无需训练，离散扩散模型直接化身多标签分类器，dLLM-SetScore方法开源即用，值得一试。
arXiv:2608.14649v1 Announce Type: new Abstract: We present dLLM-SetScore, a training-free method that uses discrete masked-diffusion language models f…
针对真实临床数据长尾分布，引入生成式数据增强与标签共现建模，提升胸片多标签分类性能。
arXiv:2607.00975v1 Announce Type: cross Abstract: Chest X-ray multi-label classification is a core task in intelligent medical imaging diagnosis. Howe…
揭秘多标签胸部X光分类中不确定性解缠的基准研究，为医疗AI可靠性提供新视角。
arXiv:2508.04457v2 Announce Type: replace-cross Abstract: Reliable uncertainty quantification is crucial for trustworthy decision-making and the deplo…