Login / Signup

SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization.

Jialong GuoXinghao ChenYehui TangYunhe Wang
Published in: CoRR (2024)
Keyphrases
  • databases
  • information retrieval
  • preprocessing
  • data sets
  • real world
  • genetic algorithm
  • artificial intelligence
  • decision trees
  • multiscale
  • computationally expensive
  • visual attention