Causal Motion Diffusion Models for Autoregressive Motion Generation

• URL: http://arxiv.org/abs/2602.22594v1
• Date: Thu, 26 Feb 2026 03:58:25 GMT
• Title: Causal Motion Diffusion Models for Autoregressive Motion Generation
• Authors: Qing Yu, Akihisa Watanabe, Kent Fujiwara,
• Abstract summary: Causal Motion Diffusion Models (CMDM) is a unified framework for autoregressive motion generation.<n> CMDM builds upon a Motion-Language-Aligned Causal VAE (MAC-VAE), which encodes motion sequences into temporally causal latent representations.<n>Experiments on HumanML3D and SnapMoGen demonstrate CMDM outperforms existing diffusion and autoregressive models in both semantic fidelity and temporal smoothness.
• Score: 19.61051102039212
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in motion diffusion models have substantially improved the realism of human motion synthesis. However, existing approaches either rely on full-sequence diffusion models with bidirectional generation, which limits temporal causality and real-time applicability, or autoregressive models that suffer from instability and cumulative errors. In this work, we present Causal Motion Diffusion Models (CMDM), a unified framework for autoregressive motion generation based on a causal diffusion transformer that operates in a semantically aligned latent space. CMDM builds upon a Motion-Language-Aligned Causal VAE (MAC-VAE), which encodes motion sequences into temporally causal latent representations. On top of this latent representation, an autoregressive diffusion transformer is trained using causal diffusion forcing to perform temporally ordered denoising across motion frames. To achieve fast inference, we introduce a frame-wise sampling schedule with causal uncertainty, where each subsequent frame is predicted from partially denoised previous frames. The resulting framework supports high-quality text-to-motion generation, streaming synthesis, and long-horizon motion generation at interactive rates. Experiments on HumanML3D and SnapMoGen demonstrate that CMDM outperforms existing diffusion and autoregressive models in both semantic fidelity and temporal smoothness, while substantially reducing inference latency.

Related papers

• FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation [51.110607281391154]
  FlowMo is a training-free guidance method for enhancing motion coherence in text-to-video models.<n>It estimates motion coherence by measuring the patch-wise variance across the temporal dimension and guides the model to reduce this variance dynamically during sampling.
  arXiv  Detail & Related papers  (2025-06-01T19:55:33Z)
• Generative Pre-trained Autoregressive Diffusion Transformer [74.25668109048418]
  GPDiT is a Generative Pre-trained Autoregressive Diffusion Transformer.<n>It unifies the strengths of diffusion and autoregressive modeling for long-range video synthesis.<n>It autoregressively predicts future latent frames using a diffusion loss, enabling natural modeling of motion dynamics.
  arXiv  Detail & Related papers  (2025-05-12T08:32:39Z)
• MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space [40.60429652169086]
  Text-conditioned streaming motion generation requires us to predict the next-step human pose based on variable-length historical motions and incoming texts.<n>Existing methods struggle to achieve streaming motion generation, e.g., diffusion models are constrained by pre-defined motion lengths.<n>We propose MotionStreamer, a novel framework that incorporates a continuous causal latent space into a probabilistic autoregressive model.
  arXiv  Detail & Related papers  (2025-03-19T17:32:24Z)
• FRMD: Fast Robot Motion Diffusion with Consistency-Distilled Movement Primitives for Smooth Action Generation [3.7351623987275873]
  We propose Fast Robot Motion Diffusion to generate smooth, temporally consistent robot motions.<n>Our method integrates Movement Primitives (MPs) with Consistency Models to enable efficient, single-step trajectory generation.<n>Our results show that FRMD generates significantly faster, smoother trajectories while achieving higher success rates.
  arXiv  Detail & Related papers  (2025-03-03T20:56:39Z)
• Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models [71.63194926457119]
  We introduce Dynamical Diffusion (DyDiff), a theoretically sound framework that incorporates temporally aware forward and reverse processes.<n>Experiments across scientifictemporal forecasting, video prediction, and time series forecasting demonstrate that Dynamical Diffusion consistently improves performance in temporal predictive tasks.
  arXiv  Detail & Related papers  (2025-03-02T16:10:32Z)
• RecMoDiffuse: Recurrent Flow Diffusion for Human Motion Generation [5.535590461577558]
  RecMoDiffuse is a new recurrent diffusion formulation for temporal modelling. We demonstrate the effectiveness of RecMoDiffuse in the temporal modelling of human motion.
  arXiv  Detail & Related papers  (2024-06-11T11:25:37Z)
• Motion-aware Latent Diffusion Models for Video Frame Interpolation [51.78737270917301]
  Motion estimation between neighboring frames plays a crucial role in avoiding motion ambiguity. We propose a novel diffusion framework, motion-aware latent diffusion models (MADiff) Our method achieves state-of-the-art performance significantly outperforming existing approaches.
  arXiv  Detail & Related papers  (2024-04-21T05:09:56Z)
• EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation [57.539634387672656]
  Current state-of-the-art generative diffusion models have produced impressive results but struggle to achieve fast generation without sacrificing quality. We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality human motion generation.
  arXiv  Detail & Related papers  (2023-12-04T18:58:38Z)
• Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models [58.357180353368896]
  We propose a conditional paradigm that benefits from the denoising diffusion probabilistic model (DDPM) to tackle the problem of realistic and diverse action-conditioned 3D skeleton-based motion generation. We are a pioneering attempt that uses DDPM to synthesize a variable number of motion sequences conditioned on a categorical action.
  arXiv  Detail & Related papers  (2023-01-10T13:15:42Z)

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.