Some of you may have already tried to ask technical questions to Chat GPT or any other LLM-Large Language Model or they new versiosn as LMM-Large Multimodal Model. How did you find their performance?
We tested 3 LMMs to automatically identify the deterioration patterns in a set of over 300 images and our results can be consulted here: https://arxiv.org/html/2406.03207v1
Any feedback is highly welcome
José