← Core AI
Artificial Intelligence › Core AI ›

Model Compression

1928 directly classified papers

Papers per year

Papers

Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm NIPS 2022
Knowledge Distillation Transfer Sets and their Impact on Downstream NLU Tasks EMNLP 2022
Functional Ensemble Distillation NIPS 2022
Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model ACL 2022
DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization ACL 2022
Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models NIPS 2022
Pyramid-BERT: Reducing Complexity via Successive Core-set based Token Selection ACL 2022
When To Prune? A Policy Towards Early Structural Pruning CVPR 2022
DECORE: Deep Compression With Reinforcement Learning CVPR 2022
Model Preserving Compression for Neural Networks NIPS 2022
FT-DeepNets: Fault-Tolerant Convolutional Neural Networks With Kernel-Based Duplication WACV 2022
From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression AAAI 2022
LayerConnect: Hypernetwork-Assisted Inter-Layer Connector to Enhance Parameter Efficiency COLING 2022
EZCrop: Energy-Zoned Channels for Robust Output Pruning WACV 2022
SDQ: Stochastic Differentiable Quantization with Mixed Precision ICML 2022
Instance-Aware Dynamic Neural Network Quantization CVPR 2022
Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning ICML 2022
Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free CVPR 2022
A Flexible Multi-Task Model for BERT Serving ACL 2022
Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation CVPR 2022
HODEC: Towards Efficient High-Order DEcomposed Convolutional Neural Networks CVPR 2022
Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations CVPR 2022
Revisiting Random Channel Pruning for Neural Network Compression CVPR 2022
DiSparse: Disentangled Sparsification for Multitask Model Compression CVPR 2022
Differentially Private Model Compression NIPS 2022