Efficient Computing

Training Up to 50 Class ML Models on 3 $ IoT Hardware via Optimizing One-vs-One Algorithm (Student Abstract) AAAI 2022 Transformer-based Transform Coding ICLR 2022 Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost NeurIPS 2022 TREC: Transient Redundancy Elimination-based Convolution NeurIPS 2022 TriCache: A User-Transparent Block Cache Enabling High-Performance Out-of-Core Processing with In-Memory Programs OSDI 2022 TRILLsson: Distilled Universal Paralinguistic Speech Representations Interspeech 2022 TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection EMNLP 2022 TRUE: Re-evaluating Factual Consistency Evaluation ACL 2022 TSPipe: Learn from Teacher Faster with Pipelines ICML 2022 TVConv: Efficient Translation Variant Convolution for Layout-Aware Visual Processing CVPR 2022 UDC: Unified DNAS for Compressible TinyML Models for Neural Processing Units NeurIPS 2022 Ultra-Low-Bitrate Speech Coding with Pretrained Transformers Interspeech 2022 Understanding the Role of Self Attention for Efficient Speech Recognition ICLR 2022 Understanding Uncertainty Maps in Vision With Statistical Testing CVPR 2022 UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification NeurIPS 2022 Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression CVPR 2022 Unified Scaling Laws for Routed Language Models ICML 2022 Uniform Subdivision of Omnidirectional Camera Space for Efficient Spherical Stereo Matching CVPR 2022 Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search NeurIPS 2022 UniKW-AT: Unified Keyword Spotting and Audio Tagging Interspeech 2022 UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning ACL 2022 Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning CVPR 2022 Up to 100x Faster Data-Free Knowledge Distillation AAAI 2022 Using NLP to Support English Teaching in Rural Schools EMNLP 2022 Variational Feature Pyramid Networks ICML 2022