Liang Yan

Liang (Divin) Yan

My work focuses on machine learning, especially generative modeling methods such as LLMs, diffusion models, and flow matching. I am also interested in mathematics, physics, astronomy and cosmology.

I was a visiting student in the Anima AI+Science lab at the California Institute of Technology, advised by Professor Anima Anandkumar. I received my graduate degree in Applied Mathematics from Fudan University, under the esteemed supervision of the distinguished scholar Prof. Zengfeng Huang. During my time at Fudan University, I audited graduate-level theoretical physics courses out of personal interest. At Fudan University, my work focused on the theory and real-world applications of graph learning and generative models. I am also a visting student at the Vision and Learning Lab, UC Merced, under the guidance of Professor Ming-Hsuan Yang and Dr. Lu Qi. I was also a research intern at Tencent AI Lab and Shanghai AI Lab.

Feel free to reach out to me if you're interested in discussing research or potential collaborations!

Email: yanliangfdu[at]gmail.com ; divinyan[at]cs.washington.edu.

Google Scholar / Github / ORCID / Twitter / LinkedIn

News

2025.10 NucleusDiff was reported by Caltech News! Check it out: https://www.caltech.edu/about/news/new-ai-model-for-drug-design-brings-more-physics-to-bear-in-predictions!
2025.09 MGB was accepted by NeurIPS 2025 AI4Mat Workshop! We present the first comprehensive material generation benchmark in the world, which includes LLMs, diffusion & flow-based models, and VAE-based models!
2025.09 UNREAL was accepted by NeurIPS 2025! We first introduce the concept of geometric imbalance of GNNs on riemannian manifold!
2025.09 NucleusDiff was accepted by PNAS 2025!
2025.08 HuDiff was accepted by Nature Machine Intelligence 2025! Congrats Jian and Fandi!

Publication

(* indicates equal contribution)

A Comprehensive Survey of Multimodal LLMs for Scientific Discovery

Liang Yan* (co-first), Xu Jian* (co-first), Jian Ma* (co-first), Yuhang Liu, Tian Bian, Qichao Wang, Abhishek Basu, Yu Rong, Tingyang Xu, Pengcheng Wu, Le Song, Imran Razzak, Junchi Yan, Zengfeng Huang, Yutong Xie

[Project Page] [Paper]

Presented at NeurIPS 2025 VLM4RWD Workshop

In Submission

MGB: The Material Generation Benchmark

Liang Yan, Beom Seok Kang, Maurice D. Hanisch, Jian Ma, Anima Anandkumar

[Paper] [Code] [Poster]

Presented at NeurIPS 2025 AI4Mat Workshop

In Submission

Geometric Imbalance in Semi-Supervised Node Classification

Liang Yan, Shengzhong Zhang, Bisheng Li, Menglin Yang, Chen Yang, Min Zhou, Weiyang Ding, Yutong Xie, Zengfeng Huang

[Project Page] [Paper] [Arxiv] [OpenReview] [Code] [Slides]

Presented at ICML 2025 DataWorld Workshop

NeurIPS 2025

Manifold-Constrained Nucleus-Level Denoising Diffusion Model for Structure-Based Drug Design

Shengchao Liu* (co-first), Liang Yan* (co-first), Weitao Du, Weiyang Liu, Zhuoxinran Li, Hongyu Guo, Christian Borgs, Jennifer Chayes, Anima Anandkumar

[Project Page] [Paper] [Arxiv] [OpenReview] [Code] [Slides]

Presented at ICML 2024 GRaM Workshop

Proceedings of the National Academy of Sciences 2025 (PNAS 2025)

An Adaptive Autoregressive Diffusion Approach to Design Active Humanized Antibody and Nanobody

Jian Ma, Fandi Wu, Tingyang Xu, Shaoyong Xu, Wei Liu, Liang Yan, Minghao Qu, Xiaoke Yang, Qifeng Bai, Junyu Xiao, Jianhua Yao

[Project Page] [Paper] [Arxiv] [OpenReview] [Code] [Slides]

Nature Machine Intelligence 2025

A Multi-Grained Symmetric Differential Equation Model for Learning Protein-Ligand Binding Dynamics

Shengchao Liu, Weitao Du, Hannan Xu, Yanjing Li, Zhuoxinran Li, Vignesh Bhethanabotla, Liang Yan, Christian Borgs, Anima Anandkumar, Hongyu Guo, Jennifer Chayes

[Project Page] [Paper] [Arxiv] [OpenReview] [Code] [Slides]

ICLR AI4DifferentialEquations Workshop 2024 Oral

Nature Communications 2025

NeuralCrystal: A Geometric Foundation Model for Crystalline Material Discovery

Shengchao Liu* (co-first), Liang (Divin) Yan* (co-first), Weitao Du, Zhuoxinran Li, Zhiling Zheng, Omar Yaghi, Christian Borgs, Hongyu Guo, Anima Anandkumar, Jennifer Chayes

[Project Page] [Paper] [Code]

NeurIPS 2024 AI4Mat Workshop

CrystalFlow: An Equivariant Flow Matching Framework for Learning Molecular Crystallization

Shengchao Liu, Liang (Divin) Yan, Hongyu Guo, Anima Anandkumar

[Project Page] [Paper] [Code]

ICML 2024 GRaM Workshop, ICML 2024 ML4LMS Workshop

Hierarchical Graph Latent Diffusion Model for Conditional Molecule Generation

Tian Bian, Yifan Niu, Heng Chang, Liang (Divin) Yan, Tingyang Xu, Yu Rong, Jia Li, Hong Cheng

[Project Page] [Paper] [OpenReview] [Code] [Slides]

CIKM 2024

Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition

Liang Yan, Gengchen Wei, Chen Yang, Shengzhong Zhang, Zengfeng Huang

[Project Page] [Paper] [Arxiv] [Code] [Slides] [Poster]

NeurIPS 2023

Training Class-Imbalanced Diffusion Model Via Overlap Optimization

Liang (Divin) Yan, Lu Qi, Vincent Tao Hu, Ming-Hsuan Yang, Meng Tang

[Project Page] [Arxiv] [OpenReview] [Code] [Slides]

Arxiv 2024

Physics Informed Spectral Element Network with Positional Parameter

Gengchen Wei, Liang Yan, Lei Bai, Wanli Ouyang, Chen Lin

[Project Page] [Arxiv] [OpenReview] [Code] [Slides]

Preprint 2024

Service

Reviewer: KDD (2023, 2024), ICLR (2024, 2025, 2026), ICML (2024, 2025), NeurIPS (2023, 2024, 2025, 2026), ACM MM (2025, 2026), ACM MM Datasets Track (2025, 2026), IJCAI-ECAI (2026)

ICML LXAI Workshop (2025), ICML AI4Math Workshop (2025), ICML AIW Workshop (2025), ICML DataWorld Workshop (2025), NeurIPS 2025 LXAI Workshop (2025), NeurIPS 2025 VLM4RWD Workshop (2025)

Personal

I originally had no connection to the field of artificial intelligence. If everything had gone as expected, I might have become a bank manager or an accountant. However, during my undergraduate years, I happened to stumble upon a book on artificial intelligence while wandering through the library. That book left a profound impact on me, and from that moment, I made up my mind to devote myself to this exciting field. This is my origin, the path I started on, and I hope I will never forget the inspiration and determination I felt at the very beginning.

I am a fan of the late NBA star Kobe Bryant. He has been a great source of inspiration for me. He once said: "If you love a thing, you will overcome all difficulties." So, the most important thing is to find something you truly love. I hope I already find mine too. RIP, Kobe.