1月6日，湖北省科技大会在武汉召开，会上宣读了《湖北省人民政府关于2024年度湖北省科学技术奖励的决定》。我院夏桂松教授团队荣获湖北省自然科学奖一等奖。夏桂松教授团队围绕从遥感图像数据到地物信息和知识转化的科学难题，通过多粒度大规模遥感解译基准数据构建理论、多维度遥感图像旋转框目标检测深度模型、多层次遥感图像场景与地物分类方法，系统地建立了遥感图像智能解译的深度学习理论与方法体系。该成果在对地观测、国防安全、...

2024年5月，国际综合性期刊《自然•方法》（Nature Methods）在线发表了论文题为“Dependency-aware deep generative models for multitasking analysis of spatial omics data”（依赖感知的多任务深度生成模型分析空间组学数据）。武汉大学为论文第一署名单位，我院田天教授为论文第一作者。这是我校生物信息方向研究成果首次刊登在Nature Methods期刊上。空间组学技术是近年来生物医学研究领域的一项重大突破。不同于单细胞组学，...

With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue. Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed for low-cost adaptation.

Many man-made objects have intrinsic symmetries and often Manhattan structure. By assuming an orthographic or a weak perspective projection model, this paper addresses the estimation of 3D structures and camera projection using symmetry and/or Manhattan structure cues.

Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and Parameter-Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting LLMs to downstream tasks.