Yan Han （韩焱）

Senior Applied Scientist @ Microsoft

Ph.D., Electrical and Computer Engineering, UT Austin

[Experience] [Publications] [Teaching] [Misc]

反者道之动；弱者道之用。天下万物生于有，有生于无。

About Me

I am a Senior Applied Scientist at Microsoft, working on agentic LLM systems, evaluation frameworks, and inference pipelines for knowledge-intensive applications.

I obtained my Ph.D. from the Department of Electrical and Computer Engineering at The University of Texas at Austin in 2023, advised by Prof. Atlas Wang, Prof. Ying Ding, and Prof. Ahmed Tewfik. I received my B.Eng. from Shanghai Jiao Tong University in 2017.

My research spans Large Language Models, Agentic AI, Retrieval-Augmented Generation, and Graph Neural Networks, with a focus on reliability, epistemic integrity, and scalable inference.

Experience

Senior Applied Scientist — Microsoft, Mar. 2026 – Present
Mountain View, CA

Applied Scientist — Amazon, Jun. 2024 – Mar. 2026
Palo Alto, CA

Machine Learning Engineer — LinkedIn, Aug. 2022 – Jun. 2024
Mountain View, CA

Applied Scientist Intern — Amazon, Feb. 2022 – Aug. 2022
Mentors: Dr. Karthik Subbian, Dr. Atlas Wang, Dr. Eddie Huang

Machine Learning Engineer Intern — LinkedIn, May. 2021 – Dec. 2021
Mentors: Dr. Qi He, Dr. Jaewon Yang, Dr. Baoxu Shi, Dr. Ji Yan

Research Intern — AbbVie, Feb. 2021 – May. 2021
Mentor: Dr. Abhik Seal

Publications

Extracting and Understanding the Superficial Knowledge in Alignment
Runjin Chen, Gabriel Jacob Perin, Xuxi Chen, Xilun Chen, Yan Han, Nina S. T. Hirata, Junyuan Hong, Bhavya Kailkhura
Annual Conference of the Nations of the Americas Chapter of the ACL (NAACL), 2025

Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models
Yingqian Cui, Pengfei He, Jingying Zeng, Hui Liu, Xianfeng Tang, Zhenwei Dai, Yan Han, Chen Luo, Jing Huang, Zhen Li, Suhang Wang, Yue Xing, Jiliang Tang, Qi He
Findings of ACL 2025 (Long Paper)

Turning A Curse into A Blessing: Data-Aware Memory-Efficient Training of Graph Neural Networks by Dynamic Exiting
Yan Han, Kaiqi Chen, Shan Li, Ji Yan, Baoxu Shi, Lei Zhang, Fei Chen, Jaewon Yang, Yunpeng Xu, Xiaoqiang Luo, Qi He, Ying Ding, Zhangyang Wang
Companion Proceedings of the ACM Web Conference 2024 (WWW)

Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling
Haotao Wang, Ziyu Jiang, Yuning You, Yan Han, Gaowen Liu, Jayanth Srinivasa, Ramana Rao Kompella, Zhangyang Wang
Conference on Neural Information Processing Systems (NeurIPS), 2023

Vision HGNN: An Image is More than a Graph of Nodes
Yan Han, Peihao Wang, Souvik Kundu, Ying Ding, Zhangyang Wang
IEEE International Conference on Computer Vision (ICCV), 2023 Oral

Graph Contrastive Learning: An Odyssey towards Generalizable, Scalable and Principled Representation Learning on Graphs
Yan Han, Yuning You, Wenqing Zheng, Scott Hoang, Tianxin Wei, Majdi Hassan, Tianlong Chen, Ying Ding, Yang Shen, Zhangyang Wang
IEEE Data Engineering Bulletin, Vol.47 No.2 June 2023

PINAT: A Permutation INvariance Augmented Transformer for NAS Predictor
Shun Lu, Yu Hu, Peihao Wang, Yan Han, Jianchao Tan, Jixiang Li, Sen Yang, Ji Liu
AAAI Conference on Artificial Intelligence (AAAI), 2023

Search Behavior Prediction: A Hypergraph Perspective
Yan Han, Eddie Huang, Wenqing Zheng, Nikhil Rao, Zhangyang Wang, Karthik Subbian
ACM International Conference on Web Search and Data Mining (WSDM), 2023

Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays
Yan Han, Gregory Holste, Ying Ding, Ahmed Tewfik, Yifan Peng, Zhangyang Wang
IEEE Transactions on Medical Imaging (TMI), 2022

Knowledge-Augmented Contrastive Learning for Abnormality Classification and Localization in Chest X-rays with Radiomics using a Feedback Loop
Yan Han, Chongyan Chen, Ahmed Tewfik, Benjamin Glicksberg, Ying Ding, Yifan Peng, Zhangyang Wang
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022

SCALP - Supervised Contrastive Learning for Cardiopulmonary Disease Classification and Localization in Chest X-rays using Patient Metadata
Ajay Jaiswal, Tianhao Li, Cyprian Zander, Yan Han, Justin F. Rousseau, Yifan Peng, Ying Ding
IEEE International Conference on Data Mining (ICDM), 2021

Using Radiomics as Prior Knowledge for Thorax Disease Classification and Localization in Chest X-rays
Yan Han, Chongyan Chen, Liyan Tang, Mingquan Lin, Ajay Jaiswal, Song Wang, Ahmed Tewfik, George Shih, Ying Ding, Yifan Peng
AMIA Annual Symposium Proceedings (AMIA), 2021

Pneumonia Detection on Chest X-ray using Radiomic Features and Contrastive Learning
Yan Han, Chongyan Chen, Ahmed H Tewfik, Ying Ding, Yifan Peng
The IEEE International Symposium on Biomedical Imaging (IEEE ISBI), 2021

Robust End-to-End Speaker Verification Using EEG
Yan Han, Gautam Krishna, Co Tran, Mason Carnahan, Ahmed H Tewfik
European Signal Processing Conference (EUSIPCO), 2020

Generating EEG features from Acoustic features
Gautam Krishna, Co Tran, Yan Han, Mason Carnahan, Ahmed H Tewfik
European Signal Processing Conference (EUSIPCO), 2020

Speech Synthesis using EEG
Gautam Krishna, Co Tran, Yan Han, Mason Carnahan, Ahmed H Tewfik
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020

Fault Clustering Technique for 3D Memory BISR
Tianjian Li, Yan Han, Xiaoyao Liang, Hsien-Hsin S.Lee, Li Jiang
Proceedings of the Conference on Design, Automation & Test in Europe (DATE), 2017

Teaching Experience

EE312: Software Design and Implementation — Teaching Assistant, UT-Austin, Summer 2020

EE385V: Brain Computer Interaction — Teaching Assistant, UT-Austin, Spring 2020

EE371R: Digital Image/Video Process — Teaching Assistant, UT-Austin, Fall 2019

EE381J: Probability and Random Process — Teaching Assistant, UT-Austin, Spring 2019

Miscellaneous

Hobbies: Guitar, PC Games.

Fun Fact: I co-own a cattery in the Bay Area. You can visit us at BestBritishCats.com.