Le Xue

Architecture, Training and Dataset Github Code: https://github.com/JiuhaiChen/BLIP3o Models: https://huggingface.co/BLIP3o/BLIP3o-Model Demo: https://huggingface.co/spaces/BLIP3o/blip-3o Motivation OpenAI’s GPT-4o has demonstrated state-of-the-art performance in image understanding, generation and editing tasks. Emerging hypotheses of its architecture suggest a hybrid…

To address the challenges in generating multimodal instruction data, we developed ProVision, a scalable, programmatic framework that employs scene graphs and human-written programs to systematically synthesize vision-centric instruction data. 

We are excited to open-source 🍃MINT-1T, the first trillion token multimodal interleaved dataset and a valuable resource for the community to study and build large multimodal models.

TL;DR: Imagine a world where machines comprehend 3D objects just as humans do. The ULIP (CVPR2023) and ULIP-2 projects, backed by Salesforce AI, are making this a reality by revolutionizing 3D understanding. ULIP…