| Name | Topic | Contact |
| Elena Alegret Regalado | Masked autoencoders are scalable vision learners | Tarun |
| Jan-Michael van der Linde | Learning transferable visual models from natural language supervision | Tarun |
| Guillermo Figueroa | Florence: A new foundation model for computer vision | Tarun |
| Vayun Goel | Segment anything | Dominik |
| Selen Çiğdem | SAM 2: Segment Anything in Images and Videos | Dominik |
| Viktor Svensson | Zero-shot text-to-image generation | Dominik |
| Tümay Tayyar Kamburoğlu | High-resolution image synthesis with latent diffusion models | Dominik |
| Yeeun Song | DreamFusion: Text-to-3D using 2D Diffusion | Tarun |
| Jun Wang | ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation | Tarun |
Login
