{"ok":true,"article":{"slug":"temper-tensorized-efficient-manifold-constrained-parameterization-for-expressive-c62e73da","title":"TEMPER: Tensorized Efficient Manifold-constrained Parameterization for Expressive Residual Routing","url":"https://arxiv.org/abs/2608.07851","canonical":"https://www.aimode.news/article/temper-tensorized-efficient-manifold-constrained-parameterization-for-expressive-c62e73da","sourceName":"arXiv cs.LG","summary":"arXiv:2608.07851v1 Announce Type: new Abstract: Residual connections rely on a static residual pathway, and are essential for training deep neural networks. Hyper-connections (HC) increase the expressivity of residual routing by incorporating multiple residual streams and learning dynamic information flow, while manif…","category":"AI","image":"https://static.arxiv.org/icons/twitter/arxiv-logo-twitter-square.png","lang":"en","publishedAt":"2026-08-11T04:00:00+00:00","createdAt":"2026-08-11T19:09:30.456448+00:00"}}