Zhen Fang

How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability

Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection

Delving into Spectral Clustering with Vision-Language Representations

Perturbations Matter: Sensitivity-Guided Hallucination Detection in LLMs

A Close Look at Negative Label Guided Out-of-distribution Detection in Pre-trained Vision-Language Models

Anchoring Entities: Retrieval-Augmented Hallucination Detection

Explainable LLM Unlearning through Reasoning

ALMC: Adaptive LLM-based Multi-Agent Collaboration Across Diverse Task Domains

Learning Robust Spectral Dynamics for Temporal Domain Generalization

Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents

Release the Powers of Prompt Tuning: Cross-Modality Prompt Transfer

An Information-theoretical Framework for Understanding Out-of-distribution Detection with Pretrained Vision-Language Models

Deep Kernel Relative Test for Machine-generated Text Detection

Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach

Rethinking Knowledge Distillation: A Mixture-of-Experts Perspective