Weijie Yin

Reliable underwater perception requires complementary sensing under variable visibility. Optical cameras capture appearance and semantics but degrade rapidly with turbidity, whereas imaging sonar preserves geometry while exhibiting distinct range-azimuth structure and acoustic artifacts. Existing MLLMs, built primarily on optical encoders, are therefore ill-suited to model sonar or adaptively exploit sonar-optical complementarity.

Abstract With large amounts of unlabeled RNA sequences data produced by high-throughput sequencing technologies, pre-trained RNA language models have been developed to estimate semantic space of RNA molecules, which facilities the understanding of grammar of RNA language. However, existing RNA language models overlook the impact of structure when modeling the RNA semantic space, resulting in incomplete feature extraction and suboptimal performance across various downstream tasks.

Weijie Yin‡, Yan Song§ and Xing Chang‡1 From the ‡Chinese Academy of Sciences Key Laboratory of Tissue Microenvironment and Tumor, Shanghai Institute of Nutrition and Health, Shanghai Institutes for Biological Sciences, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai 200031, China and the §Department of Cellular and Molecular Medicine, University of California at San Diego, La Jolla, California 92037 ↵1 To whom correspondence should be addressed.