Unverified50% confidenceFactExact time
Token Merging (ToMe) was originally proposed by Bolya et al. in 2022 to accelerate inference for image classification with Vision Transformers (ViT)
1
Sources
50%
Confidence
Long-term
Relevance
9/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe DiT architecture was formally proposed by Meta Research in 2023, introducing the Vision Transformer into the denoising process of diffusion models, with computational complexity growing quadratically with sequence length.67% similarUnverifiedVision Transformer (ViT) emerged in 2020, marking the entry of Transformers into the field of computer vision.64% similarVerifiedDiT was proposed by Peebles and Xie in 2022, introducing the Transformer architecture into the diffusion process.63% similarVerifiedThe Diffusion Transformer (DiT) architecture was first proposed by Meta Research in 2022.62% similarUnverifiedB站在2024年升级了「创作者保护计划」，引入了AI辅助的原创性判定系统62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/921769API
curl https://kongchang.com/api/v1/knowledge/claims/921769MCP
get_claim(id=921769)