Picture for Tristan Naumann

Tristan Naumann

Compositional Zero-Shot Domain Transfer with Text-to-Text Models

Mar 23, 2023
Fangyu Liu, Qianchu Liu, Shruthi Bannur, Fernando Pérez-García, Naoto Usuyama, Sheng Zhang, Tristan Naumann, Aditya Nori, Hoifung Poon, Javier Alvarez-Valle, Ozan Oktay, Stephanie L. Hyland

Figure 1 for Compositional Zero-Shot Domain Transfer with Text-to-Text Models

Figure 2 for Compositional Zero-Shot Domain Transfer with Text-to-Text Models

Figure 3 for Compositional Zero-Shot Domain Transfer with Text-to-Text Models

Figure 4 for Compositional Zero-Shot Domain Transfer with Text-to-Text Models

* Accepted at TACL, pre-MIT Press publication version. 16 pages, 4 figures

Access Paper or Ask Questions

Large-Scale Domain-Specific Pretraining for Biomedical Vision-Language Processing

Mar 02, 2023
Sheng Zhang, Yanbo Xu, Naoto Usuyama, Jaspreet Bagga, Robert Tinn, Sam Preston, Rajesh Rao, Mu Wei, Naveen Valluri, Cliff Wong, Matthew P. Lungren, Tristan Naumann, Hoifung Poon

Figure 1 for Large-Scale Domain-Specific Pretraining for Biomedical Vision-Language Processing

Figure 2 for Large-Scale Domain-Specific Pretraining for Biomedical Vision-Language Processing

Figure 3 for Large-Scale Domain-Specific Pretraining for Biomedical Vision-Language Processing

Figure 4 for Large-Scale Domain-Specific Pretraining for Biomedical Vision-Language Processing

* The models will be released soon at https://aka.ms/biomedclip

Access Paper or Ask Questions