An online iterative alignment pipeline that generates on-policy data, scores responses with a reward model, constructs preference pairs, and trains with DPO -- closing the distribution gap of offline ...

Abstract: The periodic operation pattern of high-speed train (HST) grants the immense potential for iterative learning control (ILC) approach regulating the displacement and velocity, but the ...

Abstract: The remanent-magnetization effects pose a great challenge to the application of magnetic exploration in fields such as metallic mineral prospecting, igneous rock detection, and tectonic ...

Mar. 6, 2026 A Rutgers-led study found that eating less protein may help slow liver cancer in people with impaired liver function. When damaged livers can’t properly clear toxic ammonia from protein ...

A Python-based toolkit and graphical interface that automates the micro-optimization of map lighting and performance.

Machine learning is the ability of a machine to improve its performance based on previous results. Machine learning methods enable computers to learn without being explicitly programmed and have ...