Efficient Computing

Conditioning Sequence-to-sequence Networks with Learned Activations ICLR 2022 Confident Adaptive Language Modeling NeurIPS 2022 Conformal Predictor for Improving Zero-Shot Text Classification Efficiency EMNLP 2022 Constrained Few-Shot Class-Incremental Learning CVPR 2022 Continual Sequence Generation with Adaptive Compositional Modules ACL 2022 Contribution-Aware Federated Learning for Smart Healthcare AAAI 2022 Controllable Dynamic Multi-Task Architectures CVPR 2022 Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition AAAI 2022 CoordX: Accelerating Implicit Neural Representation with a Split MLP Architecture ICLR 2022 COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models EMNLP 2022 Cross-Layer Similarity Knowledge Distillation for Speech Enhancement Interspeech 2022 CrowdFL: A Marketplace for Crowdsourced Federated Learning AAAI 2022 CS-CTCSCONV1D: Small footprint speaker verification with channel split time-channel-time separable 1-dimensional convolution Interspeech 2022 CUNI-Bergamot Submission at WMT22 General Translation Task EMNLP 2022 CUNI-KIT System for Simultaneous Speech Translation Task at IWSLT 2022 ACL 2022 CurvingLoRa to Boost LoRa Network Throughput via Concurrent Transmission NSDI 2022 DACT-BERT: Differentiable Adaptive Computation Time for an Efficient BERT Inference ACL 2022 DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning ICML 2022 DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks WACV 2022 Data-Driven Offline Optimization for Architecting Hardware Accelerators ICLR 2022 Data-Efficient Augmentation for Training Neural Networks NeurIPS 2022 Data-Efficient Double-Win Lottery Tickets from Robust Pre-training ICML 2022 Data-Efficient Graph Grammar Learning for Molecular Generation ICLR 2022 Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data NeurIPS 2022 Data-Efficient Structured Pruning via Submodular Optimization NeurIPS 2022