Transfer Learning

Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach CVPR 2024 Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning CVPR 2024 L-TTA: Lightweight Test-Time Adaptation Using a Versatile Stem Layer NeurIPS 2024 LUWA Dataset: Learning Lithic Use-Wear Analysis on Microscopic Images CVPR 2024 MACP: Efficient Model Adaptation for Cooperative Perception WACV 2024 MAIR: A Massive Benchmark for Evaluating Instructed Retrieval EMNLP 2024 Map It Anywhere: Empowering BEV Map Prediction using Large-scale Public Datasets NeurIPS 2024 MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression Comprehension EMNLP 2024 mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models ACL 2024 MedAdapter: Efficient Test-Time Adaptation of Large Language Models Towards Medical Reasoning EMNLP 2024 MELT: Materials-aware Continued Pre-training for Language Model Adaptation to Materials Science EMNLP 2024 Memory-Efficient Prompt Tuning for Incremental Histopathology Classification AAAI 2024 MEVTR: A Multilingual Model Enhanced with Visual Text Representations COLING 2024 MinT: Boosting Generalization in Mathematical Reasoning via Multi-view Fine-tuning COLING 2024 MirageRoom: 3D Scene Segmentation with 2D Pre-trained Models by Mirage Projection CVPR 2024 Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training ACL 2024 Mixture-of-LoRAs: An Efficient Multitask Tuning Method for Large Language Models COLING 2024 Mixture-of-Subspaces in Low-Rank Adaptation EMNLP 2024 MmAP: Multi-Modal Alignment Prompt for Cross-Domain Multi-Task Learning AAAI 2024 Modeling User Preferences with Automatic Metrics: Creating a High-Quality Preference Dataset for Machine Translation EMNLP 2024 Model Reprogramming: Resource-Efficient Cross-Domain Machine Learning AAAI 2024 Modular Adaptation of Multilingual Encoders to Written Swiss German Dialect EACL 2024 MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks NeurIPS 2024 MOHO: Learning Single-view Hand-held Object Reconstruction with Multi-view Occlusion-Aware Supervision CVPR 2024 MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence ICML 2024