Efficient Computing

ESL-SNNs: An Evolutionary Structure Learning Strategy for Spiking Neural Networks AAAI 2023 Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model JMLR 2023 FaLA: Fast Linear Adaptation for Replacing Backbone Models on Edge Devices EMNLP 2023 Fast Fluid Simulation via Dynamic Multi-Scale Gridding AAAI 2023 Fast Inference from Transformers via Speculative Decoding ICML 2023 FFCV: Accelerating Training by Removing Data Bottlenecks CVPR 2023 Fixed Input Parameterization for Efficient Prompting ACL 2023 FLASH: Towards a High-performance Hardware Acceleration Architecture for Cross-silo Federated Learning NSDI 2023 Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification EMNLP 2023 Focus Your Attention (with Adaptive IIR Filters) EMNLP 2023 HadSkip: Homotopic and Adaptive Layer Skipping of Pre-trained Language Models for Efficient Inference EMNLP 2023 INGENIOUS: Using Informative Data Subsets for Efficient Pre-Training of Language Models EMNLP 2023 Learning Neural Constitutive Laws from Motion Observations for Generalizable PDE Dynamics ICML 2023 Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference ICLR 2023 Learning To Zoom and Unzoom CVPR 2023 Length-Adaptive Distillation: Customizing Small Language Model for Dynamic Token Pruning EMNLP 2023 LightFormer: Light-weight Transformer Using SVD-based Weight Transfer and Parameter Sharing ACL 2023 Long-Range Language Modeling with Selective Cache EMNLP 2023 Low Emission Building Control with Zero-Shot Reinforcement Learning AAAI 2023 MECTA: Memory-Economic Continual Test-Time Model Adaptation ICLR 2023 MobileOne: An Improved One Millisecond Mobile Backbone CVPR 2023 Motion Information Propagation for Neural Video Compression CVPR 2023 MSCFFN: A New FFN with Multi-Space Cross to Accelerate Transformer EMNLP 2023 MUX-PLMs: Data Multiplexing for High-throughput Language Models EMNLP 2023 MUX-PLMs: Pre-training Language Models with Data Multiplexing ACL 2023