HiRED icon indicating copy to clipboard operation
HiRED copied to clipboard

Published 9 months ago • verified publisher icon hasanar1f
→

Metadata

[AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Vision-Language Models (e.g., LLaVA-Next) under a fixed token budget...

Results 2 HiRED issues
Sort by recently updated
recently updated
newest added

What model was used in the paper ?

6 comment

Hello, in the paper, you said that you are using LLaVA-Next-7B; however, there is no 7B version of LLaVA-Net. Can you refer me to the Hugging Face page of the...

Mohamed-Dhouib avatar Mohamed-Dhouib

pre-trained models.

1 comment

Hello, I am very interested in your work and was wondering when you might be providing the training scripts and pre-trained models. Thank you!

Han-jiaxin avatar Han-jiaxin

← Metadata

43
Stars
6
Forks
43
Watchers

Owner

verified publisher icon hasanar1f

Metadata

[AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Vision-Language Models (e.g., LLaVA-Next) under a fixed token budget...

Back