Yue Zhao
Avatar of Yue Zhao
Assistant Professor
Thomas Lord Department of Computer Science
School of Advanced Computing

University of Southern California

Los Angeles, CA, USA
Email:

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

Research Interests: My work is organized around three complementary areas that represent different levels of ML:

  1. Robust and Trustworthy AI Methods: I develop detection algorithms for outliers, anomalies, and out-of-distribution data with a focus on unsupervised model selection and evaluating system trustworthiness. These methods establish the core techniques for reliable AI.
    Keywords: Outlier Detection, Anomaly Detection, OOD Detection, AI Trustworthiness
  2. LLM and Generative AI Applications: I apply large models and generative techniques to solve challenges in areas such as political forecasting and drug discovery, effectively translating core methods into real-world solutions.
    Keywords: LLMs, Generative Models, Political Forecasting, Drug Discovery
  3. Scalable, Automated, and Open-source ML Systems: I build efficient libraries and frameworks for distributed inference, federated learning, and automated hyperparameter tuning, enabling reproducible, large-scale deployment of AI solutions. As the creator of PyOD (25M+ downloads, used by NASA, Tesla, etc.), I lead 10+ open-source projects, including PyGOD, TDC, and ADBench, which collectively have earned more than 20,000 GitHub stars.
    Keywords: Automated ML, Distributed Inference, Federated Learning, Graph Learning, Open-source AI, Scalability

Biography.

Lab Openings. We are warmly welcoming new members to the FORTIS Lab!

Ph.D. Students (1 Ph.D. student for Fall 2026):
  • Due to the large number of interested candidates, future Ph.D. students are ideally have prior collaboration with me + a few published papers (not necessarily with me) in top-tier ML, System, CV, or NLP conferences/journals.
Research Interns (Any Time, All Year Round):
  • We welcome both undergraduate and graduate interns from USC and other institutions.
  • Preferred candidates are located in North America for time zone compatibility.
Application Process: To apply for either opportunities, complete the Application Form, email me after submitting the form, and review the FORTIS Lab website for more information before reaching out.

✈ News and Travel

[Jan 2025] We have a new paper, MetaOOD: Automatic Selection of OOD Detection Models, accepted to ICLR 2025 and the KDD Workshop on Resource-Efficient Learning for Knowledge Discovery (Best Paper Award); see our Preprint!

[Jan 2025] We have a new paper, PyOD 2: A Python Library for Outlier Detection with LLM-powered Model Selection, accepted to The Web Conference 2025 Demo Track; see our Preprint!

[Dec 2024] We have a new paper evaluating how LLMs can help with anomaly detection (AD-LLM); see our Preprint!

[Dec 2024] We have a new paper on integrating LLMs into political science (Political-LLM); see our Preprint!

[Dec 2024] We have a new paper on Personalized Multimodal Large Language Models (MLLMs) providing a survey on personalization techniques, evaluation metrics, and benchmarks for these models, with many collaborators. Preprint.

[Dec 2024] We have a new paper introducing a comprehensive benchmark for NLP anomaly detection (NLP-ADBench); see our Preprint!

[Dec 2024] We have a new paper on personalized hierarchical federated learning for IoT (H-FedSN); see our Preprint!

[Dec 2024] We have a new paper on automating AI-aided drug discovery programming through LLM multi-agent collaboration; see our Preprint!

[Nov 2024] We have a new paper on concept-based zero-shot OOD detection; see our Preprint!

[Nov 2024] We have a new paper on personal biometric defense against malicious generative editing; see our Preprint!

[Nov 2024] We have a new paper on dynamic prototype updating for multimodal out-of-distribution detection; see our Preprint!

[Nov 2024] We have a new paper on data augmentation for anomaly detection accepted to IEEE TNNLS; see our Preprint!

🏅 Awards and Grants

As Principal Investigator (August 2023 onwards)
Prior to Principal Investigator Role (Before August 2023)