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

University of Southern California

Los Angeles, CA, USA
Email:
Google Scholar | Short Bio | GitHub | Twitter | LinkedIn | 知乎 (微调) | 小红书 | 微信

Collaboration with Me. I am open to external opportunities for invited talks, research collaborations, and employment (on the part-time/advising/visiting basis). Let us have a chat via email. I frequently visit major cities, e.g., Seattle, NYC, Chicago, Boston, and Bay Area to meet people and give talks.

Lab Openings and Other Opportunities. We will recruit 2-3 Ph.D. students for Fall 2025 (1 top ML or System conference is required for consideration). For undergraduate/graduate interns, it will be considered case by case. See details at RESAIL Lab. Also, I prepared a list for 100+ Ph.D. opportunities; see details. My friend Prof. Shaohua Li at CUHK also build a fantastic Ph.D. opportunity website DuoOffer to actively update openings. Why are we doing this? It is important to help you find the best match :)

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

  1. Robust and Trustworthy of AI: Enhancing AI systems through out-of-distribution (OOD) detection, outlier detection (OD), and anomaly detection.
  2. Efficient and Automated AI: Developing efficient and automated ML systems with limited human supervision.
  3. AI Applications: Applying AI technologies to address complex problems in security, finance, and healthcare sectors.
  4. Foundation models and generative AI for OD/OOD: How do these emerging directions benefit OOD detection and anomaly detection, and vice versa.

Research Keywords: (1) Robust and Trustworthy of AI: OOD Detection, Outlier Detection, Anomaly Detection (2) Efficient and Automated AI: ML Systems (MLSys), Automated ML, Decentralized Learning (3) AI Applications: AI for Security, Finance, Healthcare (4) Foundation models and generative AI for OD/OOD: LLMs for anomaly and OOD detection.

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 >22M 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.

Copy/paste from here :)

✈ News and Travel

[Sep 2024] We have a new paper on AI + Digital Twin; see our Preprint!

[Sep 2024] We have a new paper on GKAN: Graph Kolmogorov-Arnold Networks; see our Preprint!

[Aug 2024] Received Amazon Research Awards with Prof. Kaize Ding on graph anomaly detection!

[Aug 2024] MetaOOD is selected as the best paper for KDD Resource-Efficient Learning Workshop!

[Aug 2024] Get NSF support via NSF ATD!

[Aug 2024] Panelist for KDD workshops on Resource-Efficient Learning for Knowledge Discovery and Smart Data for Blockchain and Distributed Ledger.

🏅 Awards and Grants