Hannes Stark
@hannes-stark.bsky.social
📤 2809
📥 81
📝 150
MIT PhD Student - ML for biomolecules -
https://hannes-stark.com/
reposted by
Hannes Stark
Sergey Ovchinnikov
13 days ago
Will it bind? A little worried about all the "TTTTTTT" 🧐 But looks cool 😎
1
15
1
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!
13 days ago
3
103
46
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...
20 days ago
0
5
1
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...
27 days ago
0
3
0
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...
about 1 month ago
0
8
0
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...
3 months ago
0
18
3
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...
4 months ago
0
4
0
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...
4 months ago
0
3
0
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...
5 months ago
0
8
1
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...
loading . . .
Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction
YouTube video by Valence Labs
https://www.youtube.com/watch?v=iHDauMATkr0
5 months ago
0
4
1
reposted by
Hannes Stark
Gabriele Corso
5 months ago
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
2
16
1
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...
5 months ago
0
5
1
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...
5 months ago
0
10
0
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...
5 months ago
0
3
0
reposted by
Hannes Stark
MIT Jameel Clinic
5 months ago
📢 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
1
6
4
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...
6 months ago
0
8
2
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...
6 months ago
0
5
0
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...
6 months ago
0
12
3
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
7 months ago
0
14
2
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
8 months ago
0
4
0
reposted by
Hannes Stark
Hannah Wayment-Steele
8 months ago
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
2
84
27
reposted by
Hannes Stark
Hani Goodarzi
8 months ago
Check out this talk from our own Garyk Brixi talking about Evo 2!
add a skeleton here at some point
0
7
4
Video is up! "Genome modeling and design across all domains of life with Evo 2"
youtu.be/Rarn97Wpl1A
With the author Garyk Brixi!
loading . . .
Genome modeling and design across all domains of life with Evo 2 | Garyk Brixi
YouTube video by Valence Labs
https://youtu.be/Rarn97Wpl1A
8 months ago
0
18
4
reposted by
Hannes Stark
Arne Schneuing
8 months ago
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)
loading . . .
2
25
8
reposted by
Hannes Stark
Ilia Igashov
8 months ago
🚨 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
add a skeleton here at some point
1
23
7
reposted by
Hannes Stark
Karsten Kreis
8 months ago
🔥 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!🔥
add a skeleton here at some point
0
7
2
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
8 months ago
1
18
6
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...
8 months ago
2
22
3
reposted by
Hannes Stark
Karsten Kreis
8 months ago
📢📢 "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)
loading . . .
1
39
14
reposted by
Hannes Stark
Rachel (Menghua) Wu
8 months ago
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!
1
4
1
reposted by
Hannes Stark
Chaitanya K. Joshi
8 months ago
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
1
8
1
reading group session tomorrow: "The Importance of Being Scalable: Improving the Speed and Accuracy of Neural Network Interatomic Potentials Across Chemical Domains"
arxiv.org/abs/2410.241...
with the authors Join on zoom 9am PT / 12pm ET:
portal.valencelabs.com/logg
8 months ago
0
2
0
In our reading group session tomorrow, we discuss "Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps"
arxiv.org/abs/2501.09732
with the authors! Join us on Zoom at 9am PT / 12pm ET / 6pm CET:
portal.valencelabs.com/logg
9 months ago
0
2
1
Tomorrow's reading group: "The Superposition of Diffusion Models Using the Itô Density Estimator"
arxiv.org/abs/2412.17762
with the authors! Join on zoom at 9am PT / 12pm ET / 6pm CET:
portal.valencelabs.com/logg
9 months ago
0
7
0
reposted by
Hannes Stark
ML for Protein Engineering Seminar
9 months ago
Next Tues (2/18) at **5PM ET** we will have
@hannes-stark.bsky.social
and Bowen Jing present "ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids" Paper:
openreview.net/forum?id=0ct...
Sign up on our website for zoom links!
loading . . .
ProtComposer: Compositional Protein Structure Generation with 3D...
We develop ProtComposer to generate protein structures conditioned on spatial protein layouts that are specified via a set of 3D ellipsoids capturing substructure shapes and semantics. At inference...
https://openreview.net/forum?id=0ctvBgKFgc
1
4
3
reposted by
Hannes Stark
Kevin K. Yang 楊凱筌
9 months ago
A protein language model trained to predict subcellular localization for human proteins can generate de novo sequences with the desired localization and identify pathological mutations.
@itamarchinn.bsky.social
@pgmikhael.bsky.social
www.science.org/doi/10.1126/...
2
93
19
For the reading group session tomorrow we have another @Nature paper: "Targeting protein–ligand neosurfaces with a generalizable deep learning tool"
www.nature.com/articles/s41...
With three of the authors tomorrow (Mon) on Zoom at 12pm ET / 6pm CET:
portal.valencelabs.com/logg
9 months ago
0
9
0
Tomorrows reading group session is delayed by 30 min! Valentin De Bortoli joins us for his paper "Accelerated Diffusion Models via Speculative Sampling"
arxiv.org/abs/2501.05370
On zoom at 9:30am PT / 12:30pm ET / 6:30pm CET:
portal.valencelabs.com/logg
9 months ago
0
5
0
Reading group session on Monday: Valentin De Bortoli joins us for his paper "Accelerated Diffusion Models via Speculative Sampling"
arxiv.org/abs/2501.05370
On zoom at 9am PT / 12pm ET / 6pm CET:
portal.valencelabs.com/logg
9 months ago
0
14
2
On monday in our reading group we discuss "Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective"
arxiv.org/abs/2412.03487
With Neta Shaul. Join on zoom on Monday at 9am PT / 12pm ET / 6pm CET:
portal.valencelabs.com/logg
10 months ago
0
13
2
Tomorrow in the reading group, we will discuss "PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion" with Sophia Tang! Join us on Zoom at 9pm / 12pm / 6pm CET:
portal.valencelabs.com/logg
10 months ago
1
9
2
Awesome paper! BioEmu from MSR: Scalable emulation of protein equilibrium ensembles with generative deep learning
www.biorxiv.org/content/10.1...
Looking forward to hearing more explanainers in tomorrow's reading group session on zoom at 9am PT / 12pm ET / 6pm CET:
portal.valencelabs.com/logg
10 months ago
1
47
12
Tomorrow, in the reading group, Johannes Brehmer will present his paper "Does equivariance matter at scale?"
arxiv.org/abs/2410.23179
Join us on zoom at 12pm ET / 6pm CET:
portal.valencelabs.com/logg
10 months ago
0
27
4
reposted by
Hannes Stark
amelie-iska
10 months ago
youtu.be/3tIWDOjOlYE?...
loading . . .
Learning Equivariant Non-Local Electron Density Functionals | Nicholas Gao
YouTube video by Valence Labs
https://youtu.be/3tIWDOjOlYE?si=HaOgJsSQt_-TX9uS
0
4
1
reposted by
Hannes Stark
Kirill Neklyudov
11 months ago
🧵(1/7) Have you ever wanted to combine different pre-trained diffusion models but don't have time or data to retrain a new, bigger model? 🚀 Introducing SuperDiff 🦹♀️ – a principled method for efficiently combining multiple pre-trained diffusion models solely during inference!
loading . . .
1
44
11
reposted by
Hannes Stark
Kirill Neklyudov
11 months ago
🧵(3/7)This is all due to an amazing team:
@martaowesyou.bsky.social
@lazaratan.bsky.social
@joeybose.bsky.social
@alextong.bsky.social
📄Paper:
arxiv.org/abs/2412.17762
💻Code:
github.com/necludov/sup...
🤗HuggingFace:
huggingface.co/superdiff
loading . . .
The Superposition of Diffusion Models Using the Itô Density Estimator
The Cambrian explosion of easily accessible pre-trained diffusion models suggests a demand for methods that combine multiple different pre-trained diffusion models without incurring the significant co...
https://arxiv.org/abs/2412.17762
1
15
4
reposted by
Hannes Stark
Gabriele Corso
11 months ago
This is the kind of benchmarking work the field needs!
add a skeleton here at some point
0
14
3
reposted by
Hannes Stark
Janani Durairaj (Jay)
11 months ago
Here's a year-end update from
#PLINDER
. It's been really great working on this project and all the other projects that it has kickstarted - the gift that keeps on giving. Happy holidays everyone!
www.plinder.sh/blog/updates
loading . . .
Updates
Updates
https://www.plinder.sh/blog/updates
0
38
15
reposted by
Hannes Stark
Christian Dallago
11 months ago
Two major life updates: - I'm moving to Senior Applied Research Scientist in Digital Biology at NVIDIA (Jan '25) - I'm starting a new lab at Duke as Visiting Assistant Prof (early '25) Both roles focus on tackling hard problems in biological machine learning through collaborative research. Long 🧵
16
97
8
reposted by
Hannes Stark
Science News
11 months ago
MIT researchers introduce Boltz-1, a fully open-source model for predicting biomolecular structures With models like AlphaFold3 limited to academic research, the team built an equivalent alternative, to encourage innovation more broadly
www.eurekalert.org/news-release...
loading . . .
MIT researchers introduce Boltz-1, a fully open-source model for predicting biomolecular structures
Researchers in the MIT Jameel Clinic for Machine Learning in Health developed a fully open-source biomolecular structure prediction model that achieves state-of-the-art performance, at the level of Al...
https://www.eurekalert.org/news-releases/1068549
0
84
28
Load more
feeds!
log in