SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference Paper • 2502.18137 • Published Feb 25 • 59
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention Paper • 2502.11089 • Published Feb 16 • 166
DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails Paper • 2502.05163 • Published Feb 7 • 22