Li Jian Zhang (Li Zhang)

Research

I am interested in neuro-symbolic methods and interpretability for building more transparent and reliable AI systems.

• AI for Science
• Neuro-symbolic Methods
• Interpretability & XAI
• Generative Models
• Reliable AI

Selected Publications

• 
  Rethinking Circuit Evaluation: Do Circuits Explain Model Errors?

  Li Zhang*, Chuqin Geng*, Mark Zhang, Chen Yang, Luke Zhang, Haolin Ye, Xujie Si

  arXiv, 2026 · *equal contribution

  arXiv
• 
  Neural Proposals, Symbolic Guarantees: Neuro-Symbolic Graph Generation with Hard Constraints

  Chuqin Geng, Li Zhang, Mark Zhang, Haolin Ye, Ziyu Zhao, Xujie Si

  NeurIPS, 2026

  arXiv
• 
  Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning

  Chuqin Geng, Li Zhang, Haolin Ye, Ziyu Zhao, Yuhe Jiang, Tara Saba, Xinyu Wang, Xujie Si

  arXiv, 2026

  arXiv
• 
  VisionLogic: From Neuron Activations to Causally Grounded Concept Rules for Vision Models

  Chuqin Geng, Yuhe Jiang, Ziyu Zhao, Zhaoyue Wang, Haolin Ye, Anqi Xing, Li Zhang, Xujie Si

  Preprint, 2026

  PDF
• 
  NEUROLOGIC: From Neural Representations to Interpretable Logic Rules

  Chuqin Geng, Anqi Xing, Li Zhang, Ziyu Zhao, Yuhe Jiang, Xujie Si

  UCRL @ ICLR, 2026

  arXiv
• 
  PAiNT: Perspective-Aware AI Identity and Narrative Toolkit for Generating Labeled Digital Footprints

  Jisung Shin, Daniel Platnick, Tanayjyot Singh Chawla, Li Zhang, Amardeep Singh, Kazi Rahman, Arnav Chandna, Marjan Alirezaie, Hossein Rahnama

  Data, 2026

  PDF DOI

Experience

• Research Assistant · University of Toronto (Prof. Xujie Si) Jun 2025 – Present
• Machine Learning Research Intern · Flybits Feb 2025 – Dec 2025
• Student Research Automation Engineer · Acceleration Consortium (Human Organ Mimicry) Apr 2025 – Dec 2025
• Research Assistant · University of Toronto (Prof. Feng Ji) Sep 2024 – Mar 2025
• Research Assistant · University of Toronto — Rotman School of Management Jun 2024 – Nov 2024

Education

• University of Toronto · M.Sc. in Computer Science (Prof. Xujie Si) 2026 – present
• University of Toronto, Trinity College · B.Sc., Computer Science Specialist & Statistics Major 2022 – 2026

Talks

• Rethinking Deep Learning Autodiff for Rust & C · Poster, UofT AI Conference X Dec 2024