Parameter-efficient fine-tuning for pre-trained vision models: A survey

Y **n, S Luo, H Zhou, J Du, X Liu, Y Fan, Q Li… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Large-scale pre-trained vision models (PVMs) have shown great potential for adaptability
across various downstream vision tasks. However, with state-of-the-art PVMs growing to …

V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark

Y **n, S Luo, X Liu, H Zhou, X Cheng… - Advances in …, 2025‏ - proceedings.neurips.cc
Parameter-efficient transfer learning (PETL) methods show promise in adapting a pre-
trained model to various downstream tasks while training only a few parameters. In the …

Self-supervised visual preference alignment

K Zhu, L Zhao, Z Ge, X Zhang - Proceedings of the 32nd ACM …, 2024‏ - dl.acm.org
This paper makes the first attempt towards unsupervised preference alignment in Vision-
Language Models (VLMs). We generate chosen and rejected responses with regard to the …

Parameter-efficient fine-tuning in large models: A survey of methodologies

L Wang, S Chen, L Jiang, S Pan, R Cai, S Yang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
The large models, as predicted by scaling raw forecasts, have made groundbreaking
progress in many fields, particularly in natural language generation tasks, where they have …

Efficient Few-Shot Action Recognition via Multi-level Post-reasoning

C Wu, XJ Wu, L Li, T Xu, Z Feng, J Kittler - European Conference on …, 2024‏ - Springer
The integration with CLIP (Contrastive Vision-Language Pre-training) has significantly
refreshed the accuracy leaderboard of FSAR (Few-Shot Action Recognition). However, the …

KARST: Multi-Kernel Kronecker Adaptation with Re-Scaling Transmission for Visual Classification

Y Zhu, H Diao, S Gao, L Chen, H Lu - arxiv preprint arxiv:2502.06779, 2025‏ - arxiv.org
Fine-tuning pre-trained vision models for specific tasks is a common practice in computer
vision. However, this process becomes more expensive as models grow larger. Recently …

[HTML][HTML] Time Series Foundation Model for Improved Transformer Load Forecasting and Overload Detection

Y Hou, C Ma, X Li, Y Sun, H Yu, Z Fang - Energies, 2025‏ - mdpi.com
Simple load forecasting and overload prediction models, such as LSTM and XGBoost, are
unable to handle the increasing amount of data in power systems. Recently, various …

MIST: Multi-Modal Interactive Side-Tuning for Efficient Referring Expression Comprehension

X Liu, T Liu, S Huang, Y **n, Y Hu, Q Yin… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Referring expression comprehension (REC) is a vision-language task to locate a target
object in an image based on a language expression. Fully fine-tuning general-purpose pre …

Parameter-Efficient Fine-Tuning for Foundation Models

D Zhang, T Feng, L Xue, Y Wang, Y Dong… - arxiv preprint arxiv …, 2025‏ - arxiv.org
This survey delves into the realm of Parameter-Efficient Fine-Tuning (PEFT) within the
context of Foundation Models (FMs). PEFT, a cost-effective fine-tuning technique, minimizes …

Token Adaptation via Side Graph Convolution for Temporally and Spatially Efficient Fine-tuning of 3D Point Cloud Transformers

T Furuya - arxiv preprint arxiv:2502.14142, 2025‏ - arxiv.org
Parameter-efficient fine-tuning (PEFT) of pre-trained 3D point cloud Transformers has
emerged as a promising technique for 3D point cloud analysis. While existing PEFT …