본문으로 건너뛰기
Juhyeon's Blog
Search
검색
다크 모드
라이트 모드
탐색기
태그: attention
15건의 항목
2026년 6월 04일
Attention Methods
attention
index
taxonomy
2026년 6월 04일
Axial Attention in Multidimensional Transformers
paper
attention
axial
multidimensional
image-transformer
autoregressive
sparse-attention
2026년 6월 04일
BigBird - Transformers for Longer Sequences
paper
attention
bigbird
sparse
random
block
long-context
transformer
graph-theory
2026년 6월 04일
FlashAttention - Fast and Memory-Efficient Exact Attention with IO-Awareness
paper
attention
flash-attention
io-awareness
gpu-kernel
efficient-transformer
2026년 6월 04일
FlashAttention-2 - Faster Attention with Better Parallelism and Work Partitioning
paper
attention
gpu-optimization
flashattention
transformer
2026년 6월 04일
Kaggle Measuring Progress Toward AGI - Cognitive Abilities
kaggle
hackathon
AGI
benchmark
cognitive-evaluation
DeepMind
metacognition
attention
learning
executive-functions
social-cognition
2026년 6월 04일
Linear Attention - Transformers are RNNs
paper
attention
linear-attention
kernel
rnn
efficiency
ICML
2026년 6월 04일
MQA - Fast Transformer Decoding with Multi-Query Attention
paper
attention
mqa
kv-cache
decoding
multi-head-variants
2026년 6월 04일
Mistral 7B - Sliding Window Attention
paper
attention
sliding-window
mistral
causal-decoder
kv-cache
2026년 6월 04일
PagedAttention - Efficient Memory Management for LLM Serving with vLLM
paper
serving
kv-cache
paged-attention
vllm
attention
2026년 6월 04일
Performer - Rethinking Attention with Performers
paper
attention
performer
random-features
favor
linear-attention
ICLR2021
2026년 6월 04일
RWKV - Reinventing RNNs for the Transformer Era
paper
attention
rnn
linear-attention
efficient-llm
rwkv
2026년 6월 04일
Reformer - The Efficient Transformer
paper
attention
reformer
lsh
reversible
sparse-attention
efficient-transformer
long-context
2026년 6월 04일
RetNet - Retentive Network - A Successor to Transformer for LLMs
paper
attention
retention
retnet
linear-attention
efficient-llm
sequence-model
2026년 6월 04일
Sparse Transformer - Generating Long Sequences with Sparse Transformers
paper
attention
sparse-transformer
strided
fixed-pattern
long-context
OpenAI