Researchers have developed SCRIPT, a novel diffusion policy designed for controlling physics-based humanoids using natural language instructions. This method utilizes a Joint Action-State-Text Diffusion Transformer (JAST-DiT) to integrate language semantics with control dynamics. SCRIPT also incorporates a nonlinear history conditioning mechanism for stable long-horizon control and employs Reinforcement Learning with Hybrid Rewards (RLHR) for enhanced performance. AI
Summary written by gemini-2.5-flash-lite from 1 sources. How we write summaries →
IMPACT Introduces a new framework for language-driven humanoid control, potentially enabling more sophisticated embodied agents.
RANK_REASON The cluster contains a research paper detailing a new model and methodology for humanoid control. [lever_c_demoted from research: ic=1 ai=1.0]