3 papers
cs.LG2026
Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective
Jingren Liu, Zhong Ji, YunLong Yu +4
Parameter-efficient fine-tuning for continual learning (PEFT-CL) has shown promise in adapting pre-trained models to sequential tasks while mitigating catastrophic forgetting probl…
cs.CV2025
Optimal Transport Adapter Tuning for Bridging Modality Gaps in Few-Shot Remote Sensing Scene Classification
Zhong Ji, Ci Liu, Jingren Liu +3
Few-Shot Remote Sensing Scene Classification (FS-RSSC) presents the challenge of classifying remote sensing images with limited labeled samples. Existing methods typically emphasiz…
cs.CV2025
Underlying Semantic Diffusion for Effective and Efficient In-Context Learning
Zhong Ji, Weilong Cao, Yan Zhang +3
Diffusion models has emerged as a powerful framework for tasks like image controllable generation and dense prediction. However, existing models often struggle to capture underlyin…