Efficient Computing

Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems AAAI 2021 LeeBERT: Learned Early Exit for BERT with cross-level optimization ACL 2021 Machine Unlearning for Random Forests ICML 2021 Memory-efficient Transformers via Top-k Attention EMNLP 2021 MFES-HB: Efficient Hyperband with Multi-Fidelity Quality Measurements AAAI 2021 Motion-Aware Dynamic Architecture for Efficient Frame Interpolation ICCV 2021 Multi-Layer Random Perturbation Training for improving Model Generalization Efficiently EMNLP 2021 Neural Architecture Search With Random Labels CVPR 2021 NPAS: A Compiler-Aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration CVPR 2021 NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization JMLR 2021 OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection CVPR 2021 PermuteFormer: Efficient Relative Position Encoding for Long Sequences EMNLP 2021 Physics-Informed Deep Learning for Traffic State Estimation: A Hybrid Paradigm Informed By Second-Order Traffic Models AAAI 2021 Piper: Multidimensional Planner for DNN Parallelization NeurIPS 2021 Prioritized Architecture Sampling With Monto-Carlo Tree Search CVPR 2021 Rethinking BiSeNet for Real-Time Semantic Segmentation CVPR 2021 Stateful ODE-Nets using Basis Function Expansions NeurIPS 2021 Super-Human Performance in Online Low-Latency Recognition of Conversational Speech Interspeech 2021 SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning Over Traffic Events CVPR 2021 TacoLPCNet: Fast and Stable TTS by Conditioning LPCNet on Mel Spectrogram Predictions Interspeech 2021 The Energy and Carbon Footprint of Training End-to-End Speech Recognizers Interspeech 2021 THOR, Trace-based Hardware-driven Layer-Oriented Natural Gradient Descent Computation AAAI 2021 Time-Multiplexed Coded Aperture Imaging: Learned Coded Aperture and Pixel Exposures for Compressive Imaging Systems ICCV 2021 Training Dynamic based data filtering may not work for NLP datasets EMNLP 2021 Training Spiking Neural Networks with Accumulated Spiking Flow AAAI 2021