arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Beihang University(北京航空航天大学)

2026-01-21 至 2026-01-21 共收录 6
2601.14127 2026-01-21 cs.CV cs.CL

The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning

智能的副作用:MLLMs多图像推理中的安全风险

Renmiao Chen, Yida Lu, Shiyao Cui, Xuan Ouyang, Victor Shea-Jay Huang, Shumin Zhang, Chengwei Pan, Han Qiu, Minlie Huang

机构 * CoAI group, DCST, Tsinghua University(清华大学) Beihang University(北航) Tsinghua University(清华大学)

AI总结 研究发现,多图像推理能力越强的模型在安全测试中越容易产生不安全响应,揭示了模型在任务解决中可能忽视安全约束的风险。

Comments *15 pages, 5 figures. Introduces MIR-SafetyBench (2,676 instances; 9 multi-image relations). Equal contribution; †Corresponding author. Code/data: https://github.com/thu-coai/MIR-SafetyBench

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.12765 2026-01-21 cs.CV

Towards Unbiased Source-Free Object Detection via Vision Foundation Models

面向视觉基础模型的无偏源域无关目标检测

Zhi Cai, Yingjie Gao, Yanan Zhang, Xinzhu Ma, Di Huang

机构 * State Key Laboratory of Complex and Critical Software Environment, Beihang University, Beijing, 100191, China(复杂与关键软件环境国家重点实验室,北京航空航天大学,北京,100191,中国) School of Computer Science and Engineering, Beihang University, Beijing, 100191, China(计算机科学与工程学院,北京航空航天大学,北京,100191,中国) School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, 230601, China(计算机科学与信息工程学院,合肥工业大学,合肥,230601,中国)

AI总结 本文提出DSOD框架,通过VFM辅助缓解源偏问题,提升跨域目标检测性能,实验表明在多个基准上优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.12761 2026-01-21 cs.CV

Moaw: Unleashing Motion Awareness for Video Diffusion Models

Moaw:释放视频扩散模型中的运动感知

Tianqi Zhang, Ziyi Wang, Wenzhao Zheng, Weiliang Chen, Yuanhui Huang, Zhengyang Huang, Jie Zhou, Jiwen Lu

机构 * Tsinghua University(清华大学) Beihang University(北航)

AI总结 Moaw通过训练视频扩散模型进行运动感知,实现零样本运动迁移,推动生成建模与运动理解的结合。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.13947 2026-01-21 eess.IV cs.CV

Real-Time Reconstruction of 3D Bone Models via Very-Low-Dose Protocols

通过极低剂量协议实时重建3D骨模型

Yiqun Lin, Haoran Sun, Yongqing Li, Rabia Aslam, Lung Fung Tse, Tiange Cheng, Chun Sing Chui, Wing Fung Yau, Victorine R. Le Meur, Meruyert Amangeldy, Kiho Cho, Yinyu Ye, James Zou, Wei Zhao, Xiaomeng Li

机构 * Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR(香港理工大学电子与计算机工程系) Koln 3D Technology (Medical) Limited, Hong Kong SAR(香港特别行政区科隆3D技术(医疗)有限公司) Department of Physics, Beihang University, Beijing, China(北京航空航天大学物理系) Union Hospital, Hong Kong SAR(香港特别行政区联合医院) Dental Materials Science, Division of Applied Oral Sciences and Community Dental Care, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR(香港大学牙科学院牙体材料科学系) Department of Orthopaedics and Traumatology, The Chinese University of Hong Kong, Hong Kong SAR(香港中文大学骨科及创伤外科学系) Department of Management Science and Engineering, Stanford University, Stanford, CA, USA(斯坦福大学管理科学与工程系) Department of Biomedical Data Science, Stanford University, Stanford, CA, USA(斯坦福大学生物医学数据科学系)

AI总结 本研究提出SSR-KD框架,通过双平面X光在30秒内快速重建高精度3D骨模型,降低辐射暴露并提升术中应用的实用性。

Comments Accepted to npj Digital Medicine

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.01724 2026-01-21 cs.AI

ReflecSched: Solving Dynamic Flexible Job-Shop Scheduling via LLM-Powered Hierarchical Reflection

ReflecSched: 通过LLM赋能的分层反思解决动态灵活作业车间调度问题

Shijie Cao, Yuan Yuan

机构 * School of Computer Science and Engineering(计算机科学与工程学院) Beihang University(北京航空航天大学) Qingdao Research Institute(青岛研究院) Hangzhou Innovation Institute(杭州创新研究院) Zhongguancun Laboratory(中关村实验室)

AI总结 ReflecSched通过LLM赋能的分层反思机制,有效解决动态灵活作业车间调度问题,实现优于传统和学习方法的性能表现。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.12030 2026-01-21 cs.AI

ARC: Active and Reflection-driven Context Management for Long-Horizon Information Seeking Agents

ARC:面向长周期信息检索代理的主动与反思驱动上下文管理

Yilun Yao, Shan Huang, Elsie Dai, Zhewen Tan, Zhenyu Duan, Shousheng Jia, Yanbing Jiang, Tong Yang

机构 * Peking University(北京大学) Beihang University(北京航空航天大学) Qiyuan Tech(启元科技)

AI总结 ARC 通过主动和反思驱动的上下文管理方法,提升了长周期信息检索代理的性能,显著提高了准确性。

Comments 15 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏