2 papers
cs.CV2026
Ctrl-GenAug: Controllable Generative Augmentation for Medical Sequence Classification
Xinrui Zhou, Yuhao Huang, Haoran Dou +13
In the medical field, the limited availability of large-scale datasets and labor-intensive annotation processes hinder the performance of deep models. Diffusion-based generative au…
cs.LG2026
InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions
Liangjian Wen, Qun Dai, Jianzhuang Liu +7
In multimodal representation learning, synergistic interactions between modalities not only provide complementary information but also create unique outcomes through specific inter…