Lst: Ladder side-tuning for parameter and memory efficient transfer learning

YL Sung, J Cho, M Bansal - Advances in Neural …, 2022‏ - proceedings.neurips.cc
Fine-tuning large pre-trained models on downstream tasks has been adopted in a variety of
domains recently. However, it is costly to update the entire parameter set of large pre-trained …

Mamba-nd: Selective state space modeling for multi-dimensional data

S Li, H Singh, A Grover - European Conference on Computer Vision, 2024‏ - Springer
In recent years, Transformers have become the de-facto architecture for sequence modeling
on text and multi-dimensional data, such as images and video. However, the use of self …

Unipt: Universal parallel tuning for transfer learning with efficient parameter and memory

H Diao, B Wan, Y Zhang, X Jia… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Parameter-efficient transfer learning (PETL) ie fine-tuning a small portion of parameters is an
effective strategy for adapting pre-trained models to downstream domains. To further reduce …

Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?

R Ren, S Basart, A Khoja, A Gatti, L Phan, X Yin… - arxiv preprint arxiv …, 2024‏ - arxiv.org
As artificial intelligence systems grow more powerful, there has been increasing interest in"
AI safety" research to address emerging and future risks. However, the field of AI safety …

Marsformer: Martian rock semantic segmentation with transformer

Y **ong, X **ao, M Yao, H Liu… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Semantic segmentation of Mars scenes has a crucial role in Mars rovers science missions.
Current convolutional neural network (CNN)-based composition of U-Net has powerful …

Re2TAL: Rewiring pretrained video backbones for reversible temporal action localization

C Zhao, S Liu, K Mangalam… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Temporal action localization (TAL) requires long-form reasoning to predict actions of various
durations and complex content. Given limited GPU memory, training TAL end to end (ie, from …

MMIF-INet: Multimodal medical image fusion by invertible network

D He, W Li, G Wang, Y Huang, S Liu - Information Fusion, 2025‏ - Elsevier
Multimodal medical image fusion (MMIF) technology aims to generate fused images that
comprehensively reflect the information of tissues, organs, and metabolism, thereby …

Invertible diffusion models for compressed sensing

B Chen, Z Zhang, W Li, C Zhao, J Yu… - … on Pattern Analysis …, 2025‏ - ieeexplore.ieee.org
While deep neural networks (NN) significantly advance image compressed sensing (CS) by
improving reconstruction quality, the necessity of training current CS NNs from scratch …

Sherl: Synthesizing high accuracy and efficient memory for resource-limited transfer learning

H Diao, B Wan, X Jia, Y Zhuge, Y Zhang, H Lu… - … on Computer Vision, 2024‏ - Springer
Parameter-efficient transfer learning (PETL) has emerged as a flourishing research field for
adapting large pre-trained models to downstream tasks, greatly reducing trainable …

Efficient pneumonia detection using Vision Transformers on chest X-rays

S Singh, M Kumar, A Kumar, BK Verma, K Abhishek… - Scientific Reports, 2024‏ - nature.com
Pneumonia is a widespread and acute respiratory infection that impacts people of all ages.
Early detection and treatment of pneumonia are essential for avoiding complications and …