Sitemap

A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.

Posts

portfolio

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

publications

On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks

Li, X., Li, X., Pan, D., and Zhu, D.

Published in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), 2020

This paper analyzes the learning behavior of logistic and softmax losses in deep neural networks.

Explainable recommendation via interpretable feature mapping and evaluating explainability

Pan, D., Li, X., Li, X., and Zhu, D.

Published in Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI-20), 2020

This paper presents an explainable recommendation system using interpretable feature mapping.

Improving adversarial robustness via probabilistically compact loss with logit constraints

Li, X., Li, X., Pan, D., and Zhu, D. (Equal contribution)

Published in Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), 2021

This paper proposes a method to improve adversarial robustness using probabilistically compact loss with logit constraints. (Equal contribution)

Defending against adversarial attacks on medical imaging AI system, classification or detection?

Li, X., Pan, D., and Zhu, D.

Published in Proceedings of IEEE International Symposium on Biomedical Imaging (ISBI-21), 2021

This paper investigates defense strategies against adversarial attacks on medical imaging AI systems.

Explaining Deep Neural Network Models with Adversarial Gradient Integration

Pan, D., Li, X., and Zhu, D.

Published in Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI-21), 2021

This paper proposes a method for explaining deep neural networks using adversarial gradient integration.

AttCAT: Explaining Transformers via Attentive Class Activation Tokens

Qiang, Y., Pan, D., Li, C., Li, X., Jang, R., and Zhu, D.

Published in Proceedings of the Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS-22), 2022

This paper presents AttCAT, a method for explaining transformer models using attentive class activation tokens.

Learning Compact Features via In-Training Representation Alignment

Li, X., Li, X., Pan, D., Qiang, Y., and Zhu, D.

Published in Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI-23), 2023

This paper presents a method for learning compact features through in-training representation alignment.

Negative Flux Aggregation to Estimate Feature Attributions

Li, X., Pan, D., Li, C., Qiang, Y., and Zhu, D.

Published in Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI-23), 2023

This paper proposes negative flux aggregation for estimating feature attributions in neural networks.

Fast Explanations via Policy Gradient-Optimized Explainer

Pan, D., Moniz, N., Chawla, N.

Published in Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI-25), 2025

This paper presents a policy gradient-based approach for generating fast explanations of machine learning models.

On the Unstable Impact and Bias Propagation of Chain-of-Thought Reasoning in Large Language Models

Pan, D., Germino, J., Ma, Y., Elizabeth, D., Chawla, N.

This paper investigates the unstable impact and bias propagation mechanisms in chain-of-thought reasoning of large language models.

Automatic Moderator Discovery via SHAP Interaction Values

Pan, D., Peng, J., Chawla, N.

This paper presents a novel method for automatically discovering moderator variables using SHAP interaction values.

Context Attribution with Multi-Armed Bandit Optimization

Pan, D., Murugesan, K., Moniz, N., Chawla, N.

Published in Findings of the Annual Meeting of the Association for Computational Linguistics (ACL 2026), 2026

This paper presents a novel approach to context attribution using multi-armed bandit optimization techniques.

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015