 PVTAdpNet: Polyp Segmentation using Pyramid vision transformer with a novel Adapter blockInternational journal of information technology (IJIT), 2025 |
 FedDPG: An Adaptive Yet Efficient Prompt-tuning Approach in Federated Learning SettingsPacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2025 |
 Docopilot: Improving Multimodal Models for Document-Level UnderstandingComputer Vision and Pattern Recognition (CVPR), 2025 |
 Efficient Adaptation of Deep Neural Networks for Semantic Segmentation in Space ApplicationsScientific Reports (Sci Rep), 2025 |
 SChanger: Change Detection from a Semantic Change and Spatial Consistency PerspectiveIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (IEEE J-STARS), 2025 |
 PAVE: Patching and Adapting Video Large Language ModelsComputer Vision and Pattern Recognition (CVPR), 2025 |
