collaborators

5 papers

cs.CV2026

The Neglected Baseline in Model Interpretation

Yongjin Cui, Xiaohui Fan

We observe that existing model interpretation methods generally ignore the baseline, and such neglect often results in imprecise or even incorrect interpretation. In this paper, we…

cs.CV2026

Generic Interpretation Approach for Transformer Models Incorporating Heterogenous Attention Structures

Yongjin Cui, Xiaohui Fan, Huajun Chen

Transformer has significantly propelled the development of artificial intelligence, and certainly the development of agents as well. We categorize attention structures of Transform…

cs.CV2026

Debunking Grad-ECLIP: A Comprehensive Study on Its Incorrectness and Fundamental Principles for Model Interpretation

Yongjin Cui, Xiaohui Fan

Grad-ECLIP is published at ICML 2024 and represents a new Transformer interpretation technical route (intermediate features-based). First, this paper demonstrates that the intermed…

cs.AI2026

Transformer Interpretability from Perspective of Attention and Gradient

Yongjin Cui, Xiaohui Fan, Huajun Chen

Although researchers' attention is more focused on the performance of Transformer models, the interpretation of Transformer can never be ignored. Gradient is widely utilized in Tra…

cs.CL2025

A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following

Yin Fang, Xinle Deng, Kangwei Liu +5

Large language models excel at interpreting complex natural language instructions, enabling them to perform a wide range of tasks. In the life sciences, single-cell RNA sequencing…