-
doctolib-lab/doctosae-bge-large-en-v1.5
Feature Extraction • Updated • 4 -
doctolib-lab/doctosae-medembed-large-v0.1
Feature Extraction • Updated • 3 -
doctolib-lab/doctosae-gemini-embedding-001
Feature Extraction • Updated • 3 -
Explanations that Transfer: Interpreting Medical Retrieval with Sparse AutoEncoders
Paper • 2611.18179 • Published • 2
AI & ML interests
Healthcare AI
Recent Activity
View all activity
Papers
View all PapersA French medical pretraining corpus, its LLM-rephrased variant, and the annotators that built them.
-
doctolib-lab/doctosae-bge-large-en-v1.5
Feature Extraction • Updated • 4 -
doctolib-lab/doctosae-medembed-large-v0.1
Feature Extraction • Updated • 3 -
doctolib-lab/doctosae-gemini-embedding-001
Feature Extraction • Updated • 3 -
Explanations that Transfer: Interpreting Medical Retrieval with Sparse AutoEncoders
Paper • 2611.18179 • Published • 2
French medical encoders pretrained from scratch on curated and LLM-rephrased medical web data.
A French medical pretraining corpus, its LLM-rephrased variant, and the annotators that built them.