Machine LearningFeatured briefing
First-hand information for everyone
This paper introduces dynestyx, a software library that makes it easier to do Bayesian inference for dynamical systems inside a probabilisti
This paper studies why deep neural networks sometimes suffer from exploding or vanishing gradients and how residual connections (the skip li
Researchers studied a simple question with big practical consequences: when should a learning method try to align two data types in the same
Researchers asked whether large language models (LLMs) have built‑in preferences for particular financial assets and whether those preferenc
This paper reviews how machine learning is shifting materials discovery from predicting properties to proposing candidate materials that mee
Researchers introduce a method to recover the mix of data domains that shaped a large language model (LLM) using only the text the model gen
This paper describes a weakness in the common method used to align large language models (LLMs) with human preferences. The method is called
Researchers analysed when and how simple generative models stop memorising their training examples and start producing similar outputs when
This paper introduces On-Policy Consistency Training (OPCT), a way to make large language models (LLMs) behave more safely while avoiding lo
This paper proposes a practical way to draw samples from probability densities that look like exp(−f(x)−g(x)). Here f is a smooth function t