[KongchangAI]
Unverified50% confidenceFactExact time

InfoNCE 损失通过在一批候选中最大化正样本对相似度、最小化负样本对相似度进行训练,温度超参数τ越小分布越集中

1
Sources
50%
Confidence
Long-term
Relevance
7/15/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/519207
API
curl https://kongchang.com/api/v1/knowledge/claims/519207
MCP
get_claim(id=519207)