Unverified50% confidenceFactExact time
掩码扩散框架将加噪重新定义为token掩码替换，使扩散过程在离散文本域得以自洽
1
Sources
50%
Confidence
Long-term
Relevance
7/17/2026
First Seen
Sources
Related Claims
UnverifiedThe text encoder is responsible for converting natural language prompts into high-dimensional embedding vectors for use by the diffusion model's denoising process70% similarVerifiedWhisper's architecture adopts an encoder-decoder structure, where the encoder transforms the mel spectrogram of audio into high-dimensional feature representations, and the decoder generates text output word by word in an autoregressive manner.69% similarUnverified文本扩散采用掩码扩散（Masked Diffusion）方案，用[MASK]token替代真实token模拟损坏状态，再训练模型恢复原始文本，以块为单位并行输出68% similarUnverifiedMidjourney uses CLIP's text encoder to convert prompts into conditioning vectors that guide the denoising process of the diffusion model.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/542325API
curl https://kongchang.com/api/v1/knowledge/claims/542325MCP
get_claim(id=542325)