RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model on Referring Expressions Paper • 2506.03448 • Published Jun 3, 2025 • 5
Steering Rectified Flow Models in the Vector Field for Controlled Image Generation Paper • 2412.00100 • Published Nov 27, 2024 • 17
TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives Paper • 2411.02545 • Published Nov 4, 2024 • 1
Benchmark Checkpoints Collection Weights of the TripletCLIP and baselines on custom training scripts • 9 items • Updated Dec 1, 2024 • 2
