← Back to Benchmarks
simmediumhumanoidmetric · varies

UniAct: Unified Motion Generation and Action Streaming for Humanoid Robots

Description

A long-standing objective in humanoid robotics is the realization of versatile agents capable of following diverse multimodal instructions with human-level flexibility. Despite advances in humanoid control, bridging high-level multimodal perception with whole-body execution remains a significant bottleneck. Existing methods often struggle to translate heterogeneous instructions -- such as language, music, and trajectories -- into stable, real-time actions. Here we show that UniAct, a two-stage f

Source

http://arxiv.org/abs/2512.24321v1