ORCA-3DCT — precomputed 3D CT visual tokens & Data Encoder outputs for the whole of CT-RATE, released so that work on 3D CT token compression, pooling, retrieval and probing does not have to start by spending several hundred GPU-hours re-encoding the corpus. ctrate/uncompressed/ — the raw encoder grids, plus the pooled encoders' native output. Bring your own compressor. ctrate/compressed/ — ORCA and grid-average token
Independent publisher
Liang Renjie
LiangRenjie
Models in Library0
Datasets in Library1
Models on Hugging Face6
Followers1
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.
Published tasks: Image feature extraction.
Reported licenses: cc-by-nc-sa-4.0. 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.