【文献阅读】Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

文献阅读 标签

2025

08-04

【文献阅读】Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

06-30

DeepSeekMoE+MTP

02-18

【文献阅读】Better & Faster Large Language Models via Multi-token Prediction

01-08

ModernBERT介绍

2024

11-22

STaR和Quiet-STaR

02-02

【文献阅读】R-Drop: Regularized Dropout for Neural Networks

01-22

【文献阅读】LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning

01-18

【文献阅读】RAG: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

01-16

【文献阅读】Mixtral of Experts

01-11

【文献阅读】ALiBi: Attention With Linear Biases位置编码