Fang Chen

Faithfulness Under the Distribution: A New Look at Attribution Evaluation

Label-Free Attribution for Interpretability

Adversarial Bottleneck Method for Vision-Language Large Model Explainability

Steering Diffusion Models Towards Credible Content Recommendation

LACE: Lightweight Attribution-guided Concept Evolution for Continual Learning

PRISM: Pareto-Responsive Iterative Sampling with DPO for Multi-objective Planning

Signed-dictionary and Nonnegative-activation Decomposition for Concept Bottleneck Models

Can we trust the attribution method?

Conceptual Archetype Decomposition for Interpretable and Generalizable Model Decisions

C2MF: Consistent and Concept-Unified Matrix Factorization for Interpretable and Robust Concept Discovery

Revealing Multimodal Causality with Large Language Models

Splitting & Integrating: Out-of-Distribution Detection via Adversarial Gradient Attribution

Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability

SSLA: A Generalized Attribution Method for Interpreting Self-Supervised Learning without Downstream Task Dependency

Unbiased Attribution with Intrinsic Information

Feature Level Instance Attribution