Unverified50% confidenceBenchmarkExact time
ChangeFormer采用层次化Transformer编码器，在LEVIR-CD和DSIFN-CD等基准上取得了SOTA性能
1
Sources
50%
Confidence
Long-term
Relevance
8/10/2026
First Seen
Sources
Related Claims
Partially VerifiedSora采用DiT（Diffusion Transformer）架构，将视频压缩为时空patch序列后输入Transformer，以Transformer替代传统U-Net作为去噪骨干网络64% similarUnverified相比RNN/LSTM架构，Transformer支持大规模并行计算62% similarUnverifiedSwitch Transformer和Mixtral系列广泛采用了MoE架构62% similarUnverifiedSD3引入了MMDiT（Multi-Modal Diffusion Transformer）架构，用Transformer替代了传统的U-Net骨干网络，并采用三重文本编码器（CLIP ViT-L、OpenCLIP ViT-bigG、T5-XXL）62% similarVerifiedFLUX采用了DiT（Diffusion Transformer）架构，用纯Transformer替代了传统的U-Net结构59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/723118API
curl https://kongchang.com/api/v1/knowledge/claims/723118MCP
get_claim(id=723118)