Researcher, Microsoft Research
3 papers at NeurIPS 2025
BC-LLM is a novel procedure that integrates Large Language Models into a Bayesian framework for concept discovery to achieve better predictive performance, converge faster to relevant concepts, and provide rigorous uncertainty quantification.
We introduce the Generalized Induction Model (GIM), a retrieval-based in-context module that enhances interpretable next-token prediction in language modeling and fMRI response prediction.
