Percy Liang
percyliang
AI & ML interests
foundation models
Recent Activity
liked a model 2 days ago
open-athena/Marin-Mochi-535B-A23B authored a paper over 1 year ago
MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine
Learning Engineering authored a paper almost 2 years ago
Language Models Prefer What They Know: Relative Confidence Estimation
via Confidence Preferences