SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines Paper • 2502.14739 • Published 4 days ago • 88
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Paper • 2502.14786 • Published 4 days ago • 107
view article Article PaliGemma 2 Mix - New Instruction Vision Language Models by Google 5 days ago • 55
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention Paper • 2502.11089 • Published 8 days ago • 133
ReLearn: Unlearning via Learning for Large Language Models Paper • 2502.11190 • Published 8 days ago • 28
mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data Paper • 2502.08468 • Published 12 days ago • 13
InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU Paper • 2502.08910 • Published 11 days ago • 140
TransMLA: Multi-head Latent Attention Is All You Need Paper • 2502.07864 • Published 13 days ago • 43
Scaling Pre-training to One Hundred Billion Data for Vision Language Models Paper • 2502.07617 • Published 13 days ago • 28
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Paper • 2502.06703 • Published 14 days ago • 134