Unverified90% confidenceFactTime unknown
MixupMP方法发表于AISTATS 2024会议
1
Sources
90%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMixupMP建立在Fong、Holmes和Walker于2023年提出的Martingale后验框架之上73% similarUnverifiedMixupMP在分类准确率上与最佳基线方法持平甚至更优66% similarUnverifiedMixupMP返回的样本来自一个隐式定义的贝叶斯后验分布64% similarUnverifiedMixup、CutMix等现代增强技术可被纳入VRM框架解释63% similarUnverifiedMixupMP所展示的通过预测分布建模改善不确定性量化的思路，可能为大语言模型的幻觉检测和可靠性评估提供新的技术路径62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1009API
curl https://kongchang.com/api/v1/knowledge/claims/1009MCP
get_claim(id=1009)