Researchers propose Adversarial Review (AR), a protocol for cooperative code review where three agents work together: a main coding agent, a reviewer,...
Researchers have developed looped language models to improve the ability of AI systems to perform complex tasks that require multiple steps and intera...
Researchers have made new theoretical discoveries about the Jaccard distance in lattices and real valuations. They found that under certain conditions...
Researchers have developed a new method for detecting SARS-CoV-2 variants called GenEx. This approach uses graph-based analysis to examine the relatio...
Researchers have developed a tool called Redakto to anonymize text before it's fed into large language models (LLMs). This is important for ensuring p...
Researchers have explored whether large neural networks can be designed to cache frequently used parts of their architecture, reducing memory bandwidt...
Researchers have evaluated the performance of open-source Optical Character Recognition (OCR) engines and Large Language Models (LLMs) on a complex ta...
Researchers at Netflix have developed a lifecycle framework for Large Language Model (LLM) judges used in recommendation explanations. The framework c...
Researchers propose SESSE (Sketch, Expand, Sort, Summarize, Evaluate), a training-free framework for evaluating large language models. Unlike traditio...
Researchers have developed a new benchmark called ComponentBench to evaluate the performance of computer-use agents in modern web interfaces. The benc...
Researchers have proposed a method to supervise AI models using governance records generated by machine-verifiable workflows. These records link vario...
A new benchmark called THPT-Ladder has been introduced to evaluate language models on Vietnam's National High School Graduation Examination. The bench...