Efficient Computing

GACT: Activation Compressed Training for Generic Network Architectures ICML 2022 Gating Dropout: Communication-efficient Regularization for Sparsely Activated Transformers ICML 2022 Gauss-Legendre Features for Gaussian Process Regression JMLR 2022 Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks CoRL 2022 Generalized Binary Search Network for Highly-Efficient Multi-View Stereo CVPR 2022 Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness ACL 2022 Generalized Stochastic Matching AAAI 2022 Generative Adaptive Convolutions for Real-World Noisy Image Denoising AAAI 2022 GeoEngine: A Platform for Production-Ready Geospatial Research CVPR 2022 Get More at Once: Alternating Sparse Training with Gradient Correction NeurIPS 2022 GhostNetV2: Enhance Cheap Operation with Long-Range Attention NeurIPS 2022 Giga-scale Kernel Matrix-Vector Multiplication on GPU NeurIPS 2022 GLaM: Efficient Scaling of Language Models with Mixture-of-Experts ICML 2022 Go Wider Instead of Deeper AAAI 2022 GPT3.int8(): 8-bit Matrix Multiplication for Transformers at Scale NeurIPS 2022 Gradient and Mangitude Based Pruning for Sparse Deep Neural Networks AAAI 2022 Graph Condensation for Graph Neural Networks ICLR 2022 GraphFM: Improving Large-Scale GNN Training via Feature Momentum ICML 2022 Graph network simulators can learn discontinuous, rigid contact dynamics CoRL 2022 Graph Neural Networks with Adaptive Readouts NeurIPS 2022 Great Power, Great Responsibility: Recommendations for Reducing Energy for Training Language Models NAACL 2022 Green Hierarchical Vision Transformer for Masked Image Modeling NeurIPS 2022 Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics NeurIPS 2022 HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions NeurIPS 2022 HaRiM+: Evaluating Summary Quality with Hallucination Risk AACL 2022