I am Fang Sun (孙昉), a Ph.D. student in Computer Science at University of California, Los Angeles, advised by Prof. Yizhou Sun. I received my B.Sc. in Computer Science and Technology (Summa cum laude) from Peking University, and I also completed a B.Sc. in Chemistry as part of a double degree program. I was a member of the CS Turing Class hosted by Prof. John Hopcroft.
My research interests include:
- AI/ML for Drug Discovery
- Dynamical Systems Modeling
- Chemical Reaction Design
- Neural Ordinary Differential Equations (Neural ODEs)
- Graph Neural Networks
🔥 News
- 2025.03: 3 papers got accepted to ICLR 2025 MLMP (1 oral, 2 posters).
- 2025.02: Our paper on Automated Molecular Concept Generation using LLMs got accepted to COLING 2025.
- 2024.08: Our survey on GNNs for Molecular Generation got accepted to Neural Network.
- 2023.09: Started my Ph.D. at UCLA.
📝 Publications
GraphVF: Controllable Protein-Specific 3D Molecule Generation with Variational Flow
Fang Sun, Zhihao Zhan, Hongyu Guo, Ming Zhang, Jian Tang
Abstract: We propose GraphVF, a controllable 3D molecule generation framework that integrates both 3D geometry and 2D structures for protein-specific drug design. Our approach uses a valency-aware E(3)-GNN and a junction-tree encoder, achieving a 3.9% gain in high-affinity generation while preserving realistic bond distributions and property-oriented generation.
DoMiNO: Down-scaling Molecular Dynamics with Neural Graph Ordinary Differential Equations
Fang Sun, Zijie Huang, Yadi Cao, Xiao Luo, Wei Wang, Yizhou Sun
Abstract: DoMiNO addresses multi-scale molecular dynamics by down-scaling simulation steps with Neural Graph ODEs. It adaptively unifies different timescales, enabling accurate short- and long-range predictions in molecular modeling. Selected as an Oral Presentation at ICLR 2025 MLMP.
Graph Fourier Neural ODEs: Modeling Spatial-temporal Multi-scales in Molecular Dynamics
Fang Sun, Zijie Huang, Haixin Wang, Huacong Tang, Xiao Luo, Wei Wang, Yizhou Sun
Abstract: We introduce Graph Fourier Neural ODEs (GF-NODE), a novel approach for spatial-temporal multi-scale modeling. By integrating Neural ODEs with graph Fourier transforms, GF-NODE effectively captures both local and global dynamics in complex molecular systems.
DisenCTR: Dynamic Graph-based Disentangled Representation for Click-Through Rate Prediction
Yifan Wang, Yifang Qin, Fang Sun, Bo Zhang, Xuyang Hou, Ke Hu, Jia Cheng, Jun Lei, Ming Zhang
Abstract: DisenCTR leverages dynamic routing to disentangle user interests, incorporating a multivariate Hawkes process for time-aware modeling. It outperforms previous CTR methods with significant gains in recommendation accuracy.
DisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest Recommendation
Yifang Qin*, Yifan Wang*, Fang Sun*, Wei Ju, Xuyang Hou, Zhe Wang, Jia Cheng, Jun Lei, Ming Zhang (*Equal contribution)
Abstract: DisenPOI proposes a dual-graph architecture to disentangle sequential and geographical factors in POI recommendation. Contrastive learning is used to differentiate user dynamics, enabling more precise and interpretable location suggestions.
Other Publications
-
ICLR 2025 MLMP
Analysis of Neural ODE Performance in Long-term PDE Sequence Modeling,
Fang Sun, Maxwell Dalton, Yizhou Sun -
ICLR 2025 MLMP
SpectralFlowNet: Resolution-Invariant Continuous Neural Dynamics for Mesh-Based PDE Modeling,
Tianrun Yu*, Fang Sun*, Haixin Wang, Xiao Luo, Yizhou Sun (*Equal contribution) -
COLING 2025
Automated Molecular Concept Generation and Labeling with Large Language Models,
Shichang Zhang, Botao Xia, Zimin Zhang, Qianli Wu, Fang Sun, Ziniu Hu, Yizhou Sun -
Neural Networks 2024
A comprehensive survey on deep graph representation learning,
Wei Ju, Zheng Fang, Yiyang Gu, Zequn Liu, Qingqing Long, Ziyue Qiao, Yifang Qin, Jianhao Shen, Fang Sun, Zhiping Xiao, Junwei Yang, Jingyang Yuan, Yusheng Zhao, Yifan Wang, Xiao Luo, Ming Zhang (Wrote the “Molecular Generation” section.) -
arXiv preprint 2022
Over-smoothing Effect of Graph Convolutional Networks,
Fang Sun -
University Chemistry 2019
Synthesis and Applications of Borylenes,
Junhao Li, Fang Sun, Honglin Du, Huilong Hong, Kunhao Wang, and Jiang Bian.
🎖 Honors and Awards
- 2022 John Hopcroft Scholarship, Peking University
- 2021 Canon Scholarship (4/25), Peking University
- 2021 Second Award, PKU-CPC Programming Contest
- 2019 National Scholarship (2/155), Peking University
📖 Education
-
Ph.D. Student in Computer Science, 2023 – Present
University of California, Los Angeles
Advisor: Prof. Yizhou Sun -
Bachelor of Science in Computer Science (Summa cum laude), 2019 – 2023
Peking University, Beijing
Member of the CS Turing Class, supervised by Prof. John Hopcroft -
Bachelor of Science in Chemistry (Double Degree Program), 2019 – 2023
Peking University, Beijing
💻 Work Experience
Research in Industrial Projects for Students (RIPS) – Sponsored by IPAM & Relay Therapeutics
2024, UCLA / Relay Therapeutics
- Served as academic mentor, focusing on generative molecular design, structural diversity, and protein-ligand interaction analysis.
Euler-Ads: Distributed GNN Framework for Online CTR Prediction
2021-2022, Meituan Inc.
- Developed Euler-Ads, integrating large-scale graph data into CTR prediction.
- Deployed via A/B testing on Meituan’s advertising platform.
🛠 Skills and Technical Strengths
- Programming Languages: Python, C++, Java, Shell
- Machine Learning & Data Science: PyTorch, TensorFlow, NumPy, Pandas, Scikit-learn
- AI & Chemistry Tools: Huggingface, RDKit, Molecular Modeling
- Cloud Computing: AWS, GCP
- Version Control: Git
- Databases: SQL
🔍 Professional Service
Served as a reviewer for conferences including ICML, ICLR, NeurIPS, CIKM, and LoG.
🌴 Personal Interests
Avid hiker and beach lover with a passion for K pop concerts. I am a good listener who enjoys deep conversations and mentally stimulating films. Let’s explore LA’s trails or catch a show together!