REMEMBER WHO YOU ARE

Sleep well, NY.

HISTORY.

New episode of The Information Bottleneck is out 🥳🥳🥳 with Max Welling (@wellingmax ) Max is a legend and a personal hero of mine, so this one meant a lot. We got into which scientific problems ML can actually touch right now vs what's still too early, what the loop looks like when simulators, wet labs, and real experiments all feed back into each other, where the field is way too optimistic about generalization, and how you handle uncertainty when being wrong costs you a month in the lab. Also the academia → CuspAI shift and what it changed for him. One of my favorite conversations we've done.

This image doesn’t even seem real. It seems like something from the 60s. Absolutely incredible.

Today @cusp_ai and @KemiraGroup announce a milestone in AI-driven materials discovery. We have used generative AI to design new materials targeting PFAS removal from drinking and process water at trace concentrations.

The bitter lesson in 26 words: Don’t be distracted by human knowledge, as AI has been historically. Instead focus on methods for creating knowledge that scale with computation, like search and learning.

We put the paper online that provides further details (beyond my ICLR keynote) on the role of spontaneous symmetry breaking and Goldstone modes in deep learning. Enjoy! (w/ Nabil Iqbal, Thomas Andy Keller, Takeru Miyato and Yue Song.) arxiv.org/abs/2605.14685

Our perspective on closing the synthesis gap in computational materials design is now live @NatureSynthesis ! We survey how thermodynamic potentials, chemical heuristics, and machine learning models can guide compound selection, and argue the path forward couples generation, synthesis planning, and experimental validation in agentic workflows. With @lonepair , @hspark1212 , Kinga Mastej, and Panyalak Detrattanawichai. Thanks to @AIchemyHub for the funding. Read the full text: rdcu.be/fhbWG

Two papers accepted to ICML 🥳 See you all in Seoul 🇰🇷

Categorical Flow Maps got accepted to #ICML2026 🎉 See you in 🇰🇷 :D Many thanks to @osclsd @daan_roos_ @mmbronstein @wellingmax @ismaililkanc @LucaAmb and @jwvdm ♥️ Wanna know more about flow-based LLMs: flow-based-llms.github.io/

Three years since the first flight of Starship, the next generation is here. New ship. New booster. New engines. New pad and new test site. SpaceX engineers are working to solve one of the most difficult engineering challenges in history: developing a fully, rapidly reusable rocket

Molecular simulation is the backbone of drug discovery and materials science, but it’s notoriously complex. Today, we’re excited to open source kUPS - a molecular simulation engine built for the AI era, optimized for GPU in collaboration with @nvidia.

I’ve joined @cusp_ai as a Member of Technical Staff, working on agentic systems for high-throughput materials discovery 🤖✖️💎!

Sky placed 🥇 1st out of 115 team projects globally and won the @LilaSciences Prize 🏆 at the LLM Hackathon for Applications in Materials Science & Chemistry. Massive thanks to my incredible teammates Hyunsoo Park @hspark1212 and Kinga Mastej, our supervisor Prof. Aron Walsh, the Department of Materials (@ImpMaterials ) and Imperial College London @imperialcollege for supporting us in hosting the LLM Hackathon at the London site, and the entire LLM Hackathon for Applications in Materials Science & Chemistry community led by Ben Blaiszik @BenBlaiszik Finally, huge gratitude to the sponsors & partners of the event, and every participant pushing #AI4Science forward. Meet Sky 👋 : youtu.be/ffLqLH87yLo?si=b1_p… Work with Sky ⚡ : github.com/hspark1212/synthe… Related work: Our synthesisability preprint: "Closing the synthesis gap in computational materials design" - chemrxiv.org/engage/chemrxiv… MatSX ( 🏆 🇰🇷 2025 KRICT Hackathon winner): github.com/hspark1212/MatSX

My tools are those of a mathematician, but my aesthetic is that of an early natural scientist.