Unverified50% confidenceFactExact time
Mercury 3 uses diffusion for parallel refinement to generate text, rather than traditional token-by-token autoregressive output.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMercury 2 将扩散技术（Diffusion）应用到语言生成领域，通过并行去噪过程同步优化多个 Token，而非逐一自回归生成75% 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54% similarVerifiedStable Diffusion's text guidance converts prompts into vectors through the CLIP text encoder.51% similarUnverifiedThe core principle of Stable Diffusion is to perform denoising generation in a compressed latent space, using a three-stage process consisting of a CLIP text encoder to understand prompts, a U-Net architecture to perform denoising, and a VAE decoder to restore the image.50% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1070766API
curl https://kongchang.com/api/v1/knowledge/claims/1070766MCP
get_claim(id=1070766)