Transformers without Normalization
Paper • 2503.10622 • Published • 172
Dmitriy Didenko
Dimildizio
·
AI & ML interests
None yet
Organizations
upvoted 4
papers over 1 year ago
SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference
Paper • 2502.18137 • Published • 60
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Paper • 2502.11089 • Published • 170
DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails
Paper • 2502.05163 • Published • 23