architecture · first seen 4 Oct 2026
residual connections
Also: skip connections
Shortcut paths that add a layer's input to its output to ease deep network training.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Should We Skip Diffusion?Papers · 4 Oct 2026 · Yiping Ji, James Martens, Simon Lucey
- Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention ResidualsPapers · 8 Oct 2026 · Pengxiang Li, Dilxat Muhtar, Di He, Guinan Su, Lu Yin, Shiwei Liu
- Multi-Stream Attention ResidualsPapers · 9 Oct 2026 · Xiaohan Qin, Xiangdong Zhang, Tuo Dai, Sunan Zou, Huaijin Wu, Yebin Yang, Zhuo X…
- keyu-wang-2002/ScalingDepthCode · 11 Oct 2026 · keyu-wang-2002 · 24 stars
- Depth MemoryPapers · 13 Oct 2026 · David González-Martínez, Philipp Nazari, T. Konstantin Rusch, Shiwei Liu
- Hierarchical Residuals: A Minimalist Decoupling of Residual Width from Compute WidthPapers · 30 Oct 2026 · Ziteng Wang, Jianqiao Lu, Xinyu Ma, Jintao Zhang, Jun Zhu, Yiyuan Ma, Jianfei Ch…
Latest sources
- Loopback Transformer: Towards a Unified View of Residual Looped TransformersPapers · 4 Nov 2026 · Xuan Ouyang, Zefan Cai, Chenlong Zhang, Cheng Luo, Ke Wan, Junjie Hu
- Hierarchical Residuals: A Minimalist Decoupling of Residual Width from Compute WidthPapers · 30 Oct 2026 · Ziteng Wang, Jianqiao Lu, Xinyu Ma, Jintao Zhang, Jun Zhu, Yiyuan Ma, Jianfei Ch…
- Depth MemoryPapers · 13 Oct 2026 · David González-Martínez, Philipp Nazari, T. Konstantin Rusch, Shiwei Liu
- keyu-wang-2002/ScalingDepthCode · 11 Oct 2026 · keyu-wang-2002 · 24 stars
- Multi-Stream Attention ResidualsPapers · 9 Oct 2026 · Xiaohan Qin, Xiangdong Zhang, Tuo Dai, Sunan Zou, Huaijin Wu, Yebin Yang, Zhuo X…
- Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention ResidualsPapers · 8 Oct 2026 · Pengxiang Li, Dilxat Muhtar, Di He, Guinan Su, Lu Yin, Shiwei Liu
- Should We Skip Diffusion?Papers · 4 Oct 2026 · Yiping Ji, James Martens, Simon Lucey