Papers
Important
| Name | Date | Source | Note |
|---|---|---|---|
| Attention Is All You Need | arxiv:1706.03762 | influential paper that introduced Transformer | |
| An Image is Worth 16x16 Words | arxiv:2010.11929 | Transformers for Image Recognition at Scale - Vision Transformer (ViT) | |
| Block-Recurrent Transformers | arxiv:2203.07852 | ||
| Language Models are Few-Shot Learners | arxiv:2005.14165 | GPT | |
| Memorizing Transformers | arxiv:2203.08913 | ||
| MobileViT | arxiv:2110.02178 | Light-weight, General-purpose, and Mobile-friendly Vision Transformer | |
| OpenAI CLIP | arxiv:2103.00020 [[1]] | Learning Transferable Visual Models From Natural Language Supervision | |
| STaR | arxiv:2203.14465 | Bootstrapping Reasoning With Reasoning | |
| Transformer-XL | arxiv:1901.02860 | Attentive Language Models Beyond a Fixed-Length Context |
Others
https://arxiv.org/abs/2301.13779 (FLAME: A small language model for spreadsheet formulas) - Small model specifically for spreadsheets by Miscrofot