Unverified50% confidenceFactExact time
Exponential moving average (EMA) is a weight smoothing technique used in training that maintains a sliding-average copy of the parameters and is insensitive to the noise and abrupt changes of single-step gradients.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDecoupled exponential moving average (D-EMA) adopts a configurable grouped averaging strategy that constrains interference-sensitive pretrained parameters while preserving flexibility for other parameters.79% similarUnverified欧拉框架下每个训练信号衡量相邻两帧之间的运动，位移较小可稳定落在光流估计器可靠工作区间内，从而约束监督误差不随序列长度累积放大65% similarUnverifiedAccelerated LoRA is optimized during training for a specific sampler scheduling strategy and model weights; when the actual sampler's step size distribution, noise schedule, or model quantization method is inconsistent with the training conditions, the shortcut paths learned by the LoRA may fail entirely.64% similarUnverifiedMotion VAE is a class of methods that applies variational autoencoders to human motion sequence modeling; its encoder typically uses a Transformer or graph convolutional network, the decoder outputs a skeletal pose sequence, and the training objective is to maximize the ELBO.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1037828API
curl https://kongchang.com/api/v1/knowledge/claims/1037828MCP
get_claim(id=1037828)