Pretraining

Prompt Learning with Quaternion Networks ICLR 2024 PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild CVPR 2024 Quantifying Unintended Memorization in BEST-RQ ASR Encoders Interspeech 2024 Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How ICLR 2024 ReactXT: Understanding Molecular “Reaction-ship” via Reaction-Contextualized Molecule-Text Pretraining ACL 2024 Reading Does Not Equal Reading: Comparing, Simulating and Exploiting Reading Behavior across Populations COLING 2024 Reduce, Reuse, Recycle: Is Perturbed Data Better than Other Language Augmentation for Low Resource Self-Supervised Speech Models Interspeech 2024 REFeREE: A REference-FREE Model-Based Metric for Text Simplification COLING 2024 Relationship Prompt Learning is Enough for Open-Vocabulary Semantic Segmentation NeurIPS 2024 Release of Pre-Trained Models for the Japanese Language COLING 2024 ReMAP: Neural Model Reprogramming with Network Inversion and Retrieval-Augmented Mapping for Adaptive Motion Forecasting NeurIPS 2024 Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling ACL 2024 Restoration by Generation with Constrained Priors CVPR 2024 Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models COLING 2024 Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery CVPR 2024 Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models NeurIPS 2024 Retrieval Across Any Domains via Large-scale Pre-trained Model ICML 2024 Retrieval-Augmented Egocentric Video Captioning CVPR 2024 Return of Unconditional Generation: A Self-supervised Representation Generation Method NeurIPS 2024 Revisiting the Power of Prompt for Visual Tuning ICML 2024 ROCES: Robust Class Expression Synthesis in Description Logics via Iterative Sampling IJCAI 2024 S2MAE: A Spatial-Spectral Pretraining Foundation Model for Spectral Remote Sensing Data CVPR 2024 SA²VP: Spatially Aligned-and-Adapted Visual Prompt AAAI 2024 SA3DIP: Segment Any 3D Instance with Potential 3D Priors NeurIPS 2024 Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training ECCV 2024