I am an assistant professor in the CSE department at The Ohio State University and a part-time research scientist at Yahoo! Research. I’m interested in theoretical and applied machine learning, focusing on robustness, interpretability, and model compression for large-scale models like LLMs.

Current Graduate Students

Zhiqun Zuo (Research Project: Counterfactual Reasoning)

Zhongteng Cai (Research Project: Privacy-Aware Model Compression and Quantization)

Ding Zhu (Research Project: Trustworthy Model Compression, Time Series Data Analysis Using Foundation Models)

Vishnu Chhabra (Research Project: Mechanistic Interpretability for Foundation Models)

Recent News

2024

• New paper titled “Neuroplasticity and Corruption in Model Mechanisms: A case study of Indirect Object Identification” is accepted in the ICML 2024 Mechanistic Interpretability Workshop.

• New paper titled “ECG Signal Denoising Using Multi-scale Patch Embedding and Transformers” is accepted in the ICML 2024 Next Generation of Sequence Modeling Architectures Workshop.

• Received a GPU server for the lab.

• Invited to give a talk on Counterfactual Reseaning for Fair Machine Learning at the Midwest Machine Learning Symposium.

• Zhongteng Cai received a travel grant to attend the UAI conference and present his work.

• New paper titled “Privacy-Aware Randomized Quantization via Linear Programming” is accepted in the 40th Conference on Uncertainty in Artificial Intelligence (UAI).

• Received a grant from the Translational Data Analytics Institute to build interpretable and efficient AI models for medical diagnosis.

• New PhD student, Vishnu Chhabra joined my lab. He will be working on Mechanistic Interpretability for foundation models.

• New paper titled “Imposing Fairness Constraints in Synthetic Data Generation” is accepted in the 27th International Conference on Artificial Intelligence and Statistics (AISTATS).

• Received a grant from the college of engineering to build safe, robust, and interpretable AI models for large-scale systems.

2023

• New paper titled “Counterfactually Fair Representation” is accepted in the Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS).

• New paper titled “Loss Balancing for Fair Supervised Learning” is accepted in the International Conference of Machine Learning (ICML).

• New paper titled “Symbolic Metamodels for Interpreting Black-boxes Using Primitive Functions” is accepted (for oral presentation) in the AAAI Conference on Artificial Intelligence.

• New paper titled “Counterfactual Fairness in Synthetic Data Generation” is accepted in the Neurips workshop on Synthetic Data for Machine Learning.

• New paper titled “Towards Fair Representation Learning in Knowledge Graph with Stable Adversarial Debiasing” is accepted in the ICDM workshop on Knowledge Graph.

• Recived an NSF Grant to buid a safe and private AI system for health monitoring with my collaborators at UIUC and UCSD.

• Recived an NSF Grant to improve fairness and robustness of AI in dynamic environmnets.