Bowen Jing

GitHub | Google Scholar

I am a 4th year Ph.D. student in Electrical Engineering and Computer Science at MIT, co-advised by Tommi Jaakkola and Bonnie Berger. I work on deep learning for structural biology and drug discovery, with a focus on generative models and molecular simulation.

Previously, I completed a B.S. in Computer Science at Stanford University. I was advised by Ron Dror and worked on equivariant neural networks for protein structure.


Publications

[show selected]

Generative Modeling of Molecular Dynamics Trajectories
B Jing,* H Stärk,* T Jaakkola, B Berger
NeurIPS, 2024
[openreview] [arxiv] [code]

AlphaFold Meets Flow Matching for Generating Protein Ensembles
B Jing, B Berger, T Jaakkola
ICML, 2024 (Oral)
[proceedings] [arxiv] [code]

Dirichlet Flow Matching with Applications to DNA Sequence Design
H Stärk,* B Jing,* B Berger, R Barzilay, T Jaakkola
ICML, 2024
[proceedings] [arxiv] [code]

Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Design
H Stärk, B Jing, R Barzilay, T Jaakkola
ICML, 2024
[proceedings] [arxiv] [code]

Evolution of highly multimodal Rayleigh-Taylor instabilities
B Cheng, B Jing, P Bradley, J Sauppe, R Roycroft
High Energy Density Physics, 2024
[doi]

Diffusion models in protein structure and docking
J Yim, H Stärk, G Corso, B Jing, R Barizilay, T Jaakkola
WIREs Computational Molecular Science, 2024
[doi]

Equivariant Scalar Fields for Molecular Docking with Fast Fourier Transforms
B Jing, T Jaakkola, B Berger
ICLR, 2024
[openreview] [arxiv] [code]

Protein Model Quality Assessment Using Rotation-Equivariant Transformations on Point Clouds
S Eismann,* P Suriana,* B Jing, R Townshend, R Dror
Proteins, 2023; 91: 1089–1096
[doi] [arxiv] [server] [code]

DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
G Corso,* H Stärk,* B Jing,* R Barzilay, T Jaakkola
ICLR, 2023
[openreview] [arxiv] [code] [news]

Torsional Diffusion for Molecular Conformer Generation
B Jing,* G Corso,* J Chang, R Barzilay, T Jaakkola
NeurIPS, 2022 (Oral)
[proceedings] [openreview] [arxiv] [code]

Subspace Diffusion Generative Models
B Jing,* G Corso,* R Berlinghieri, T Jaakkola
ECCV, 2022
[doi] [ecva.si] [arxiv] [code]

ATOM3D: Tasks On Molecules in Three Dimensions
R Townshend,* M Vögele,* P Suriana,* A Derry,* A Powers, Y Laloudakis, S Balachandar, B Jing, B Anderson, S Eismann, R Kondor, R Altman, R Dror
NeurIPS Datasets and Benchmarks, 2021 (Best Paper)
[proceedings] [openreview] [arxiv] [site] [docs] [code]

Learning from Protein Structure with Geometric Vector Perceptrons
B Jing,* S Eismann,* P Suriana, R Townshend, R Dror
ICLR, 2021 (Spotlight)
[openreview] [arxiv] [code]

Hierarchical, Rotation-Equivariant Neural Networks to Select Structural Models of Protein Complexes
S Eismann,* R Townshend,* N Thomas,* M Jagota, B Jing, R Dror
Proteins, 2021; 89: 493–501
[doi] [arxiv] [server]

Workshop Papers


Verlet Flows: Exact-Likelihood Integrators for Flow-Based Generative Models
E Erives, B Jing, T Jaakkola
Workshop on AI4DifferentialEquations In Science @ ICLR, 2024
[openreview] [arxiv]

Scalable Multimer Structure Prediction using Diffusion Models
P Pao-Huang, B Jing, B Berger
ML for Structural Biology Workshop @ NeurIPS, 2023
[workshop]

EigenFold: Generative Protein Structure Prediction with Diffusion Models
B Jing, E Erives, P Pao-Huang, G Corso, B Berger, T Jaakkola
ML for Drug Discovery Workshop @ ICLR, 2023
[workshop] [arxiv] [code]

Equivariant Graph Neural Networks for 3D Macromolecular Structure
B Jing, S Eismann, P Soni, R Dror
Workshop on Computational Biology @ ICML, 2021 (Best Spotlight Talk)
[workshop] [arxiv] [code]