Unverified50% confidenceOpinionExact time
DePoser relies on depth foundation models for annotation, so the quality ceiling of its pseudo-ground truth is determined by the depth foundation model, and errors propagate into subsequent fine-tuning.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedErrors introduced by quantization accumulate layer by layer with network depth, ultimately affecting the quality of the model's output.73% similarUnverifiedThe residual is the gap between the true value and the current prediction, representing the model's current error.69% similarUnverifiedLarge models may merely be absorbing the loss from compression using excess parameters and hidden state capacity, making the compression robustness observed on saturated tasks an illusion.69% similarUnverifiedFine-tuning on data with narrow defects can sometimes cause models to become broadly misaligned.69% similarVerified若用含测试集的全量数据计算均值和标准差，会导致预处理泄漏，使评估指标虚高，无法真实反映模型泛化能力68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1074616API
curl https://kongchang.com/api/v1/knowledge/claims/1074616MCP
get_claim(id=1074616)