Efficient Computing

Accelerating Inference for Pretrained Language Models by Unified Multi-Perspective Early Exiting COLING 2022 AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition CVPR 2022 A Hardware Perspective to Evaluating Probabilistic Circuits PGM 2022 A Holistic Assessment of the Carbon Footprint of Noor, a Very Large Arabic Language Model ACL 2022 Algorithmic Diversity and Tiny Models: Comparing Binary Networks and the Fruit Fly Algorithm on Document Representation Tasks EMNLP 2022 Algorithms for the Communication of Samples ICML 2022 Analyzing and Mitigating Interference in Neural Architecture Search ICML 2022 A Simple yet Effective Learnable Positional Encoding Method for Improving Document Transformer Model AACL 2022 Attention Mechanism with Energy-Friendly Operations ACL 2022 Automated Progressive Learning for Efficient Training of Vision Transformers CVPR 2022 Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning JMLR 2022 AutoSNN: Towards Energy-Efficient Spiking Neural Networks ICML 2022 BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule CVPR 2022 BiBERT: Accurate Fully Binarized BERT ICLR 2022 BigDL 2.0: Seamless Scaling of AI Pipelines From Laptops to Distributed Cluster CVPR 2022 Block-Skim: Efficient Question Answering for Transformer AAAI 2022 Carbink: Fault-Tolerant Far Memory OSDI 2022 COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models EMNLP 2022 Deep residual spiking neural network for keyword spotting in low-resource settings Interspeech 2022 Distribution Consistent Neural Architecture Search CVPR 2022 EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation EMNLP 2022 Efficient Test-Time Model Adaptation without Forgetting ICML 2022 ErfAct and Pserf: Non-monotonic Smooth Trainable Activation Functions AAAI 2022 Fast Monte-Carlo Approximation of the Attention Mechanism AAAI 2022 Federated Learning With Position-Aware Neurons CVPR 2022