release aidev NEEDS REVIEW SIG 1/5

MiniMax publishes VTP-Large image feature extraction model

MiniMax published VTP-Large-f16d64 on Hugging Face, a larger variant of the VTP image-feature-extraction model family (arxiv:2512.13687). No capability or benchmark details are available beyond the pipeline tag.

PUBLISHED2025-12-16
OBSERVED2026-08-11
AGE8mo
SOURCES1

Model published on Hugging Face under MiniMaxAI organisation.

  • Pipeline: image-feature-extraction
  • Library: transformers
  • Tags: vtp, safetensors, arxiv:2512.13687, endpoints_compatible
  • License: other
model-support

COMMUNITY

No curated reactions recorded for this event. Facts and takes are kept in separate layers — community context is added by hand, never blended into the record above.