Unverified50% confidenceFactExact time
Sora is based on the Diffusion Transformer (DiT) architecture, which was proposed by William Peebles and Saining Xie of UC Berkeley in 2023.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/7/2026
First Seen
Valid until: 12/6/2026
Sources
Related Entities
Related Claims
VerifiedDiT was proposed by Peebles and Xie in 2023; it replaces the U-Net backbone in traditional diffusion models with Transformer blocks and has become the technical foundation for video generation models such as Sora.73% similarUnverifiedDiT was proposed by Peebles and Xie in 2022, introducing the Transformer architecture into the diffusion process.72% similarVerifiedThe DiT (Diffusion Transformer) architecture was proposed in 2022 by Meta AI researcher William Peebles and Saining Xie.71% similarVerifiedThe Diffusion Transformer (DiT) architecture was first proposed by Meta Research in 2022.69% similarUnverifiedOpenAI Sora于2024年初公开展示，将DiT架构（源自Peebles & Xie 2022年论文）推向行业标准地位68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/870340API
curl https://kongchang.com/api/v1/knowledge/claims/870340MCP
get_claim(id=870340)