Hong Chen

S$^2$MAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection

UltraHorizon: Benchmarking LLM-Agent Capabilities in Ultra Long-Horizon Scenarios

Detecting LLM Hallucinations via Nonlinear Manifold Separation

A Statistical Approach for Controlled Training Data Detection

Towards Generalization Bounds of GCNs for Adversarially Robust Node Classification

How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reduction

On the Generalization Ability of Next-Token-Prediction Pretraining

S$^2$MAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection

Adversarial Robust Generalization of Graph Neural Networks

From Conflicts to Convergence: A Zeroth-order Method for Multi-Objective Learning