Techniques

On the Connection between Pre-training Data Diversity and Fine-tuning Robustness NeurIPS 2023 On the Difference of BERT-style and CLIP-style Text Encoders ACL 2023 On the Expressivity Role of LayerNorm in Transformers’ Attention ACL 2023 On the impact of activation and normalization in obtaining isometric embeddings at initialization NeurIPS 2023 On the Importance and Applicability of Pre-Training for Federated Learning ICLR 2023 On the (In)Efficiency of Acoustic Feature Extractors for Self-Supervised Speech Representation Learning Interspeech 2023 On the Soft-Subnetwork for Few-Shot Class Incremental Learning ICLR 2023 Open-Category Human-Object Interaction Pre-Training via Language Modeling Framework CVPR 2023 OpenMapFlow: A Library for Rapid Map Creation with Machine Learning and Remote Sensing Data AAAI 2023 OpenRT: An Open-source Framework for Reasoning Over Tabular Data ACL 2023 Open Vocabulary Semantic Segmentation With Patch Aligned Contrastive Learning CVPR 2023 OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions ICCV 2023 Optimizing Dynamic Neural Networks with Brainstorm OSDI 2023 Orthogonal Subspace Learning for Language Model Continual Learning EMNLP 2023 Orthogonal Transforms for Learning Invariant Representations in Equivariant Neural Networks WACV 2023 OTOv2: Automatic, Generic, User-Friendly ICLR 2023 Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation NeurIPS 2023 Over-parameterized Model Optimization with Polyak-{\L}ojasiewicz Condition ICLR 2023 Over-Training with Mixup May Hurt Generalization ICLR 2023 PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers CVPR 2023 PAD-Net: An Efficient Framework for Dynamic Networks ACL 2023 Paparazzi: A Deep Dive into the Capabilities of Language and Vision Models for Grounding Viewpoint Descriptions EACL 2023 ParaFormer: Parallel Attention Transformer for Efficient Feature Matching AAAI 2023 Parallel Context Windows for Large Language Models ACL 2023 Parameter-Efficient Cross-lingual Transfer of Vision and Language Models via Translation-based Alignment EMNLP 2023