I am a Postdoctoral Researcher at The Wharton School, University of Pennsylvania, conducting applied AI research. My research focuses on generative AI, human-centered and collaborative AI, federated and privacy-preserving learning, and foundation-model–driven analytics, with applications spanning healthcare, business intelligence and analytics, and large-scale operational systems.

I received my Ph.D. in Electrical and Computer Engineering from the University of California, San Diego (UCSD), specializing in machine learning and data science.

My work combines applied AI research with real-world, high-dimensional data, addressing challenges in scalable learning, data heterogeneity, alignment between model predictions and decision-making, LLM alignment, and responsible AI deployment. I have published several papers in leading venues including NeurIPS, AAAI, and journals such as IEEE Transactions on Artificial Intelligence and ACM. I regularly serve as a reviewer for top AI conferences (NeurIPS, ICLR, AISTATS) and journals (IEEE TMC, IEEE Internet of Things Journal, SIAM Journal on Optimization).

In addition to academia, I have conducted industry AI research through internships at Tesla Autopilot and Qualcomm AI Research, where I worked on production-scale machine learning systems, applied AI research, and real-world deployment constraints. I am broadly interested in bridging cutting-edge AI research with high-impact applications.

I am always open to collaborating on interesting AI research projects and occasionally provide AI consulting to companies and startups. Please feel free to reach out.

Google Scholar Citations: 501, H-index: 9.

News

[December 2025] We are organizing FedVision’26 at CVPR 2026. Submit your best works here. Submission Deadline: March 20, 2026

[July 2025] New paper available on arxiv: “Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data”.

[December 2024] Our paper “Federated Learning Client Pruning for Noisy Labels” Accepted to ACM Transactions on Modeling and Performance Evaluation of Computing Systems [Paper, Code].

[September 2024] Our paper “Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration” Accepted to NeurIPS 2024 [Paper, Project Website, Code].