Jian Li

When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs

CAdam: Confidence-Based Optimization for Online Learning

Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws

Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks

Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior

Consistency Model is an Effective Posterior Sample Approximation for Diffusion Inverse Solvers