Yaoqing Yang

The False Promise of Zero-Shot Super-Resolution in Machine-Learned Operators

Mitigating Memorization in Language Models

LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning

Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias

Your Task May Vary: A Systematic Understanding of Alignment and Safety Degradation when Fine-tuning LLMs

Crafting Heavy-Tails in Weight Matrix Spectrum without Gradient Noise

Model Zoos for Benchmarking Phase Transitions in Neural Networks