cs.RONov 18, 2026

SemPhys: Semantic-Physical Co-Learning for Humanoid Motion Generation via Differentiable World Models

Authors: Zejian Kang, Yeqiang Wang, Zekai Chen, Boyang Shen, Mingyu Ma, Bingqian Wu, Fan Zhou, Jianjie Zhang, 

Organizations: Zhejiang University · Westlake University · Shanghai Jiao Tong University · Shanghai Innovation Institute · 

Abstract

In human-robot collaboration, natural language lets people direct a humanoid's whole-body movements without programming joint trajectories. A common approach generates a kinematic reference from an instruction and relies on a tracking controller to execute it. However, as the controller maintains balance under contact constraints, the executed motion can depart from the reference in ways that change the action it conveys. Our central insight is that semantic alignment must be evaluated directly on the complete motion the robot physically executes. Building on this insight, we introduce SemPhys, a framework that trains motion generators using semantic feedback from simulated executions. A differentiable world model and a fixed tracking controller predict a short segment of a recorded execution. SemPhys inserts this prediction at its original position, scores the complete trajectory against the instruction, and backpropagates through the predicted segment. A paired anchoring loss stabilizes adaptation by keeping each generated reference close to its counterpart from the initial generator. On BONES-SEED, SemPhys largely preserves instruction retrieval accuracy from reference to execution and achieves the highest retrieval accuracy on executed motions among the evaluated methods.

Figures & tables

Explore similar work

CardsList
  1. Sample, Simulate, Select: Physics-in-the-Loop Text-to-Motion for Humanoids Without Training

    Sep 22, 2026Raphael Memmesheimer, Sven BehnkeHuman Motion GenerationRobot Motion Generation

  2. RoboForge: Physically Optimized Text-guided Whole-Body Locomotion for Humanoids

    Mar 18, 2026Xichen Yuan, Zhe Li, Bofan Lyu +4Humanoid Robot LocomotionHuman Motion Generation

  3. PhyGile: Physics-Prefix Guided Motion Generation for Agile General Humanoid Motion Tracking

    Mar 13, 2026Jiacheng Bao, Haoran Yang, Yucheng Xin +7Robot Trajectory TrackingHumanoid Robot Control