Sign in

Hannes Stark

@hannes-stark.bsky.social
2.9K followers 83 following 167 posts

MIT PhD Student - ML for biomolecules - hannes-stark.com

PostsRepliesMedia
Hannes Stark @hannes-stark.bsky.social · 06/09/2026
Nobel Prize winner talks about how he works, how to "challenge your brain", and his research. 15 minutes well spent! open.spotify.com/episode/4Cx0...
open.spotify.com
Episode 37: Mario R. Capecchi (Nobel Prize for Medicine and Physiology): The first knockout-mice and anxiety in pigs
Paper Podcast · Episode
030
Hannes Stark @hannes-stark.bsky.social · 06/09/2026
If you can make it to Boston on Oct 14th, consider submitting a paper to the MIT Molecular ML conference! 2-4 pages 🤗 www.moml.mit.edu/submit
010
Hannes Stark @hannes-stark.bsky.social · 18/05/2026
Monday reading group: a bit of insight in autoregressive protei nstructure generation given a tokenization scheme. "Adaptive Protein Tokenization" with @rohit_dilip_ arxiv.org/abs/2602.06418 On Zoom 12pm ET / 6pm CEST: hannes-stark.com/starkly-spea...
030
Hannes Stark @hannes-stark.bsky.social · 12/05/2026
Super fun session today discussing DISCO enzyme design with @jarridrb, @martoskreto, and Chenghao Liu! www.youtube.com/watch?v=btJq...
youtube.com
General Multimodal Protein Design Enables DNA-Encoding of Chemistry
YouTube video by Valence Labs
021
Hannes Stark @hannes-stark.bsky.social · 04/05/2026
Reading group tomorrow (Monday) about "Leveraging Discrete Function Decomposability for Scientific Design" arxiv.org/abs/2511.03032 With James Bowden from Jennifer Listgarten lab! Join on Zoom at 9am PT / 12pm ET / 6pm CEST: hannes-stark.com/starkly-spea...
050
Hannes Stark @hannes-stark.bsky.social · 28/04/2026
Would be fun to see some of you at my thesis defense on Friday, May 1st, 11:15 am ET :) 🤗 "Generative Models for Biomolecular Structures and Design" www.csail.mit.edu/event/thesis... At MIT, 32 Vassar Street (Stata Center), Room G449 (Kiva)
260
Hannes Stark @hannes-stark.bsky.social · 30/03/2026
Reading group tomorrow: One-step Language Modeling via Continuous Denoising arxiv.org/abs/2602.16813 With @nmboffi 🤗 Join us on zoom Monday at 9am PT / 12pm ET / 6pm CEST: hannes-stark.com/starkly-spea...
050
Hannes Stark @hannes-stark.bsky.social · 21/03/2026
Join our reading group session with the NVIDIA team about their new Proteina binder design model with the authors Karsten Kreis and Kieran Didi! Paper: research.nvidia.com/labs/genair/... Zoom link for Monday 9am PT / 12pm ET / 5pm CET: portal.valencelabs.com/starklyspeak...
0121
Reposted by Hannes Stark
Anton Bushuiev @anton-bushuiev.bsky.social · 05/03/2026
ProteinTTT is now easy to run on Hugging Face Spaces and Google Colab. We’ll also be presenting the paper at ICLR 2026 🇧🇷 🤗 Hugging Face Space: huggingface.co/spaces/pimen... ⚙️ Google Colab: colab.research.google.com/drive/1l_h7c... 🧵👇
2429
Hannes Stark @hannes-stark.bsky.social · 05/03/2026
We have a little new paper at ICLR led by @AntonBushuiev. Test time training for proteins :) arxiv.org/abs/2411.02109 For example, you know the sequence that you want to fold, so fine-tune ESM on it at test time to get a better ESMFold structure prediction!
092
Hannes Stark @hannes-stark.bsky.social · 01/03/2026
Video of our discussion with MingYang Deng about his paper "Generative Modeling via Drifting"! A new perspective on generative modeling, admitting a one-step model with performance similar to diffusion/flow models on ImageNet and other tasks: www.youtube.com/watch?v=4eHn...
youtube.com
Generative Modeling via Drifting | MingYang Deng
YouTube video by Valence Labs
050
Reposted by Hannes Stark
Data Science Institute @dsi-uchicago.bsky.social · 06/02/2026
Explore BoltzGen, an all-atom generative model for designing proteins and peptides across all modalities, at today’s AI & Scientific Discovery Online Seminar! Featuring @hannes-stark.bsky.social, PhD student at MIT Join us online or at DSI at 11am CT - ai-scientific-discovery.github.io
031
Hannes Stark @hannes-stark.bsky.social · 21/02/2026
Join us on Monday to discuss "Generative Modeling via Drifting" with the author MingYang Deng! A one-step generative model trained with an MMD loss. On Zoom at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/starklyspeak...
060
Hannes Stark @hannes-stark.bsky.social · 01/02/2026
Tomorrow in the reading group we discuss "SeedFold: Scaling Biomolecular Structure Prediction" arxiv.org/abs/2512.24354 Outperforming AF3 on multiple tasks a little bit. Join us on zoom at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/starklyspeak...
091
Hannes Stark @hannes-stark.bsky.social · 25/01/2026
In the reading group tomorrow we discuss "SLAE: Strictly Local All-atom Environment for Protein Representation" with Yilin Chen from @PossuHuangLab! www.biorxiv.org/content/10.1... Join us on Zoom at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/starklyspeak...
040
Hannes Stark @hannes-stark.bsky.social · 01/01/2026
A video where I present our biomolecular binder design model, BoltzGen! youtu.be/9d_QWUUI1Qo Happy New Year! I am very excited to continue working in our amazing ML for bio community in 2026 - let's continue! 🤗
youtu.be
BoltzGen: Toward Universal Binder Design | Generative AI for Drug Discovery (Hannes Stark, MIT)
YouTube video by Hannes Stärk
0100
Hannes Stark @hannes-stark.bsky.social · 11/12/2025
Join our online BoltzGen presentation and Q&A on Wed. Dec. 17th at noon ET! A few new results, many new insights, and lots of good discussion, I am sure! Paper: www.biorxiv.org/content/10.1... Presentation sign up + Zoom: luma.com/b24bd37m
luma.com
BoltzGen Zoom presentation + Q&A · Zoom · Luma
Join us on Zoom on Wednesday, Dec. 17th for details on our new model BoltzGen and discussions on the future of biomolecular design 🧬 There will be a 35 minute…
041
Hannes Stark @hannes-stark.bsky.social · 24/11/2025
Today in the reading group in 5h we discuss Germinal with the authors! "Efficient generation of epitope-targeted de novo antibodies with Germinal" www.biorxiv.org/content/10.1... On zoom at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/starklyspeak...
biorxiv.org
Efficient generation of epitope-targeted de novo antibodies with Germinal
Obtaining novel antibodies against specific protein targets is a widely important yet experimentally laborious process. Meanwhile, computational methods for antibody design have been limited by low su...
030
Hannes Stark @hannes-stark.bsky.social · 16/11/2025
Reading group tomorrow: "How to build a consistency model: Learning flow maps via self-distillation" with Nicholas Boffi! arxiv.org/abs/2505.18825 Join us on zoom at 9am PT, 12pm ET, 6pm CET: portal.valencelabs.com/starklyspeak...
0122
Reposted by Hannes Stark
Sergey Ovchinnikov @sokrypton.org · 27/10/2025
Will it bind? A little worried about all the "TTTTTTT" 🧐 But looks cool 😎
1171
Hannes Stark @hannes-stark.bsky.social · 26/10/2025
Excited to release BoltzGen which brings SOTA folding performance to binder design! The best part of this project is collaborating with a broad network of leading wetlabs that test BoltzGen at an unprecedented scale, showing success on many novel targets and pushing the model to its limits!
310341
Hannes Stark @hannes-stark.bsky.social · 19/10/2025
Reading group session on Monday: "Lookup multivariate Kolmogorov-Arnold Networks" arxiv.org/abs/2509.07103 with Sergey Pozdnyakov On zoom at 9am PT / 12pm ET / 6pm CE(S)T: portal.valencelabs.com/starklyspeak...
061
Hannes Stark @hannes-stark.bsky.social · 12/10/2025
Tomorrow on Zoom we talk with Tobias Kreimann about his "Transformers Discover Molecular Structure Without Graph Priors" arxiv.org/abs/2510.02259 Experiments on the new OMol25 dataset! On zoom 9am PT / noon ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
040
Hannes Stark @hannes-stark.bsky.social · 05/10/2025
Tomorrow we have a reading group session with @nscorley and @SimMat20 about "Accelerating Biomolecular Modeling with AtomWorks and RF3" www.biorxiv.org/content/10.1... We will also discuss how to close the gap between AF3 and its open source replications! portal.valencelabs.com/starklyspeak...
090
Hannes Stark @hannes-stark.bsky.social · 04/08/2025
Tomorrow we discuss diffusion models for sampling unnormalized densities "Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching" arxiv.org/abs/2504.11713 Join us on zoom at 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
0193
Hannes Stark @hannes-stark.bsky.social · 21/07/2025
In 1h we discuss "Predicting cellular responses to perturbation across diverse contexts with State" in the reading group with the author Abhinav Adduri! www.biorxiv.org/content/10.1... Join us on zoom at 9am PT / 12pm ET: portal.valencelabs.com/starklyspeak...
050
Hannes Stark @hannes-stark.bsky.social · 29/06/2025
Starkly Speaking tomorrow: @bwood_m will present "UMA: A Family of Universal Models for Atoms" ai.meta.com/research/pub... Join us on Zoom 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
040
Hannes Stark @hannes-stark.bsky.social · 22/06/2025
Monday Starkly Speaking: we understand a core diffusion model ingredient better - classifier free guidance. Via "Classifier-Free Guidance: From High-Dimensional Analysis to Generalized Guidance Forms" arxiv.org/abs/2502.07849 On Zoom 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
091
Hannes Stark @hannes-stark.bsky.social · 18/06/2025
Presentation of Boltz-2 by @pas_saro @GabriCorso @jeremyWohlwend! Structure models and careful affinity data handling result in an affinity predictor approaching FEP accuracy at 1000x the speed. www.youtube.com/watch?v=iHDa...
youtube.com
Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction
YouTube video by Valence Labs
051
Reposted by Hannes Stark
Gabriele Corso @gcorso.bsky.social · 14/06/2025
Thank you everyone for attending the Boltz-2 Boston, San Francisco and Paris events this week! Given the success of the in-person seminars and the many requests, we are organizing a virtual seminar on Tuesday at 12pm ET / 6pm CET! Sign up here: lu.ma/4bpuwbsr
2161
Hannes Stark @hannes-stark.bsky.social · 14/06/2025
On Tue 12pm ET on Zoom: Saro Passaro, Gabriele Corso, Jeremy Wohlwend will present Boltz-2! bit.ly/boltz2-pdf Structure models and careful affinity data handling result in an affinity predictor approaching FEP accuracy at 1000x the speed. Zoom link: portal.valencelabs.com/starklyspeak...
061
Hannes Stark @hannes-stark.bsky.social · 08/06/2025
Tomorrow in our reading group we will discuss "Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional" arxiv.org/abs/2504.18506 On zoom 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
0110
Hannes Stark @hannes-stark.bsky.social · 01/06/2025
Reading group tomorrow: Identifying perturbation targets through causal differential networks arxiv.org/abs/2410.03380 With @menghua_wu! Join us on Zoom at 9am PT 12pm ET 6pm CEST: portal.valencelabs.com/starklyspeak...
040
Reposted by Hannes Stark
MIT Jameel Clinic @mitjameelclinic.bsky.social · 28/05/2025
📢 Thrilled to announce the return of MoML @ MIT on Oct. 22 and that paper submissions are now open! Students & postdocs w/ accepted papers will be granted FREE admission to attend and have the chance at winning the Octavian-Eugen Ganea Prize for Best Paper! 🧵 #AcademicSky #compchem #drugdesign
Graphic that reads "MoML @ MIT Call for Papers | 6th Molecular Machine Learning Conference" followed by smaller text that says "Topics of interest include but are not limited to: Geometric deep learning • Graph machine learning • Molecular dynamics • Structure prediction • Machine learning for quantum chemistry"At the bottom third of the graphic, the text reads "Deadline: Friday, Sept. 26, 2025 | Conference Date: Wednesday, Oct. 22, 2025 | Win a cash prize of $1,526 for Best Paper!"
174
Hannes Stark @hannes-stark.bsky.social · 25/05/2025
Tomorrow @TimothyDuignan joins us to discuss "Orb-v3: atomistic simulation at scale" arxiv.org/abs/2504.06231 and surrounding models to get our understanding of that field up to date! On Zoom 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
092
Hannes Stark @hannes-stark.bsky.social · 18/05/2025
Tomorrow the authors @YuanqiD and Jiajun He will present their paper "FEAT: Free energy Estimators with Adaptive Transport" arxiv.org/abs/2504.11516 Estimating FED is a strong tool for comparing drug's binding affinities Join us on zoom at 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
050
Hannes Stark @hannes-stark.bsky.social · 11/05/2025
Reading group tomorrow: @json_yim and @woodyahern present "Atom level enzyme active site scaffolding using RFdiffusion2" www.biorxiv.org/content/10.1... Join on Zoom at 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeak...
0123
Hannes Stark @hannes-stark.bsky.social · 20/04/2025
In the reading group sessions tomorrow Ezra Erives, I and whoever joins, will discuss "A General Framework for Inference-time Scaling and Steering of Diffusion Models" arxiv.org/abs/2501.06848 On zoom at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/logg
0132
Hannes Stark @hannes-stark.bsky.social · 23/03/2025
Reading group session tomorrow, March 24th, is at 3pm PT / 6pm ET / midnight CEST about: "One-step Diffusion Models with f-Divergence Distribution Matching" arxiv.org/abs/2502.15681 Presented by @xuyilun2 Zoom link: portal.valencelabs.com/logg
040
Reposted by Hannes Stark
Hannah Wayment-Steele @hkws.bsky.social · 20/03/2025
Protein dynamics was the first research to enchant me >10yrs ago, but I left in PhD bc I couldn't find big experimental data to evaluate models. Today w @ginaelnesr.bsky.social, I'm thrilled to share the big dynamics data I've been dreaming of, and the mdl we trained w them: Dyna-1. 📝: rb.gy/de5axp
28425
Reposted by Hannes Stark
Hani Goodarzi @genophoria.bsky.social · 14/03/2025
Check out this talk from our own Garyk Brixi talking about Evo 2!
074
Hannes Stark @hannes-stark.bsky.social · 13/03/2025
Video is up! "Genome modeling and design across all domains of life with Evo 2" youtu.be/Rarn97Wpl1A With the author Garyk Brixi!
youtu.be
Genome modeling and design across all domains of life with Evo 2 | Garyk Brixi
YouTube video by Valence Labs
0183
Reposted by Hannes Stark
Arne Schneuing @rne.bsky.social · 07/03/2025
The code & camera-ready version of our #ICLR2025 paper on "Multi-domain Distribution Learning for De Novo Drug Design" are now available 📚 Paper: openreview.net/forum?id=g3V... 💻 Code: github.com/LPDI-EPFL/Dr... (1/4)
2257
Reposted by Hannes Stark
Ilia Igashov @igashov.bsky.social · 11/03/2025
🚨 Check out DrugFlow, our new generative model for structure-based drug design. DrugFlow provides an atom-level confidence score for each designed molecule, and can adjust molecular size on the fly! Additional details in thread 🧵 #ICLR2025
1237
Reposted by Hannes Stark
Karsten Kreis @karstenkreis.bsky.social · 11/03/2025
🔥 ProtComposer (ICLR'25 Oral) is a Swiss Army knife: (i) Manually create new protein structure layouts? ✅ (ii) Generation with favorable designability/diversity/novelty trade-offs? ✅ (iii) Spatially edit given proteins? ✅ Very original work by the amazing @hannes-stark.bsky.social and Bowen Jing!🔥
072
Hannes Stark @hannes-stark.bsky.social · 10/03/2025
New paper (and #ICLR2025 Oral :)): ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids arxiv.org/abs/2503.05025 Condition on your 3D layout (of ellipsoids) to generate proteins like this or to get better designability/diversity/novelty tradeoffs. 1/6
1185
Hannes Stark @hannes-stark.bsky.social · 09/03/2025
The Evo 2 authors join us tomorrow in the reading group to discuss their paper: "Genome modeling and design across all domains of life with Evo 2" www.biorxiv.org/content/10.1... Join on zoom (Monday) at 9am PT / 12pm ET / 6pm CET: www.biorxiv.org/content/10.1...
2223
Reposted by Hannes Stark
Karsten Kreis @karstenkreis.bsky.social · 04/03/2025
📢📢 "Proteina: Scaling Flow-based Protein Structure Generative Models" #ICLR2025 (Oral Presentation) 🔥 Project page: research.nvidia.com/labs/genair/... 📜 Paper: arxiv.org/abs/2503.00710 🛠️ Code and weights: github.com/NVIDIA-Digit... 🧵Details in thread... (1/n)
13910
Reposted by Hannes Stark
Rachel (Menghua) Wu @rachelwu.bsky.social · 04/03/2025
Excited to share my #ICLR2025 paper, with JC Hütter and friends! Genetic perturbation screens allow biologists to manipulate and measure the genes in cells = discover causal relationships! BUT they are expensive to run, expensive to interpret. ... We use LLMs to help!
141
Reposted by Hannes Stark
Chaitanya K. Joshi @chaitjo.bsky.social · 04/03/2025
Feeling mostly very relieved to share that gRNAde was accepted at @iclr-conf.bsky.social as a Spotlight! What started as a side project over 2 years ago has lead to a spotlight paper and a new scientific journey for me -- Here I am learning how to pipette :D
181