Follow the instructions to install dependencies. git clone [email protected]:OreoChocolate/LAIN.git conda create -n lain python=3.8.18 conda activate lain conda install pytorch==2.4.1 torchvision==0.19.1 ...
TL;DR (1) - Add an adaptive mask onto the image to enhance LVLM performance. TL;DR (2) - Mask is generated by an auxiliary LVLM based on the relevance between the image regions and the query. 🔧 The ...