Simon Kornblith

Simon Kornblith on Hugging Face Daily Papers: 6 papers, 3 in the top 3 of their day, 110 upvotes.

1. Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5? 4 upvotes, #12 of 2023-11-15
2. Small-scale proxies for large-scale Transformer training instabilities 22 upvotes, #3 of 2023-09-26
3. Replacing softmax with ReLU in Vision Transformers 18 upvotes, #2 of 2023-09-18
4. OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models 34 upvotes, #3 of 2023-08-04
5. Guiding Image Captioning Models Toward More Specific Captions 18 upvotes, #6 of 2023-08-01
6. Towards Generalist Biomedical AI 14 upvotes, #5 of 2023-07-27

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.