Yingqiang Ge

Yingqiang Ge

Ph.D. in Machine Learning

Yingqiang Ge (葛英强)

About Me

I’m Yingqiang Ge, an Applied Scientist at Amazon. I got my Ph.D. from Rutgers University (2023, advised by Prof. Yongfeng Zhang), where I worked on Trustworthy AI, fairness, and explainability in recommender systems.

During my PhD, I published extensively on fairness-aware recommendation, causal reasoning, and explainable AI at top venues including SIGIR, WSDM, WWW, ACL, and NeurIPS. I also co-created OpenAGI, an open-source research platform for LLM-based agents, and contributed to P5, one of the early works on unifying recommendation as language processing.

My personal research interest is Agentic Safety — making sure autonomous AI agents act reliably and safely in the real world. As agents move from answering questions to taking actions — executing code, calling APIs, managing infrastructure — the safety challenges are fundamentally different from traditional AI. I build open-source systems like AIOS (an LLM agent operating system, published at COLM 2025) and GuardClaw (a real-time safety interception framework), exploring how to give AI agents more autonomy without losing human control.

News

  • 2025-07-01 Our paper “AIOS: LLM Agent Operating System” has been accepted by COLM 2025.
  • 2025-03-01 Our survey “Causal Inference for Recommendation” has been accepted for publication in ACM Transactions on Intelligent Systems and Technology (ACM TIST).
  • 2025-01-15 Our survey on Trustworthy Recommender Systems has been published in ACM Transactions on Recommender Systems (ACM TORS).
  • 2024-07-14 Our paper “IDGenRec: LLM-RecSys Alignment with Textual ID Learning” accepted by SIGIR 2024.
  • 2024-03-20 Our paper “GenRec: Large Language Model for Generative Recommendation” accepted by ECIR 2024.
  • 2024-02-19 Our survey on Trustworthy Recommender Systems has been accepted for publication in ACM Transactions on Recommender Systems.
  • 2023-12-11 Started a new position as Applied Scientist at Amazon.
  • 2023-10-24 Received NeurIPS 2023 Scholar Award.
  • 2023-10-19 Gave a guest lecture for CS 483 (Big Data Mining), Department of Computer Science, UIC.
  • 2023-10-17 Successfully defended my PhD degree on the topic of “Towards Trustworthy Recommender Systems” and proudly hold the title of Dr.!
  • 2023-09-22 Our research framework for LLM-based Agents, OpenAGI accepted by NeurIPS’23, Datasets and Benchmarks.
  • 2023-08-04 Our research on “Logistics Audience Expansion” accepted by CIKM’23.
  • 2023-07-17 Our survey on “Fairness in Recommendation” accepted by ACM TIST’23.
  • 2023-07-15 Our research on “User-Controllable Recommendation” accepted by ECAI’23
  • 2023-05-16 Gave a presentation “When LLMs Meet Domain Experts” at NEC Laboratories America.
  • 2022-12-02 Gave a presentation “Towards Fairer Recommender Systems through Deep Reinforcement Learning” at the Institute of Computing Technology, Chinese Academy of Sciences.
  • 2022-10-18 Our research on “Counterfactual Data Augmentation” accepted by WSDM’23.
  • 2022-06-28 Our research on “Federated Fairness” and “P5” accepted by RecSyc’22.
  • 2022-06-09 Gave a talk on “Fairness in Recommender System” in Amazon.
  • 2022-05-24 Successfully passed my PhD Qualifying Exam!
  • 2022-04-26 Received SIGIR 2022 Student Travel Grant.
  • 2022-03-25 Our research on “Explainable Fairness” and “AutoLoss” are accepted by SIGIR 2022.
  • 2022-03-09 Our research on “Fairness Evaluation” has been accepted for publication in the Journal of the Association for Information Science and Technology (JASIST).
  • 2022-02-24 Our research on “Explainable Recommendation through Visualization” has been accepted to appear at the ACL 2022 Main conference.
  • 2022-01-13 Our research on “Explainable Recommendation over Knowledge Graphs”, “Explainable GNN” are accepted as long papers on the Web Conference 2022.
  • 2021-12-27 Received ACM WSDM’22 Student Travel Awards.
  • 2021-10-11 Our research on “Pareto Efficient Fairness-Utility Trade-off” has been accepted as full paper by WSDM 2022.
  • 2021-08-09 Our proposal “Fairness of Machine Learning in Recommender Systems” has been accepted for presentation as a tutorial at the CIKM 2021.
  • 2021-08-08 Our research on “Counterfactual explainable recommendation” has been accepted by CIKM 2021.
  • 2021-04-27 Our proposal “Fairness of Machine Learning in Recommender Systems” has been accepted for presentation as a tutorial at the SIGIR 2021.
  • 2021-04-14 Our research on “Personalized Fairness” is accepted by SIGIR 2021.
  • 2021-01-17 Received SIGIR Student Travel Grant.
  • 2021-01-16 Papers on “Fairness”, “Generative Recommendation”, “Knowledge Graph Embedding” accepted to WWW 2021.
  • 2020-10-16 Our research on “Long-term Fairness” is accepted as a full paper to the WSDM 2021 conference.
  • 2020-08-10 Our research on “Neural Symbolic Reasoning for Explainable Recommendation” is accepted by the CIKM 2020 conference.
  • 2020-06-20 Our research on “Risk-aware Recommendation”, “Fairness-aware Recommendation”, and “Echo Chamber Analysis” are accepted as long papers on the SIGIR 2020.
  • 2019-01-20 Our recent research on bridging machine learning and economic principles for economic analysis of web-based systems is accepted by the Web Conference 2019 (WWW 2019).