Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
nkkbr
/
ViCA
like
0
Video-Text-to-Text
Transformers
Safetensors
nkkbr/ViCA-322K
nkkbr/ViCA-thinking-2.68k
English
doi:10.57967/hf/7545
llava
text-generation
multimodal
vision-language
video understanding
spatial reasoning
visuospatial cognition
qwen
llava-video
Eval Results (legacy)
arxiv:
2505.12312
arxiv:
2505.12363
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
ViCA
/
assets
/
training_record
641 kB
1 contributor
History:
1 commit
nkkbr
update readme
ed35572
9 months ago
vica-train_grad_norm.svg
226 kB
update readme
9 months ago
vica-train_learning_rate.svg
31.7 kB
update readme
9 months ago
vica-train_loss_with_ema.svg
384 kB
update readme
9 months ago