Research map / Probabilistic and scientific modeling / Variational and generative sampling
Autoregressive Motion Generation with Gaussian Mixture-Guided Latent Sampling
Linnan Tu, Lingwei Meng, Zongyi Li, Hefei Ling, Shijuan Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes GMMotion, a text-to-motion method that combines continuous autoregressive generation with Gaussian mixture-guided latent sampling to avoid discretization errors and slow diffusion sampling.
Problem
Text-to-motion synthesis: generative transformers with discrete representations introduce motion errors from discretization, while diffusion models with continuous representations sample slowly.
Approach
Combines a continuous autoregressive framework with Gaussian mixture-guided latent sampling, so the model keeps continuous motion representations while avoiding the slow sampling of diffusion models (abstract is truncated, so details are limited).
Closest papers by meaning
- Generative Pre-trained Autoregressive Diffusion Transformer (NeurIPS 2025 · similarity 0.90)
- Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression (CVPR 2025 · similarity 0.88)
- Human Motion Diffusion as a Generative Prior (ICLR 2024 · similarity 0.87)
- ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model (CVPR 2025 · similarity 0.87)
- Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model (AAAI 2024 · similarity 0.86)
- AMD: Autoregressive Motion Diffusion (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
