Unverified50% confidenceFactExact time
The controller trained only on normal data achieved zero physical violations on the development stress set.
1
Sources
50%
Confidence
Long-term
Relevance
10/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedControlNet's zero convolution layer design (initialized with zero weights) ensures that the original model's capabilities are not disrupted during early training, with training costs far lower than training a new model from scratch.69% similarUnverifiedThe model did not use any pretrained weights during training.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1109979API
curl https://kongchang.com/api/v1/knowledge/claims/1109979MCP
get_claim(id=1109979)