First screen, captured .
Looks similar
Parametric Matrix Models(arxiv.org)
50 points by evanb | 5 comments
TimeGPT-1(arxiv.org)
373 points by PaulHoule | 114 comments
arXiv paper introducing TimeGPT, a foundation model for time series forecasting that performs zero-shot predictions on unseen datasets.
Matryoshka Representation Learning(arxiv.org)
71 points by fzliu | 10 comments
Related stories
Deep Learning Is Not So Mysterious or Different(arxiv.org)
445 points by wuubuu | 112 comments
arXiv paper by Andrew Gordon Wilson arguing deep learning generalization phenomena like benign overfitting and double descent are explainable by soft inductive biases.
AI Made Writing Code Easier. It Made Being an Engineer Harder(ivanturkovic.com)
343 points by saikatsg | 242 comments
Blog post by Ivan Turkovic arguing that AI tools make producing code easier while making the broader job of being a software engineer harder.
Deep learning gets the glory, deep fact checking gets ignored(rachel.fast.ai)
549 points by chmaynard | 134 comments
Rachel Thomas blog post on how a high-profile Nature paper using a Transformer to predict enzyme functions contained many errors that received far less attention than the original result.
Neural networks are clean(already-clean.goodfire.com)
768 points by themgt | 300 comments
An informal research essay by Nick Cammarata at Goodfire arguing polysemanticity stems from fixable issues, not superposition, making neurons interpretable at scale.
Training language models to be warm and empathetic makes them less reliable(arxiv.org)
334 points by Cynddl | 333 comments
arXiv paper finding that fine-tuning language models to be warm and empathetic raises error rates and makes them more sycophantic on safety-critical tasks.
AI tools are spotting errors in research papers(nature.com)
555 points by kgwgk | 200 comments
Nature news article on a growing movement using AI and large language models to detect errors in research papers, sparked by a flawed black plastic utensils study.