arXiv Machine Learning June 11, 2026 By Christoph Koller, Johannes F\"urnkranz, Timo Bertram

RePAIR: Predictive Self-Supervised Representation Learning in Chess

Read the original on arXiv Machine Learning →

arXiv:2606. 11860v1 Announce Type: new Abstract: In this paper, we introduce Representation Prediction via Autoencoding using Iterative Refinement (RePAIR) - a novel self-supervised representation learning architecture that synthesizes Masked Autoencoders (MAE), Joint Embedding Predictive Architectures (JEPA), and Bidirectional Encoder Representations from Transformers (BERT).

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.

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 Machine Learning

Jun 25

ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning

arXiv:2501. 14622v5 Announce Type: replace Abstract: Learning efficient representations for decision-making policies is a challenge in imitation learning (IL).

By Aleksandar Vujinovic, Aleksandar Kovacevic

rag diffusion

arXiv AI

Jul 2

Play Like Champions: Counterfactual Feedback Generation in Latent Space

arXiv:2607. 00190v1 Announce Type: cross Abstract: Recent advances in reinforcement learning have produced superhuman agents across a wide range of competitive games.

By Andrzej Bia{\l}ecki, Adam Mastalerz, Han Zhou

agents diffusion reinforcement-learning

arXiv AI

Jul 7

Mask-based Predictive Representations for Reinforcement Learning

arXiv:2607. 04153v1 Announce Type: cross Abstract: Vision-based deep reinforcement learning involves dealing with high-dimensional inputs of image information.

By Kai Zhao

llms agents diffusion computer-vision nlp reinforcement-learning benchmarks

arXiv Machine Learning

Jun 16

Next-Latent Prediction Transformers Learn Compact World Models

arXiv:2511. 05963v4 Announce Type: replace Abstract: Transformers replace recurrence with a memory that grows with sequence length and self-attention that enables ad-hoc lookups over past tokens.

By Jayden Teoh, Manan Tomar, Kwangjun Ahn, Edward S. Hu, Tim Pearce, Pratyusha Sharma, Akshay Krishnamurthy, Riashat Islam, Alex Lamb, John Langford

llms diffusion benchmarks safety

arXiv AI

Aug 26

Disentangled Skill Representations for Predictive Human Modeling

The paper introduces Skill Abstraction with Interpretable Latents (SAIL), a method that models human skill as a persistent, multi‑dimensional construct inferred from naturalistic behavior over time. SAIL produces a robust skill embedding that blends expert and novice bases, learns transferable subskills through counterfactual subskill swaps, and supports skill‑informed behavior prediction across various in‑domain contexts. Experiments on racing and baseball demonstrate that SAIL achieves strong predictive performance, improves behaviorally grounded disentanglement compared to baselines, and enhances downstream AI coaching outcomes.

By Mariah Schrum, Deepak Gopinath, Srijan Srivatsa, Guy Rosman, Tiffany Chen

rag safety

One email a morning, machine-written

Related stories

Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization

ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning

Play Like Champions: Counterfactual Feedback Generation in Latent Space

Mask-based Predictive Representations for Reinforcement Learning

Next-Latent Prediction Transformers Learn Compact World Models

Disentangled Skill Representations for Predictive Human Modeling