Attention Is All You Need
arXiv:1706.03762 · one column, hyperref links, figures
Deep Residual Learning for Image Recognition
arXiv:1512.03385 · two columns, many figures and tables
arXiv 2601.05637
arXiv:2601.05637 · recent paper
Auto-Encoding Variational Bayes
arXiv:1312.6114 · equations
Language Models are Few-Shot Learners
arXiv:2005.14165 · 75 pages: stress test
The Large N Limit of Superconformal Field Theories
arXiv:hep-th/9711200 · old TeX, no hyperref