SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Paper • 2502.14786 • Published Feb 20 • 143
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention Paper • 2502.11089 • Published Feb 16 • 155
Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models Paper • 2401.04658 • Published Jan 9, 2024 • 28
