I am a Computer Science Postdoctoral Researcher at Scalable Analytics Institute, hosted by Prof. Wei Wang & Prof. Yizhou Sun. I recently got my Ph.D. in Electrical & Computer Engineering at the University of Southern California, under the supervison of Prof. Salman Avestimehr. My research focuses on the intersection of federated learning and graph generative models, and AI4Science. Recently, I have a keen interest in generative flow networks. I have been selected as a 2025 North America Finalist at the Qualcomm Innovation Fellowship.

Research Topics

Federated Learning

GFlowNets

Graph Neural Networks

Uncertainty Estimation

Probabilistic Modeling

AI For Science

Conformal Prediction

LLM Reasoning

My Contributions +

As AI systems are increasingly deployed in complex tasks across decentralized real-world applications, I believe it's vital to build foundations of ML fro graphs over federated settings. My work has introduced the federated training of graph neural networks and continues to pursue applications required for collaborative and decentralized science with the coexistence of AI.

Currently, I'm focused on the theory and applications of GFlowNets to tackle more complex problems. My overall goal is to improve the reliability, efficiency, and reasoning capabilities of AI systems, particularly in scenarios that demand robust decision-making under uncertainty. For this goal, I am collaborating with Salem Lahlou and Saurav Prakash.

Application-wise, my current focuses are automated analog circuit design and semiconductor physics using tools such as GNNs, LLMs and Bayesian Optimization to tackle complex problems in the aforementioned domains. For this goal, I am collaborating with Hamidreza Aghasi and Rehan Kapadia.

Recent News

• Sep 2026 - New position: Postdoctoral Researcher at UCLA CS Department!
• April 2026 - I gave an invited talk titled "Federated Learning with Generative Models " at STAI Lab, Stanford University,
• Jan 2026 - I gave an invited talk titled "Three Modern Pillars of AI4Science with Graphs: Federation, Domain Knowledge, and Discovery " at California Institute of Technology CMS Department,
• Oct 2025 - Selected as a Top Reviewer at NeurIPS'25!,
• Sep 2025 - Our work, FALCON, has been accepted to NeurIPS'25!
• Sep 2025 - Officially, a Ph.D. candidate!
• May 2025 - FALCON, an end-to-end ML framework for analog circuit design (including topology selection, layout-aware parameter selection, and performance prediction) is out!
• February 2025 - Became a finalist at the 2025 Qualcomm Innovation Fellowship.
• February 2025 - Awarded with Travel Grant for the SIAM-SDM'25 conference, a top-tier conference in ML & data-mining..
• January 2025 - Became a semi-finalist at the 2025 Qualcomm Innovation Fellowship .
• December 2024 - FedGrAINS, first GFlowNet paper to improve subgraph federated learning has been accepted to the SIAM-SDM'25 conference. Preprint is available in this link.