Curriculum Vitae
Yue Huang
A short record of education, experience, recognition, and service.
Education
Department of Computer Science & Engineering (CSE), College of Engineering
Ph.D. Student at MINE Lab, advised by Prof. Xiangliang Zhang.
2024 — Present
Notre Dame, IN
School of Cyber Science and Engineering
B.Eng. in Cybersecurity
Elite Student · Sichuan University Cyber Science
2020 — 2024
Chengdu, China
Experience
MIT-IBMWatson AI Lab
Research
Research Intern, mentored by Prasanna Sattigeri.
May 2025 — Aug. 2025
Cambridge, MA
Sep. 2023 — Jan. 2024
Beijing, China
Talks & Tutorials
Jan 2026Tutorial
Towards Trustworthy and Socially Responsible Generative Foundation Models
Dec 2025Tutorial
Science of Trustworthy Generative Foundation Models
Nov 2025Tutorial
Responsible Generative Foundation Models — From Principles to Real-World Impact
Nov 2025Tutorial
Generative Models for Synthetic Data — Transforming Data Mining in the GenAI Era
Nov 2025Tutorial
Socially Responsible and Trustworthy Generative Foundation Models
May 2025Talk
Toward Socially Impactful and Trustworthy Generative Foundation Models
@ NLP Seminar, University of Illinois Urbana-Champaign · Host: Heng Ji & Chi Han
Apr 2025Talk
On the Trustworthiness of Generative Foundation Models
Mar 2025Guest Lecture
Trustworthiness in Large Language Models
@ University of Virginia · Instructor: Chirag Agarwal
Feb 2025Guest Lecture
Toward Socially Impactful and Trustworthy Generative Foundation Models
@ University of Southern California · Instructor: Jieyu Zhao
Jul 2024Talk
Bias of Large Language Models
Feb 2024Talk
Trustworthiness in Large Language Models
Honors & Awards
Jun 2026
KDD 2026 Student Travel Grant
Mar 2026
CHI 2026 Honourable Mention Award
Dec 2025
Tinker Research Grant
Nov 2025
Jetstream2 NAIRR AI Fellow
Aug 2025
NSF Discover ACCESS Project
Aug 2025
NSF POSE Training Award (Industry Mentor)
Jul 2025
Best Paper Award · SciSocLLM @ KDD 2025
Jul 2025
Best Paper Award · DIG-BUG @ ICML 2025
Jan 2025
KAUST AI Rising Star
Jul 2024
OpenAI Researcher Access Program
Jun 2024
Elite Student · Sichuan University Cyber Science
Jan 2024
Microsoft Accelerate Foundation Models Research
Recognition & Impact
Government & Policy
U.S. Department of Homeland Security
TrustLLM highlighted in this report.
International AI Safety Report
International Scientific Report on the Safety of Advanced AI
Our Sora review included in the Interim Report (May 2024), the precursor of the International AI Safety Report.
U.S. DoD CDAO Responsible AI Toolkit
TrustLLM listed in the official toolkit.
NIST AI 100-2e2025
TrustLLM featured in Section 3.6 of the official report.
FLI AI Safety Index
TrustLLM adopted as an official benchmark across all three editions: 2024, Summer 2025, Winter 2025.
German Federal Office for Information Security (BSI)
Our prompt-injection attack on LLM-as-a-Judge (JudgeDeceiver) included in the official guide Evasion Attacks on LLMs – Countermeasures in Practice (2025).
Japan Science and Technology Agency (JST)
Center for Democracy & Technology
Cited Prioritization First, Principles Second to define "helpful" AI in Anti-Woke AI is a Technical Mirage (2025).
Industry & National Labs
Salesforce · G7 Hiroshima AI Process Report
Adopted TrustLLM's trust & safety metrics (bias, privacy, robustness, etc.) to evaluate its AI models in its official G7 HAIP Transparency Report on the OECD.AI platform.
Lawrence Livermore National Laboratory
Profiled TrustLLM in Evaluating trust and safety of large language models.
Oak Ridge National Laboratory
Built a scalable workflow for evaluating LLM trustworthiness on TrustLLM in a technical report (2024).
U.S. National Laboratories
TrustLLM included in the joint LLNL, PNNL, Sandia and Argonne report Safety in Artificial Intelligence: Challenges and Opportunities for the U.S. National Labs and Beyond (2024).
Academia & Publications
Springer Textbook
TrustLLM received chapter-length treatment in Introduction to Foundation Models (2025, Ch. 12).
Hoover Institution
Featured TrustGen in their Technology Policy Accelerator.
Notre Dame–IBM Technology Ethics Lab
Selected TrustGen as a Collaborative Project; highlighted Justice or Prejudice? with an official feature and a tutorial video.
Paper Digest
TrustLLM ranked #17 among the most influential arXiv cs.CL papers of 2024 (Oct 2024 list); JudgeDeceiver ranked #20 among cs.CR papers of 2024 (Apr 2026 list).
In the News
Science
Reported on lab safety risks research in Leading AI models miss dangerous lab risks.
New Scientist
Lab Manager · Tech Xplore · Muy Interesante
ITmedia AI+ · Ledge.ai · MoguLive
Japanese coverage of My Favorite Streamer is an LLM (CHI 2026) in ITmedia AI+, Ledge.ai and MoguLive.
Service
Workshop Organizer
NeurIPS 2025 Workshop on Socially Responsible and Trustworthy Foundation Models (ResponsibleFM)
KDD 2026 Workshop on Reliable Scientific Foundation Models (RelSciFM)
Journal Reviewer
Nature Communications, IEEE TAI, IEEE TDSC, IEEE TPAMI, IEEE/ACM TASLP, ACM TIST.
Conference Reviewer
NeurIPS, ICLR, ICML, AAAI, KDD, ICDM, WWW, COLM, ACL Rolling Review, EMNLP / NAACL / ACL Demo Tracks.
Technical Committee
2024 IEEE Computer Society North America Student Challenge.
Acknowledgment
My research is supported and recognized by partners and sponsors I deeply appreciate.
Personal
- Spent 18 years in Fujian and four wonderful years in Sichuan (I can handle spicy food).
- I enjoy exchanging ideas across fields — it helps me see the world more broadly.
- Favorite singers: Eason Chan, Steve Chou; lately also Patti Tsai.
- Favorite sports: swimming and badminton; I also enjoy capturing scenic moments with my camera.
- Deeply grateful to those who have helped me along the way.