multimodal-llms

There are 5 repositories under multimodal-llms topic.

aimagelab/LLaVA-MORE
LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning
Language:Python113 6 88
DingchenYang99/Pensieve
The official repo of our work "Pensieve: Retrospect-then-Compare mitigates Visual Hallucination"
Language:Python14 3 30
Kartik-3004/facexbench
FaceXBench: Evaluating Multimodal LLMs on Face Understanding
Language:Python13 1 51
jhCOR/EgoOrientBench
The Official Code Repo for EgoOrientBench [CVPR25]
Language:Jupyter Notebook10 2 00
Adm-2005/PicNarrate-Image-Captioner
A tool for generating accurate and detailed captions for images.
Language:JavaScript