Efficient Computing

Anytime Inference with Distilled Hierarchical Neural Ensembles AAAI 2021 AQD: Towards Accurate Quantized Object Detection CVPR 2021 Arabic Compact Language Modelling for Resource Limited Devices EACL 2021 ARCH: Efficient Adversarial Regularized Training with Caching EMNLP 2021 “Are you calling for the vaporizer you ordered?” Combining Search and Prediction to Identify Orders in Contact Centers ACL 2021 Assessing Reference-Free Peer Evaluation for Machine Translation NAACL 2021 Associative Convolutional Layers AISTATS 2021 ATP: In-network Aggregation for Multi-tenant Learning NSDI 2021 Attention Bottlenecks for Multimodal Fusion NeurIPS 2021 Attention-Guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton CVPR 2021 Attribute-Efficient Learning of Halfspaces with Malicious Noise: Near-Optimal Label Complexity and Noise Tolerance ALT 2021 Audio Segmentation Based Conversational Silence Detection for Contact Center Calls Interspeech 2021 AutoAttend: Automated Attention Representation Search ICML 2021 AutoLR: Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep Networks AAAI 2021 Automated Log-Scale Quantization for Low-Cost Deep Neural Networks CVPR 2021 Automated Model Design and Benchmarking of Deep Learning Models for COVID-19 Detection with Chest CT Scans AAAI 2021 Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators ICML 2021 Autonomous Robot for Measuring Room Impulse Responses Interspeech 2021 AutoText: An End-to-End AutoAI Framework for Text AAAI 2021 A Variational Information Bottleneck Based Method to Compress Sequential Networks for Human Action Recognition WACV 2021 Bag of Tricks for Optimizing Transformer Efficiency EMNLP 2021 Basis-MelGAN: Efficient Neural Vocoder Based on Audio Decomposition Interspeech 2021 BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer NeurIPS 2021 BCNet: Searching for Network Width With Bilaterally Coupled Network CVPR 2021 Benchmarking a transformer-FREE model for ad-hoc retrieval EACL 2021