Chelsea Finn

Continuous scoring from LLM-as-a-Verifier leads to state-of-the-art verification accuracy and improved sample efficiency in reinforcement learning tasks.

Flow Reversal Steering transforms vague human commands into precise robotic actions, achieving up to 95% higher success rates in real-world tasks with minimal training.

A single VLA model enables decentralized multi-robot collaboration, achieving a 64% performance boost without the need for individual policies or communication.

Naively scaling test-time compute is wasteful; strategically allocating it with DIRECT can enhance embodied agent performance while slashing latency by up to 65%.

Achieve near-perfect robotic manipulation with just 20 minutes of robot experience by smartly finetuning vision-language-action models with reinforcement learning.

Get the performance boost of expensive sampling-based RL policies for a fraction of the compute by learning to prune action candidates early in the diffusion denoising process.

Verification at test time can be a surprisingly effective alternative to scaling policy learning for vision-language-action alignment, yielding substantial gains in both simulated and real-world robotic tasks.

Closing the reality gap: iteratively refining a world model with real-world robot data yields a significant boost in vision-language-action policy performance.