Skip to content
conftrace_

layer dropout

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

dynamic encoder transducer (1) encoder layer (1) dynamic encoder (1) network training (1) large language model (1) early exit inference (1) neural network (1) encoder transducer (1) on-device speech recognition (1) self-speculative decoding (1)

Papers

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding ACL 2024 Dynamic Encoder Transducer: A Flexible Solution for Trading Off Accuracy for Latency Interspeech 2021 Gradual DropIn of Layers to Train Very Deep Neural Networks CVPR 2016