model compression

TRILLsson: Distilled Universal Paralinguistic Speech Representations Interspeech 2022 TSPipe: Learn from Teacher Faster with Pipelines ICML 2022 Tutoring Helps Students Learn Better: Improving Knowledge Distillation for BERT with Tutor Network EMNLP 2022 UDC: Unified DNAS for Compressible TinyML Models for Neural Processing Units NeurIPS 2022 Understanding and Improving Knowledge Distillation for Quantization Aware Training of Large Transformer Encoders EMNLP 2022 Unified Visual Transformer Compression ICLR 2022 Unsupervised Non-transferable Text Classification EMNLP 2022 Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning CVPR 2022 Unsupervised Tokenization Learning EMNLP 2022 Up to 100x Faster Data-Free Knowledge Distillation AAAI 2022 Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space CVPR 2022 VTC-LFC: Vision Transformer Compression with Low-Frequency Components NeurIPS 2022 W2V2-Light: A Lightweight Version of Wav2vec 2.0 for Automatic Speech Recognition Interspeech 2022 Wavelet Feature Maps Compression for Image-to-Image CNNs NeurIPS 2022 Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation CVPR 2022 Weighted Distillation with Unlabeled Examples NeurIPS 2022 Weighted Mutual Learning with Diversity-Driven Model Compression NeurIPS 2022 What Do Compressed Multilingual Machine Translation Models Forget? EMNLP 2022 When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism AAAI 2022 When the Student Becomes the Master: Learning Better and Smaller Monolingual Models from mBERT COLING 2022 When To Prune? A Policy Towards Early Structural Pruning CVPR 2022 Why Knowledge Distillation Amplifies Gender Bias and How to Mitigate from the Perspective of DistilBERT NAACL 2022 Wider & Closer: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition EMNLP 2022 Width & Depth Pruning for Vision Transformers AAAI 2022 Winning the Lottery Ahead of Time: Efficient Early Network Pruning ICML 2022