This repository hosts the full MedHEB-Bench benchmark — a multimodal medical embedding / retrieval benchmark spanning 2D imaging, 3D imaging, and biomedical text. A small reviewer-facing sample (≈ 2.5 GB) is available separately at Test JSON (under 2DTask/, 3DTask/, TextTask/): Train JSONL (under TrainData/) — chat-style records with messages / images / positivemessages: Image paths in test JSONs resolve relative to the matching sub-folder under 2DImages/ / 3DImages/. Train JSONL paths are relative to the repository root. Image archives for the following datasets are not redistributed here because their upstream license / data-use agreements restrict re-hosting. A LICENSENOTICE.md…
Independent publisher
MEDHEB
MEDHEB
Models in Library0
Datasets in Library1
Models on Hugging Face—
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Reported licenses: other. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.