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.
Pages
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.
Context Attribution with Multi-Armed Bandit Optimization
Pan, D., Murugesan, K., Moniz, N., Chawla, N.
This paper presents a novel approach to context attribution using multi-armed bandit optimization techniques.
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.
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
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
This is a description of a teaching experience. You can use markdown like any other post.