1
GRAIN: Group Aggregation via Min-Norm Objective
最小范数目标驱动的组聚合方法，为高维数据分组与优化带来全新解法。
arXiv:2606.22917v1 Announce Type: new Abstract: Learning instability is a long-standing problem across machine learning, but it is especially acute in…
2
Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs
无需训练就能剪掉多余视觉token，让视频大模型推理更快、理解更细。
arXiv:2604.20937v2 Announce Type: replace Abstract: Video Large Language Models (Video LLMs) incur high inference latency due to a large number of vis…
3
COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion
大模型在纵向电子病历推理中常因缺乏精细化统计导致幻觉，COTCAgent通过概率化思维链补全实现预防性咨询，为临床决策支持提供新范式。
arXiv:2605.15016v1 Announce Type: cross Abstract: As large language models empower healthcare, intelligent clinical decision support has developed rap…