conftrace_

gated linear unit

5 papers

Explore in graph

Also known as

GLU

Co-occurring keywords · papers mentioning both

attention mechanism (2) pretraining efficiency (1) spatial-temporal prediction (1) feed-forward layer (1) sequence to sequence (1) traffic prediction (1) channel pruning (1) transformer encoder (1) graph convolutional network (1) masked language modeling (1)

Papers

On the Role of Transformer Feed-Forward Layers in Nonlinear In-Context Learning ALT 2026 MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining NeurIPS 2023 DEMUCS-Mobile : On-Device Lightweight Speech Enhancement Interspeech 2021 LSGCN: Long Short-Term Traffic Prediction with Graph Convolutional Networks IJCAI 2020 Convolutional Sequence to Sequence Learning ICML 2017