efficient computing

Squeezeformer: An Efficient Transformer for Automatic Speech Recognition NeurIPS 2022 SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition AAAI 2022 Thrifty Neural Architecture Search for Medical Image Segmentation (Student Abstract) AAAI 2022 Token and Head Adaptive Transformers for Efficient Natural Language Processing COLING 2022 Towards Climate Awareness in NLP Research EMNLP 2022 Towards Efficient NLP: A Standard Evaluation and A Strong Baseline NAACL 2022 Towards Fully Sparse Training: Information Restoration with Spatial Similarity AAAI 2022 Transformer Quality in Linear Time ICML 2022 Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost NeurIPS 2022 TREC: Transient Redundancy Elimination-based Convolution NeurIPS 2022 TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection EMNLP 2022 TVConv: Efficient Translation Variant Convolution for Layout-Aware Visual Processing CVPR 2022 Unified Visual Transformer Compression ICLR 2022 Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space CVPR 2022 VLUE: A Multi-Task Multi-Dimension Benchmark for Evaluating Vision-Language Pre-training ICML 2022 VTC-LFC: Vision Transformer Compression with Low-Frequency Components NeurIPS 2022 XTC: Extreme Compression for Pre-trained Transformers Made Simple and Efficient NeurIPS 2022 Zero-Shot Dynamic Quantization for Transformer Inference EMNLP 2022 2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition CVPR 2021 Accelerating Neural Architecture Search via Proxy Data IJCAI 2021 ACT: an Attentive Convolutional Transformer for Efficient Text Classification AAAI 2021 AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition ICCV 2021 AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition ICCV 2021 Adder Attention for Vision Transformer NeurIPS 2021 Aligned Structured Sparsity Learning for Efficient Image Super-Resolution NeurIPS 2021