Video-Based Optimal Transport for Feedback-Efficient Offline Preference-Based Reinforcement Learning (ICML 2026)
-
Updated
Aug 20, 2026 - Python
Video-Based Optimal Transport for Feedback-Efficient Offline Preference-Based Reinforcement Learning (ICML 2026)
Frozen V-JEPA 2 (300M params) + PPO policy head achieves +763 mean reward on CarRacing-v3 — 2.4x over CNN baseline, single RTX 3080
A curated survey hub for video understanding, generation, unified video models, and video world models.
To associate your repository with the video-foundation-models topic, visit your repo's landing page and select "manage topics."