Skip to content
conftrace_

layer output

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

internal covariate shift (1) learnable weight (1) perplexity (1) model quality (1) earth mover distance (1) cross attention (1) residual connection (1) deep neural network (1) neural network optimization (1) batch normalization (1)

Papers

DeepCrossAttention: Supercharging Transformer Residual Connections ICML 2025 An Internal Covariate Shift Bounding Algorithm for Deep Neural Networks by Unitizing Layers' Outputs CVPR 2020