Representation Learning

Task-Customized Self-Supervised Pre-training with Scalable Dynamic Routing AAAI 2022 Task Decoupled Framework for Reference-Based Super-Resolution CVPR 2022 Task Discovery: Finding the Tasks that Neural Networks Generalize on NeurIPS 2022 Temporally-Consistent Survival Analysis NeurIPS 2022 Text Revision by On-the-Fly Representation Optimization ACL 2022 Text Revision By On-the-Fly Representation Optimization AAAI 2022 The Devil in Linear Transformer EMNLP 2022 The Effects of Corpus Choice and Morphosyntax on Multilingual Space Induction EMNLP 2022 The Geometry of Multilingual Language Model Representations EMNLP 2022 The HCCL System for the NIST SRE21 Interspeech 2022 The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning NeurIPS 2022 The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy CVPR 2022 The Role of Pretrained Representations for the OOD Generalization of RL Agents ICLR 2022 The (Undesired) Attenuation of Human Biases by Multilinguality EMNLP 2022 TIGGER: Scalable Generative Modelling for Temporal Interaction Graphs AAAI 2022 Topic Modeling by Clustering Language Model Embeddings: Human Validation on an Industry Dataset EMNLP 2022 Towards End-to-End Image Compression and Analysis with Transformers AAAI 2022 Towards Robust k-Nearest-Neighbor Machine Translation EMNLP 2022 Towards Total Recall in Industrial Anomaly Detection CVPR 2022 Towards Understanding Grokking: An Effective Theory of Representation Learning NeurIPS 2022 Toward Unifying Text Segmentation and Long Document Summarization EMNLP 2022 Tracking Semantic Shifts in German Court Decisions with Diachronic Word Embeddings EMNLP 2022 Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data ACL 2022 Training stochastic stabilized supralinear networks by dynamics-neutral growth NeurIPS 2022 Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space EMNLP 2022