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 e mais 5
De quem é
- New York Universityafiliação declarada pelos autores, segundo o OpenAlex
- Salesforceafiliação declarada pelos autores, segundo o OpenAlex
- University of Maryland, College Parkafiliação declarada pelos autores, segundo o OpenAlex
- Virginia Techafiliação declarada pelos autores, segundo o OpenAlex
Outros papers das mesmas organizações
- Hallusionbench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language ModelsUniversity of Maryland, College Park · 1.299 citações
- A comprehensive survey on pretrained foundation models: a history from BERT to ChatGPTBeihang University · 1.211 citações
- Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall SpacesNew York University · 924 citações
- SiT: Exploring Flow and Diffusion-Based Generative Models with Scalable Interpolant TransformersNew York University · 908 citações
- Revisiting Feature Prediction for Learning Visual Representations from VideoNew York University · 846 citações
- Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You ThinkKorea Advanced Institute of Science and Technology · 701 citações