metadata
license: apache-2.0
tags:
- multimodal
- vision-language
- video understanding
- visuospatial cognition
- spatial reasoning
- vlm
- llava
- qwen
- siglip
- hiera
- sam2
- dual-encoder
language:
- en
library_name: transformers
pipeline_tag: video-text-to-text
model_name: ViCA2-7B-Init
Usage and Full Documentation
For detailed model description, training setup, datasets, evaluation results, and inference code, please refer to the following links:
