Marvin Alberts

PhD Student @IBMResearch; Previously MSci Chemistry @imperialcollege | Bringing #AI to Chemistry

[Marvin Alberts @malberts99]

Check out this Video summarising my latest work in @ChemRxiv on predicting Molecular Structure from IR Spectra. @acvaucher @teodorolaino @IBMResearch

Paper: https://t.co/BqH5PPl0eh

Bonus points for those who know what the Molecule tastes like 😉

[Marvin Alberts @malberts99]

Interested in Automating Structure Elucidation using AI? Come check out my talk at #ACSFall2024 . Today at 11:35 in Bluebird Ballroom 2G

[Nina Hartrampf @NinaHartrampf]

Our preprint on “Merging Flow Synthesis and Enzymatic Maturation to Expand the Chemical Space of Lasso Peptides” is now available from @ChemRxiv 🧪🧫. Congratulations to first author Kevin Schiefelbein and everyone else involved 🥳

https://t.co/LUCMkGb4XA @Hartrampf_Lab

[NCCR Catalysis @NCCR_Catalysis]

Thrilled to launch the NCCR Catalysis #Trailblazers series on exceptional individuals breaking barriers! 🤩 On #InternationalWomensDay, meet Alessandra @AlessToniato, a mum of 2 & PhD researcher 👩🏼‍💻 at @IBMResearch with @teodorolaino.
💬 Full interview: https://t.co/FYCi2rXexh

[Marvin Alberts @malberts99]

Thank you for the invitation @drecmb! I had a great time giving a talk on Automated Structure Elucidation in Lausanne @SchwallerGroup!

[Marvin Alberts @malberts99]

@liyucheng_2 @RealAAAI @nickgermann @IBMResearch Thank you!

[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

[Oliver Schilter @OSchilter]

Introducing Clipboard-to-SMILES Converter: a macOS app for effortless conversion of screenshots into molecular structures (SMILES, SELFIES, etc.) right from your clipboard, complete with a convenient history feature!

Check out our paper and download it: https://t.co/gYmDT79ami

[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!

[Alessandra Toniato @AlessToniato]

How to better start Christmas than by defending your PhD? 😊🎄🎓🎉

A super interesting discussion yesterday at @ETH_DCHAB with @teodorolaino @kjelljorner Markus Reiher and Gunnar Jeschke

Thanks to all the people that supported me in this journey !

[Jannis Born @JannisBorn]

We're in 2nd half of #NeurIPS2023, but still much exciting research ahead!Thrilled to present some work from #AI4SD team @IBMResearch. Topics cover quantum computing, foundation models, optimal transport, digitization of lab workflows, language models in molecular design & more⬇️

[Oliver Schilter @OSchilter]

I’m excited to share my work at #NeurIPS2023! Join me at the #AI4Mat and #AI4Science poster session this Friday and Saturday to explore how our AI model seamlessly maps molecules to their H-NMR spectrum! @SchwallerGroup @IBMResearch

[Andrés M Bran @drecmb]

I'll be presenting our work on autonomous agents for chemistry #ChemCrow at the #AI4Science workshop this saturday, do not miss it!

An amazing colab with @SamCox822 @andrewwhite01 @OSchilter @
https://t.co/LXgQeeQ0Fg

[Andrés M Bran @drecmb]

So excited for this!
Thank you @pschwllr for your words, this wouldnt have be possible without all your support and the awesome environment at the @SchwallerGroup!

And ofc kudos to all the students for the amazing work! Super glad to learn so much from you too ❤️

[Robert Palgrave @Robert_Palgrave]

This exciting paper shows AI design of materials, robotic synthesis. 10s of new compounds in 17 days.

But did they?

This paper has very serious problems in materials characterisation. In my view it should never have got near publication. Hold on tight let's take a look 😱

[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:
https://t.co/zHhVJfy9LS

[Nina Hartrampf @NinaHartrampf]

📣 We have 3️⃣ open PhD positions in chemical protein synthesis on our SNSF Sinergia project „MYConnect“ 🧫🧪

Please apply as soon as possible via https://t.co/jCL518VnSz

We look forward to exploring MYC phosphorylation with @ZerbeOliver and Linda Penn!

Thank you @snsf_ch 🙏

[Andrés M Bran @drecmb]

Applications of Transformers in chemistry have evolved a lot over the years, with great success in many tasks! 🚀🧪🚀
Our new review preprint is out 🥳, key points below

Awesome work with @SchwallerGroup @pschwllr @NCCR_Catalysis @EPFL_en

1/n
https://t.co/ht2W4vnr7n

[Marvin Alberts @malberts99]

Particularly exciting for reaction prediction, protein language modelling and structure prediction from spectra!

[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!!
🔗https://t.co/3oE7PRjGNW

[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!