Yue Zhao
Avatar of Yue Zhao
Assistant Professor
Thomas Lord Department of Computer Science

University of Southern California

Los Angeles, CA, USA

Lab Openings. We plan to recruit 1-2 Ph.D. students for Fall 2025. For undergraduate/graduate interns, it will be considered on a case basis. I personally do not want to have a large group of "interns" without enough support. See details at ASAP Lab (Openings).

Research Interests. My work focuses on creating robust, efficient, and automated machine learning (ML) and data mining (DM) algorithms, systems, and applications. My primary areas of interest are:

  1. Robustness and Security of AI: Enhancing the robustness and security of AI systems through out-of-distribution (OOD) detection, outlier detection, and anomaly detection.
  2. Efficient and Scalable AI: Developing efficient and scalable ML systems and automation techniques.
  3. Applications in Security, Finance, and Healthcare: Applying AI technologies to address complex problems in security, finance, and healthcare sectors.

Research Keywords: (1) Robustness and Security of AI: OOD Detection, Outlier Detection, Anomaly Detection (2) Efficient and Scalable AI: ML Systems (MLSys), Automated ML, Decentralized Learning (3) Applications: AI for Security, Finance, Healthcare.

Open-source ML . I created PyOD (used by NASA, Tesla, Morgan Stanley, and more) - the most popular library for anomaly detection in 2017. Also, I have led more than 10 ML open-source initiatives, receiving 20,000 GitHub stars (top 0.002%) and >20M downloads. Popular ones: PyOD, PyGOD, TDC, ADBench

Social Platforms. I am active on Twitter, LinkedIn, and 中文平台 知乎 (微调), 小红书 (微调). I have more than 250,000 followers on all social platforms in combination. 我有一系列北美在读CS PhD找实习和全职的微信群 (不是PhD申请群),以及一个2025年CS教职/教授申请群 (24年底申请,25年入职)。可以添加微信yzhao062(或者二维码)入群。

Biography. Dr. Yue Zhao is an Assistant Professor of Computer Science at the University of Southern California. His research primarily focuses on advancing machine learning (ML) and data mining in areas such as robustness and security of AI through anomaly detection, out-of-distribution (OOD) detection, and outlier detection, efficient and scalable AI with ML systems and automation, and applications in security, finance, and healthcare. He has contributed over 40 papers to leading venues. Dr. Zhao is recognized for his work in open-source ML systems, having created more than 10 projects with over 20,000 GitHub stars and 20 million downloads. His notable projects, including PyOD, PyGOD, TDC, and ADBench, are used in organizations like NASA and Morgan Stanley for high-stakes applications. He has received awards such as the AAAI New Faculty Highlights Awards, Google Cloud Research Innovators, Norton Fellowship, Meta AI4AI Research Award, and the CMU Presidential Fellowship. In his professional capacity, he serves as an associate editor of IEEE Transactions on Neural Networks and Learning Systems (TNNLS), an action editor of the Journal of Data-centric Machine Learning Research (DMLR), a workflow co-chair for KDD 2023, and an area chair for numerous ML conferences.

Copy/paste from here :)

✈ News and Travel

[Jun 2024] We have a new paper on multimodal OOD; see our Preprint and star our Code!

[May 2024] Have two papers accepted to ICML 2024 and one to KDD 2024 -- see publications for details.

[Apr 2024] My last piece of Ph.D. work, HPOD, will appear in AutoML Conference! Finally!

[Mar 2024] We get more than 5,000 GPU hours on A100 and equivalent from NSF and Google.

[Mar 2024] Selected to be a Google Cloud Research Innovators!

🏅 Awards and Grants