'It seemed to defy the laws of physics': The everlasting 'memory crystals' that could slash data centre emissions

In the face of rising emissions from data centres, researchers are turning to micro-explosions in glass and the use of DNA to ...

AI Is Unlocking a New Way of Doing Math

Over the past couple of months, several researchers have begun making the same provocative claim: They used generative-AI tools to solve a previously unanswered math problem. The most extreme promises ...
eLife

Size tuning of neural response variability in laminar circuits of macaque primary visual cortex

The trial-to-trial variability of neuronal responses and the correlated response variability among neurons are modulated by visual stimulus size in a manner that depends on cortical layer, suggesting ...
InfoWorld

Multi-token prediction technique triples LLM inference speed without auxiliary draft models

With reported 3x speed gains and limited degradation in output quality, the method targets one of the biggest pain points in production AI systems: latency at scale.

Researchers baked 3x inference speedups directly into LLM weights — without speculative decoding

Researchers from the University of Maryland, Lawrence Livermore, Columbia and TogetherAI have developed a training technique that triples LLM inference speed without auxiliary models or infrastructure ...