GEBench: Benchmarking Image Generation Models as GUI Environments Paper • 2602.09007 • Published 23 days ago • 39
Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis Paper • 2602.03139 • Published 29 days ago • 42
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Paper • 2502.14786 • Published Feb 20, 2025 • 158
LLM2CLIP Collection LLM2CLIP makes SOTA pretrained CLIP modal more SOTA ever. • 10 items • Updated 2 days ago • 65