Efficient Computing

RAPQ: Rescuing Accuracy for Power-of-Two Low-bit Post-training Quantization IJCAI 2022 Reinforcement Learning for Datacenter Congestion Control AAAI 2022 Rep-Net: Efficient On-Device Learning via Feature Reprogramming CVPR 2022 Reversible Vision Transformers CVPR 2022 Revisiting Random Channel Pruning for Neural Network Compression CVPR 2022 ReX: An Efficient Approach to Reducing Memory Cost in Image Classification AAAI 2022 Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search CVPR 2022 ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks ICML 2022 Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences NAACL 2022 SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization JMLR 2022 Sparse Instance Activation for Real-Time Instance Segmentation CVPR 2022 Sparsifying Transformer Models with Trainable Representation Pooling ACL 2022 SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems CVPR 2022 STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction AAAI 2022 TabNAS: Rejection Sampling for Neural Architecture Search on Tabular Datasets NeurIPS 2022 TA-GATES: An Encoding Scheme for Neural Network Architectures NeurIPS 2022 Temporal Effective Batch Normalization in Spiking Neural Networks NeurIPS 2022 To Fold or Not to Fold: a Necessary and Sufficient Condition on Batch-Normalization Layers Folding IJCAI 2022 Token and Head Adaptive Transformers for Efficient Natural Language Processing COLING 2022 Token Dropping for Efficient BERT Pretraining ACL 2022 Towards Efficient NLP: A Standard Evaluation and A Strong Baseline NAACL 2022 Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation CVPR 2022 TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection EMNLP 2022 Zero-Shot Dynamic Quantization for Transformer Inference EMNLP 2022 zIO: Accelerating IO-Intensive Applications with Transparent Zero-Copy IO OSDI 2022