arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

The University of Hong Kong(香港大学)

2026-01-19 至 2026-01-19 共收录 3
2601.11518 2026-01-19 cs.CL

How Long Is a Piece of String? A Brief Empirical Analysis of Tokenizers

字符串有多长?对分词器的简要实证分析

Jonathan Roberts, Kai Han, Samuel Albanie

机构 * University of Cambridge(剑桥大学) The University of Hong Kong(香港大学)

AI总结 本文通过实证分析揭示了不同分词器和文本分布下token长度的显著差异,挑战了传统对token长度的简化假设。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.11400 2026-01-19 cs.CV cs.AI

Wetland mapping from sparse annotations with satellite image time series and temporal-aware segment anything model

基于卫星影像时间序列和时序感知的分割任何模型进行稀疏标注的湿地制图

Shuai Yuan, Tianwu Lin, Shuang Chen, Yu Xia, Peng Qin, Xiangyu Liu, Xiaoqing Xu, Nan Xu, Hongsheng Zhang, Jie Wang, Peng Gong

机构 * Department of Geography, The University of Hong Kong, Hong Kong, China(香港大学地理系) Pengcheng Laboratory, Shenzhen, China(深圳鹏城实验室) Department of Electronics and Information Engineering, Harbin Institute of Technology (Shenzhen), Shenzhen, China(哈尔滨工业大学(深圳)电子与信息工程学院) Key Laboratory for Geo-Environmental Monitoring of Great Bay Area, Ministry of Natural Resources, Guangdong Key Laboratory of Urban Informatics, Shenzhen Key Laboratory of Spatial Smart Sensing and Services, Shenzhen University, Shenzhen, China(粤港澳大湾区地理环境监测重点实验室,自然资源部,广东省城市信息学重点实验室,深圳空间智能感知与服务重点实验室,深圳大学)

AI总结 WetSAM通过整合卫星影像时间序列和双分支设计,有效解决稀疏标注下的湿地制图问题,实现高精度分割与低标注成本。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.11096 2026-01-19 cs.CV

CoDance: An Unbind-Rebind Paradigm for Robust Multi-Subject Animation

CoDance: 一种用于鲁棒多主体动画的解绑-重新绑定范式

Shuai Tan, Biao Gong, Ke Ma, Yutong Feng, Qiyuan Zhang, Yan Wang, Yujun Shen, Hengshuang Zhao

机构 * The University of Hong Kong(香港大学) Ant Group(蚂蚁集团) Huazhong University of Science and Technology(华中科技大学) Tsinghua University(清华大学) University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校)

AI总结 CoDance通过解绑-重新绑定框架实现鲁棒多主体动画,解决传统方法在处理任意主体数量、类型及空间错位时的局限性。

Comments https://lucaria-academy.github.io/CoDance/

详情

展开后加载摘要…

URL PDF HTML 收藏