arXiv Machine Learning July 31, 2026 By Anthony Liang, Pavel Czempin, Matthew M. Hong, Yutai Zhou, Jingzhen Wang, Erdem Biyik, Stephen Tu

CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations

Read the original on arXiv Machine Learning →

arXiv:2505. 04999v2 Announce Type: replace-cross Abstract: Learning robot control policies from demonstrations typically requires action-labeled expert data, which is expensive to collect through teleoperation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

robotics

arXiv AI

Jul 20

SLAC: Safe and Efficient Real-Robot Reinforcement Learning via Unsupervised Simulation Pre-Training

arXiv:2506. 04147v5 Announce Type: replace-cross Abstract: Building capable household and industrial robots requires mastering the control of versatile, high-degree-of-freedom (DoF) systems such as mobile manipulators.

By Jiaheng Hu, Peter Stone, Roberto Mart\'in-Mart\'in

reinforcement-learning robotics benchmarks safety

Hugging Face Trending Papers

Jul 27

DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning

Generalizable robot manipulation requires policies that can anticipate how visual scenes evolve while executing language instructions. While recent Vision-Language-Action models benefit from large-scale pretraining, their predominantly static pretraining objectives provide limited supervision for physical dynamics and temporal causality, leaving control-relevant knowledge to be learned from downstream robot demonstrations.

robotics multimodal benchmarks

arXiv Computer Vision

Sep 4

RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning

RoboTok is an internet‑scale data engine that retrieves human manipulation videos from the web to train dexterous robot policies. It learns a latent motion space from 3D hand trajectories in actor‑centered reference frames, allowing manipulation behaviors to be compared across different viewpoints, scenes, and occlusions while remaining compact for efficient search. Experiments show RoboTok retrieves more relevant demonstrations and improves downstream robot task success compared to existing retrieval methods.

By Howard Qian, Yiting Chen, Yunfei Xie, Kejia Ren, Podshara Chanrungmaneekul, Gaotian Wang, Bowen Wen, Chen Wei, Kaiyu Hang

robotics benchmarks

arXiv AI

Jun 2

From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data

arXiv:2606. 00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models.

By Zhiyuan Feng, Qixiu Li, Huizhi Liang, Rushuai Yang, Yichao Shen, Zhiying Du, Zhaowei Zhang, Yu Deng, Li Zhao, Hao Zhao, Zongqing Lu, Oier Mees, Marc Pollefeys, Jiaolong Yang, Baining Guo

robotics multimodal

arXiv AI

2d ago

TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models

arXiv:2610.00899v1 Announce Type: cross Abstract: Autoregressive Vision-Language-Action models often represent continuous robot actions as discrete token sequences, enabling action prediction with st...

By Keisuke Shirai, Tomohiro Motoda, Hanbit Oh, Ryoichi Nakajo, Roman Mykhailyshyn, Ryo Hanai, Shotaro Miwa, Yukiyasu Domae

nlp robotics efficiency multimodal

arXiv AI

Jul 3

Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs

arXiv:2607. 02466v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are fundamentally bottlenecked by the scarcity of expert demonstrations -- triplets of observations, instructions, and actions that are costly to collect at scale.

By Junhao Shi, Siyin Wang, Xiaopeng Yu, Li Ji, Jingjing Gong, Xipeng Qiu

agents robotics multimodal benchmarks safety

One email a morning, machine-written

Related stories

SLAC: Safe and Efficient Real-Robot Reinforcement Learning via Unsupervised Simulation Pre-Training

DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning

RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning

From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data

TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models

Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs