2 papers
cs.CV2026
Noise-aware few-shot learning through bi-directional multi-view prompt alignment
Lu Niu, Cheng Xue
Vision-language models offer strong few-shot capability through prompt tuning but remain vulnerable to noisy labels, which can corrupt prompts and degrade cross-modal alignment. Ex…
cs.CL2023
Dealing with negative samples with multi-task learning on span-based joint entity-relation extraction
Chenguang Xue, Jiamin Lu
Recent span-based joint extraction models have demonstrated significant advantages in both entity recognition and relation extraction. These models treat text spans as candidate en…