SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Paper • 2502.14786 • Published Feb 20 • 144
LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models Paper • 2502.14834 • Published Feb 20 • 24
DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks Paper • 2502.17157 • Published Feb 24 • 53
