排序方式：按更新时间排序 | 按标题排序 | 按浏览次数排序
论文：Perceiver - General Perception with Iterative Attention
论文   Transformer   Google   Deepmind  
CLS, COMPOSITE SLICE TRANSFORMER: AN EFFICIENT TRANSFORMER WITH COMPOSITION OF MULTI-SCALE MULTI-RANGE ATTENTIONS
论文   TRANSFORMER  
ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs
字节   Transformer  
KV Cache（键值缓存）
Transformer   LLM  
Vision Transformer（ViT）
Transformer   机器视觉  
可逆Transformer（Reversible Transformer）
Transformer  
Reformer: The Efficient Transformer
Transformer  
Q-Former技术（Querying Transformer）
Transformer  
论文：The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers
论文   Transformer  
Speculative decoding（推测性解码）
NLP   Transformer  
论文阅读 TOKEN MERGING: YOUR VIT BUT FASTER（ToMe模型）
Transformer  
Swin Transformer
计算机视觉   Transformer  
Differential Transformer
Transformer  
论文 | TRANSFORMER - VQ: LINEAR - TIME TRANSFORMERS VIA VECTOR QUANTIZATION
论文   transformer  
transformer 资料集锦
DNN   transformer  
论文 | Fast Transformer Decoding: One Write-Head is All You Need
论文   Transformer  
论文 | Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
论文   Transformer