Efficient Computing

On Enhancing Fine-Tuning for Pre-trained Language Models EMNLP 2023 One-Shot Model for Mixed-Precision Quantization CVPR 2023 OneWAN is better than two: Unifying a split WAN architecture NSDI 2023 Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statistics Interspeech 2023 Online Punctuation Restoration using ELECTRA Model for streaming ASR Systems Interspeech 2023 On Modular Learning of Distributed Systems for Predicting End-to-End Latency NSDI 2023 On Representing Linear Programs by Graph Neural Networks ICLR 2023 On the choice of Perception Loss Function for Learned Video Compression NeurIPS 2023 On the (In)Efficiency of Acoustic Feature Extractors for Self-Supervised Speech Representation Learning Interspeech 2023 OpenDataVal: a Unified Benchmark for Data Valuation NeurIPS 2023 Open-ended Long Text Generation via Masked Language Modeling ACL 2023 OpenMapFlow: A Library for Rapid Map Creation with Machine Learning and Remote Sensing Data AAAI 2023 Operator Selection and Ordering in a Pipeline Approach to Efficiency Optimizations for Transformers ACL 2023 Optimal Budget Allocation for Crowdsourcing Labels for Graphs UAI 2023 Optimal Parameter and Neuron Pruning for Out-of-Distribution Detection NeurIPS 2023 Optimal Proposal Learning for Deployable End-to-End Pedestrian Detection CVPR 2023 Optimized Crystallographic Graph Generation for Material Science IJCAI 2023 Optimizing Dynamic Neural Networks with Brainstorm OSDI 2023 Optimizing Hyperparameters with Conformal Quantile Regression ICML 2023 Optimizing Retrieval-augmented Reader Models via Token Elimination EMNLP 2023 ORC: Increasing Cloud Memory Density via Object Reuse with Capabilities OSDI 2023 Oscillation-free Quantization for Low-bit Vision Transformers ICML 2023 OSDP: Optimal Sharded Data Parallel for Distributed Deep Learning IJCAI 2023 Outlier Suppression+: Accurate quantization of large language models by equivalent and effective shifting and scaling EMNLP 2023 PackQViT: Faster Sub-8-bit Vision Transformers via Full and Packed Quantization on the Mobile NeurIPS 2023