LiGHT: Laboratory for Intelligent Global Health and Humanitarian Response Technologies
Popular repositories Loading
-
FullyOpenMeditron
FullyOpenMeditron PublicWe release Open Meditron, a fully open, clinician-audited medical training corpus and evaluation protocol that closes the open-vs-closed gap on open-ended clinical evaluation.
-
LiGHT-Conferences-Calendar
LiGHT-Conferences-Calendar PublicTrack research conference deadlines: calendar, countdowns, ICS export, Slack reminders
TypeScript 16
-
-
talk2yourdata
talk2yourdata PublicTalk2YourData MCP is a production-ready AI orchestrator that enables natural language querying of DHIS2 health data.
Repositories
- BiGHT-course Public
This course teaches the principles and practice of designing, building, and rigorously evaluating trustworthy, representative, and contextually appropriate AI systems for high-stakes decision making in global health and humanitarian response.
- LiGHT-Conferences-Calendar Public
Track research conference deadlines: calendar, countdowns, ICS export, Slack reminders
- mmore Public
Ever needed to take 8000 PDFs, 2000 videos, and 500 spreadsheets and feed them to an LLM as a knowledge base? Well, mmore is here to help you! mmore is a scalable multimodal pipeline for processing, indexing, and querying multimodal documents
- FullyOpenMeditron Public
We release Open Meditron, a fully open, clinician-audited medical training corpus and evaluation protocol that closes the open-vs-closed gap on open-ended clinical evaluation.
- talk2yourdata Public
Talk2YourData MCP is a production-ready AI orchestrator that enables natural language querying of DHIS2 health data.
-
-
- Asthmoscope-MDPI-2025 Public
- DeepBreath-NatMed23 Public
- MyTH Public
This code implements MyTH, an approach for privacy-preserving and visually interpretable identification of data bias in federated learning for images (the paper is under review in npj Digital Medicine). Authors: Klavdiia Naumova (EPFL), Arnout Devos (ETH), Sai Praneeth Karimireddy (UC Berkeley, USC), Martin Jaggi (EPFL), Mary-Anne Hartley (Yale)
Most used topics
Loading…