arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

高校专区

Beihang University(北京航空航天大学)

2026-03-03 至 2026-03-03 共收录 13
2603.01706 2026-03-03 cs.CV cs.LG

Search Multilayer Perceptron-Based Fusion for Efficient and Accurate Siamese Tracking

基于多层感知机的融合搜索用于高效准确的孪生跟踪

Tianqi Shen, Huakao Lin, Ning An

机构 * Institute of Mining Artificial Intelligence, Chinese Institute of Coal Science(采矿人工智能研究所,中国煤炭科学研究院) Department of Computer Science, City University of Hong Kong(计算机科学系,香港城市大学) Image Processing Center, School of Astronautics, Beihang University(图像处理中心,航天学院,北航) State Key Laboratory of Intelligent Coal Mining and Strata Control(智能煤炭开采与岩层控制国家重点实验室)

AI总结 本文提出了一种基于多层感知机的融合搜索方法,用于改进孪生跟踪器的效率与准确性,在多个基准测试中取得优异成绩。

Comments 23 pages, 12 figures, 7 tables. This work was completed in 2024 and accepted for publication in IEEE TCDS (2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.01418 2026-03-03 cs.CV cs.MM cs.SD

UniTalking: A Unified Audio-Video Framework for Talking Portrait Generation

UniTalking: 一种统一的音频-视频框架用于说话肖像生成

Hebeizi Li, Zihao Liang, Benyuan Sun, Zihao Yin, Xiao Sha, Chenliang Wang, Yi Yang

机构 * Central Media Technology Institute, Huawei(华为中央媒体技术研究所) School of Computer Science and Engineering, Beihang University(北航计算机科学与工程学院)

AI总结 UniTalking提出了一种统一的端到端扩散框架,用于生成高质量的语音和唇同步视频,通过多模态Transformer块和个性化语音克隆技术,提升了视觉保真度和训练效率。

Comments Accepted at CVPR 2026 (Findings Track)

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.01385 2026-03-03 cs.CL cs.AI

Toward Graph-Tokenizing Large Language Models with Reconstructive Graph Instruction Tuning

迈向通过重构图指令微调的大型语言模型的图-词化

Zhongjian Zhang, Xiao Wang, Mengmei Zhang, Jiarui Tan, Chuan Shi

机构 * Beijing University of Posts and Telecommunications(北京邮电大学) Beihang University(北航)

AI总结 本文提出RGLM方法,通过重构图信息和显式图监督改进图-词化LLMs的对齐效果,提升对图结构的理解与利用。

Comments accepted by WWW 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.01260 2026-03-03 cs.LG cs.AI

MOSAIC: A Unified Platform for Cross-Paradigm Comparison and Evaluation of Homogeneous and Heterogeneous Multi-Agent RL, LLM, VLM, and Human Decision-Makers

MOSAIC:一个用于跨范式比较和评估同质和异质多智能体RL、LLM、VLM和人类决策者的统一平台

Abdulhamid M. Mousa, Yu Fu, Rakhmonberdi Khajiev, Jalaledin M. Azzabi, Abdulkarim M. Mousa, Peng Yang, Yunusa Haruna, Ming Liu

机构 * School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China(北京理工大学光学工程学院) School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China(北京航空航天大学自动化科学与电气工程学院) Faculty of Science, Ain Shams University, Cairo, Egypt(爱思唯命大学科学学院)

AI总结 MOSAIC是一个开源平台,通过统一接口和跨范式评估框架,支持在相同环境中比较不同决策范式的智能体,促进可重复的跨领域研究。

Comments 13 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.03819 2026-03-03 cs.LG

Transmit Weights, Not Features: Orthogonal-Basis Aided Wireless Point-Cloud Transmission

传输权重,而非特征:基于正交基的无线点云传输

Junlin Chang, Yubo Han, Hang Yue, John S Thompson, Rongke Liu

机构 * Beihang University(北京航空航天大学) Pengcheng Laboratory(鹏城实验室) Shenzhen Institute of Beihang University(北京航空航天大学深圳研究院) University of Edinburgh(爱丁堡大学) IDCOM(影像、数据与通讯研究所)

AI总结 本文提出基于正交基的无线点云传输框架,通过预测接收端语义正交特征池的组合权重,实现紧凑表示和稳健重建,并在不同带宽下表现出色。

Comments 5 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.15281 2026-03-03 cs.IR cs.LG

MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation

MMQ: 多模态混合量化标记化用于语义ID生成和用户行为适应

Yi Xu, Moyu Zhang, Chenxuan Li, Zhihao Liao, Haibo Xing, Hao Deng, Jinxin Hu, Yu Zhang, Xiaoyi Zeng, Jing Zhang

机构 * Alibaba Group(阿里巴巴集团) Peking University(北京大学) Beijing University of Aeronautics and Astronautics(北京航空航天大学) Wuhan University, School of Computer Science(武汉大学计算机学院)

AI总结 MMQ通过多模态混合量化标记化方法,解决推荐系统中多模态协同、特定性和行为适应的挑战,提升语义ID生成和用户行为适应能力。

Journal ref Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.18041 2026-03-03 cs.CV cs.RO

Openfly: A comprehensive platform for aerial vision-language navigation

Openfly:面向空中视觉-语言导航的综合性平台

Yunpeng Gao, Chenhui Li, Zhongrui You, Junli Liu, Zhen Li, Pengan Chen, Qizhi Chen, Zhonghan Tang, Liansheng Wang, Penghui Yang, Yiwen Tang, Yuhang Tang, Shuai Liang, Songyi Zhu, Ziqin Xiong, Yifei Su, Xinyi Ye, Jianan Li, Yan Ding, Dong Wang, Xuelong Li, Zhigang Wang, Bin Zhao

机构 * Shanghai AI Laboratory(上海人工智能实验室) Northwestern Polytechnical University(西北工业大学) Beihang University(北航) Shanghai Jiao Tong University(上海交通大学) The University of Hong Kong(香港大学) Zhejiang University(浙江大学) University of Science and Technology of China(中国科学技术大学) East China University of Science and Technology(东华大学) Fudan University(复旦大学) Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所) TeleAI

AI总结 OpenFly平台通过整合多种渲染引擎和自动化工具链,构建大规模空中VLN数据集,并提出关键帧感知的VLN模型,提升户外空中视觉-语言导航的研究与应用。

Comments accepted by ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.00979 2026-03-03 cs.CV

Fake It Right: Injecting Anatomical Logic into Synthetic Supervised Pre-training for Medical Segmentation

伪造正确:将解剖学逻辑注入合成监督预训练以进行医学分割

Jiaqi Tang, Mengyan Zheng, Shu Zhang, Fandong Zhang, Qingchao Chen

机构 * Peking University(北京大学) Beihang University(北航) Deepwise Ltd.(深睿科技)

AI总结 本文提出了解剖学指导的合成监督预训练框架,通过结合FDSL与解剖学现实,提升医学分割的性能和数据效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.00978 2026-03-03 cs.CV cs.AI

EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimization

EraseAnything++: 通过多对象优化实现Rectified Flow Transformers中的概念擦除

Zhaoxin Fan, Nanxiang Jiang, Daiheng Gao, Shiji Zhou, Wenjun Wu

机构 * Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, School of Artificial Intelligence, Beihang University(北京未来区块链与隐私计算先进创新中心,人工智能学院,北航) University of Science and Technology of China(中国科学技术大学)

AI总结 EraseAnything++通过多目标优化实现图像和视频扩散模型中的概念擦除,提升生成质量与时间一致性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.00599 2026-03-03 cs.AI cs.LG

Heterophily-Agnostic Hypergraph Neural Networks with Riemannian Local Exchanger

无异质性偏见的超图神经网络与黎曼局部交换器

Li Sun, Ming Zhang, Wenxin Jin, Zhongtian Sun, Zhenhao Huang, Hao Peng, Sen Su, Philip Yu

机构 * Beijing University of Posts and Telecommunications(北京邮电大学) North China Electric Power University(华北电力大学) University of Kent(肯特大学) Beihang University(北航) University of Illinois(伊利诺伊大学)

AI总结 本文提出HealHGNN,通过黎曼几何和自适应局部交换器实现异质性无关的超图神经网络,提升长距离依赖建模和表示区分性。

Comments Accepted by WWW'26, 12 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.00532 2026-03-03 cs.AI

DenoiseFlow: Uncertainty-Aware Denoising for Reliable LLM Agentic Workflows

DenoiseFlow:面向可靠LLM代理工作流的不确定性感知去噪

Yandong Yan, Junwei Peng, Shijie Li, Chenxi Li, Yifei Shang, Can Deng, Ruiting Dai, Yongqiang Zhao, Jiaqi Zhu, Yu Huang

机构 * School of Computer Science, Peking University(北京大学计算机科学学院) School of Electronics Engineering and Computer Science, Peking University(北京大学电子工程与计算机科学学院) SKLCCSE, School of Computer Science and Engineering, Beihang University(北航计算机科学与工程学院) Tsinghua University(清华大学) University of Electronic Science and Technology of China(电子科技大学) Key Laboratory of High Confidence Software Technologies(PKU), MOE(北京大学高可信软件技术重点实验室) Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所) National Engineering Research Center for Software Engineering, Peking University(软件工程国家工程研究中心)

AI总结 DenoiseFlow通过闭环框架实现多步推理的不确定性感知去噪,提升LLM代理工作流的可靠性与效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.10575 2026-03-03 cs.CV

UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation

UniFlow:一种统一的像素流标记器用于视觉理解和生成

Zhengrong Yue, Haiyu Zhang, Xiangyu Zeng, Boyu Chen, Chenting Wang, Shaobin Zhuang, Lu Dong, Yi Wang, Limin Wang, Yali Wang

机构 * Shanghai Jiao Tong University(上海交通大学) Shanghai AI Laboratory(上海人工智能实验室) Beihang University(北京航空航天大学) Shenzhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(深圳计算机视觉与模式识别重点实验室,深圳先进技术研究院,中国科学院) Nanjing University(南京大学) University of Science and Technology of China(中国科学技术大学) School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)

AI总结 UniFlow是一种统一的像素流标记器,通过灵活适配视觉编码器和轻量级解码器,在视觉理解和生成任务中实现了性能的双赢。

Comments ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.01454 2026-03-03 cs.CR cs.LG

Sparsification Under Siege: Dual-Level Defense Against Poisoning in Communication-Efficient Federated Learning

在通信高效联邦学习中受攻击的稀疏化:双层防御对抗污染

Zhiyong Jin, Runhua Xu, Chao Li, Yizhong Liu, Jianxin Li, James Joshi

机构 * School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院) School of Cyber Science and Technology at Beihang University(北京航空航天大学网络安全科学与技术学院) School of Cyberspace Science and Technology, Beijing Jiaotong University(北京交通大学网络空间科学与技术学院) Beijing Key Laboratory of Security and Privacy in Intelligent Transportation(北京智能交通安全与隐私重点实验室) Zhongguancun Laboratory(中关村实验室) School of Computing and Information,University of Pittsburgh(匹兹堡大学计算与信息学院)

AI总结 SafeSparse通过双层防御机制,在通信高效联邦学习中有效对抗污染攻击,提升模型鲁棒性与准确性。

详情

展开后加载摘要…

URL PDF HTML 收藏