Skip to content
conftrace_

layer dropping

7 papers

Explore in graph

Co-occurring keywords · papers mentioning both

model compression (5) neural network optimization (3) large language model (2) associative reinforcement learning (1) block dropping (1) computation budget (1) flexible depth (1) stagewise training (1) subnetwork training (1) variable depth (1)

Papers

Efficient stagewise pretraining via progressive subnetworks ICLR 2025 EvoPress: Accurate Dynamic Model Compression via Evolutionary Search ICML 2025 TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs ACL 2025 Acceleration of Large Transformer Model Training by Sensitivity-Based Layer Dropping AAAI 2023 No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models NeurIPS 2023 Training Flexible Depth Model by Multi-Task Learning for Neural Machine Translation EMNLP 2020 BlockDrop: Dynamic Inference Paths in Residual Networks CVPR 2018