Log inSign up
Image
user avatar
Hannes Stark
@HannesStaerk
@MIT PhD student • Generative models for simulating and designing biomolecules
Cambridge, MA
hannes-stark.com
Joined June 2019
491
Following
14.2K
Followers
  • Pinned
    user avatar
    Hannes Stark
    @HannesStaerk
    Oct 26, 2025
    Excited to release BoltzGen which brings SOTA folding performance to binder design! The best part of this project has been collaborating with many leading biologists who tested BoltzGen at an unprecedented scale, showing success on many novel targets and pushing its limits! 🧵..
    Image
    305K
  • user avatar
    Hannes Stark
    @HannesStaerk
    Feb 24, 2024
    Oke, the AlphaFlow paper is awesome: AlphaFold Meets Flow Matching for Generating Protein Ensembles arxiv.org/abs/2402.04845 Just watch how AlphaFlow's ensemble reproduces details of MD. Weights + code github.com/bjing2016 We have it in the reading group on Mon 11am EST! 1/2
    Image
    GIF
    105K
  • user avatar
    Hannes Stark
    @HannesStaerk
    May 4, 2024
    Intested in KAN: Kolmogorov-Arnold Networks? arxiv.org/abs/2404.19756 Fair, I guess everyone is 🙃 Good that @ZimingLiu11 will join us on Mon May 13th 11am EDT, to discuss it in our Zoom reading group. Sign up for reminders or join our slack here: portal.valencelabs.com/logg
    Image
    46K
  • user avatar
    Hannes Stark
    @HannesStaerk
    Apr 7, 2022
    I am starting my PhD @MIT this summer! ☺️ Me = beyond happy :D I can't wait to work there 👇 in the groups of Profs @BarzilayRegina and Jaakkola! A thousand thanks to my collaborators and friends - I'm looking forward to enjoying even more research and time together! Let's go🤗
    Image
    Image
  • user avatar
    Hannes Stark
    @HannesStaerk
    May 23, 2022
    Our paper "EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction" was accepted to @icmlconf! My first ICML paper🤗arxiv.org/abs/2202.05146 With @octavianEganea (joint first) @lucky_pattanaik @BarzilayRegina and Tommi Jaakkola!
    Image
  • user avatar
    Hannes Stark
    @HannesStaerk
    Aug 8, 2022
    This Tuesday Jinwoo Kim presents his recent "Pure Transformers are Powerful Graph Learners"! arxiv.org/abs/2207.02505 Just tokenize the edges as well and throw everything in a "pure" transformer. Join the discussion on Zoom at 11am EST / 3pm UTC tomorrow: hannes-stark.com/logag-reading-…
    Image
  • user avatar
    Hannes Stark
    @HannesStaerk
    Oct 30, 2021
    How to get a paper accepted at ICLR? Easy: be male, don't live in Asia, submit to RL, have many coauthors, work at FAIR/Google or similar, and write "Theorem" in your paper. In more seriousness, this paper compiles some interesting ICLR statistics: openreview.net/forum?id=1DUwC… 1/9👇
    Image
  • user avatar
    Hannes Stark
    @HannesStaerk
    Apr 9, 2022
    New Video with Professor @nimatabari explaining his Lie-Conv Neural Nets! youtu.be/pvu9auw071A The amazing added bonuses to automatic symmetry discovery are exciting connections to physics! Paper Link: arxiv.org/abs/2109.07103 Join the reading group: hannes-stark.com/logag-reading-…
    Image
  • user avatar
    Hannes Stark
    @HannesStaerk
    Mar 16, 2024
    New paper :) "Dirichlet Flow Matching with Applications to DNA Sequence Design" arxiv.org/abs/2402.05841 TLDR 1. try linear flow matching on simplex 2. oh problem: explain 3. fix it with Dirichlet flow matching 4. Try on DNA, nice, better than language model 1/4
    Image
    56K
  • user avatar
    Hannes Stark
    @HannesStaerk
    Oct 15, 2023
    Reading group Monday: The better perspective on flow matching? 🙃@msalbergo will present everything about their clean stochastic interpolants framework: arxiv.org/abs/2303.08797 arxiv.org/abs/2310.03725… Join on Zoom at 11am EDT / 3pm UTC / 5pm CEST: m2d2.io/talks/logg/abo…
    Image
    63K
  • user avatar
    Hannes Stark
    @HannesStaerk
    Oct 21, 2024
    Reading group session tomorrow: Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold arxiv.org/abs/2408.14608 Learning a flow that can push variable start distributions forward At 9am PT / 12pm ET / 6pm CE(S)T on zoom with link here: portal.valencelabs.com/logg
    Image
    32K
  • user avatar
    Hannes Stark
    @HannesStaerk
    Sep 14, 2024
    Come discuss an @icmlconf best paper award with the author @brekelmaniac in our reading group on Monday! "Probabilistic Inference in LMs via Twisted Sequential Monte Carlo" arxiv.org/abs/2404.17546 On zoom Mon 9am PT / 12pm ET / 5pm CEST. Links: portal.valencelabs.com/logg
    Image
    31K
  • user avatar
    Hannes Stark
    @HannesStaerk
    Oct 5, 2022
    New paper! DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking arxiv.org/abs/2210.01776 1. Diffusion over molecule position, rotation, and torsion angles 2. From 23% accuracy to 38% on a time-split 🤗 3. Confidence estimates with high selective accuracy 1/3
    Image
    00:00
  • user avatar
    Hannes Stark
    @HannesStaerk
    May 11, 2024
    Coming Monday @ZimingLiu11 will present his "KAN: Kolmogorov-Arnold Networks" :) arxiv.org/abs/2404.19756 Clearly this one is popular, but come hear more about what the author thinks to be the most relevant KAN uses and what they can do. On Zoom 11am EDT: portal.valencelabs.com/logg
    Image
    89K