Techniques

Locally Distributed Activation Vectors for Guided Feature Attribution COLING 2022 Logical Activation Functions: Logit-space equivalents of Probabilistic Boolean Operators NeurIPS 2022 Logic Rule Guided Attribution with Dynamic Ablation AAAI 2022 Logographic Information Aids Learning Better Representations for Natural Language Inference AACL 2022 Log-Polar Space Convolution Layers NeurIPS 2022 Long-range Sequence Modeling with Predictable Sparse Attention ACL 2022 Long-term Spatio-Temporal Forecasting via Dynamic Multiple-Graph Attention IJCAI 2022 Lossless Compression with Probabilistic Circuits ICLR 2022 LOT: Layer-wise Orthogonal Training on Improving l2 Certified Robustness NeurIPS 2022 Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks NeurIPS 2022 LTRC @ Causal News Corpus 2022: Extracting and Identifying Causal Elements using Adapters EMNLP 2022 LUL’s WMT22 Automatic Post-Editing Shared Task Submission EMNLP 2022 LwPosr: Lightweight Efficient Fine Grained Head Pose Estimation WACV 2022 MAE-AST: Masked Autoencoding Audio Spectrogram Transformer Interspeech 2022 Margin Calibration for Long-Tailed Visual Recognition ACML 2022 MarkupLM: Pre-training of Text and Markup Language for Visually Rich Document Understanding ACL 2022 Masked Autoencoders Are Scalable Vision Learners CVPR 2022 Masked Training of Neural Networks with Partial Gradients AISTATS 2022 Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network CVPR 2022 MaskTune: Mitigating Spurious Correlations by Forcing to Explore NeurIPS 2022 MaxMatch-Dropout: Subword Regularization for WordPiece COLING 2022 MCP: Self-supervised Pre-training for Personalized Chatbots with Multi-level Contrastive Sampling EMNLP 2022 Measuring the Mixing of Contextual Information in the Transformer EMNLP 2022 Memory-Augmented Non-Local Attention for Video Super-Resolution CVPR 2022 MemSR: Training Memory-efficient Lightweight Model for Image Super-Resolution ICML 2022