I am an Assistant Professor in the Computer Science and Engineering Department at Oakland University. My research mainly focuses on Natural Language Processing (NLP), Large Language Models (LLMs), Trustworthy Artificial Intelligence (AI), and Machine Learning Theory and Applications. My dedication to these areas has led to the publication of numerous research papers at top AI conferences, including NeurIPS, IJCAI, AAAI, ICML, EACL, MICCAI, and IJCNN, among others. I have a strong passion for research and a demonstrated ability to apply my knowledge to real-world challenges.

I am looking for self-motivated Master’s/Ph.D. students to join my group for Winter/Fall 2025. If you are interested in Trustworthy AI, NLP, LLMs, and Generative AI, please feel free to email me with your CV.

🔥 News

  • 2024.09:  ✨ New preprint on LLM Application is available at arxiv.
  • 2024.09:  💼 I gave a talk titled “Designing for Reliability: Fairness and Interpretability Aware Vision Transformer” at the CS Department Graduate Seminar of Wayne State University. Many thanks to Dr. Nathan Fisher for the kind invitation.
  • 2024.08:  💼 I start working at OU this August.
  • 2024.07:  🎉 1 Paper accepted by ECCV 2024.
  • 2024.07:  🎉 I have successfully pass my Ph.D dissertation.
  • 2024.04:  💼 I will be joining the CSE Department of SECS at Oakland University as a Tenure-track Assistant Professor in Fall 2024.
  • 2024.04:  💼 I deliver a presentation on Trustworthy AI for the AI Reading Group Seminar at UNC Charlote.
  • 2024.02:  ✨ New preprint on LLM Safety is available at arxiv.
  • 2024.01:  🎉 1 Paper accepted by EACL 2024.
  • 2024.01:  🎉 1 Paper accepted by ACM The Web Conference 2024.
  • 2023.12:  ✨ I passed the exam of the prospectus of my Ph.D dissertation.
  • 2023.11:  ✨ New preprint on LLM Safety is available at arxiv.
  • 2023.09:  ✨ New preprint on Trustworthy AI is available at arxiv.
  • 2023.08:  ✨ New preprint on Trustworthy AI is available at arxiv.
  • 2023.06:  🎉 1 Paper accepted by MICCAI 2023.
  • 2023.05:  🎖 I won the Michael E. Conrad Award in the academic year 2022-2023 (only 1 awardee among graduates in Department of Computer Science, Wayne State University).
  • 2023.05:  💼 I started my Applied Scientist Internship at Amazon, working on LLM Safety.
  • 2023.04:  🎉 1 Paper accepted by IJCA 2023.
  • 2023.02:  🚁 I attended AAAI 2023 at Washington D.c. and illustrated our paper poster.
  • 2022.11:  🚁 I attended NeurIPS 2022 at New Orleans and illustrated our paper poster.
  • 2022.12:  🎖 I won the AAAI-23 Student Scholarship.
  • 2022.11:  🎉 1 Paper accepted by AAAI 2023.
  • 2022.12:  🎖 I won the NeurIPS 2022 Scholar Award.
  • 2022.09:  🎉 1 Paper accepted by NeurIPS 2023.
  • 2022.07:  🚁 I attended IJCAI 2022 at Vienna, Austria and presented our paper.
  • 2022.07:  🚁 I attended IJCNN 2022 at Padua, Italy and presented our paper.
  • 2022.05:  🎖 I won the Department Travel Award for Outstanding Conference Publications.
  • 2022.05:  🎖 I won the Graduate Student Professional Travel Award.
  • 2022.05:  🎖 I won the IEEE CIS Conference Participation and Travel Grants.
  • 2022.05:  🎖 I won the IJCAI 2022 Travel and Accessibility Grant.
  • 2022.04:  🎉 1 Paper accepted by IJCA 2022.
  • 2020.04:  🎖 I won the Department Oustanding GTA Award in the academic year 2019-2020.
  • 2019.06:  🎖 I won the Graduate School Master’s Scholarship Award.

📝 Publications

Full publications here

Fairness-aware Vision Transformer via Debiased Self-Attention (ECCV 2024)

Yao Qiang, Chengyin Li, Prashant Khanduri, and Dongxiao Zhu

Prompt Perturbation Consistency Learning (PPCL) for Robust Language Models (EACL 2024)

Yao Qiang, Subhrangshu Nandi, Ninareh Mehrabi, Greg Ver Steeg, Anoop Kumar, Anna Rumshisky, and Aram Galstyan

Attcat: Explaining transformers via attentive class activation tokens (NeurIPS 2022)

Yao Qiang, Deng Pan, Chengyin Li, Xin Li, Rhongho Jang, and Dongxiao Zhu

Counterfactual interpolation augmentation (CIA): A unified approach to enhance fairness and explainability of DNN (IJCAI 2022)

Yao Qiang, Chengyin Li, Marco Brocanelli, and Dongxiao Zhu

Learning to Poison Large Language Models During Instruction Tuning (Pre-print)

Yao Qiang, Xiangyu Zhou, Saleh Zare Zade, Mohammad Amin Roshani, Douglas Zytko, Dongxiao Zhu

Hijacking Large Language Models via Adversarial In-Context Learning (Pre-print)

Yao Qiang, Xiangyu Zhou, and Dongxiao Zhu

Tiny rnn model with certified robustness for text classification (IJCNN 2022)

Yao Qiang, Supriya Tumkur Suresh Kumar, Marco Brocanelli, and Dongxiao Zhu

Toward tag-free aspect based sentiment analysis: A multiple attention network approach (IJCNN 2020)

Yao Qiang, Xin Li, and Dongxiao Zhu

Benchmark and Neural Architecture for Conversational Entity Retrieval from a Knowledge Graph (The Web Conference 2024)

Mona Zamiri, Yao Qiang, Fedor Nikolaev, Dongxiao Zhu, Alexander Kotov

Learning compact features via in-training representation alignment (AAAI 2023)

Xin Li, Xiangrui Li, Deng Pan, Yao Qiang, and Dongxiao Zhuu

Negative Flux Aggregation to Estimate Feature Attributions (IJCAI 2023)

Xin Li, Deng Pan, Chengyin Li, Yao Qiang, and Dongxiao Zhu

FocalUNETR: A Focal Transformer for Boundary-Aware Prostate Segmentation Using CT Images (MICCAI 2022)

Chengyin Li, Yao Qiang, Rafi Ibn Sultan, Hassan Bagher-Ebadian, Prashant Khanduri, Indrin J. Chetty, and Dongxiao Zhu

📖 Educations

  • 2019.09 - 2024.06, Doctor of Philosophy in Computer Science, Wayne State University
  • 2018.09 - 2019.12, Master of Science in Computer Science, Wayne State University
  • 2006.09 - 2010.07, Bachelor of Science in Computer Science, Wayne State University

💻 Experience

  • 2024.08- Present, Assistant Professor, CSE, Oakland University
  • 2019.09 - 2024.06, Graduate Research Assistant, Trustworthy AI Lab, Wayne State University
  • 2023.05 - 2023.08, Applied Scientist Intern, Trustworthy AI Lab, Robust and Modeling Team, Alexa, Amazon
  • 2018.08 - 2019.08, Student Research Assistant, Part-time, Mike Ilitch School of Business, Wayne State University
  • 2010.08 - 2017.12, Computer Hardware Designer, Xi’an Microelectronics Technology Institute

📃 Teaching

  • 2024 - 2025, Lecturer for CSI 4100/5100 Ethics and Bias in AI
  • 2020 - 2023, Invited Lecturer for CSC 5825 Machine Learning&Apps (Graduate Level)
  • 2020 - 2022, Invited Lecturer for CSC 7825 Machine Learning (Graduate Level)
  • 2021, Instructor for CSC 3101 Computer Architecture and Organization: Lab
  • 2020, Instructor for CSC 2111 Computer Science: Lab
  • 2020 - 2022, Teaching Assistant for CSC 2111 Computer Science, CSC 3101 Computer Architecture and Organization, CSC 5825 Machine Learning&Apps (Graduate Level), Design and Analysis of Algorithms (Graduate Level), CSC 7825 Machine Learning (Graduate Level)

💼 Academic Service

  • Program Committee Member: SDM 2023, KDD 2023, AAAI 2022-2023, ICML 2022-2024, CIKM 2024
  • Journal Reviewer: TKDD 2023, AI 2022, TIOT 2021
  • Conference Reviewer: SDM 2023, KDD 2023-2024, CVPR 2023, AAAI 2020-2023, NeurIPS 2020-2024, ICLR 2022-2023, IJCAI 2021-2024, MICCAI 2022-2023, ICML 2022-2024, ACL 2024
  • Conference Student Volunteering, AAAI 2023, NeurIPS 2022, IJCAI 2022, IJCNN 2022

🎖 Honors and Awards

  • Michael E. Conrad Award (Highest Honor at WSU CS Department), 2023
  • AAAI 2023 Student Scholarship, 2022
  • NeurIPS 2022 Scholar Award, 2022
  • Department Travel Award for Outstanding Conference Publications, 2022
  • Graduate Student Professional Travel Award, 2022
  • IEEE CIS Conference Participation and Travel Grants, 2022
  • IJCAI 2022 Travel and Accessibility Grant, 2022
  • Department Oustanding GTA Award, 2020
  • Graduate School Master’s Scholarship Award, 2019

💼 CV

🔗 Links