Unverified50% confidenceFactExact time
Time-series foundation models have zero-shot or few-shot forecasting capability and avoid the information loss caused by serializing numerical values into text.
1
Sources
50%
Confidence
Long-term
Relevance
11/8/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedA zero-shot model can make predictions directly on a new dataset it has never seen before, without task-specific retraining or fine-tuning.78% similarUnverified时序基础模型实现零样本泛化通常需要归一化策略(如RevIN)和频率嵌入或时间特征编码76% similarVerifiedZero-shot learning refers to a model making predictions at inference time without relying on any labeled samples for the task, directly based on pre-trained knowledge or external structural information.73% similarUnverifiedZero-shot LLMs are often worse than simple baseline methods on prediction tasks such as determining whether a given layer has been fine-tuned and estimating the order of magnitude of a model's parameter count.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1147693API
curl https://kongchang.com/api/v1/knowledge/claims/1147693MCP
get_claim(id=1147693)