multimodal_cognitive_ai

multimodal_cognitive_ai copied to clipboard

The code of LVLM Interpret.

2

Thank you for the amazing work: LVLM Interpret. Whether the relevant code will be open-sourced in the near future?

mrwu-mac

about counting

1

Hi, author, if image caption is about counting , e.g. There are four birds in the sky. How to generate counterfactual image，**Change all birds to other animals**？

mirial65

wuhongyan123

Yanli2190

Bumps the pip group with 1 update in the /Demos/NeuroPrompts directory: [gradio](https://github.com/gradio-app/gradio). Updates `gradio` from 3.39.0 to 4.37.1 Release notes Sourced from gradio's releases. @​gradio/model3d@​0.11.2 Dependency updates @​gradio/atoms@​0.7.8 @​gradio/icons@​0.6.1 @​gradio/utils@​0.5.2...

dependabot[bot]

Great work! Could you please let us know when the code for COCO-Counterfactuals will be released?

ShaoqLin

Hi, I am wondering whether this support training for second gen Gemma based llava. When we trained with the new Gemma with this repo, we ran into an error of:...

shan23chen