Fang Sun

Fang Sun

Ph.D. Candidate @ UCLA, advised by Prof. Yizhou Sun

AI for Quantum Computing & Quantum Chemistry (QCQC)

I am Fang Sun (孙昉), a Ph.D. candidate 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. During my undergrad, I worked closely with Prof. Ming Zhang and Prof. Jian Tang on GNNs for drug discovery and recommender systems.

My research focus is AI for Quantum Computing and Quantum Chemistry (QCQC). More broadly, I develop geometric deep learning methods that tighten the simulation–design loop in molecular and materials science along two complementary pillars: (I) accelerating molecular and quantum simulation, and (II) property-conditioned generative design of molecules and materials. My Ph.D. prospectus, Charting the Chemical Landscape: Geometric Deep Learning for Simulation-Driven Molecular Design, develops these ideas with applications spanning drug discovery and next-generation semiconductor materials.

📄 A full CV is available here.

I am actively looking for talented undergraduate and master’s students interested in research opportunities. Students from CS, Chemistry, Physics, Applied Math, and related majors are welcome. If you’re interested, please send me an email with a brief introduction, your CV, and potential research directions you’d like to work on or propose.

🔥 News

  • 2026.07: Our paper RetroAgent on agentic retrosynthesis planning got accepted to COLM 2026.
  • 2026.07: DoMiNO got accepted to ACM Transactions on Knowledge Discovery from Data (TKDD).
  • 2026.05: Received Gold Reviewer Award (top 25% reviewer) at ICML 2026.
  • 2026.05: Our paper on Verifiable Physiological Waveform Reasoning got accepted to ICML 2026.
  • 2026.05: Two papers got accepted to KDD 2026: FD-Bench (DB Track) and CoRGI.
  • 2026.04: Our paper on Moral Evolution with LLM-based Agent Simulation got accepted to ACL 2026.
  • 2026.03: Received my M.S. in Computer Science from UCLA.
  • 2025: Our paper on Controllable Generation of Drug-like Molecular Materials got accepted to LoG 2025.
  • 2025: Our paper on Symmetry-Preserving Conformer Ensemble Networks got accepted to NeurIPS 2025.
  • 2025: Our paper on Deep Knowledge Tracing for Explainable Problem Recommendations got accepted to IJCAI 2025.
  • 2025: GF-NODE got accepted to TMLR 2025.
  • 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

My work is organized around two complementary pillars — (I) AI for Molecular & Physical Simulation and (II) Generative Models for Molecular & Materials Design — unified by geometric deep learning. The graph-neural-network and time-series methods that serve as the machine-learning foundations for these works are listed separately below. (* denotes equal contribution.)

🔬 Pillar I — AI for Molecular & Physical Simulation

TMLR 2025
GF-NODE

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.

TKDD 2026
DoMiNO

DoMiNO: Decomposing Molecular Dynamics with Multi-Scale Neural Graph Ordinary Differential Equations

Fang Sun, Zijie Huang, Yadi Cao, Xiao Luo, Wei Wang, Yizhou Sun

Abstract: DoMiNO models multi-scale molecular dynamics by decomposing trajectories with multi-scale Neural Graph ODEs, adaptively unifying different timescales to enable accurate short- and long-range prediction. Published in ACM TKDD; an earlier version received an Oral Presentation at ICLR 2025 MLMP.

🧬 Pillar II — Generative Models for Molecular & Materials Design

LoG 2025
Multi-modal Variational Flow

Controllable Generation of Drug-like Molecular Materials with Multi-modal Variational Flow

Fang Sun, Zhihao Zhan, Hongyu Guo, Ming Zhang, Jian Tang, Yizhou Sun

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 31.1% high-affinity rate on CrossDocked with zero-shot controllability over substructures and physicochemical properties.

  • COLM 2026
    RetroAgent: Agentic Retrosynthesis Planning with Search Over Structured Memory,
    Yanqiao Zhu, Jingru Gan, Xiaoqi Sun, Fang Sun, Yidan Shi, Md Mofijul Islam, Chao Shang, Wenhao Gao, Connor W. Coley, Yizhou Sun, Wei Wang

  • 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

🕸️ Foundations: Graph Neural Networks

⏱️ Foundations: Time Series

📄 Other Publications

🎖 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

💻 Work Experience

Research in Industrial Projects for Students – 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.

🛠 Technical Strengths

  • Deep Learning: PyTorch, PyTorch Geometric, Hugging Face Transformers, JAX
  • Quantum Computing & Chemistry: Qiskit, PySCF, Q-Chem, Synopsys QuantumATK
  • Cheminformatics & Materials: RDKit, ASE, pymatgen
  • Scientific Computing: Python, C++, NumPy, SciPy, CUDA
  • Infrastructure: AWS, GCP, Docker, Git

🔍 Professional Service

  • Tutorials Chair, Learning on Graphs (LoG) 2025
  • Session Chair, AI and Predictive Modeling, IEEE SoutheastCon 2026
  • Gold Reviewer Award (top 25% reviewer), ICML 2026
  • Reviewer: ICML, ICLR, NeurIPS, CIKM, LoG

🌴 Personal Interests

Avid hiker, beach lover, and tennis enthusiast. I love thinking about how AI can be used in creative and imaginative ways, especially art, and I’m drawn to the post-apocalyptic, cyberpunk aesthetics of Blade Runner and Dune. Always happy to hit LA’s trails or the tennis court, or to trade thoughts on speculative futures. Let’s explore together!