DexPIE is a post‑training framework that improves dexterous manipulation policies using real‑world experience. It introduces a dexterous‑hand‑adapted intervention system and multi‑stage DAgger‑style data collection to enhance exploration, aligns training and inference to reduce distribution shift, and conditions the policy on a continuous optimality indicator for fine‑grained data quality use. In three real‑world tasks, DexPIE boosts success rates by 37.3% over a demonstration‑based baseline, outperforming all other methods and showing stronger robustness.
By Ruizhe Liao, Wenrui Chen, Liangji Zeng, Haoran Lin, Fan Yang, Kailun Yang, Yaonan Wang
arXiv:2607. 01225v1 Announce Type: cross Abstract: Prior work on imitation learning from suboptimal demonstrations typically relies on compressed supervision signals such as confidence estimates, discriminator scores, or importance weights.
By Chih-Han Yang, Dai-Jie Wu, Yun-Ping Huang, Ping-Chun Hsieh, Kenneth Marino, Shao-Hua Sun
arXiv:2609.37135v1 Announce Type: new
Abstract: Using language instructions as conditions to guide robot policy learning has recently become an important research domain. However, existing language-g...
By Yi-Pei Chiu, Wei-Ta Chu
arXiv:2606. 00083v1 Announce Type: cross Abstract: Reinforcement learning relies on accurate reward functions, which are often hand-crafted or even unavailable in real-world applications, such as robotics.
By Christian Gumbsch, Leonardo Barcellona, Lennard Sch\"unemann, Platon Karageorgis, Andrii Zadaianchuk, Zehao Wang, Sergey Zakharov, Fabien Despinoy, Rahaf Aljundi, Efstratios Gavves
arXiv:2607. 07859v1 Announce Type: new Abstract: Reinforcement learning (RL) research has increasingly shifted focus towards alignment, ensuring agents learn behaviors adhering to human values.
By Benjamin Poole, Minwoo Lee
arXiv:2606. 18247v1 Announce Type: cross Abstract: Robots deployed in the real world should learn from their experience and improve over time.
By Mingtong Zhang, Dhruv Shah
arXiv:2512. 00062v2 Announce Type: replace-cross Abstract: Robotic policy learning for complex real-world manipulation tasks has seen rapid recent progress, enabled in large part by the ability to collect demonstrations through human operation.
By Taewook Nam, Junmo Cho, Youngsoo Jang, Sung Ju Hwang
KnowDemo is a framework that generates diverse robot demonstrations from human videos by leveraging structured manipulation knowledge. It uses a vision‑language model to extract task requirements and permissible execution variations, then resolves these against target‑scene entities to guide candidate generation and screening before motion planning. The resulting demonstrations feature multimodal behavior, alternative contact strategies, and valid subtask orders, and have been shown to improve planning success and enable sim‑to‑real policy transfer across three tasks.
By Zhiyuan Gao, Yanxiang Zhan, Mohammad Khoshnazar, Jeroen Sch\"afer, Michael Beetz
arXiv:2512. 16861v2 Announce Type: replace-cross Abstract: Long-horizon manipulation has been a long-standing challenge in the robotics community.
By Zihan Zhou, Animesh Garg, Ajay Mandlekar, Caelan Garrett
Vision-language-action (VLA) models can learn manipulation skills from demonstrations, but their capabilities are bounded by the skills in the training data. We present InSight, a framework that unlocks autonomous skill acquisition by rendering VLAs steerable at the primitive-action level (e.
arXiv:2607. 10601v1 Announce Type: new Abstract: Large Language Model (LLM) agents are commonly trained from expert trajectories using supervised fine-tuning (SFT), which treats multi-turn agent behavior as ordinary text imitation.
By Yixiong Chen, Alan Yuille
The paper introduces SUN (Semantically UNified) Programs, typed executables that translate grounded relations into optimal control objectives, satisfaction predicates, and learning rewards. Using the Kuafu harness, a foundation model orchestrates scene preparation, verification, residual reinforcement learning, and data generation, repairing candidate programs and calibrating reward weights. Across nine multi‑stage manipulation tasks, Kuafu achieves an 82.03% success rate, outperforms learned baselines, generates demonstrations 10.57× faster than human teleoperation, and transfers zero‑shot to physical Franka and Kinova robots.
By Weiqi Wang, Zhi Li, Yudong Lei, David Martinez, Xiaofeng Gao, Yuxin Jiang, Chenfanfu Jiang, Yingnian Wu, Demetri Terzopoulos, Ran Gong