Alex Tong

Alex Tong

@alextong.bsky.social

ML + Cells + Proteins. PI @ AITHYRA https://alextong.net

1.3K followers46 following17 posts

Alex Tong
@alextong.bsky.social

Happy to share I've been named a 2026 #AI2050 Early Career Fellow by @SchmidtSciences. I’ll investigate generative models for molecules as part of a global cohort working to ensure AI benefits society by 2050.

Alex Tong
@alextong.bsky.social

Such an incredible journey building DISCO 🪩. Love working with this team. DISCO is a co-design model with functional, de novo, new-to-nature enzymes. Huge shoutout to my co-authors for making this a reality! 🚀👇

Marta Skreta@martaowesyou.bsky.social

What if AI could invent enzymes that nature hasn’t seen? 👩‍🔬🧑‍🔬 Introducing 🪩 DISCO: Diffusion for Sequence-structure CO-design 📝 Blog: disco-design.github.io 📄 Paper: arxiv.org/abs/2604.05181 💻 Code: github.com/DISCO-design...

Alex Tong
@alextong.bsky.social

Come join us in Vienna! 🇦🇹 I started via this call 6 months ago and couldn't ask for a better place to do AI/ML research. It's a highly collaborative and dynamic institute. Don't hesitate to reach out if you're thinking of applying and have questions!

AITHYRA Research Institute of the Austrian Academy of Sciences@aithyra.bsky.social

AITHYRA is recruiting an AI/ML STARTING PI Generative Models, Large Language Models, Agentic AI, Active & Reinforcement Learning, AI-driven Scientific Discovery & Lab Automation, ML-driven molecular simulations... Job Ad: aithyra.at/fileadmin/do... Apply by 30.4.2026 #StartingPI #AI/ML #AITHYRA

Alex Tong
@alextong.bsky.social

6 Papers (2 Oral 4 poster) at #ICLR from my group amoung the many more from #AITHYRA. See you in Rio!

AITHYRA Research Institute of the Austrian Academy of Sciences@aithyra.bsky.social

AITHYRA at #ICLR: 20 Papers, Including 3 Orals (top 1.2%) #AITHYRA has a strong presence at the upcoming International Conf on Learning Representations (ICLR) taking place in Apr in Rio de Janeiro, Brazil. Congrats to all our team members and collaborators! More info: aithyra.at/news/detail/...

Alex Tong reposted

Michael Bronstein
@mmbronstein.bsky.social

“One of the continuing scandals in the physical sciences is that it remains in general impossible to predict the structure of even the simplest crystalline solids” (John Maddox) OXtal is a new all-atom generative diffusion model addressing this holy grail problem

oxtal.github.ioOXtal: Generative Molecular Crystal Structure PredictionOXtal: Generative Molecular Crystal Structure Prediction
Alex Tong@alextong.bsky.social

🔮Introducing OXtal – a new all-atom diffusion model for crystal structure prediction! We tackle a grand challenge in computational chemistry: predicting the structure of crystalline solids directly from their chemical composition. Paper: arxiv.org/abs/2512.06987 Blog Post: oxtal.github.io 1/8

View full thread
View full thread
Alex Tong
@alextong.bsky.social

Transparency: CSP isn’t solved, but OXtal enables high-throughput CSP screening upstream of physics-based ranking. Future work will address ranking, sample efficiency, and most importantly, the direct design of molecular crystals ⚛️ 🧵6/8

View full thread
Alex Tong
@alextong.bsky.social

Organic crystals are chaotic. Unlike proteins (structured by backbones) or inorganic materials (strong bonds), organic crystals are held together by weak, finicky forces. Simulating usually requires expensive search that takes days. We wanted to do it in seconds at a fraction of the cost. 💰 🧵4/8

Alex Tong
@alextong.bsky.social

To solve the "infinite lattice" problem on a GPU, we developed S4. Instead of predicting the lattice directly, we train on local neighborhoods ("shells"). We teach the model how molecules sit next to each other. At inference, global periodicity naturally emerges from these local rules. 🧵5/8

Alex Tong
@alextong.bsky.social

How do we turn a 2D graph into a 3D crystal? OXtal makes 3 bold choices to enable scalability: 📈 Ditches explicit equivariance for scaling & soft symmetries ✨ Models growth via "Stoichiometric Stochastic Shell Sampling" (S4) 🔮Skips unit-cells to generate full supercells 🧵2/8

Alex Tong
@alextong.bsky.social

OXtal generates crystal structures conditioned on 2D molecular graphs. Trained on 600K data points, it works with: - Rigid molecules - Flexible molecules - Co-crystals Spanning applications in drug discovery 💊 and organic electronics 💡. 🧵3/8

Alex Tong
@alextong.bsky.social

#AITHYRA, Vienna's new Biomedical AI institute, is hiring Postdocs! Come work with us. Openings in: 🔹 Generative AI 🔹 Multimodal ML 🔹 Virology 🔹 Enzyme Function Apply by Nov 20: oeaw.ac.at/aithyra/post... #PostDoc #AI #ML #Vienna #ScienceJobs

oeaw.ac.atPostDoc Search
AITHYRA Research Institute of the Austrian Academy of Sciences@aithyra.bsky.social

The Starting Principal Investigators at #AITHYRA the Research Institute for Biomedical Artificial Intelligence of the OeAW in Vienna invite outstanding candidates to apply for postdoctoral positions in the field of AI/ML & Life Sciences. www.oeaw.ac.at/aithyra/post... Please apply by 20 Nov 2025!

Alex Tong reposted

Simon Olsson
@smnlssn.bsky.social

Registration for this years CHAIR Structured Learning Workshop is open. Speakers include: Klaus Robert Müller, Jens Sjölund, @alextong.bsky.social , @janstuehmer.bsky.social, @arnauddoucet.bsky.social, @marcocuturi.bsky.social , Marta Betcke, Elena Agliari, Beatriz Seoane, Alessandro Ingrosso

ui.ungpd.com2025 CHAIR Structured Learning WorkshopWelcome to the 2025 Chalmers AI Research Center Workshop for Structured Learning. In this workshop we broadly cover topics related to Structured Learning targeting specifically the following questions...
Alex Tong
@alextong.bsky.social

I've spent more compute time than I care to admit calculating the likelihood under flow models. Now 5x-10x faster likelihoods for stochastic flows🤯. Check out our work on SuperDiff for a great use case of model mixing.

Kirill Neklyudov@k-neklyudov.bsky.social

🧵(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!

Alex Tong reposted

Sander Dieleman
@sedielem.bsky.social

Amazing blog post on flow matching, stunning visuals! It also makes the connection with normalising flows crystal clear. Incredible effort!

Mathurin Massias@mathurinmassias.bsky.social

Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition! We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423

Alex Tong reposted

Gabriele Corso
@gcorso.bsky.social

Thrilled to announce Boltz-1, the first open-source and commercially available model to achieve AlphaFold3-level accuracy on biomolecular structure prediction! An exciting collaboration with Jeremy, Saro, and an amazing team at MIT and Genesis Therapeutics. A thread!

You are up to date.