Yifan Liu
Photo by Yaokun Liu.

Yifan Liu 刘一帆

yifan40 [at] illinois [dot] edu

Hi! I'm a PhD student in Information Sciences supervised by Prof. Dong Wang at the University of Illinois Urbana-Champaign. Before that, I graduated with an M.S. in Computer Science from Georgia Institute of Technology and a BSc in Computer Science (Hons) from University College London. My research interests are:

  • Trustworthy and Responsible AI: model alignment and steering (safety, fairness, and privacy); alignment tax.
  • Personalization: user modeling and recommender systems.
  • Multimodality: modality fusion and alignment.

I am actively seeking U.S.-based research internship opportunities for Summer 2027 in areas related to agentic AI, AI safety, and trustworthy information retrieval.

News

  • A paper on generative recommendation and item tokenization has been accepted to the ACM RecSys 2026! 🎉
  • A paper on cross-module interference in agentic systems has been accepted to the Failure Modes in Agentic AI Workshop at ICML! 🎉
  • Two papers on generative recommendation and session-based recommendation accepted to SIGIR 2026! 🎉
  • Two papers on uncertainty estimation and image generation red-teaming accepted to theWebConf 2026!
  • Journal paper on reasoning-based uncertainty estimation accepted to Knowledge-Based System! 🎉
  • Paper on designing explanations for misinformation detection accepted to CSCW 2025! 🎉
  • Paper on unauthorized individual image generation protection accepted to ICCV 2025! 🎉
  • Paper on face component fairness accepted to ACM FAccT 2025! 🎉
  • Paper on multimodal interactive MoE for fake news detection accepted to ACM theWebConf 2025! See you in Sydney! 🎉
  • Released a new dataset for multidimensional media bias.
  • A paper on retrieval augmented fact verification is accepted to ACL Findings 2024!
  • Released a new dataset for multidimensional media bias.
  • Started my PhD study at UIUC!

Work Experience

  • IBM Research
    May. 2026 – Aug. 2026
    Research Intern
    Yorktown Heights, NY, USA
    Developing methods to attribute and explain actions in LLM-based agent systems, with a focus on safety and accountability.

Selected Publications

Query-Conditioned Agent Action Attribution with White-Box Proxies

Yifan Liu, Praveen Venkateswaran, Abdulhamid Adebayo, Dong Wang
AI Safety Preprint, under review 2026

Mitigating the Fairness Steering Tax via Adaptive Inference-time Subspace Intervention

Yifan Liu, Yaokun Liu, Ching-Yu Lin, Daniel Yue Zhang, Ruichen Yao, Zelin Li, Mano Paul, Rahul Gupta, Dong Wang
AI Safety Fairness Preprint, under review 2026

PropUQ-MAS: Propagation-Aware Uncertainty Quantification for LLM Multi-Agent Systems

Yaokun Liu*, Yifan Liu*, Daniel Yue Zhang, Zelin Li, Ruichen Yao, Dong Wang (* equal contribution)
AI Safety Preprint, under review 2026

Learning Decomposed Contextual Token Representations from Pretrained and Collaborative Signals for Generative Recommendation

Yifan Liu*, Yaokun Liu*, Zelin Li, Zhenrui Yue, Gyuseok Lee, Ruichen Yao, Yang Zhang, Dong Wang (* equal contribution)
RecSys SIGIR 2026
[Paper] [Code]

Reasoning-Based Uncertainty Estimation for Scalable Multidimensional Media Bias Annotation: A Benchmark Across Diverse Media Spaces

Yifan Liu, Aliya Maussymbayeva, Aslanbek Murzakhmetov, Alexandra Nemerenco, Yike Li, Dong Wang
Fairness KBS 2025 & ASONAM 2024
[Paper] [Code]

Modality Interactive Mixture-of-Experts for Fake News Detection

Yifan Liu, Yaokun Liu, Zelin Li, Ruichen Yao, Yang Zhang, Dong Wang
AI Safety Multimodality theWebConf 2025
[Paper] [Code]

Component-Based Fairness in Face Attribute Classification with Bayesian Network-informed Meta Learning

Yifan Liu, Ruichen Yao, Yaokun Liu, Ruohan Zong, Zelin Li, Yang Zhang, Dong Wang
Fairness FAccT 2025
[Paper] [Code]

Education

  • University of Illinois Urbana-Champaign
    Sep. 2023 – Present
    Ph.D. in Information Sciences
    Advisor: Prof. Dong Wang
  • Georgia Institute of Technology
    Sep. 2021 – May 2023
    M.S. in Computer Science
    Advisor: Prof. Harish Ravichandar
  • University College London
    Sep. 2017 – May 2019
    BSc in Computer Science
    Advisor: Prof. Mark Herbster

Teaching and Service

Teaching Assistant Fall 2023, Spring 2024, Fall 2024
University of Illinois Urbana-Champaign
  • IS 202: Social Aspects of Information Technology — Facilitated discussion sections and graded coursework.
  • IS 305: Programming for Information Problems — Graded programming assignments and provided feedback.
  • IS 597: Human-Centered Data Science — Designed assignments and delivered concept tutorials.
Reviewer: ACM Web Conference 2025; AAAI Conference on Artificial Intelligence 2026; ACM SIGIR Conference 2026; Conference on Language Modeling (COLM) 2026; IEEE Transactions on Big Data

My Cats 🐾

QiaoQiao
QiaoQiao
XiangXiang
XiangXiang
Qiao & Xiang
Qiao & Xiang
Qiao & Xiang
Qiao & Xiang