Model Architecture

Stochastic Training is Not Necessary for Generalization ICLR 2022 Sub-8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognition Interspeech 2022 SUMNAS: Supernet with Unbiased Meta-Features for Neural Architecture Search ICLR 2022 Survey on Efficient Training of Large Neural Networks IJCAI 2022 Survey on Graph Neural Network Acceleration: An Algorithmic Perspective IJCAI 2022 Swift: Adaptive Video Streaming with Layered Neural Codecs NSDI 2022 Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity JMLR 2022 TAda! Temporally-Adaptive Convolutions for Video Understanding ICLR 2022 TA-GATES: An Encoding Scheme for Neural Network Architectures NeurIPS 2022 Task Discovery: Finding the Tasks that Neural Networks Generalize on NeurIPS 2022 Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting ICLR 2022 Tensor Program Optimization with Probabilistic Programs NeurIPS 2022 Text-Driven Separation of Arbitrary Sounds Interspeech 2022 Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks EMNLP 2022 The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks ICML 2022 The Devil Is in the Margin: Margin-Based Label Smoothing for Network Calibration CVPR 2022 The Devil Is in the Pose: Ambiguity-Free 3D Rotation-Invariant Learning via Pose-Aware Convolution CVPR 2022 The Gyro-Structure of Some Matrix Manifolds NeurIPS 2022 The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization ICLR 2022 The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy CVPR 2022 The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training ICLR 2022 Time-domain Ad-hoc Array Speech Enhancement Using a Triple-path Network Interspeech 2022 Tiny-Sepformer: A Tiny Time-Domain Transformer Network For Speech Separation Interspeech 2022 To update or not to update? Neurons at equilibrium in deep models NeurIPS 2022 Toward Efficient Robust Training against Union of ℓ_p Threat Models NeurIPS 2022