captioning fine-tuning florence-2 multimodal objectdetection paligemma phi-3-vision qwen2-vl transformers vision-and-language vqa

Mathematics (40%)

chatgpt evaluation evaluation-metrics foundation-models gpt gpt-4 hallucination iclr iclr2024 llama llava multimodal object-detection prompt-engineering vicuna vision vision-and-language vqa

annotations cvpr cvpr2021 dataset multimodal multimodal-deep-learning paper traffic-events video-qa video-reasoning vqa vqa-dataset