3 papers
cs.LG2026
Actor-Curator: Co-adaptive Curriculum Learning via Policy-Improvement Bandits for RL Post-Training
Zhengyao Gu, Jonathan Light, Raul Astudillo +7
Post-training large foundation models with reinforcement learning typically relies on massive and heterogeneous datasets, making effective curriculum learning both critical and cha…
q-bio.BM2025
Steering Generative Models with Experimental Data for Protein Fitness Optimization
Jason Yang, Wenda Chu, Daniel Khalil +4
Protein fitness optimization involves finding a protein sequence that maximizes desired quantitative properties in a combinatorially large design space of possible sequences. Recen…
cs.LG2024
Practical Bayesian Algorithm Execution via Posterior Sampling
Chu Xin Cheng, Raul Astudillo, Thomas Desautels +1
We consider Bayesian algorithm execution (BAX), a framework for efficiently selecting evaluation points of an expensive function to infer a property of interest encoded as the outp…