DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning

Gaoyue Zhou; Hengkai Pan; Yann LeCun; Lerrel Pinto

2025 ICML ICML 2025

DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Reinforcement Learning and Robotics

Authors

Gaoyue Zhou, Hengkai Pan, Yann LeCun, Lerrel Pinto

Topics

Artificial Intelligence > Core AI > Multimodal Learning Robotics > Capabilities > Motion Planning Reinforcement Learning > Methods > Model-Based RL

Keywords

patch feature dinov2 action sequence optimization offline trajectories task-agnostic planning zero-shot solutions

Download PDF