Chelsea Finn
2 papers · Latest:
Machine Learning
FASTER: Value-Guided Sampling for Fast RL
FASTER introduces a value-guided sampling method for diffusion-based RL policies, significantly reducing computational cost while maintaining performance.
2604.19730
Machine LearningWorld Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
WAV improves world model robustness by verifying state plausibility and action reachability, achieving 2x sample efficiency and 18% better policy performance.
2604.01985
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.