Jiahan Li Ced

Peking University
Logo B.S., Peking University (2023)

Hi, my name is Jiahan Li (李嘉涵), but you can also call me Ced. I earned my B.S. degree from Yuanpei College at Peking University in 2023. I also worked as an R&D scientist at an AI biotech startup for three years.

My research interests lie at the intersection of generative models and geometric learning. Currently, I am focusing on molecular design, discrete generation, and equivariant models. I am also interested in multi-modal large language models and causal reasoning.

I love music and work as a hip-hop producer.

Google Scholar GitHub WeChat Twitter
Education
  • Peking University
    Peking University
    B.S. in Data Science
    Sep. 2019 - Jul. 2023
Honors & Awards
  • Chinese National Biology Team
    2018 - 2019
  • Gold medal in the Chinese National Biology Olympiad, 10th
    2018
Selected Publications (view all )
Categorical Flow Matching on Statistical Manifolds
Categorical Flow Matching on Statistical Manifolds

Chaoran Cheng*, Jiahan Li*, Jian Peng, Ge Liu (* equal contribution)

Conference and Workshop on Neural Information Processing Systems (NeurIPS) 2024

A novel flow matching framework on the manifold of parameterized probability measures for discrete generation.

[paper] [Code] [Proceedings]

Categorical Flow Matching on Statistical Manifolds
Categorical Flow Matching on Statistical Manifolds

Chaoran Cheng*, Jiahan Li*, Jian Peng, Ge Liu (* equal contribution)

Conference and Workshop on Neural Information Processing Systems (NeurIPS) 2024

A novel flow matching framework on the manifold of parameterized probability measures for discrete generation.

[paper] [Code] [Proceedings]

Full-Atom Peptide Design based on Multi-modal Flow Matching
Full-Atom Peptide Design based on Multi-modal Flow Matching

Jiahan Li*, Chaoran Cheng*, Zuofan Wu, Ruihan Guo, Shitong Luo, Zhizhou Ren, Jian Peng, Jianzhu Ma (* equal contribution)

International Conference on Machine Learning (ICML) 2024

The first multi-modal multi-task flow matching method for target-specific full-atom peptide design and analysis.

[paper] [Code] [Proceedings]

Full-Atom Peptide Design based on Multi-modal Flow Matching
Full-Atom Peptide Design based on Multi-modal Flow Matching

Jiahan Li*, Chaoran Cheng*, Zuofan Wu, Ruihan Guo, Shitong Luo, Zhizhou Ren, Jian Peng, Jianzhu Ma (* equal contribution)

International Conference on Machine Learning (ICML) 2024

The first multi-modal multi-task flow matching method for target-specific full-atom peptide design and analysis.

[paper] [Code] [Proceedings]

Proximal Exploration for Model-guided Protein Sequence Design
Proximal Exploration for Model-guided Protein Sequence Design

Zhizhou Ren*, Jiahan Li*, Fan Ding, Yuan Zhou, Jianzhu Ma, Jian Peng (* equal contribution)

International Conference on Machine Learning (ICML) 2022 Spotlight

Addressing model-guided sequence design using evolutionary search to find high-fitness mutants with low mutation counts.

[Paper] [Code] [Proceedings]

Proximal Exploration for Model-guided Protein Sequence Design
Proximal Exploration for Model-guided Protein Sequence Design

Zhizhou Ren*, Jiahan Li*, Fan Ding, Yuan Zhou, Jianzhu Ma, Jian Peng (* equal contribution)

International Conference on Machine Learning (ICML) 2022 Spotlight

Addressing model-guided sequence design using evolutionary search to find high-fitness mutants with low mutation counts.

[Paper] [Code] [Proceedings]

Orientation-Aware Graph Neural Networks for Protein Structure Representation Learning
Orientation-Aware Graph Neural Networks for Protein Structure Representation Learning

Jiahan Li*, Shitong Luo*, Congyue Deng*, Chaoran Cheng*, Jiaqi Guan, Leonidas Guibas, Jian Peng, Jianzhu Ma (* equal contribution)

Under Review

A new type of vector-based neural network combines directional 3D weights with equivariant message passing.

[Paper]

Orientation-Aware Graph Neural Networks for Protein Structure Representation Learning
Orientation-Aware Graph Neural Networks for Protein Structure Representation Learning

Jiahan Li*, Shitong Luo*, Congyue Deng*, Chaoran Cheng*, Jiaqi Guan, Leonidas Guibas, Jian Peng, Jianzhu Ma (* equal contribution)

Under Review

A new type of vector-based neural network combines directional 3D weights with equivariant message passing.

[Paper]

Equivariant Point Cloud Analysis via Learning Orientations for Message Passing
Equivariant Point Cloud Analysis via Learning Orientations for Message Passing

Shitong Luo*, Jiahan Li*, Jiaqi Guan*, Yufeng Su, Chaoran Cheng, Jian Peng, Jianzhu Ma (* equal contribution)

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022 Oral

Learning virtual orientations for each point. Projecting neighbor points to local orientations before aggregating information from them.

[Paper] [Code] [Proceedings]

Equivariant Point Cloud Analysis via Learning Orientations for Message Passing
Equivariant Point Cloud Analysis via Learning Orientations for Message Passing

Shitong Luo*, Jiahan Li*, Jiaqi Guan*, Yufeng Su, Chaoran Cheng, Jian Peng, Jianzhu Ma (* equal contribution)

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022 Oral

Learning virtual orientations for each point. Projecting neighbor points to local orientations before aggregating information from them.

[Paper] [Code] [Proceedings]

All publications