Efficient Computing

Benchmarking: Past, Present and Future ACL 2021 BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networks EMNLP 2021 Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification NeurIPS 2021 Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference EMNLP 2021 Beyond malloc efficiency to fleet efficiency: a hugepage-aware memory allocator OSDI 2021 Beyond Sentence-Level End-to-End Speech Translation: Context Helps ACL 2021 Bi-GCN: Binary Graph Convolutional Network CVPR 2021 Binary Graph Neural Networks CVPR 2021 BiPointNet: Binary Neural Network for Point Clouds ICLR 2021 BlockCopy: High-Resolution Video Processing With Block-Sparse Feature Propagation and Online Policies ICCV 2021 Blocking-based Neighbor Sampling for Large-scale Graph Neural Networks IJCAI 2021 Block-wise Word Embedding Compression Revisited: Better Weighting and Structuring EMNLP 2021 BOBCAT: Bilevel Optimization-Based Computerized Adaptive Testing IJCAI 2021 Boosting Monocular Depth Estimation With Lightweight 3D Point Fusion ICCV 2021 Boosting the Throughput and Accelerator Utilization of Specialized CNN Inference Beyond Increasing Batch Size ICML 2021 BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction ICLR 2021 Bringing UMAP Closer to the Speed of Light with GPU Acceleration AAAI 2021 Broadcasted Residual Learning for Efficient Keyword Spotting Interspeech 2021 BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization ICLR 2021 BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining NeurIPS 2021 CADA: Communication-Adaptive Distributed Adam AISTATS 2021 CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D Networks AAAI 2021 CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks NeurIPS 2021 CAP: Context-Aware Pruning for Semantic Segmentation WACV 2021 CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade EMNLP 2021