Michael Cardei

Excited to share that our work "Neuro-Symbolic Generative Diffusion Models" received a DARPA Disruptive Idea Award at NeuS 2025! 🌟

This work pushes toward integrating symbolic reasoning and generative modeling to meet the safety and robustness demands of scientific applications.

🙋‍♂️

Excited to share our #NeurIPS2024 work on combining diffusion models with constrained optimization to generate data adhering to constraints and physical principles (with guarantees!) will be a spotlight at the workshop on AI for Accelerated Materials Design!

🔗 arxiv.org/abs/2402.03559

Bluesky is emerging as the new platform for science - Mike Young Academy Scientific Twitter is about to find its true successor. And it is not X. This, our latest release, shows that the Bluesky network of scientists is growing — and growing.

A mapping of how Bluesky is becoming the new Scientific Twitter

mikeyoungacademy.dk/bluesky-is-e...

GitHub - gle-bellier/flow-matching: Annotated Flow Matching paper Annotated Flow Matching paper. Contribute to gle-bellier/flow-matching development by creating an account on GitHub.

I created 3 introductory notebooks on Flow Matching models to help get started with this exciting topic! ✨

1. Annotated Flow Matching paper: github.com/gle-bellier/...
2. Discrete Flow Matching: github.com/gle-bellier/...
3. Minimal FM in Jax: github.com/gle-bellier/...

I'm making a list of AI for Science researchers on bluesky — let me know if I missed you / if you'd like to join!

go.bsky.app/AcP9Lix

Would love to join!

This looks great, would appreciate to be added

Super cool, would appreciate to be added :)