arXiv Machine Learning July 2, 2026 By Jinwen Wang, Youfang Lin, Xiaobo Hu, Siyu Yang, Sheng Han, Shuo Wang, Kai Lv

From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training

Read the original on arXiv Machine Learning →

arXiv:2607. 00811v1 Announce Type: new Abstract: Unsupervised pre-training on large-scale datasets has demonstrated significant potential for improving the sample efficiency and performance of Reinforcement Learning (RL).

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

reinforcement-learning

arXiv Machine Learning

Jul 2

Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos

arXiv:2607. 00808v1 Announce Type: new Abstract: Pre-training on large-scale videos to improve reinforcement learning efficiency is promising yet remains challenging.

By Jinwen Wang, Youfang Lin, Xiaobo Hu, Shuo Wang, Kai Lv

agents reinforcement-learning robotics

arXiv Machine Learning

Jul 2

Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization

arXiv:2607. 00796v1 Announce Type: new Abstract: Visual Reinforcement Learning (VRL) has achieved considerable success in solving control tasks.

By Jinwen Wang, Youfang Lin, Xiaobo Hu, Qian Xu, Shuo Wang, Zhuo Chen, Kai Lv

agents reinforcement-learning robotics benchmarks

arXiv AI

Jul 31

DLAM: Distributional Latent Actions with Temporal Constraints

arXiv:2607. 27138v1 Announce Type: cross Abstract: Vision-language-action (VLA) models remain constrained by scarce action-labeled robot data, whereas action-free videos offer abundant observations of physical change.

By Zuojin Tang, Feifan Luo, Haoyun Liu, Botai Yuan, Dekang Qi, Ronghan Chen, Yandan Yang, Tong Lin, Xinyuan Chang, Mu Xu, Bin Liu, De Ma, Zhiheng Ma

robotics multimodal

arXiv AI

Jul 3

Rank-Then-Act: Reward-Free Control from Frame-Order Progress

arXiv:2607. 01897v1 Announce Type: cross Abstract: We introduce Rank-Then-Act (RTA), a framework for learning control policies from expert video demonstrations without environment rewards.

By Yuriy Maksyuta, George Bredis, Ruslan Rakhimov, Daniil Gavrilov

llms reinforcement-learning multimodal benchmarks

arXiv AI

Jun 12

ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding

arXiv:2506. 01274v2 Announce Type: replace-cross Abstract: Recent progress in Large Multi-modal Models (LMMs) has enabled effective vision-language reasoning, yet the ability to video understanding remains constrained by suboptimal frame selection strategies, albeit with the rapid development of video-specialized LMMs.

By Hosu Lee, Junho Kim, Hyunjun Kim, Yong Man Ro

llms reinforcement-learning multimodal benchmarks

arXiv AI

Jun 29

Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding

arXiv:2606. 27922v1 Announce Type: cross Abstract: Current multimodal reflection mechanisms for long video understanding predominantly rely on closed-loop self-reflection within internal parameters.

By Shuimu Chen, Yuteng Chen, Yuanshen Guan, Zebang Cheng, Zeyu Zhang, Shengqian Qin, Bin Xia, Jiaran Li, Wenming Yang, Fei Ma

reinforcement-learning multimodal benchmarks safety

Related stories

Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos

Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization

DLAM: Distributional Latent Actions with Temporal Constraints

Rank-Then-Act: Reward-Free Control from Frame-Order Progress

ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding

Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding