Pretraining

Diversity-Aware Meta Visual Prompting CVPR 2023 DocSplit: Simple Contrastive Pretraining for Large Document Embeddings EMNLP 2023 Does progress on ImageNet transfer to real-world datasets? NeurIPS 2023 Do not Mask Randomly: Effective Domain-adaptive Pre-training by Masking In-domain Keywords ACL 2023 Don’t Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner NeurIPS 2023 Do Pre-Trained Models Benefit Equally in Continual Learning? WACV 2023 Do Transformers Parse while Predicting the Masked Word? EMNLP 2023 Do we need Label Regularization to Fine-tune Pre-trained Language Models? EACL 2023 Downstream Datasets Make Surprisingly Good Pretraining Corpora ACL 2023 DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions NeurIPS 2023 DR-Tune: Improving Fine-tuning of Pretrained Visual Models by Distribution Regularization with Semantic Calibration ICCV 2023 Dynamic Stance: Modeling Discussions by Labeling the Interactions EMNLP 2023 Editing models with task arithmetic ICLR 2023 EEG to fMRI Synthesis Benefits from Attentional Graphs of Electrode Relationships MLHC 2023 Effective Self-supervised Pre-training on Low-compute Networks without Distillation ICLR 2023 Efficient Equivariant Transfer Learning from Pretrained Models NeurIPS 2023 Efficient Low-rank Backpropagation for Vision Transformer Adaptation NeurIPS 2023 Efficient Multimodal Fusion via Interactive Prompting CVPR 2023 EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones ICCV 2023 Ego-Only: Egocentric Action Detection without Exocentric Transferring ICCV 2023 ELiRF-VRAIN at BioNLP Task 1B: Radiology Report Summarization ACL 2023 Embedding Articulatory Constraints for Low-resource Speech Recognition Based on Large Pre-trained Model Interspeech 2023 EMMA-X: An EM-like Multilingual Pre-training Algorithm for Cross-lingual Representation Learning NeurIPS 2023 Encoder and Decoder, Not One Less for Pre-trained Language Model Sponsored NMT ACL 2023 Energy-Inspired Self-Supervised Pretraining for Vision Models ICLR 2023