PulseAugur
EN
LIVE 09:47:08

SCRIPT model advances humanoid control with language and diffusion

By PulseAugur Editorial · [3 sources] ·

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

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]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

COVERAGE [3]

  1. arXiv cs.LG TIER_1 English(EN) · Jingyan Zhang, Han Liang, Ruichi Zhang, Bin Li, Juze Zhang, Xin Chen, Jingya Wang, Lan Xu, Jingyi Yu ·

    SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control

    arXiv:2605.22894v1 Announce Type: cross Abstract: Controlling physics-based humanoids from natural-language instructions is a critical step toward general-purpose embodied agents. However, existing methods remain constrained by a tension between semantic expressiveness and physic…

  2. arXiv cs.CV TIER_1 English(EN) · Bin Li, Ruichi Zhang, Han Liang, Jingyan Zhang, Juze Zhang, Xin Chen, Jingya Wang ·

    MIND: Multi-Scale Intent Diffusion for Text-Driven Physics-Based Humanoid Control

    arXiv:2605.26006v1 Announce Type: new Abstract: Enabling physics-based humanoids to execute diverse behaviors from high-level textual commands remains a significant challenge. Existing methods typically follow either a two-stage paradigm that combines kinematic motion generation …

  3. arXiv cs.CV TIER_1 English(EN) · Jingya Wang ·

    MIND: Multi-Scale Intent Diffusion for Text-Driven Physics-Based Humanoid Control

    Enabling physics-based humanoids to execute diverse behaviors from high-level textual commands remains a significant challenge. Existing methods typically follow either a two-stage paradigm that combines kinematic motion generation with physics-based tracking, or an end-to-end im…

RELATED TOPICS