Authors

Wotao Yin

Publications 2

Preprint Open access

Training Numerical Intelligence via Auto-Diagnosis and Skill Discovery

AI agents are becoming increasingly capable of generating scientific code, but generating code is not the same as improving the algorithms behind it. For numerical solvers, execution feedback can expose poor performance, but rarely reveals its underlying cause and how to address it. We introduce Auto-Diagnosis and Skil …

Preprint Open access

A Zeroth-Order Paradigm for LLM Preference Alignment

Peter Chen, Xi Chen, Wotao Yin et al. · 2026

Direct preference alignment methods are widely used to align large language models (LLMs) with human preferences because of their computational and memory efficiency. However, likelihood displacement motivates alternative ways to extract information from preference pairs with small likelihood margins. In this paper, we …

Co-authors