Machine LearningFeatured briefing
First-hand information for everyone
Researchers tested whether very small and simply wired reservoir computers can both store and select among multiple chaotic behaviors. They
HorizonMath is a new benchmark that asks whether artificial intelligence can make genuine mathematical discoveries. The team collected more
This paper introduces a fast, data-driven way to estimate the condition number of large sparse matrices using graph neural networks (GNNs).
This paper proposes a simple, geometric way to compare two datasets that live in the same feature space. The authors treat the question “can
This paper shows how to combine modern score-based generative models with a popular optimization algorithm, the alternating direction method
This paper proposes a simple post-training method for generative recommender systems that uses only observed user rewards. The authors weigh
Researchers tested how much genomic language models (GLMs) can memorize specific DNA sequences and how that creates privacy risks. They buil
This paper looks at how large language models (LLMs) can turn a researcher’s plain-language request into running code and tools, while still
This paper introduces SAHOO, a practical framework to watch and control subtle shifts in behavior when machine learning systems update thems
Researchers tested whether dense numerical summaries of DNA sequences — called embeddings — can be turned back into the original DNA. Embedd