跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 26 天前AI 評分37

ThinkWorld:世界想像強化動態鏈推理

ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning

AI 導讀

ThinkWorld提出一種視覺-語言-動作(VLA)學習框架,以世界動力學為動作推理奠基,並透過世界想像的強化學習提升機械人泛化能力。框架以動態鏈(CoD)表示動作,利用未標註人類影片中的狀態轉移提供監督;模擬及真實機械人實驗顯示,該方法能促進人類經驗向機械人遷移,並泛化至未見任務和環境。

正文

Published on Oct 27

Authors:

,

,

,

,

,

Abstract

ThinkWorld improves robotic generalization by representing actions as dynamics chains and using world imagination to learn from unlabeled human videos.

Vision-Language-Action (VLA) models have made substantial progress in robotic manipulation, but their generalization remains constrained by the diversity and coverage of action-labeled robot demonstrations. Human videos provide much broader behavioral and environmental experience, while learning from them faces a fundamental trade-off between scalable data and explicit action grounding. We introduce ThinkWorld, a VLA learning framework that grounds action reasoning in world dynamics and strengthens it through reinforcement learning with world imagination. ThinkWorld represents each action thought as a Chain-of-Dynamics (CoD), a sequence of discrete motion tokens that captures the intermediate dynamics connecting the current world to a future state and serves as a common action representation across embodiments. We first initialize CoD with action-labeled demonstrations, then predict the future induced by each CoD and reinforce those whose predictions better match the observed outcome. This enables videos without action annotations to provide direct supervision from observed state transitions, allowing human and robot experience to refine the same reasoning space. Experiments in simulation and on real robots demonstrate effective human-to-robot transfer and strong generalization to unseen tasks and environments.

View arXiv page View PDF Project page Add to collection

Get this paper in your agent:

hf papers read 2610.37666

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.37666 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.37666 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.37666 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co