|
Chuqin (Allen) Geng I am a Computer Science Ph.D. student at McGill University and Mila - Quebec AI Institute. I am currently a visiting scholar at the University of Toronto (U of T), working with Prof. Xujie Si. Prior to that, I earned my M.Sc. in Computer Science at Georgia Tech, and my B.Sc. in Math & Statistics at the University of Toronto. |
|
ResearchI am broadly interested in neuro-symbolic methods and interpretability, with the goal of building AI systems that are more transparent and reliable. My past work has focused on neural network verification and interpretable, reliable learning in the graph domain, and I'm now extending these ideas to large language models. |
Selected Publications |
|
Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning [paper]
arXiv preprint, 2026 Chuqin Geng, Li Zhang, Haolin Ye, Ziyu Zhao, Yuhe Jiang, Tara Saba, Xinyu Wang, Xujie Si |
|
Neural Proposals, Symbolic Guarantees: Neuro-Symbolic Graph Generation with Hard Constraints [paper]
arXiv preprint, 2026 Chuqin Geng, Li Zhang, Mark Zhang, Haolin Ye, Ziyu Zhao, Xujie Si |
|
DreamProver: Evolving Transferable Lemma Libraries via a Wake-Sleep Theorem-Proving Agent [paper]
COLM 2026 Youyuan Zhang, Jialiang Sun, Hangrui Bi, Chuqin Geng, Wenjie Ma, Zhaoyu Li, Xujie Si |
|
LogicXGNN: Grounded Logical Rules for Explaining Graph Neural Networks [paper]
ICLR 2026 (Top ~2%) Chuqin Geng, Ziyu Zhao, Zhaoyue Wang, Haolin Ye, Yuhe Jiang, Xujie Si |
|
NEUROLOGIC: From Neural Representations to Interpretable Logic Rules [paper]
UCRL Workshop @ ICLR, 2026 Chuqin Geng, Anqi Xing, Li Zhang, Ziyu Zhao, Yuhe Jiang, Xujie Si |
|
Learning Minimal Neural Specifications [paper]
NeuS 2025 (Oral) Chuqin Geng, Zhaoyue Wang, Haolin Ye, Xujie Si |
|
VisionLogic: From Neuron Activations to Causally Grounded Concept Rules for Vision Models [paper]
Preprint, 2025 Chuqin Geng, Yuhe Jiang, Ziyu Zhao, Zhaoyue Wang, Haolin Ye, Anqi Xing, Li Zhang, Xujie Si |
|
Towards Robust Saliency Maps [paper]
ACML 2024 Van Nham Le, Chuqin Geng, Xujie Si, Arie Gurfinkel |
|
Towards Reliable Neural Specifications [paper]
ICML 2023 (Oral) Chuqin Geng, Van Nham Le, Xiaojie Xu, Zhaoyue Wang, Arie Gurfinkel, Xujie Si |
|
Identifying Different Student Clusters in Functional Programming Assignments: From Quick Learners to Struggling Students [paper]
SIGCSE TS 2023 Chuqin Geng, Wenwen Xu, Yingjie Xu, Brigitte Pientka, Xujie Si |
|
TorchProbe: Fuzzing Dynamic Deep Learning Compilers [paper]
APLAS 2023 Qidong Su, Chuqin Geng, Gennady Pekhimenko, Xujie Si |
|
Scalar Invariant Networks with Zero Bias [paper]
NeurReps Workshop @ NeurIPS, 2023 Chuqin Geng, Xiaojie Xu, Haolin Ye, Xujie Si |
|
Novice Type Error Diagnosis with Natural Language Models [paper]
APLAS 2022 Chuqin Geng, Haolin Ye, Yixuan Li, Tianyu Han, Brigitte Pientka, Xujie Si |
Academic ServiceI have consistently served as a reviewer for top-tier conferences, including:
|
MiscellaneousOutside of research, I spend a lot of time outdoors, hiking and fishing whenever I get the chance. Being out in nature is when I do my best thinking, about how humans, animals, and the rest of the natural world all fit together, and how intelligence came to be in the first place. I also enjoy reading about paleontology, geology, and evolutionary biology in my spare time. |