Efficient Computing

TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Training NeurIPS 2022 Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction NeurIPS 2022 The RoyalFlush System for the WMT 2022 Efficiency Task EMNLP 2022 Token Dropping for Efficient BERT Pretraining ACL 2022 Topologically-Aware Deformation Fields for Single-View 3D Reconstruction CVPR 2022 Toward Low-Cost End-to-End Spoken Language Understanding Interspeech 2022 Toward Robust Spiking Neural Network Against Adversarial Perturbation NeurIPS 2022 Towards Efficient and Scalable Sharpness-Aware Minimization CVPR 2022 Towards Fully Sparse Training: Information Restoration with Spatial Similarity AAAI 2022 Towards Light-Weight and Real-Time Line Segment Detection AAAI 2022 Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations ICLR 2022 Training Up to 50 Class ML Models on 3 $ IoT Hardware via Optimizing One-vs-One Algorithm (Student Abstract) AAAI 2022 Transformer Quality in Linear Time ICML 2022 Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost NeurIPS 2022 Transkimmer: Transformer Learns to Layer-wise Skim ACL 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 Understanding and Improving Knowledge Distillation for Quantization Aware Training of Large Transformer Encoders EMNLP 2022 Uniform Subdivision of Omnidirectional Camera Space for Efficient Spherical Stereo Matching CVPR 2022 ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints NeurIPS 2022 Wavelet Feature Maps Compression for Image-to-Image CNNs NeurIPS 2022 When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation ACL 2022 Who Says Elephants Can’t Run: Bringing Large Scale MoE Models into Cloud Scale Production EMNLP 2022 ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity ICLR 2022