Nicolas Deutschmann

534 posts

Nicolas Deutschmann

Nicolas Deutschmann

@nickgermann

ML Researcher @cradlebio GenAI for proteins with a touch of uncertainty quantification. Views are my own. (he/him)

Zurich, Switzerland Katılım Kasım 2007
456 Takip Edilen236 Takipçiler
Sabitlenmiş Tweet
Nicolas Deutschmann
Nicolas Deutschmann@nickgermann·
Our paper got accepted at #AAAI24! 🎉 We propose two new sequence generation algorithms with "error bars", by adapting beam search to conformal predictions. If you use LLMs for science, like predicting molecules or proteins that verify some conditions, check it out!
Nicolas Deutschmann@nickgermann

Here's our preprint on conformal sequence generation! w/ @malberts99 @MariaRoCompBio arxiv.org/abs/2309.03797 Two new algorithms for sequence prediction sets with guarantees: - Conformal sub-beams: pruning standard beams - Conformal dynamic beams: step-by-step conformal decoding.

English
0
8
25
3.3K
Nicolas Deutschmann retweetledi
Proteinbase
Proteinbase@proteinbase·
Today we’re launching Proteinbase, a single hub for experimental protein design data. Over 1,000 novel proteins are already live, each with computational predictions, experimental validation, and the method used to design them. Everything comes from one lab under standardized protocols, which means the results are reproducible, comparable, and include negative data that usually never gets shared.
Proteinbase tweet media
English
6
51
193
13.7K
Nicolas Deutschmann retweetledi
Nathan Benaich
Nathan Benaich@nathanbenaich·
Zurich AI meetup speakers and friends for 4 Mar! - Peter Kontschieder, Research Director at Meta. We met back in Mapillary (acq. Meta) days! - Philippe Schwaller, Asst. Prof at EPFL, AI for chemistry. I love his papers. - Stef van Grieken, CEO at @cradlebio, AI for proteins. We met back in his Google days! This'll be a blast :)
Nathan Benaich tweet media
Nathan Benaich@nathanbenaich

zurich has always been a city where ai thrives on 4 march, @airstreet is coming to zurich to host our ai meetup! join us :-) - 3 talks on research and applied topics with a focus on best practices - 100 people building ai for real - good vibes airstreet(dot)com/zurichai

English
3
4
29
8.4K
Nicolas Deutschmann retweetledi
Miles Cranmer
Miles Cranmer@MilesCranmer·
Nice write up by Kyle! I’ll add on - answering questions like "why do we exist" needs no industrial application! It is the *endgame*, sitting atop Maslow's hierarchy. I prefer asking: "how can technology help us understand ourselves and our universe?"
Kyle Cranmer@KyleCranmer

My first draft of a reaction to @beenwrekt's blog post on the Higgs discovery. TL;DR, yes it did. theoryandpractice.org/2024/10/Yes,%2…

English
1
3
31
3.5K
Nicolas Deutschmann retweetledi
Patrick Kidger
Patrick Kidger@PatrickKidger·
⚡️ New blog post... whilst wearing my Cradle hat!! 🧬 "State-of-the-art enzyme engineering with fully-automated GenAI" cradle.bio/blog/align-to-… TL;DR: Dataset goes in, SOTA protein function models come out. *Zero human intervention required.* 1/3
Patrick Kidger tweet media
English
2
5
46
5.1K
Nicolas Deutschmann
Nicolas Deutschmann@nickgermann·
@DrAndreDavid Conclusion: higher orders are only relevant for asymptotic series with a convergence radius of 0 ;)
English
0
0
0
30
Nicolas Deutschmann retweetledi
Patrick Kidger
Patrick Kidger@PatrickKidger·
✨Aaaand it's time for ICML! DM me or @constance_frg if you'd like to chat about 🧬ML-for-proteins or 🚀startups! :D
Patrick Kidger tweet media
English
2
3
85
7.2K
Nicolas Deutschmann retweetledi
Sylvain Bourmeau
Sylvain Bourmeau@bourmeau·
Si nous étions en Grande-Bretagne ou aux USA, une telle information ne se serait pas enfouie dans un live mais ferait le gros titre de Une du journal, et une équipe de journalistes serait sur la brèche pour savoir si d’autres candidats ont reçu le même message du Président.
Sylvain Bourmeau tweet media
Français
52
2.2K
4.2K
266K
Nicolas Deutschmann retweetledi
Marianna Rapsomaniki
Marianna Rapsomaniki@marianna_raps·
📢 We are hiring! 📢 Are you a MSc/PhD👩‍🎓👨‍🎓 passionate about #AI #ML in #cancer, looking for your next career step? Join our newly-founded AI/ML for Biomedicine group part of the Biomedical Data Science Center at @unil and @CHUVLausanne in beautiful Lausanne!🇨🇭🏔🌈 👇
English
6
82
232
67.3K
Nicolas Deutschmann retweetledi
Marianna Rapsomaniki
Marianna Rapsomaniki@marianna_raps·
Join our Track on #AI for #drugdiscovery at #AMLD2024 March 25 in Lausanne 🇨🇭! 🔥 Sessions on #AI for #molecules, #singlecell #omics 🔊 Stellar invited talks from @mo_lotfollahi @fra_grisoni and @DRoqueiro 🗒️ Submit your abstract and get selected for a short talk or a poster 👇
AMLD Intelligence Summit@appliedmldays

The call for Posters is now open for AMLD EPFL 2024! Passionate about AI and machine learning? Join a track at AMLD EPFL 2024! Find out more here. go.epfl.ch/AMLDTracks Early Bird rates until 25 January. Register now! go.epfl.ch/AMLD #AMLDEPFL2024 #AI #MachineLearning

English
2
3
12
5.5K
Nicolas Deutschmann retweetledi
Marvin Alberts
Marvin Alberts@malberts99·
Interested in Uncertainty Quantification for Sequence Prediction? Come check out our poster at @RealAAAI today. We add rigorous uncertainty quantification to Beam Search using Conformal Predictions! @nickgermann @IBMResearch
Marvin Alberts tweet media
English
1
12
26
2K
Nicolas Deutschmann retweetledi
Alek Sobczyk
Alek Sobczyk@AleksandrosSob1·
We have a new preprint on DFT and eigenvalue algorithms: "Hermitian Pseudospectral Shattering, Cholesky, Hermitian Eigenvalues, and Density Functional Theory in Nearly Matrix Multiplication Time". Link to Arxiv: arxiv.org/abs/2311.10459
English
2
5
22
3.9K
Nicolas Deutschmann retweetledi
Marvin Alberts
Marvin Alberts@malberts99·
Excited our Preprint on Conformal Beam Search with @nickgermann and @MariaRoCompBio is out on @Arxiv. We add rigorous uncertainty quantifications to Beam Search using Conformal Predictions. Applicable to any model without changes in the architecture!! 🔗ibm.biz/conformal_beams
English
1
4
18
2.1K
Nicolas Deutschmann
Nicolas Deutschmann@nickgermann·
One of the cool surprises from this work is how well calibrated the set sizes turned out to be in our experiments with dynamic beam sizes: Great correlation between how wide the beams need to be vs how they actually are. Excited to see how well this holds in other exps!
Marvin Alberts@malberts99

This is relevant for any problem where an autoregressive language model is tasked with generating an exact or approximately exact sequence. Our algorithm generates prediction sets with a guarantee (e.g. 99%) that the correct sequence is present in the set!

English
1
2
9
2.3K
Nicolas Deutschmann retweetledi
Johann Brehmer
Johann Brehmer@johannbrehmer·
Are you dealing with geometric data, be it from molecules or robots? Would you like inductive biases *and* scalability? Our Geometric Algebra Transformer (GATr 🐊) may be for you. New work w/ @pimdehaan, Sönke Behrends, and @TacoCohen: arxiv.org/abs/2305.18415 1/9
Johann Brehmer tweet media
English
4
84
346
85.6K

Keşfet

@cradlebio @CMSExperiment @DrAndreDavid @constance_frg @unil @CHUVLausanne @mo_lotfollahi @fra_grisoni