Existing learning-based methods effectively reconstruct HDR images from multi-exposure LDR inputs with extended dynamic range and improved detail, but they rely more on empirical design rather than ...

Reliable protein multiple sequence alignment (MSA) is essential for downstream biomedical research and directly impacts the accuracy of analytical results. However, protein sequences often exhibit low ...

Standard methods for aligning large language models with human preferences learn from pairwise comparisons among sampled candidate responses and regularize toward a reference policy. Despite their ...

Abstract: A novel iterative learning control (ILC) strategy is developed for displacement and velocity tracking control of high-speed trains (HSTs) across all operational phases. In practical ...

Large language models (LLMs) demonstrate impressive performance but lack the flexibility to adapt to human preferences quickly without retraining. In this work, we introduce Test-time Preference ...