Training-Free Dual Hyperbolic Adapters for Better Cross-Modal Reasoning
无需训练的双双曲适配器用于更高效的跨模态推理
机构 * College of Computer Science and Software Engineering, Shenzhen University(深圳大学计算机科学与软件工程学院) ; Department of Electrical and Electronic Engineering, Southern University of Science and Technology(南方科技大学电子与电气工程系) ; Department of Applied Mathematics and Theoretical Physics, University of Cambridge(剑桥大学应用数学与理论物理系) ; Yau Mathematical Sciences Center, Tsinghua University(清华大学应用数学中心)
AI总结 本文提出无需训练的双双曲适配器方法,通过双曲空间嵌入提升跨模态推理性能,实现更高效的领域泛化和少样本识别。
Comments Accepted in IEEE Transactions on Multimedia (TMM)