3 papers
cs.LG2026
Nonlinearity-Aware LoRA: Structured Gate Adaptation under Low-Rank Constraints
Shuai Yuan, Sudong Cai, Bingzhi Chen +4
Low-rank adaptation (LoRA) is commonly viewed as an update-space approximation to full fine-tuning, yet this view is incomplete for self-gated Transformer feed-forward networks. In…
cs.CV2025
Cross Modal Fine-Grained Alignment via Granularity-Aware and Region-Uncertain Modeling
Jiale Liu, Haoming Zhou, Yishu Liu +2
Fine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-langu…
cs.CV2025
Cause-Effect Driven Optimization for Robust Medical Visual Question Answering with Language Biases
Huanjia Zhu, Yishu Liu, Xiaozhao Fang +2
Existing Medical Visual Question Answering (Med-VQA) models often suffer from language biases, where spurious correlations between question types and answer categories are inadvert…