Jiaying Wu | National University of Singapore

Welcome to Jiaying’s Homepage!

I am a Postdoctoral Research Fellow at National University of Singapore (NUS), working with Prof. Min-Yen Kan as a member of the NUS Web IR / NLP Group (WING) and the NUS Centre for Trusted Internet and Community (CTIC).

I received my Ph.D. in Computer Science from NUS in 2024, where I was advised by Prof. Bryan Hooi.

Research Interests

My research lies at the intersection of NLP and data mining, where I design socially intelligent agentic systems for safe and reliable decision-making in complex information ecosystems. My agenda is organized around three core objectives:

Guard: Securing information ecosystems against harm and manipulation through socially-aware detection and governance frameworks. (e.g., CrowdNotes+, DeceptionDecoded, IMOL, SheepDog, DECOR)
Discover: Automating evidence-grounded knowledge synthesis and communication via agentic retrieval and reasoning systems. (e.g., XtraGPT, MLR-Agent, CCSBench)
Converse: Advancing pluralistic, uncertainty-aware reasoning frameworks for navigating disagreement, epistemic ambiguity, and competing values. (e.g., ConfTuner, JudgeLRM, ProCal)

I am currently on the job market, seeking research opportunities in both academia and industry (including postdoc positions) starting Summer/Fall 2026, and always open to collaborations. Feel free to get in touch by email.

News

[May 2026] One paper accepted to IEEE T-PAMI.
[May 2026] One paper accepted to KDD 2026.
[May 2026] Recognized as a Gold Reviewer for ICML 2026.
[Apr. 2026] Six papers accepted to ACL 2026 (including one Oral).
[Mar. 2026] Invited to serve as Area Chair for NeurIPS 2026 and CIKM 2026.
[Jan. 2026] One paper accepted to ICLR 2026.
[Jan. 2026] One paper accepted to WWW 2026.
[Nov. 2025] Two papers accepted to AAAI 2026 (including one Oral).
[Sep. 2025] Featured in NUS CTIC's September 2025 Newsletter.
[Sep. 2025] Three papers accepted to NeurIPS 2025.
[Aug. 2025] One paper accepted to CIKM 2025.
[Jul. 2025] One paper accepted to ACM MM 2025.
[May 2025] Two papers accepted to ACL 2025 (including one Oral).
[May 2025] Invited to serve as Area Chair for CIKM 2025.
[Jan. 2025] Co-organizing the ICLR 2025 Workshop on Reasoning and Planning for Large Language Models. Submissions are welcome!
[Nov. 2024] Celebrating success of SSNLP 2024! See our event highlights, including the photo album. Looking forward to seeing everyone again at SSNLP 2025 :)
[Oct. 2024] Serving as General Chair for the 2024 Singapore Symposium on Natural Language Processing (SSNLP 2024). Stay tuned for more exciting updates!

Selected Publications / Preprints

Please see my Google Scholar for a full, up-to-date list.
( ^* Equal Contribution, ^{^} Mentorship)

arXiv

Better with Experience: Self-Evolving LLM Agents for Evidence-Grounded Health Community Notes

Zihang Fu^{^}, Fanxiao Li, Jianyang Gu, Haonan Wang, Preslav Nakov, Bryan Hooi, Min-Yen Kan, Jiaying Wu

arXiv preprint 2026

PDF

arXiv

The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation

Herun Wan^{^}, Jiaying Wu, Minnan Luo, Fanxiao Li, Ningnan Wang, Nancy F. Chen, Min-Yen Kan

arXiv preprint 2026

PDF Code

arXiv

FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems

Fanxiao Li^{^}, Jiaying Wu, Tingchao Fu, Natasha Jaques, Wei Zhou, Min-Yen Kan

arXiv preprint 2026

PDF Code

IEEE T-PAMI

Efficient Inference for Large Reasoning Models: A Survey

Yue Liu^*, Jiaying Wu^*, Yufei He^*, Ruihan Gong^*, Jun Xia, Liang Li, Hongcheng Gao, Hongyu Chen, Baolong Bi, Jiaheng Zhang, Zhiqi Huang, Bryan Hooi, Stan Z. Li, Keqin Li

IEEE T-PAMI 2026

PDF Project Page

ACL

Beyond the Crowd: LLM-Augmented Community Notes for Governing Health Misinformation

Jiaying Wu^*, Zihang Fu^*, Haonan Wang, Fanxiao Li, Jiafeng Guo, Preslav Nakov, Min-Yen Kan

ACL 2026

PDF Code Oral

ACL

What's Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews

Fanxiao Li^{^}, Jiaying Wu, Tingchao Fu, Dayang Li, Herun Wan, Wei Zhou, Min-Yen Kan

ACL 2026

PDF Code

ACL

XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration

Nuo Chen, Andre Lin HuiKai, Jiaying Wu, Junyi Hou, Zining Zhang, Qian Wang, Xidong Wang, Bingsheng He

ACL 2026

PDF Code

ACS Nano Medicine

Quantitative Computational Validation of Nanoscale Interactions between Drug Molecules and Diabetic Wound-Related Proteins for Drug Discovery

Ziyang Zhang, Yanxia Qin, ..., Jiaying Wu, Chen-Hua Yeow, Min-Yen Kan, Giorgia Pastorin

ACS Nano Medicine 2026

PDF

ICLR

Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models

Jiaying Wu, Fanxiao Li, Zihang Fu, Min-Yen Kan, Bryan Hooi

ICLR 2026

PDF Code

AAAI

Reasoning About the Unsaid: Misinformation Detection with Omission-Aware Graph Inference

Zhengjia Wang, Danding Wang, Qiang Sheng, Jiaying Wu, Juan Cao

AAAI 2026

PDF Code Oral

NeurIPS

Truth over Tricks: Measuring and Mitigating Shortcut Learning in Misinformation Detection

Herun Wan^{^}, Jiaying Wu, Minnan Luo, Zhi Zeng, Zhixiong Su

NeurIPS 2025

PDF Code

NeurIPS

ConfTuner: Training Large Language Models to Express Their Confidence Verbally

Yibo Li, Miao Xiong, Jiaying Wu, Bryan Hooi

NeurIPS 2025

PDF Code

NeurIPS D&B

MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research

Hui Chen, Miao Xiong, Yujie Lu, Wei Han, Ailin Deng, Yufei He, Jiaying Wu, Yibo Li, Yue Liu, Bryan Hooi

NeurIPS 2025 (Datasets and Benchmarks)

PDF Code

KDD Workshop

CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization

Yixi Ding^{^}, Jiaying Wu, Tongyao Zhu, Yanxia Qin, Qian Liu, Min-Yen Kan

KDD 2025 SciSoc LLM Workshop

PDF Code Oral

ACL

IMOL: Incomplete-Modality-Tolerant Learning for Multi-Domain Fake News Video Detection

Zhi Zeng^{^}, Jiaying Wu, Minnan Luo, Herun Wan, Xiangzheng Kong, Zihan Ma, Guang Dai, Qinghua Zheng

ACL 2025

PDF Code Oral

NeurIPS

ID3: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition

Shen Li^*, Jianqing Xu^*, Jiaying Wu, Miao Xiong, Ailin Deng, Jiazhen Ji, Yuge Huang, Wenjie Feng, Shouhong Ding, Bryan Hooi

NeurIPS 2024

PDF

KDD

Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attacks

Jiaying Wu, Jiafeng Guo, Bryan Hooi

KDD 2024

PDF Code

NeurIPS

Proximity-Informed Calibration for Deep Neural Networks

Miao Xiong, Ailin Deng, Pang Wei Koh, Jiaying Wu, Shen Li, Jianqing Xu, Bryan Hooi

NeurIPS 2023

PDF Code Spotlight

CIKM

Prompt-and-Align: Prompt-Based Social Alignment for Few-Shot Fake News Detection

Jiaying Wu, Shen Li, Ailin Deng, Miao Xiong, Bryan Hooi

CIKM 2023

PDF Code

KDD

DECOR: Degree-Corrected Social Graph Refinement for Fake News Detection

Jiaying Wu, Bryan Hooi

KDD 2023

PDF Code

CVPR

Probabilistic Knowledge Distillation of Face Ensembles

Jianqing Xu, Shen Li, Ailin Deng, Miao Xiong, Jiaying Wu, Jiaxiang Wu, Shouhong Ding, Bryan Hooi

CVPR 2023

PDF

ECML PKDD

Probing Spurious Correlations in Popular Event-Based Rumor Detection Benchmarks

Jiaying Wu, Bryan Hooi

ECML-PKDD 2022

PDF Code

Services

Organizer

Co-Organizer, ICLR 2025 Workshop on Reasoning and Planning for LLMs
General Chair, 2024 Singapore Symposium on Natural Language Processing

Conference Area Chair / SPC

NeurIPS 2026; CIKM 2025, 2026

Conference Reviewer / PC Member

NeurIPS, ICML, ICLR, ACL Rolling Review, COLM, KDD, WWW, CIKM, CVPR, ACM MM, AISTATS

Journal Reviewer

IEEE TKDE, IEEE T-IFS, ACM TIST

Beyond Research

I completed a B.Eng. in Computer Science and a Double Degree (B.A.) in English at Beijing Foreign Studies University (2016–2020). Those years nurtured a deep appreciation for language, not only as structure but also as a medium through which ideas, values, and perspectives are shaped. During this time, I became a CATTI-certified English–Chinese translator (Level 2) and interpreter (Level 3), and contributed to the translation of four books and one book series published in China. These experiences continue to influence how I think about communication, meaning, and the design of socially intelligent systems.