Model Compression

Improving Machine Translation with Phrase Pair Injection and Corpus Filtering EMNLP 2022 Information-Theoretic GAN Compression with Variational Energy-based Model NeurIPS 2022 Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers EMNLP 2022 Is Integer Arithmetic Enough for Deep Learning Training? NeurIPS 2022 Knowledge Distillation For CTC-based Speech Recognition Via Consistent Acoustic Representation Learning Interspeech 2022 Knowledge Distillation via Module Replacing for Automatic Speech Recognition with Recurrent Neural Network Transducer Interspeech 2022 Knowledge Distillation With the Reused Teacher Classifier CVPR 2022 Knowledge Inheritance for Pre-trained Language Models NAACL 2022 Knowledge Transfer and Distillation from Autoregressive to Non-Autoregessive Speech Recognition Interspeech 2022 KroneckerBERT: Significant Compression of Pre-trained Language Models Through Kronecker Decomposition and Knowledge Distillation NAACL 2022 LayerConnect: Hypernetwork-Assisted Inter-Layer Connector to Enhance Parameter Efficiency COLING 2022 Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training NeurIPS 2022 Layer-Wised Model Aggregation for Personalized Federated Learning CVPR 2022 Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval NAACL 2022 Learning To Collaborate in Decentralized Learning of Personalized Models CVPR 2022 Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training NAACL 2022 Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models EMNLP 2022 Less is More: Summary of Long Instructions is Better for Program Synthesis EMNLP 2022 Leveraging Inter-Layer Dependency for Post -Training Quantization NeurIPS 2022 Localization Distillation for Dense Object Detection CVPR 2022 "Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach NeurIPS 2022 Low-bit Shift Network for End-to-End Spoken Language Understanding Interspeech 2022 Low-complex and Highly-performed Binary Residual Neural Network for Small-footprint Keyword Spotting Interspeech 2022 LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning NeurIPS 2022 Maximum Bayes Smatch Ensemble Distillation for AMR Parsing NAACL 2022