Tommi Jaakkola
MIT EECS professor; pioneer in graphical models, deep generative models, and AI for chemistry / drug discovery.
- Role
- professor
- Currently at
- MIT CSAIL
- Scholar
- scholar.google.com/citations
- Papers
- 23
Cite
Notes
Only stored in your browser.
Authored papers
23How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
arXiv 2026
SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
arXiv 2025
Flow Map Distillation Without Data
arXiv 2025
Deep Confident Steps to New Pockets: Strategies for Docking Generalization
arXiv 2024
Generative Modeling of Molecular Dynamics Trajectories
arXiv 2024
Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective
arXiv 2024
Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning
arXiv 2024
DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents
arXiv 2024
Dirichlet Flow Matching with Applications to DNA Sequence Design
arXiv 2024
Think While You Generate: Discrete Diffusion with Planned Denoising
arXiv 2024
Improving Protein Optimization with Smoothed Fitness Landscapes
arXiv 2023
Correcting Diffusion Generation through Resampling
CVPR 2024 1
Removing Biases from Molecular Representations via Information Maximization
arXiv 2023
SE(3) diffusion model with application to protein backbone generation
arXiv 2023
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models
arXiv 2023
Restart Sampling for Improving Generative Processes
NeurIPS 2023 11
Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models
arXiv 2023
Equivariant Scalar Fields for Molecular Docking with Fast Fourier Transforms
arXiv 2023
EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction
arXiv 2022
Crystal Diffusion Variational Autoencoder for Periodic Material Generation
crystal-diffusion-variational-autoencoder-for
Analyzing Learned Molecular Representations for Property Prediction
arXiv 2019
Educating Text Autoencoders: Latent Representation Guidance via Denoising
ICML 2020 1
Junction Tree Variational Autoencoder for Molecular Graph Generation
junction-tree-variational-autoencoder-for-1
Affiliations
Frequent co-authors
10from 23 papers