BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
Jiuhai Chen, Zhiyang Xu, Xichen Pan, Yushi Hu, Can Qin, Tom Goldstein, Lifu Huang, Tianyi Zhou and 5 more
Who it is from
- New York Universityaffiliation declared by the authors, according to OpenAlex
- Salesforceaffiliation declared by the authors, according to OpenAlex
- University of Maryland, College Parkaffiliation declared by the authors, according to OpenAlex
- Virginia Techaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- Hallusionbench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language ModelsUniversity of Maryland, College Park · 1,299 citations
- A comprehensive survey on pretrained foundation models: a history from BERT to ChatGPTBeihang University · 1,211 citations
- Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall SpacesNew York University · 924 citations
- SiT: Exploring Flow and Diffusion-Based Generative Models with Scalable Interpolant TransformersNew York University · 908 citations
- Revisiting Feature Prediction for Learning Visual Representations from VideoNew York University · 846 citations
- Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You ThinkKorea Advanced Institute of Science and Technology · 701 citations