Skip to content
View xll0328's full-sized avatar

Block or report xll0328

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
xll0328/README.md

👋 Hi, I'm Songning Lai (Sony)

Quant Researcher @ JoinQuant · Research in Trustworthy AI 🤖

Website Email Google Scholar

Explainability 🔍 · Robustness 🛡️ · Faithfulness ✅ · Safety 🔒


📌 About Me

I am Songning Lai (you can call me Sony). I received my B.S. from the School of Information Science and Engineering, Chongxin College, Shandong University, supervised by Prof. Zhi Liu. I was a Research Assistant at HKUST(GZ) AI Thrust & INFO Hub, supervised by Prof. Yutao Yue. I also had an international research experience as a Visiting Student at KAUST. I am currently a Quant Researcher at JoinQuant.

My primary research interest lies in Trustworthy AI, encompassing explainability, robustness, faithfulness, and safety. I have focused extensively on Concept Bottleneck Models (CBMs) and their applications in vision-language interpretation, medical diagnosis, continual learning, and autonomous driving. I also work on faithful time series forecasting, LLM explainability & knowledge editing, and multimodal learning.


🔬 Research Interests

Area Topics
Concept Bottleneck Models Faithful vision-language interpretation (ICLR 2024), medical multi-dimensional explanation (NeurIPS 2024), continual learning (ACM MM 2025 BNI), backdoor & security
Trustworthy ML Robustness, faithfulness, interpretability, time series under uncertainty (ICML 2025, ICASSP 2026)
Applications Medical imaging, autonomous driving (ICRA 2025), LLM knowledge editing (ICLR 2026)

🔥 Recent News

  • 01.2026ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall accepted at ICLR 2026.
  • 01.2026 — Time series forecasting under uncertainty (ambiguity & novelty rejection) accepted at ICASSP 2026 (CCF B).
  • 01.2026 — TPTD (privacy-preserving truth discovery) accepted at Knowledge-Based Systems (KBS) (JCR Q1).
  • 12.2025 — Da Yu (USV-based image captioning) accepted at IEEE TCSVT (IF 11.1, CCF B).
  • 10.2025 — Mimicking the Physicist's Eye (VLM for physics formula discovery) accepted at NeurIPS 2025 Workshop (spotlight).
  • 08.2025 — 3 papers at ACM MM 2025 BNI Track (CONCIL, Physics-Informed Radio-Map, Audio LM metaphorical reasoning).
  • 07.2025 — 4 papers at ACM MM 2025 (FTS, ANT, Text2Weight, CFSSeg).
  • 05.2025SVCT: Stable Vision Concept Transformers for Medical Diagnosis at ECML-PKDD 2025.
  • 09.2024Med-MICN: Multi-dimensional Explanation for Medical Classification at NeurIPS 2024 (CCF A).

More news on my website.


📝 Selected Publications

Year Venue Paper Project / Code
2026 ICLR ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall Web · Code
2026 ICASSP Towards Reliable Time Series Forecasting under Future Uncertainty
2025 ACM MM BNI CONCIL: Continual Learning for Multimodal Concept Bottleneck Models Web · Code
2025 ACM MM FTS: Faithful TimeSieve for Multimedia Web Forecasting Web · Code
2025 ICRA DRIVE: Interpretable Ensemble Framework in Autonomous Driving Web · Code
2025 ECML SVCT: Stable Vision Concept Transformers for Medical Diagnosis Web · Code
2025 ICASSP PEPL: Precision-Enhanced Pseudo-Labeling for Fine-Grained Image Classification
2024 NeurIPS Med-MICN: Multi-dimensional Explanation for Medical Classification Web · Code
2024 ICLR FVLC: Faithful Vision-Language Interpretation via Concept Bottleneck Models Web · Code

Full list: xll0328.github.io — Publications


🎖 Honors & Awards

Type Award
🏆 NeurIPS 2024 Travel Award
🏆 ICRA 2025 Travel Award
IEEE/EI CISP-BMEI 2022 Best Paper Award
🥇 First Prize, Contemporary Undergraduate Mathematical Contest in Modeling (National, top 0.6%)
🥇 First Prize, MathorCup University Mathematical Modeling Challenge (National, top 3%)
🥈 Second Prize, National Undergraduate Electronic Design Contest (Shandong Province)
🥈 Second Prize, National Crypto-math Challenge (East China)
🎓 Outstanding graduate of Shandong Province & Shandong University
📊 40+ university-level awards (competitions, social practice, innovation, sports, volunteer, scholarship)

📖 Education & Experience

Period Role Place
Now Quant Researcher JoinQuant
Apr 2024 – Sep 2025 Research Assistant HKUST(GZ) AI Thrust & INFO Hub
Apr 2023 – Mar 2024 Visiting Student KAUST
Sep 2020 – Jun 2024 B.S. (Information Science and Engineering) Shandong University, Chongxin College

💻 Service

Conference & Journal Reviewer: ECAI, ICML, KDD, ICLR, CVPR, ICCV, NeurIPS, ACM MM, IJCAI, Expert Systems with Applications, etc.


👥 Collaborators & Friends

Jiayu Yang · Wenshuo Chen · Jiemin Wu · Weilin Ruan · Jiakang Li · and more on my website


Interested in collaboration or chat? 📧 Email me · 🌐 Full site

Pinned Loading

  1. ECML25-SVCT ECML25-SVCT Public

    Jupyter Notebook 1

  2. MM25-CONCIL MM25-CONCIL Public

    Jupyter Notebook 1

  3. ICRA25-DRIVE ICRA25-DRIVE Public

    Python

  4. MM25-FTS MM25-FTS Public

    Python 1 1

  5. ICLR24-FVLC ICLR24-FVLC Public

    Jupyter Notebook 1

  6. NeurIPS24-Med_MICN NeurIPS24-Med_MICN Public

    Python