arXiv AI July 24, 2026 By Jonas Pech\'e, Aliaksei Tsishurou, Alexander Zap, G\"unter Wallner

Multi-Task Learning for Heterogeneous Prediction from Video Game State with Transfer Learning

arXiv:2607. 21290v1 Announce Type: cross Abstract: Multi-task learning (MTL) is a promising approach for prediction tasks derived from video game state data, as modern game telemetry provides multiple related supervision signals from the same structured observations.

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

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 Machine Learning

Jun 25

Towards Scalable Multi-Task Reinforcement Learning with Large Decision Models

arXiv:2606. 24962v1 Announce Type: new Abstract: Recent progress in large-scale sequence modeling has shown that a single model can learn useful representations across highly diverse data distributions.

By Thibaut Kulak

llms agents reinforcement-learning robotics multimodal

arXiv AI

Jun 16

Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time

arXiv:2606. 15631v1 Announce Type: cross Abstract: Extending a vision-language-action (VLA) policy to a new task typically requires task-specific teleoperated demonstrations and per-task fine-tuning, making adaptation costly in both data collection and compute.

By Jeongeun Park, Juhan Park, Taekyung Kim, Sungjoon Choi, Dongyoon Han, Sangdoo Yun

rag robotics fine-tuning multimodal

arXiv AI

Jul 7

Multiplayer Interactive World Models with Representation Autoencoders

arXiv:2607. 05352v1 Announce Type: cross Abstract: We introduce the first multiplayer world model for highly dynamic environments governed by complex physical interactions.

By Anthony Hu, V\'aclav Volhejn, Adrien Ramanana Rahary, Chris Mulder, Aditya Makkar, Am\'elie Royer, Manu Orsini, Alyx Liao, Adam Jelley, Eloi Alonso, Florian Laurent, Fredrik Nor\'en, James Swingos, Jan H\"unermann, Kent Rollins, Lucas Hosseini, Matthieu Le Cauchois, Maxim Peter, Pim de Witte, Tim Brown, Vincent Micheli, Moritz B\"ohle, Gabriel de Marmiesse, Viktoriia Sharmanska, Lucia Specia, Michael Black, Patrick P\'erez

agents diffusion

arXiv Machine Learning

Jun 5

Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning

arXiv:2512. 09706v2 Announce Type: replace Abstract: The paradigm of agentic AI is shifting from engineered complex workflows to post-training native models.

By Kaichen He, Zihao Wang, Muyao Li, Anji Liu, Yitao Liang

agents reinforcement-learning robotics fine-tuning benchmarks

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

Related stories

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

Towards Scalable Multi-Task Reinforcement Learning with Large Decision Models

Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time

Multiplayer Interactive World Models with Representation Autoencoders

Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning

Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization