Newest papers

Learning Adaptable Dexterous Skills via Hybrid Dexterous Mimicking

Yuxuan Kuang, Jiashun Wang, Yixuan Sun, Yufei Ye, Sungjae Park, Umar Iqbal, Katerina Fragkiadaki, Shubham Tulsiani · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28628 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

Dexterous多指手持有承诺释放各种技能,如功能的抓,手指重定向,和动态转移,以人类设计的世界假设,但现有的学习配方迫使一个交易。目标达到的增强学习框架将概括到任意的对象姿势,但缺乏任何人类的先前数据,汇聚到不自然和不可靠的手指战略;运动跟踪从单个剪辑复制人类的行为,但不能偏离它。我们介绍AdaDex,一个目标条件的增强RL框架,转换到单个手对象的轨道,但在几秒钟――从莫扎普或HOI数据,从野外的RGB(D)再建到一个可适应的基本技能视频。在我们的运动功能的核心是AdaDex Hybrid Dexter Mimicking:我们

Machine translation (Meta M2M100); the English original follows.

Abstract

Dexterous multi-finger hands hold promise to unlock diverse skills like functional grasps, in-hand reorientation, and dynamic handover that the human-designed world assumes, yet existing learning recipes force a trade-off. Goal-reaching reinforcement learning generalizes to arbitrary object poses but, lacking any human prior, converges to unnatural and unreliable finger strategies; motion tracking reproduces human-like behavior from a single clip but cannot deviate from it. We present AdaDex, a goal-conditioned RL framework that turns a single hand-object trajectory of a few seconds---from mocap data or HOI reconstruction from in-the-wild RGB(D) video---into an adaptable dexterous skill. At the core of AdaDex is Hybrid Dexterous Mimicking: a shared policy is trained on two populations of massively parallel environments: motion tracking environments trained with dense motion tracking objective, which instill the human prior from human motion; and generalization environments with noised initial states and goals and a sparse object-success reward, which force the skill to work far off the reference. From seconds of human motion per skill, the resulting policies can learn diverse adaptable dexterous skills, such as functional grasping, object reposing, in-hand reorientation with finger gaiting, and dynamic behaviors like throw-and-catch. Our method outperforms baselines in terms of generalization and functionality, and we demonstrate transfer across simulators and to the real world. Project page: https://yuxuank.com/AdaDex/.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Generalization, Computer science, Artificial intelligence, Reinforcement learning, Trajectory, Motion (physics)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange