Li Jian Zhang (Li Zhang)

Interests

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

Publications

• Neural Proposals, Symbolic Guarantees: Neuro-Symbolic Graph Generation with Hard Constraints
  Chuqin Geng, Li Zhang, Mark Zhang, Haolin Ye, Ziyu Zhao, Xujie Si
  arXiv, 2026 · In Submission
  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 · In Submission
  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

Work Experience

• Research Assistant · University of Toronto (Prof. Xujie Si)
  June 2025 – Present
• Student Research Intern · Flybits
  February 2025 – December 2025
• AI Automation Research Engineer · Acceleration Consortium (Human Organ Mimicry)
  April 2025 – January 2026

Presentations

• Rethinking Deep Learning Autodiff for Rust & C
  Poster, December 2024 (UofT AI)

Education

• University of Toronto, Toronto, Canada
  B.Sc. in Computer Science & Statistics · 2022 – 2026