Unverified50% confidenceFactExact time
CFMs simply combine unit-level variances at inference time, implicitly assuming that errors across different units are independent.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn class-imbalanced scenarios, accuracy alone can be misleading and needs to be combined with a confusion matrix for more fine-grained evaluation.75% similarUnverifiedIn the homogeneous missingness setting (where each covariate is observed with independent probability q), the error bound derived by the authors exhibits a complex rather than standard dependence on q.73% similarUnverifiedThe study theoretically derives that when the encoder merges the distinguishable outcomes of different actions under the same state as well as different appearances, a positive lower bound exists on the squared inverse prediction error.70% similarUnverifiedClassifier-free guidance (CFG) runs both a conditional branch and an unconditional branch simultaneously, amplifying the conditional signal by subtracting the unconditional direction from the conditional direction, trading a doubling of inference cost for quality improvement.69% similarUnverifiedThe study formally proves that unit-level errors are in fact correlated due to posterior uncertainty about the data-generating process.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1068323API
curl https://kongchang.com/api/v1/knowledge/claims/1068323MCP
get_claim(id=1068323)