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

• URL: http://arxiv.org/abs/2605.22894v2
• Date: Mon, 25 May 2026 05:33:57 GMT
• Title: SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid Control
• Abstract summary: SCRIPT is a scalable diffusion policy with a multi-stage training framework for language-driven physics-based humanoid control.<n>The core of SCRIPT is a Joint Action-State-Text Diffusion Transformer (JAST-DiT), which represents actions, physical states, and text as dedicated token streams.<n>To stabilize autore control, we introduce a nonlinear history conditioning mechanism, which preserves the dense recent context and samples increasingly sparse cues from long-term history.
• Score: 72.5651722107621
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 physical feasibility, often failing to jointly achieve faithful instruction following, high-quality motion, and stable long-horizon control. We propose SCRIPT, a scalable diffusion policy with a multi-stage training framework for language-driven physics-based humanoid control. The core of SCRIPT is a Joint Action-State-Text Diffusion Transformer (JAST-DiT), which represents actions, physical states, and text as dedicated token streams and couples them through joint attention, enabling direct interaction between language semantics and control dynamics. To stabilize autoregressive control, we introduce a nonlinear history conditioning mechanism, which preserves the dense recent context and samples increasingly sparse cues from long-term history. Beyond supervised imitation pre-training, we propose a post-training stage, further improving the performance using Reinforcement Learning with Hybrid Rewards (RLHR). By injecting learnable noise into the flow-sampling process, RLHR effectively improves motion quality and instruction following within closed-loop simulations using hybrid physical feedback and text rewards. Quantitative evaluations demonstrate that SCRIPT outperforms prior state-of-the-art methods, with gains across text alignment, motion quality, and physical realism metrics. Furthermore, scaling studies on the 1200-hour MotionMillion dataset demonstrate consistent performance gains with model scaling, highlighting SCRIPT's robust scalability for large-scale pre-training. Our code will be publicly available for future research.

Related papers

• In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics [109.99871326497333]
  In-Context Model Predictive Generation (ICMPG) is a framework that integrates language-model planning with inference-time physical feedback.<n>ICMPG reformulates motion synthesis as a Model Predictive Control (MPC)-like process with two modules.
  arXiv  Detail & Related papers  (2026-06-25T12:50:33Z)
• LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning [90.86828952599147]
  We present LaST-R1, a novel reinforcement learning framework designed to harness "latent reasoning-before-acting" policies.<n>LaST-R1 achieves a near-perfect 99.9% average success rate on the LIBERO benchmark.<n>In real-world deployments, LaST-R1 yields up to a 22.5% average improvement over SOTA supervised fine-tuning approach.
  arXiv  Detail & Related papers  (2026-04-30T17:59:52Z)
• CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation [4.726851899243877]
  LG-Flow Policy is a trajectory-level imitation learning framework that performs flow matching in a continuous latent action space.<n>By encoding action sequences into temporally regularized latent trajectories and learning an explicit latent-space flow, the proposed approach decouples global motion structure from low-level control noise.
  arXiv  Detail & Related papers  (2026-01-30T15:36:43Z)
• On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning [61.38273866396522]
  Vision-Language-Action models have emerged as a powerful paradigm for general-purpose robot learning.<n>Current methods remain unsuitable for challenging simulated- or physical-world deployments.<n>We introduce a Test-Time Reinforcement Learning for VLAs framework that enables on-the-fly policy adaptation during inference.
  arXiv  Detail & Related papers  (2026-01-11T01:51:30Z)
• No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Prompts [16.05508249584636]
  We propose a post-training framework that fine-tunes pretrained motion diffusion models using only textual prompts.<n>Our approach is a flexible, data-efficient, and privacy-preserving solution for motion adaptation.
  arXiv  Detail & Related papers  (2025-10-08T13:12:10Z)
• RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control [32.37239524019001]
  This paper focuses on translating text-driven human motions into executable actions for humanoid robots.<n>Existing text-to-motion generation methods produce kinematically or physically infeasible motions unsuitable for real-world deployment.<n>We propose Reinforcement Learning from Physical Feedback, a novel framework that integrates physics-aware motion evaluation with text-conditioned motion generation.
  arXiv  Detail & Related papers  (2025-06-15T08:39:49Z)
• Dynamic Manipulation of Deformable Objects in 3D: Simulation, Benchmark and Learning Strategy [88.8665000676562]
  Prior methods often simplify the problem to low-speed or 2D settings, limiting their applicability to real-world 3D tasks.<n>To mitigate data scarcity, we introduce a novel simulation framework and benchmark grounded in reduced-order dynamics.<n>We propose Dynamics Informed Diffusion Policy (DIDP), a framework that integrates imitation pretraining with physics-informed test-time adaptation.
  arXiv  Detail & Related papers  (2025-05-23T03:28:25Z)
• LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory Simulation [102.1527101235251]
  LangTraj is a language-conditioned scene-diffusion model that simulates the joint behavior of all agents in traffic scenarios.<n>By conditioning on natural language inputs, LangTraj provides flexible and intuitive control over interactive behaviors.<n>LangTraj demonstrates strong performance in realism, language controllability, and language-conditioned safety-critical simulation.
  arXiv  Detail & Related papers  (2025-04-15T17:14:06Z)
• CASIM: Composite Aware Semantic Injection for Text to Motion Generation [15.53049009014166]
  We propose a composite-aware semantic injection mechanism that learns the dynamic correspondence between text and motion tokens.<n> Experiments on HumanML3D and KIT benchmarks demonstrate that CASIM consistently improves motion quality, text-motion alignment, and retrieval scores.
  arXiv  Detail & Related papers  (2025-02-04T07:22:07Z)
• TLControl: Trajectory and Language Control for Human Motion Synthesis [68.09806223962323]
  We present TLControl, a novel method for realistic human motion synthesis. It incorporates both low-level Trajectory and high-level Language semantics controls. It is practical for interactive and high-quality animation generation.
  arXiv  Detail & Related papers  (2023-11-28T18:54:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.