← Keywords

model compression

3283 papers

Explore in graph

Also known as

MC

Co-occurring keywords

knowledge distillation (3680) large language model (12755) neural network (6616) efficient computing (779) neural network optimization (1293) transfer learning (5442) convolutional neural network (4216) neural network pruning (265) language model (4573) parameter efficiency (415)

Papers

Spike-Thrift: Towards Energy-Efficient Deep Spiking Neural Networks by Limiting Spiking Activity via Attention-Guided Compression WACV 2021
Improving Stance Detection with Multi-Dataset Learning and Knowledge Distillation EMNLP 2021
Editing Factual Knowledge in Language Models EMNLP 2021
Finetuning Pretrained Transformers into RNNs EMNLP 2021
RW-KD: Sample-wise Loss Terms Re-Weighting for Knowledge Distillation EMNLP 2021
Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers EMNLP 2021
Block-wise Word Embedding Compression Revisited: Better Weighting and Structuring EMNLP 2021
HW-TSC’s Participation in the WMT 2021 Efficiency Shared Task EMNLP 2021
Matching Distributions between Model and Data: Cross-domain Knowledge Distillation for Unsupervised Domain Adaptation IJCNLP 2021
Importance-based Neuron Allocation for Multilingual Neural Machine Translation ACL 2021
Efficient Domain Adaptation of Language Models via Adaptive Tokenization EMNLP 2021
Iterative Deep Model Compression and Acceleration in the Frequency Domain ACML 2021
Layer-Wise Neural Network Compression via Layer Fusion ACML 2021
NetAdaptV2: Efficient Neural Architecture Search With Fast Super-Network Training and Architecture Optimization CVPR 2021
AutoLR: Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep Networks AAAI 2021
The NiuTrans System for the WMT 2021 Efficiency Task EMNLP 2021
MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge NIPS 2021
TenTrans High-Performance Inference Toolkit for WMT2021 Efficiency Task EMNLP 2021
Efficient Deep Image Denoising via Class Specific Convolution AAAI 2021
S$^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks NIPS 2021
DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks NIPS 2021
Comprehensive Knowledge Distillation with Causal Intervention NIPS 2021
Optimizing Information Theory Based Bitwise Bottlenecks for Efficient Mixed-Precision Activation Quantization AAAI 2021
AQD: Towards Accurate Quantized Object Detection CVPR 2021
Extremely Small BERT Models from Mixed-Vocabulary Training EACL 2021