Researchers propose a new approach to training large language models called Spaced Repetition Training (SRT). This method schedules the review of hist...
Researchers propose a new approach to safe decision-making in uncertain environments called RATTL (Risk-Adversarial Total-Reward Learning). The method...
Researchers have developed a framework called TRUSS for generating software agent skills that are both functionally effective and safety reliable. The...
Researchers have developed MoNe, a lightweight neural memory system that can handle long context inference tasks without requiring retraining of the u...
Researchers have developed a method to accurately count crowds using drones without labeled training data. This is crucial for large events like the F...
Researchers have developed a precise correspondence between two ways of describing the do-operator in acyclic structural causal models. The do-operato...
Researchers have developed a new method to read out the internal reasoning states of mixture-of-experts (MoE) models. This allows for the extraction o...
Researchers have found that large language models (LLMs) are not consistent in their preference judgments. When asked how much someone would be willin...
Researchers from China have developed an AI-powered tool called GraphWake that can manipulate groups of language models to polarize their opinions. Th...
Researchers have audited the behavior of three AI systems designed to evolve and improve their performance over time. The study found that while these...
Researchers have developed a new method called InnerExpert that can detect hallucinations in large language models (LLMs) at the level of individual t...
Researchers have studied the performance of a type of AI model called prediction cascades when faced with degraded input data. Prediction cascades rou...