MICDE recently organized the SciFM conference and had an incredible reception for the event. Based on the feedback from that meeting and further discussions with National Lab and academic partners, we are excited to organize the SciFM Summer School from July 8 to July 26. We wish for this to be a recurring event hosted at different locations across the country. The first instance is going to be run in parallel at the University of Michigan (UM) and at Argonne National Laboratory (ANL). The summer school will:
Fill in the google form below or access it here.
Welcome and Summer School Goals
Successes of SciFM
FoundSci DARPA program
FoundSci DARPA program
Vision for SciFM Institute
09:30
-Tutorial 1a - Data Modalities
01:30
-Tutorial 1b - Tokenization
09:30
-Tutorial 2a - Training Models
01:30
-Tutorial 2b - Diffusion Models
03:00
-Tutorial 2c - Scaling Laws
09:30
-Tutorial 3a - Retrieval-Augmented Generation (RAG)
01:30
-Tutorial 3b - Agents for Biology
03:00
-Tutorial 3c - Agents for Chemistry
Goal Setting for Hackathon
Hackathon
Tutorial 4 - AI Accelerators - GPUs and Specialized Hardware
Tutorial 5 - Federated Learning
Hackathon
Hackathon Team Presentations
Keynote - Open questions for Foundation Models for Science
Panel - Security, Equity, Safety
Ecosystem Gathering (Academia, National Labs, Venture Funding, Philanthropy)
Future Outlook
Participants will explore innovative applications of Foundation Model in four application domains:
Foundation Models for material science have been used for a range of material property prediction, retrosysnthesis and structure search tasks.
In Biology, Foundation Models have enable numerous breakthroughs including protein structure prediction and the classfication of emergent variants of viruses.
A Computational Science Foundation Model capable of designing and orchestrating computational research campaigns will enable scientists to focus on domain science through the creative specification of hypotheses and greatly accelerate scientific discovery.
Foundation Models may be the route to enabling data efficient, general purpose PDE solvers.