Efficient Computing

bert2BERT: Towards Reusable Pretrained Language Models ACL 2022 Beyond Fixation: Dynamic Window Visual Transformer CVPR 2022 Beyond neural scaling laws: beating power law scaling via data pruning NeurIPS 2022 BiFSMN: Binary Neural Network for Keyword Spotting IJCAI 2022 BigDL 2.0: Seamless Scaling of AI Pipelines From Laptops to Distributed Cluster CVPR 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 BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models ACL 2022 BiT: Robustly Binarized Multi-distilled Transformer NeurIPS 2022 Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization ICML 2022 Bi-volution: A Static and Dynamic Coupled Filter AAAI 2022 Block-NeRF: Scalable Large Scene Neural View Synthesis CVPR 2022 Block-Skim: Efficient Question Answering for Transformer AAAI 2022 BMCook: A Task-agnostic Compression Toolkit for Big Models EMNLP 2022 BMInf: An Efficient Toolkit for Big Model Inference and Tuning ACL 2022 Boosting Code Summarization by Embedding Code Structures COLING 2022 Bottleneck Low-rank Transformers for Low-resource Spoken Language Understanding Interspeech 2022 Bridge the Gap Between Architecture Spaces via A Cross-Domain Predictor NeurIPS 2022 Bridging Fairness and Environmental Sustainability in Natural Language Processing EMNLP 2022 Bunched LPCNet2: Efficient Neural Vocoders Covering Devices from Cloud to Edge Interspeech 2022 Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation EMNLP 2022 CAP-VMs: Capability-Based Isolation and Sharing in the Cloud OSDI 2022 Carbink: Fault-Tolerant Far Memory OSDI 2022 CCA: An ML Pipeline for Cloud Anomaly Troubleshooting AAAI 2022 Channel Balancing for Accurate Quantization of Winograd Convolutions CVPR 2022