Unverified50% confidenceFactExact time
The Transformer architecture was originally used for text and later extended to images (ViT), audio (AST) and multimodality.
1
Sources
50%
Confidence
Long-term
Relevance
11/1/2026
First Seen
Sources
Related Entities
Related Claims
Partially VerifiedTransformers框架支持文本、视觉、音频及多模态模型76% similarUnverifiedDALL·E 1基于离散VAE和Transformer架构实现文本到图像生成72% similarUnverifiedThe latest generation of editing models adopts the DiT (Diffusion Transformer) architecture, which processes image tokens and text tokens in a unified manner, thereby achieving finer cross-modal alignment.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1121927API
curl https://kongchang.com/api/v1/knowledge/claims/1121927MCP
get_claim(id=1121927)