multimodal-llm
SIMIT: Self-Improving Vision-Language Models via Imagination at Test-Time, official pip library of the paper, SIMIT-ICL: vision-language models that imagine their own in-context demonstrations at test time
Kani extension for supporting vision-language models (VLMs). Comes with model-agnostic support for GPT-Vision and LLaVA.
Open-source red teaming framework for MLLMs with 42+ attack methods
