arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

The Hong Kong University of Science and Technology(香港科技大学)

2026-06-18 至 2026-06-18 共收录 6
2606.01139 2026-06-18 cs.AI 版本更新

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

SkillRevise: 通过轨迹条件技能修订改进LLM撰写的智能体技能

Yuxuan Liu, Zhaochen Su, Lingyun Xie, Yuhao Zhang, Qing Zong, Jiahe Guo, Zhongwei Xie, Yiyan Ji, Yauwai Yim, Hongyu Luo, Xiyu Ren, Ruan Chenyu, Haoran Li, Yangqiu Song

机构 * The Hong Kong University of Science and Technology(香港科学与技术大学) Harbin Institute of Technology(哈尔滨工业大学) Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳)) Nanjing University(南京大学) The University of Hong Kong(香港大学)

AI总结 提出SkillRevise框架,通过执行证据诊断、修复原则检索和执行锚定编辑,迭代优化初始技能,在SkillsBench上将基础智能体成功率从36.05%提升至61.63%,并展现跨模型迁移性。

Comments 15 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.26903 2026-06-18 cs.CR cs.AI 版本更新

Practical Anonymous Two-Party Gradient Boosting Decision Tree

实用的匿名两方梯度提升决策树

Chenyu Huang, Fan Zhang, Minxin Du, Sherman S. M. Chow, Huangxun Chen, Huaming Rao, Danqing Huang, Bo Qian, Peng Chen

机构 * Tencent(腾讯) Hong Kong Polytechnic University(香港理工大学) Chinese University of Hong Kong(香港中文大学) HKUST-GZ

AI总结 针对两方垂直分割数据上的梯度提升决策树训练,提出一种基于双电路隐私集合求交和遗忘可编程伪随机函数的匿名协议,在隐藏记录标识符的同时保持效率。

Comments 19 pages; 2026 IEEE Symposium on Security and Privacy (SP)

Journal ref 2026 IEEE Symposium on Security and Privacy (SP)

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.03156 2026-06-18 cs.CV 版本更新

CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator

CAMEO: 一种条件感知与质量驱动的多智能体图像编辑编排器

Yuhan Pu, Hao Zheng, Ziqian Mo, Zirui Pang, Hill Zhang, Tianyi Fan, Shuhong Wu, Jiaheng Wei

机构 * The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) Harbin Institute of Technology(哈尔滨工业大学) Shenzhen University(深圳大学) Claremont McKenna College(克莱蒙特麦肯纳学院) Research Institute of Petroleum Exploration and Development, CNPC(石油勘探开发研究院,中石油)

AI总结 提出CAMEO多智能体框架,将条件图像编辑重构为质量感知的反馈驱动过程,通过分解编辑阶段、嵌入评估循环,在异常插入和人体姿态切换任务中平均胜率提升20%。

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.14399 2026-06-18 cs.LG cs.CV physics.ao-ph stat.ML 版本更新

Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecasting

面向全球站点业务天气预报的物理信息时间序列模型基准测试

Tao Han, Zhibin Wen, Zhenghao Chen, Dazhao Du, Song Guo, Lei Bai

机构 * Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong SAR China(香港科技大学计算机科学与工程系) Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China(南方科技大学计算机科学与工程系) School of Computer and Information Sciences, University of Newcastle, Newcastle, Australia(新castle大学计算机与信息科学学院) Hangzhou Innovation Institute of Beihang University, Hangzhou, China(北京航空航天大学杭州创新研究院) Shanghai Artificial Intelligence Laboratory, Shanghai, China(上海人工智能实验室)

AI总结 提出大规模观测数据集WEATHER-5K和物理信息模型PhysicsFormer,通过压力-风对齐和能量感知平滑损失增强物理一致性,在多个天气变量和极端事件预测上评估学术模型与业务系统的差距。

Comments Accepted by ICML2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.20302 2026-06-18 cs.CV 版本更新

CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation

CrossEarth-Gate:基于Fisher引导的自适应调优引擎用于高效跨域遥感语义分割

Shilei Cao, Ziyang Gong, Hehai Lin, Yang Liu, Jiashun Cheng, Xiaoxing Hu, Haoyuan Liang, Guowen Li, Chengwei Qin, Hong Cheng, Xue Yang, Juepeng Zheng, Haohuan Fu

机构 * Sun Yat-sen University(中山大学) The Chinese University of Hong Kong(香港中文大学) Shanghai Jiao Tong University(上海交通大学) National Supercomputing Center in Shenzhen(深圳国家超算中心) The Hong Kong University of Science and Technology(香港科技大学) Beijing Institute of Technology(北京理工大学) The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) Tsinghua University(清华大学)

AI总结 提出CrossEarth-Gate,通过Fisher信息引导的自适应模块选择机制,动态激活最关键的跨域模块,在18个跨域基准中16个达到最优性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.22020 2026-06-18 cs.LG 版本更新

Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models

面向天气基础模型的任务自适应参数高效微调

Shilei Cao, Hehai Lin, Jiashun Cheng, Yang Liu, Guowen Li, Xuehe Wang, Juepeng Zheng, Haoyuan Liang, Meng Jin, Chengwei Qin, Hong Cheng, Haohuan Fu

机构 * Sun Yat-sen University(中山大学) The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) The Hong Kong University of Science and Technology(香港科技大学) The Chinese University of Hong Kong(香港中文大学) National Supercomputing Center in Shenzhen(深圳国家超算中心) Huawei Technologies Co., Ltd(华为技术有限公司) Tsinghua University(清华大学)

AI总结 提出WeatherPEFT框架,通过任务自适应动态提示和随机Fisher引导自适应选择,在天气下游任务上以更少参数达到全微调性能。

详情

展开后加载摘要…

URL PDF HTML 收藏