Next-Scale Autoregressive Models for Text-to-Motion Generation
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation
We present ScaleMoGen, a scale-wise autoregressive framework for text-driven human motion generation. Unlike conventional autoregressive approaches that rely on standard next-token prediction, ScaleMoGen frames motion ge…
NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discret…
Text-to-Image GenerationImage EditingMotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space
This paper addresses the challenge of text-conditioned streaming motion generation, which requires us to predict the next-step human pose based on variable-length historical motions and incoming texts. Existing methods s…
Motion GenerationFlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching
Autoregressive (AR) modeling has achieved remarkable success in natural language processing by enabling models to generate text with coherence and contextual understanding through next token prediction. Recently, in imag…
Image GenerationPredictionNextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation
We present NextFlow, a unified decoder-only autoregressive transformer trained on 6 trillion interleaved text-image discrete tokens. By leveraging a unified vision representation within a unified autoregressive architect…
Reinforcement LearningVideo GenerationImage Editing