UniAct: Unified Control for Humanoid Robots

Published:Dec 30, 2025 16:20
1 min read
ArXiv

Analysis

This paper addresses a key challenge in humanoid robotics: bridging high-level multimodal instructions with whole-body execution. The proposed UniAct framework offers a novel two-stage approach using a fine-tuned MLLM and a causal streaming pipeline to achieve low-latency execution of diverse instructions (language, music, trajectories). The use of a shared discrete codebook (FSQ) for cross-modal alignment and physically grounded motions is a significant contribution, leading to improved performance in zero-shot tracking. The validation on a new motion benchmark (UniMoCap) further strengthens the paper's impact, suggesting a step towards more responsive and general-purpose humanoid assistants.

Reference

UniAct achieves a 19% improvement in the success rate of zero-shot tracking of imperfect reference motions.