#transformer architectures
topictransformer architectures
3 papers · 1 filter
cs.LG2026
Journey Operators for Structured Multi-Axis Composition
Mahesh Godavarti
The paper introduces a framework for modeling data with structure along multiple axes using journey operators that combine per‑axis transformations, showing when such compositions…
cs.LG2026
xHC: Expanded Hyper-Connections
Xiangdong Zhang, Xiaohan Qin, Sunan Zou +10
The paper introduces xHC, a method that expands the residual stream of Transformers to many parallel streams using temporal feature augmentation and a sparse update scheme, enablin…
cs.CV2026
Adaptive Routing for Efficient Diffusion Transformer-Based PNI Prediction
Youngung Han, Dohyun Kweon, Kyeonghun Kim +15
The paper proposes a diffusion‑based transformer model with adaptive routing to predict perineural invasion in cholangiocarcinoma from MRI scans, achieving competitive accuracy whi…