Unverified50% confidenceFactExact time
Universal Transformer had already explored cross-layer weight sharing (parameter sharing).
1
Sources
50%
Confidence
Long-term
Relevance
9/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe hybrid Transformer-UNet architecture combines the Transformer's advantage in global semantic understanding with UNet's capability in spatial hierarchical feature extraction.79% similarUnverifiedThe Universal Transformer proposed by Dehghani et al. in 2019 was the first to design Transformer layers as repeatable recurrent units, and introduced an adaptive computation time mechanism to dynamically determine the number of recurrent iterations.76% similarUnverifiedSwitch Transformer and the Mixtral series have widely adopted the MoE architecture.72% similarUnverified在Transformer架构中，每个层由多头自注意力机制和多层感知机（MLP）两个核心子模块组成72% similarUnverified在Transformer架构中，MLP层承担了大量的信息处理工作71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/918321API
curl https://kongchang.com/api/v1/knowledge/claims/918321MCP
get_claim(id=918321)