Multi-modal learning combining medical images and clinical text is promising for disease diagnosis. However, standard multi-modal training leads to shortcut learning: models exploit the easier modality (e.g., diagnostic cues in text) while neglecting harder-to-learn features (e.g., subtle visual patterns). We propose U...
Zijian Gu, Weikai Lin, Shuang Zhou et al.· 0 citations
Reasoning distillation from powerful teacher models to smaller students faces the Gap Curse: as teachers grow more sophisticated, their complex distributions increasingly diverge from what students can approximate, causing performance degradation. Existing mitigation strategies either filter out challenging examples th...
Zhen-Yu Lei, Zi-Han Chen, Yao-Chen Zhu et al.· 0 citations
ProMoS is introduced, the first unsupervised generalist GAD framework, which detects anomalies by modeling the abundant normality in unlabeled data, and proposes prototype-guided soft-label distillation to align teacher and student in a shared prototype space, enhancing cross-graph generalizability.
Yiming Xu, Zihan Chen, Z. Peng et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.