AI Research Foundry London: Session 02 - Generative Design in AI for Science
AI Research Foundry London is a paper club for AI researchers. Free forever. It's a community not a sales pitch.
Session 02: Generative Design in AI for Science
Statistical structure in physical design spaces
What if AI could help us explore vast design spaces and discover promising solutions we might never have imagined, without having to simulate or physically test every candidate?
Inspired by a recent essay by Anima Anandkumar on how AI could push the frontiers of scientific discovery, this session brings together researchers from across science and engineering domains to discuss the current capabilities and open challenges of generative design.
Four talks from researchers in industry and academia: the papers and the research they are pursuing. 20 minutes each, plus 10 minutes Q&A. Talks start around 6:30pm.
Speakers
Sanmitra Ghosh - PhysicsX, Principal Research Scientist
Highlights
Generative optimization and inverse design for engineering.
Olivia Gallup - University of Oxford / InstaDeep, ML Researcher
Highlights
Generative design of synthetic gene circuits for functional and evolutionary properties.
Bridget J. Li - Latent Labs, ML Research Scientist
Highlights
MIT research on integrating spatial transcriptomics data across species.
Janosch Menke - deepmirror, Research Engineer
Highlights
Generative chemistry for drug design.
Who it's for
AI researchers in academia, big tech and startups. People who want to dig into how AI systems work, how to build them better and how to understand them.
How it works
We start with a paper discussion, then open it up. Read the paper if you can. We share links to summaries before the session.
Why
London has communities for builders. It has nothing for researchers to go deep on one shared idea. So we are making it.
Seminar room energy. Lots of curiosity. A hunger to push the frontier.
