One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation Paper • 2512.07829 • Published Dec 8, 2025 • 24
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Paper • 2502.14786 • Published Feb 20, 2025 • 162
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head Paper • 2601.07832 • Published Jan 12 • 52
view article Article Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM +2 Mar 12, 2025 • 493