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

• URL: http://arxiv.org/abs/2604.03799v1
• Date: Sat, 04 Apr 2026 17:07:37 GMT
• Title: Next-Scale Autoregressive Models for Text-to-Motion Generation
• Abstract summary: MoScale is a next-scale AR framework that generates motion hierarchically from coarse to fine temporal resolutions.<n>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.
• Score: 35.54703580430989
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation [21.04046292025699]
  ScaleMoGen is a scale-wise autoregressive framework for text-driven human motion generation.<n>We quantize 3D motions into compositional discrete tokens across multiple skeletal-emporal scales.<n>Our skeletal-temporal multi-scale representation naturally facilitates training-free, text-guided motion editing.
  arXiv  Detail & Related papers  (2026-05-12T07:58:58Z)
• LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling [74.94985663101906]
  We present LeapTS, a novel framework that reformulates time series forecasting as a dynamic scheduling process over the prediction horizon.<n>We show that LeapTS improves overall forecasting performance by at least 7.4% while achieving a 2.6$times$ to 5.3$times$ inference speedup over representative Transformer-based models.
  arXiv  Detail & Related papers  (2026-05-11T09:54:02Z)
• StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models [98.72926158261937]
  We propose a training-free token pruning framework for Visual AutoRegressive models.<n>We employ a lightweight high-pass filter to capture local texture details, while leveraging Principal Component Analysis (PCA) to preserve global structural information.<n>To maintain valid next-scale prediction under sparse tokens, we introduce a nearest neighbor feature propagation strategy.
  arXiv  Detail & Related papers  (2026-03-02T11:35:05Z)
• LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens [19.167250154665812]
  We propose LLaMo, a framework that extends pretrained large language models through a modality-specific Mixture-of-Transformers architecture.<n>We encode human motion into a causal continuous latent space and maintain the next-token prediction paradigm in the decoder-only backbone.<n>Our experiments demonstrate that LLaMo achieves high-fidelity text-to-motion generation and motion-to-text captioning in general settings.
  arXiv  Detail & Related papers  (2026-02-12T20:02:21Z)
• Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations [55.047454145941366]
  Streaming Merging is an innovative model updating paradigm that conceptualizes merging as an iterative optimization process.<n> ARM is a strategy designed to approximate gradient descent dynamics.<n> ARM requires only early SFT checkpoints and, through iterative merging, surpasses the fully converged SFT model.
  arXiv  Detail & Related papers  (2026-02-03T08:15:57Z)
• SAMPO:Scale-wise Autoregression with Motion PrOmpt for generative world models [42.814012901180774]
  textbfSAMPO is a hybrid framework that combines visual autoregressive modeling for intra-frame generation with causal modeling for next-frame generation.<n>We show that SAMPO achieves competitive performance in action-conditioned video prediction and model-based control.<n>We also evaluate SAMPO's zero-shot generalization and scaling behavior, demonstrating its ability to generalize to unseen tasks.
  arXiv  Detail & Related papers  (2025-09-19T02:41:37Z)
• Towards Efficient General Feature Prediction in Masked Skeleton Modeling [59.46799426434277]
  We propose a novel General Feature Prediction framework (GFP) for efficient mask skeleton modeling.<n>Our key innovation is replacing conventional low-level reconstruction with high-level feature prediction that spans from local motion patterns to global semantic representations.
  arXiv  Detail & Related papers  (2025-09-03T18:05:02Z)
• Absolute Coordinates Make Motion Generation Easy [8.153961351540834]
  State-of-the-art text-to-motion generation models rely on the kinematic-aware, local-relative motion representation popularized by HumanML3D.<n>We propose a radically simplified and long-abandoned alternative for text-to-motion generation: absolute joint coordinates in global space.
  arXiv  Detail & Related papers  (2025-05-26T00:36:00Z)
• ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer [58.49950218437718]
  We present ReCoM, an efficient framework for generating high-fidelity and generalizable human body motions synchronized with speech.<n>The core innovation lies in the Recurrent Embedded Transformer (RET), which integrates Dynamic Embedding Regularization (DER) into a Vision Transformer (ViT) core architecture.<n>To enhance model robustness, we incorporate the proposed DER strategy, which equips the model with dual capabilities of noise resistance and cross-domain generalization.
  arXiv  Detail & Related papers  (2025-03-27T16:39:40Z)
• Expressive and Generalizable Low-rank Adaptation for Large Models via Slow Cascaded Learning [55.5715496559514]
  LoRA Slow Cascade Learning (LoRASC) is an innovative technique designed to enhance LoRA's expressiveness and generalization capabilities. Our approach augments expressiveness through a cascaded learning strategy that enables a mixture-of-low-rank adaptation, thereby increasing the model's ability to capture complex patterns.
  arXiv  Detail & Related papers  (2024-07-01T17:28:59Z)
• Motion Flow Matching for Human Motion Synthesis and Editing [75.13665467944314]
  We propose emphMotion Flow Matching, a novel generative model for human motion generation featuring efficient sampling and effectiveness in motion editing applications. Our method reduces the sampling complexity from thousand steps in previous diffusion models to just ten steps, while achieving comparable performance in text-to-motion and action-to-motion generation benchmarks.
  arXiv  Detail & Related papers  (2023-12-14T12:57:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.