Publications
A collection of my research work.
CGU-Bayes: Causal Graph Uncertainty-Guided Bayesian Inference for Domain Generalization
Naiyu Yin, Hangjing Wang, Yue Yu, Tian Gao, Amit Dhurandhar, Chung-Hao Lee, Qiang Ji
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026
A Bayesian framework leveraging causal graph uncertainty for robust domain generalization.
Scalable Circuit Learning for Interpreting Large Language Models
Naiyu Yin, Dennis Wei, Tian Gao, Amit Dhurandhar, Karthikeyan Natesan Ramamurthy, Yue Yu
Mechanistic Interpretability Workshop at ICML 2026
A scalable circuit learning method that uses sparse linear regression over sparse-autoencoder features to recover interpretable circuits, matching the structural accuracy of intervention-based methods at a fraction of the computational cost.
Learning Causal Graphs at Scale: A Foundation Model Approach
Naiyu Yin, Tian Gao, Yue Yu
arXiv preprint 2025
A foundation model for causal discovery that uses an attention-based architecture (Attention-DAG) to learn multiple linear SEMs, enabling efficient zero-shot DAG inference with improved accuracy in small-sample regimes.
Fake It Till You Make It: Multi-Physics Synthesis Breaks the Data Barrier in Chemical Language Models
Naiyu Yin, Ning Liu, Brian Y. Lattimer, Jim Lua, Yue Yu
Machine Learning and the Physical Sciences Workshop at NeurIPS 2025
A physics-augmented chemical language model for polymer property prediction and targeted discovery.
Effective Causal Discovery under Identifiable Heteroscedastic Noise Model
Naiyu Yin, Tian Gao, Yue Yu, Qiang Ji
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) 2024
Novel iterative causal graph learning method handling heteroscedastic noise with proven identifiability conditions.
Integrating Markov Blanket Discovery into Causal Representation Learning for Domain Generalization
Naiyu Yin, Hanjing Wang, Yue Yu, Tian Gao, Amit Dhurandhar, Qiang Ji
European Conference on Computer Vision (ECCV) 2024
A unified framework combining causal discovery and representation learning for domain generalization via Markov blanket features.
Efficient Nonlinear DAG Learning Under Projection Framework
Naiyu Yin, Yue Yu, Tian Gao, Qiang Ji
International Conference on Pattern Recognition (ICPR) 2024
Efficient causal graph learning via projection framework, eliminating explicit acyclicity constraints. Oral presentation, nominated for Best Industrial Paper Award.
Causal Markov Blanket Representation Learning for Out-of-Distribution Generalization
Naiyu Yin, Hanjing Wang, Tian Gao, Amit Dhurandhar, Qiang Ji
Causal Representation Learning Workshop at NeurIPS 2023
Causal Markov blanket representation learning for OOD generalization.
Bayesian Approaches for Robust Constraint-Based Causal Discovery Under Insufficient Data
Zijun Cui, Naiyu Yin, Yuru Wang, Qiang Ji
Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI) 2022
Bayesian methods for robust causal discovery under limited data settings.