelcited by 55
  25. 2024ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Modelcited by 53
  26. 2025Diffusion Language Models are Super Data Learnerscited by 48
  27. 2025SnapMoGen: Human Motion Generation from Expressive Textscited by 47
  28. 2024The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motioncited by 46
  29. 2023Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphscited by 45
  30. 2025PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generationcited by 41
  31. 2023DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusioncited by 37
  32. 2021AdaFusion: Visual-LiDAR Fusion with Adaptive Weights for Place Recognitioncited by 36
  33. 2024Towards Open Domain Text-Driven Synthesis of Multi-Person Motionscited by 29
  34. 2024STAR: Scale-wise Text-conditioned AutoRegressive image generationcited by 28
  35. 2024UniMuMo: Unified Text, Music and Motion Generationcited by 19
  36. 2024Acoustic Volume Rendering for Neural Impulse Response Fieldscited by 14
  37. 2025PersonaBooth: Personalized Text-to-Motion Generationcited by 14
  38. 2025MOSPA: Human Motion Generation Driven by Spatial Audiocited by 12

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generationcited by 4
  2. 2026SeMoCo: A Semantic-First Motion Codec for Motion Language Modelingcited by 1
  3. 2026RoboSTAR: Next-Scale Autoregressive Sign Language Translation for Humanoid Robotscited by 0
  4. 2026BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusioncited by 0