Model Compression

TernaryBERT: Distillation-aware Ultra-low Bit BERT EMNLP 2020 The Knowledge Within: Methods for Data-Free Model Compression CVPR 2020 The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks ICML 2020 The NiuTrans System for WNGT 2020 Efficiency Task ACL 2020 The Tree Ensemble Layer: Differentiability meets Conditional Computation ICML 2020 TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids Interspeech 2020 TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning NeurIPS 2020 TKD: Temporal Knowledge Distillation for Active Perception WACV 2020 Towards Accurate Low Bit-Width Quantization with Multiple Phase Adaptations AAAI 2020 Towards Certificated Model Robustness Against Weight Perturbations AAAI 2020 Towards Efficient Model Compression via Learned Global Ranking CVPR 2020 Towards Fully 8-bit Integer Inference for the Transformer Model IJCAI 2020 Towards Unified INT8 Training for Convolutional Neural Network CVPR 2020 Training Binary Neural Networks through Learning with Noisy Supervision ICML 2020 Training Flexible Depth Model by Multi-Task Learning for Neural Machine Translation EMNLP 2020 Training Quantized Neural Networks With a Full-Precision Auxiliary Module CVPR 2020 Understanding and Exploring the Network with Stochastic Architectures NeurIPS 2020 Up or Down? Adaptive Rounding for Post-Training Quantization ICML 2020 URNet: User-Resizable Residual Networks with Conditional Gating Module AAAI 2020 Variational Bayesian Quantization ICML 2020 Vector-Vector-Matrix Architecture: A Novel Hardware-Aware Framework for Low-Latency Inference in NLP Applications EMNLP 2020 ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection WACV 2020 VoiceFilter-Lite: Streaming Targeted Voice Separation for On-Device Speech Recognition Interspeech 2020 Weight Poisoning Attacks on Pretrained Models ACL 2020 When BERT Plays the Lottery, All Tickets Are Winning EMNLP 2020