Text-to-Image Models Need Less from Text Encoders Than You Think Paper • 2606.03715 • Published 25 days ago • 11
Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching Paper • 2606.03911 • Published 25 days ago • 22
Versatile Editing of Video Content, Actions, and Dynamics without Training Paper • 2603.17989 • Published Mar 18 • 18
Spanning the Visual Analogy Space with a Weight Basis of LoRAs Paper • 2602.15727 • Published Feb 17 • 13
Spanning the Visual Analogy Space with a Weight Basis of LoRAs Paper • 2602.15727 • Published Feb 17 • 13
Spanning the Visual Analogy Space with a Weight Basis of LoRAs Paper • 2602.15727 • Published Feb 17 • 13
MineTheGap: Automatic Mining of Biases in Text-to-Image Models Paper • 2512.13427 • Published Dec 15, 2025 • 2