Awesome World Models / arXiv

V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning

作者：作者信息待提取 · 单位：Bojanowski1, Vasil Khalidov1, Patrick Labatut1, Francisco Massa1, Marc Szafraniec1, Kapil, FAIR at Meta, Mila – Quebec AI Institute and Polytechnique Montréal · 来源：General Approaches to World Models · 发布日期：2025 · 分类：6. Latent Space World Models

基础世界模型潜空间世界模型基于模型的强化学习评测/基准视频生成
新标签打开 AlphaXiv新标签打开 Project新标签打开 Code
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning figure
AlphaXiv 中文概览（可滚动查看）