Attention Is Not What You Need (2025)(arxiv.org)
158 points by westurner | 53 comments
arXiv paper proposing an attention-free sequence model using Grassmann flows and Plucker coordinates, compared against Transformers on Wikitext-2 and SNLI.
1 story tagged grassmann-manifold, newest first.
158 points by westurner | 53 comments
arXiv paper proposing an attention-free sequence model using Grassmann flows and Plucker coordinates, compared against Transformers on Wikitext-2 and SNLI.