Model Compression

Aligned Weight Regularizers for Pruning Pretrained Neural Networks ACL 2022 AlignQ: Alignment Quantization With ADMM-Based Correlation Preservation CVPR 2022 AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models EMNLP 2022 An Information-Theoretic Justification for Model Pruning AISTATS 2022 An Operator Theoretic View On Pruning Deep Neural Networks ICLR 2022 A Novel Differentiable Mixed-Precision Quantization Search Framework for Alleviating the Matthew Effect and Improving Robustness ACML 2022 A Passive Similarity based CNN Filter Pruning for Efficient Acoustic Scene Classification Interspeech 2022 AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network CVPR 2022 Attention Fusion: a light yet efficient late fusion mechanism for task adaptation in NLU NAACL 2022 A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models NeurIPS 2022 BackdoorBench: A Comprehensive Benchmark of Backdoor Learning NeurIPS 2022 Batch Normalization Tells You Which Filter Is Important WACV 2022 BATUDE: Budget-Aware Neural Network Compression Based on Tucker Decomposition AAAI 2022 BiFSMN: Binary Neural Network for Keyword Spotting IJCAI 2022 BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons NeurIPS 2022 Binary Early-Exit Network for Adaptive Inference on Low-Resource Devices Interspeech 2022 BMCook: A Task-agnostic Compression Toolkit for Big Models EMNLP 2022 C3PO: A Lightweight Copying Mechanism for Translating Pseudocode to Code AACL 2022 Can Functional Transfer Methods Capture Simple Inductive Biases? AISTATS 2022 Channel Balancing for Accurate Quantization of Winograd Convolutions CVPR 2022 Channel Pruning via Lookahead Search Guided Reinforcement Learning WACV 2022 ClimbQ: Class Imbalanced Quantization Enabling Robustness on Efficient Inferences NeurIPS 2022 Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets ICML 2022 Combining Compressions for Multiplicative Size Scaling on Natural Language Tasks COLING 2022 Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound ICLR 2022