hugpadhugpad

dmis-lab / Gemma4-12B-CVRR

Other1100Updated Sep 28, 2026
Hugging Face

Downloads

110

Likes

0

Last updated

Sep 28, 2026

License

apache-2.0

Latent visual reasoning is not just about storing visual information in hidden states. That information should matter for the model's answer. When an answer decoder can access the original multimodal context through a parallel path, the presence of informative latent states al…

Tasks & library

  • visual question answering
  • transformers

Tags

  • transformers
  • cvrr_merged
  • feature-extraction
  • cvrr
  • custom_code
  • latent-reasoning

Technical specifications

ParametersNot available
Librarytransformers
LanguagesNot available
Base modelgoogle/gemma-4-12B-it
Licenseapache-2.0