Techniques

Sinkformers: Transformers with Doubly Stochastic Attention AISTATS 2022 SkoltechNLP at SemEval-2022 Task 8: Multilingual News Article Similarity via Exploration of News Texts to Vector Representations SemEval 2022 Smooth Maximum Unit: Smooth Activation Function for Deep Networks Using Smoothing Maximum Technique CVPR 2022 So3krates: Equivariant attention for interactions on arbitrary length-scales in molecular systems NeurIPS 2022 Soft-Labeled Contrastive Pre-Training for Function-Level Code Representation EMNLP 2022 SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning ICLR 2022 Sound and Complete Neural Network Repair with Minimality and Locality Guarantees ICLR 2022 Sound and Complete Verification of Polynomial Networks NeurIPS 2022 Sound and Visual Representation Learning With Multiple Pretraining Tasks CVPR 2022 SpanConv: A New Convolution via Spanning Kernel Space for Lightweight Pansharpening IJCAI 2022 Sparse Attention with Learning to Hash ICLR 2022 Sparse Cross-Scale Attention Network for Efficient LiDAR Panoptic Segmentation AAAI 2022 Sparse Double Descent: Where Network Pruning Aggravates Overfitting ICML 2022 Sparse MLP for Image Recognition: Is Self-Attention Really Necessary? AAAI 2022 SparseTT: Visual Tracking with Sparse Transformers IJCAI 2022 Sparsity Winning Twice: Better Robust Generalization from More Efficient Training ICLR 2022 Spatial-aware Speaker Diarizaiton for Multi-channel Multi-party Meeting Interspeech 2022 Spatiotemporal Initialization for 3D CNNs With Generated Motion Patterns WACV 2022 SPDY: Accurate Pruning with Speedup Guarantees ICML 2022 Speaking Rate Control of end-to-end TTS Models by Direct Manipulation of the Encoder's Output Embeddings Interspeech 2022 Spectral Probing EMNLP 2022 Spectral Pruning for Recurrent Neural Networks AISTATS 2022 SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing ACL 2022 Spherization Layer: Representation Using Only Angles NeurIPS 2022 Spoofing-Aware Speaker Verification by Multi-Level Fusion Interspeech 2022