I am currently a research fellow at the National University of Singapore under Prof. Dong Jin Song. Before that, I received my Ph.D. degree from NUS in 2025 and my bachelor's degree at Fudan University in 2020.

My research focuses on the trustworthiness of large language models (LLMs), with a particular interest in: - Data-Centric AI, including data attribution, - Enhancing the safety and reliability of LLMs, - Addressing data quality issues in machine learning.

I am open to discussions and collaborations. If you are interested in my research, feel free to reach out.

[Google Scholar] | [GitHub] | [LinkedIn] [Email]
RECENT NEWS 🧅
  • 11/2024. I will be joining NUS as a Research Fellow!
  • 05/2024. I become an MLE intern at ByteDance!
  • 01/2024. I become a research intern at Lenovo working on AI Agent!
  • 11/2023. I was honored to receive the Dean’s Graduate Award from NUS. Thanks Prof. Dong for the nomination and support!
  • 07/2023. Our paper DeepDebugger: An Interactive Time-Travelling Debugging Approach for Deep Classifiers has been accepted to ESEC/FSE 2023!
  • 05/2023. Our paper Thompson Sampling with Less Exploration is Fast and Optimal has been accepted to ICML 2023!
  • 09/2022. Our paper Debugging and Explaining Metric Learning Approaches: An Influence Function Based Perspective has been accepted to NeurIPS 2022!
  • 04/2022. Our paper Temporality Spatialization: A Scalable and Faithful Time-Travelling Visualization for Deep Classifier Training has been accepted to IJCAI 2022!
  • 03/2022. Our paper Inferring Phishing Intention via Webpage Appearance and Dynamics: A Deep Vision Based Approach has been accepted to USENIX 2022!
  • 02/2022. Our paper DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training has been accepted to AAAI22 with oral presentation (4%)!
PUBLICATIONS
  • Xianglin Yang, Gelei Deng, Jieming Shi, Tianwei Zhang, Jin Song Dong.
    Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning. Preprint, 2025..
  • Xianglin Yang, Jin Song Dong.
    Exploring the Evolution of Hidden Activations with Live-Update Visualization. Preprint, 2024.
  • Xianglin Yang, Yun Lin, Yifan Zhang, Linpeng Huang, Jin Song Dong, Hong Mei.
    DeepDebugger: An Interactive Time-Travelling Debugging Approach for Deep Classifiers. ESEC/FSE 2023 .
  • Tianyuan Jin, Xianglin Yang, Xiaokui Xiao, Pan Xu.
    Thompson Sampling with Less Exploration is Fast and Optimal. ICML 2023 .
  • Ruofan Liu, Yun Lin, Xianglin Yang, Jin Song Dong.
    Debugging and Explaining Metric Learning Approaches: An Influence Function Based Perspective. NeurIPS 2022 .
  • Xianglin Yang, Yun Lin, Ruofan Liu, Jin Song Dong.
    Temporality Spatialization: A Scalable and Faithful Time-Travelling Visualization for Deep Classifier Training. IJCAI 2022 . [code] [website]
  • Ruofan Liu, Yun Lin, Xianglin Yang, Siang Hwee Ng, Dinil Mon Divakaran, Jin Song Dong.
    Inferring Phishing Intention via Webpage Appearance and Dynamics: A Deep Vision Based Approach. USENIX Security 2022 . [code] [website]
  • Xianglin Yang#, Yun Lin#, Ruofan Liu, Zhenfeng He, Chao Wang, Jin Song Dong, and Hong Mei.
    DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training. AAAI 2022. [oral presentation, 4.5%]. [paper] [video] [code] [website]
WORKING EXPERIENCE
  • (Jun 2024 - Aug 2024) MLE Intern @ ByteDance, Shanghai, China
  • (Jan 2024 - May 2024) Research Intern @ Lenovo, Beijing, China
  • (Jul 2019 - Oct 2020) Research Assistent @ National University of Singapore, Singapore
EDUCATION
  • (Aug 2020 - Feb 2025) Ph.D. @ NUS, School of Computing
  • (Sep 2016 - Jul 2020) B.S. @ Fudan University, School of Computer Science and Technology
Review Service
  • ICLR 25, ICML 25, IJCAI 25
AWARDS
  • Dean's Graduate Research Excellence Award
  • First prize in Research Prototype Competition in ChinaSoft with "Deep Classifier Oriented Interactive Debugger". video
  • NUS SOC Research Achievement Award in Sem 2 AY2021/2022
  • 2nd Prize - Scholarship of Fudan University for Outstanding Students (15%) 2019-2020
  • 2nd Prize - Scholarship of Fudan University for Outstanding Students (15%) 2017-2018
  • 3rd Prize - Scholarship of Fudan University for Outstanding Students (30%) in 2017-2018
  • 1st Prize - The Preliminary Test of The 29th Chinese Chemistry Olympiad (Fujian) in 2015
  • Rank 1 - 2013 National Chemistry Quality and Experiment Ability Competition for Junior Middle School Students (Xiamen)
CONTACT

Computing 2,
15 Computing Drive, National University of Singapore,
Singapore, 117418


© 2024 YANG Xianglin | Powered by Skeleton and Jiarui Gan's template | Updated 2024-05-24