FuguReport

In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics

Authors Xiaomeng Fu, Junfan Lin, Yang Liu, Yaowei Wang, Guanbin Li, Liang Lin, Ziliang Chen
Affiliations Peng Cheng Laboratory / Sun Yat-Sen University / Harbin Institute of Technology
Categories Method / Motion Synthesis / Model predictive control framework, Application / Language Model Utilization / Motion generation from language input, Evaluation / Physics-Based Control / Inference-time physical feedback
License CC BY 4.0

Abstract Overview

This paper introduces In-Context Model Predictive Generation (ICMPG), a framework for text-driven human motion synthesis that combines large language model planning with inference-time physical feedback. The method decomposes open-vocabulary instructions into structured action descriptions, generates candidate motion-token sequences, and then iteratively refines them using a model-predictive procedure guided by semantic and physical rewards. Its architecture includes a Context-Aware Motion Generation module for LLM-based token generation and a Model Predictive Generation module that evaluates candidates in simulation and selects the best continuation. The goal is to reduce the usual trade-off between semantic expressiveness and physical plausibility in open-vocabulary motion generation.

Novelty

The distinctive contribution is the reformulation of motion synthesis as an MPC-like closed-loop generation process rather than open-loop text-to-motion decoding or task-specific reinforcement learning. The framework uses frozen or lightly adapted LLMs as planners/generators and combines them with simulation-based physical feedback at inference time, avoiding task-specific policy retraining while retaining open-vocabulary flexibility.

Results

On the open-vocabulary BABEL benchmark, the LoRA-tuned variant achieves the best reported semantic metrics among the compared methods, including FID 0.492, CLIP_Score 29.32, and R-Precision 0.316/0.603, while maintaining 82.9% simulation success and Phys-Err 3.704. The non-fine-tuned ICMPG also outperforms AvatarCLIP and MotionCLIP on FID, CLIP_Score, and R-Precision, and the paper reports competitive results on HumanML3D and KIT-ML with improved physically constrained realism relative to non-physics-aware baselines.

Key Points

  1. ICMPG couples LLM-based semantic planning with simulation-based reward feedback, selecting motion continuations through a receding-horizon refinement loop.
  2. The method targets open-vocabulary motion synthesis and uses SemAligner, motion tokenization via VQ-VAE, and combined semantic/physical rewards to improve alignment and feasibility.
  3. Experiments show stronger open-vocabulary generalization and competitive physical realism, with ablations indicating that the planner, reward design, and LLM backbone materially affect performance.

References

This page was created using generative AI such as GPT-5, Claude Opus 4, Gemini 3, Gemini 3.1 Flash Image, and their higher-end successor versions. No guarantee can be made regarding its contents.