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)

共收录 1226
2601.18547 2026-01-27 cs.CV cs.MM

REMAC: Reference-Based Martian Asymmetrical Image Compression

基于参考的火星不对称图像压缩

Qing Ding, Mai Xu, Shengxi Li, Xin Deng, Xin Zou

机构 * School of Electronic and Information Engineering, Beihang University(北京航空航天大学电子与信息学院) Beihang University(北京航空航天大学) Beijing Institute of Spacecraft System Engineering(北京航天飞行系统工程研究所)

AI总结 REMAC通过将计算复杂度转移至资源丰富的解码器,并利用参考图像和内图像相似性,提升火星图像压缩性能。

Comments Accepted for publication in IEEE Transactions on Geoscience and Remote Sensing (TGRS). 2025 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. 18 pages, 20 figures

Journal ref Year: 2025, Volume: 64, Article Sequence Number: 5601018

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.18168 2026-01-27 cs.CV

TempDiffReg: Temporal Diffusion Model for Non-Rigid 2D-3D Vascular Registration

TempDiffReg:用于非刚性2D-3D血管配准的时序扩散模型

Zehua Liu, Shihao Zou, Jincai Huang, Yanfang Zhang, Chao Tong, Weixin Si

机构 * School of Computer Science and Engineering, Beihang University, Beijing, China(北京航空航天大学计算机科学与工程学院) State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China(北京航空航天大学虚拟现实技术与系统国家重点实验室) Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China(中国科学院深圳先进技术研究所) School of Computer Science and Control Engineering, Shenzhen University of Advanced Technology, Shenzhen, China(深圳先进技术大学计算机科学与控制工程学院) Department of Interventional Radiology, Shenzhen People’s Hospital, Shenzhen, China(深圳人民医院介入放射科)

AI总结 TempDiffReg通过时序扩散模型和结构感知视角n点模块,实现高精度的2D-3D血管配准,提升TACE手术的准确性和安全性。

Comments Accepted by IEEE BIBM 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.00051 2026-01-27 cs.CV cs.RO

Correspondence-Free Pose Estimation with Patterns: A Unified Approach for Multi-Dimensional Vision

无对应姿态估计与模式:多维视觉的统一方法

Quan Quan, Dun Dai

机构 * School of Automation Science and Electrical Engineering, Beihang University(自动化科学与电气工程学院,北京航空航天大学)

AI总结 本文提出了一种无对应姿态估计方法,通过模式特征函数建立优化方程,适用于多种视觉变换和姿态估计场景。

Journal ref 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , 2025, 20203-20209

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.22031 2026-01-27 cs.RO cs.SY eess.SY

A Degree of Flowability for Virtual Tubes

虚拟管的流动性度

Quan Quan, Shuhan Huang, Kai-Yuan Cai

机构 * School of Automation Science and Electrical Engineering, Beihang University(自动化科学与电气工程学院,北京航空航天大学)

AI总结 本文提出了一种基于最小能量原理的二维虚拟管流动性度计算方法,并通过仿真验证了其有效性。

Comments 22 pages, 16 figures. This is a preprint, currently under review for publication in Robotics and Autonomous Systems, Elsevier. Version 2 is submitted to fix the rendering fault in HTML and correct spelling mistakes in the abstract and the references

Journal ref Robotics and Autonomous Systems, 2025, 193:105108

详情

展开后加载摘要…

URL PDF HTML 收藏
2206.03809 2026-01-27 cs.RO

Control with Patterns: A D-learning Method

基于模式的控制:一种D学习方法

Quan Quan, Kai-Yuan Cai, Chenyu Wang

机构 * Beihang University(北京航空航天大学)

AI总结 本文提出了一种基于模式的控制方法,利用D学习在无需系统动力学知识的情况下解决非线性动力系统稳定性问题,并通过模拟和实际飞行实验验证其有效性。

Comments Accepted for publication at 8th Conference on Robot Learning (CoRL), Munich, Germany. 2024

Journal ref In 8th Annual Conference on Robot Learning, Munich,2024:270

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.15124 2026-01-27 cs.LG cs.AI

RAG-GFM: Overcoming In-Memory Bottlenecks in Graph Foundation Models via Retrieval-Augmented Generation

RAG-GFM:通过检索增强生成克服图基础模型中的内存瓶颈

Haonan Yuan, Qingyun Sun, Jiacheng Tao, Xingcheng Fu, Jianxin Li

机构 * SKLCCSE, School of Computer Science and Engineering(计算机科学与工程学院) Beihang University(北航) Guangxi Normal University(广西师范大学)

AI总结 RAG-GFM通过检索增强生成方法,解决图基础模型中的内存瓶颈问题,提升模型的效率和效果。

Comments Accepted by the Web Conference 2026 (Research Track)

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.05171 2026-01-27 cs.CL

Inside Out: Evolving User-Centric Core Memory Trees for Long-Term Personalized Dialogue Systems

Inside Out: 为长期个性化对话系统演化用户导向的核心内存树

Jihao Zhao, Ding Chen, Zhaoxin Fan, Kerun Xu, Mengting Hu, Bo Tang, Feiyu Xiong, Zhiyu Li

机构 * School of Information, Renmin University of China(中国人民大学信息学院) MemTensor (Shanghai) Technology Co., Ltd.(MemTensor(上海)科技有限公司) Institute for Advanced Algorithms Research, Shanghai(上海先进算法研究所) China Telecom Research Institute(中国电信研究院) Beijing University of Aeronautics and Astronautics(北京航空航天大学) Nankai University(南开大学)

AI总结 Inside Out通过演化用户导向的核心内存树,提升长期个性化对话系统的内存压缩与身份一致性,采用轻量级MemListener实现动态更新与高效响应生成。

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.16170 2026-01-27 cs.CV

CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction

CARE Transformer: 通过解耦双交互实现高效的线性视觉Transformer

Yuan Zhou, Qingshan Xu, Jiequan Cui, Junbao Zhou, Jing Zhang, Richang Hong, Hanwang Zhang

机构 * Nanyang Technological University(南洋理工大学) Beihang University(北京航空航天大学) Hefei University of Technology(合肥工业大学)

AI总结 CARE Transformer通过解耦双交互机制,实现高效的线性视觉Transformer,在移动端实现高精度与高效率的平衡。

Comments https://github.com/zhouyuan888888/CARE-Transformer

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.17008 2026-01-27 cs.LG q-fin.TR

Bayesian Robust Financial Trading with Adversarial Synthetic Market Data

对抗性合成市场数据下的贝叶斯稳健金融交易

Haochong Xia, Simin Li, Ruixiao Xu, Zhixia Zhang, Hongxiang Wang, Zhiqian Liu, Teng Yao Long, Molei Qin, Chuqiao Zong, Bo An

机构 * Nanyang Technological University(南洋理工大学) Beihang University(北航)

AI总结 本文提出一种贝叶斯稳健框架,通过生成对抗性合成市场数据和稳健策略学习,提升金融交易在不确定市场环境下的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.11139 2026-01-26 cs.LG cs.AI cs.SC

ViSymRe: Vision Multimodal Symbolic Regression

ViSymRe:视觉多模态符号回归

Da Li, Junping Yin, Jin Xu, Xinxin Li, Juan Zhang

机构 * Academy for Advanced Interdisciplinary Studies, Northeast Normal University(先进跨学科研究院,东北师范大学) Institute of Artificial Intelligence, Beihang University(人工智能研究院,北航) Institute of Applied Physics and Computational Mathematics(应用物理与计算数学研究院) National Key Laboratory of Computational Physics(计算物理国家重点实验室) School of Mathematical Sciences, East China Normal University(数学科学学院,华东师范大学) Shanghai Zhangjiang Institute of Mathematics(上海张江数学研究所)

AI总结 ViSymRe通过引入视觉模态提升基于Transformer的符号回归性能,采用多视图随机切片技术解决高维场景下的训练难题,实现高效且稳定的模型收敛。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.08521 2026-01-23 cs.LG

Your Group-Relative Advantage Is Biased

你的组相对优势存在偏差

Fengkai Yang, Zherui Chen, Xiaohan Wang, Xiaodong Lu, Jiajun Chai, Guojun Yin, Wei Lin, Shuai Ma, Fuzhen Zhuang, Deqing Wang, Yaodong Yang, Jianxin Li, Yikun Ban

机构 * Beihang University(北航大学) University of California, Berkeley(加州大学伯克利分校) Peking University(北京大学) Meituan(美团)

AI总结 本文提出HA-DW方法,通过修正组相对优势估计的偏差,提升基于组的强化学习在数学推理任务中的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.00439 2026-01-23 cs.CL

UniAttn: Reducing Inference Costs via Softmax Unification for Post-Training LLMs

UniAttn: 通过Softmax统一降低推理成本以适应训练后的LLM

Yizhe Xiong, Wei Huang, Xin Ye, Hui Chen, Zijia Lin, Haoran Lian, Zhenpeng Su, Jungong Han, Guiguang Ding

机构 * School of Software, Tsinghua University(清华大学软件学院) School of Computer Science, Beijing University of Posts and Telecommunications(北京邮电大学计算机学院) Beihang University(北航) Department of Automation, Tsinghua University(清华大学自动化系)

AI总结 UniAttn通过统一Softmax操作降低训练后LLM的推理成本,同时保持性能。

Comments 8 pages, 6 figures. Preprint, under review

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.14731 2026-01-22 cs.SE cs.LG

ARFT-Transformer: Modeling Metric Dependencies for Cross-Project Aging-Related Bug Prediction

ARFT-Transformer:建模度量依赖性以进行跨项目老化相关缺陷预测

Shuning Ge, Fangyun Qin, Xiaohui Wan, Yang Liu, Qian Dai, Zheng Zheng

机构 * College of Information Engineering, Capital Normal University, Beijing, China(信息工程学院,首都师范大学,北京,中国) Suzhou Aerospace Information Research Institute, Suzhou, China(苏州航天信息研究所,苏州,中国) School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, China(机械电子控制工程学院,北京交通大学,北京,中国) Beijing Institute of Computer Technology and Applications, Beijing, China(北京计算机技术与应用研究所,北京,中国) School of Automation Science and Electrical Engineering, Beihang University, Beijing, China(自动化科学与电气工程学院,北航,北京,中国)

AI总结 ARFT-Transformer通过引入多头注意力机制和Focal Loss处理跨项目老化相关缺陷预测中的度量依赖性和类别不平衡问题,提升预测性能。

Comments Accepted by The Journal of Systems & Software (JSS), 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.14681 2026-01-22 cs.RO

FARE: Fast-Slow Agentic Robotic Exploration

FARE:快速-缓慢代理机器人探索

Shuhao Liao, Xuxin Lv, Jeric Lew, Shizhe Zhang, Jingsong Liang, Peizhuo Li, Yuhong Cao, Wenjun Wu, Guillaume Sartoretti

机构 * Beihang University, China(北航大学) Department of Mechanical Engineering, National University of Singapore(机械工程系,新加坡国立大学)

AI总结 FARE通过结合大型语言模型和强化学习策略,实现了高效且稳健的机器人探索,显著提升了探索效率并验证了其在大规模建筑环境中的有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.00971 2026-01-22 cs.SE cs.AI

Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code

超越功能正确性:探索LLM生成代码中的幻觉

Fang Liu, Yang Liu, Lin Shi, Zhen Yang, Li Zhang, Xiaoli Lian, Zhongqi Li, Yuchi Ma

机构 * 2 State Key Laboratory of Complex \& Critical Software Environment (SKLCCSE) School of Computer Science Engineering, Beihang University, Beijing, China 3 School of Software, Beihang University, Beijing, China 4 School of Computer Science Technology, Shandong University, Qingdao, China 5 Huawei Cloud Computing Technologies Co., Ltd, China

AI总结 本文探讨了LLM生成代码中的幻觉问题,通过分类和分析建立全面的幻觉分类体系,并提出轻量级的幻觉缓解方法。

Comments Accepted by Transactions on Software Engineering (TSE)

详情

展开后加载摘要…

URL PDF HTML 收藏
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
2601.11342 2026-01-19 cs.LG cs.CL

Unlocking the Potentials of Retrieval-Augmented Generation for Diffusion Language Models

解锁检索增强生成在扩散语言模型中的潜力

Chuanyue Yu, Jiahui Wang, Yuhan Li, Heng Chang, Ge Lan, Qingyun Sun, Jia Li, Jianxin Li, Ziwei Zhang

机构 * Nankai University(南开大学) Beihang University(北航) HKUST (Guangzhou)(香港科技大学(广州)) Huawei Technologies Co., Ltd.(华为技术有限公司)

AI总结 本文提出SPREAD框架,通过引入查询相关性引导的去噪策略,解决DLMs在RAG框架中生成精度低和语义漂移的问题。

Comments Preprints

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.11151 2026-01-19 cs.IR cs.AI

Cross-Modal Attention Network with Dual Graph Learning in Multimodal Recommendation

跨模态注意力网络与双图学习在多模态推荐中的应用

Ji Dai, Quan Fang, Jun Hu, Desheng Cai, Yang Yang, Can Zhao

机构 * Beijing University of Posts and Telecommunications(北京邮电大学) National University of Singapore(新加坡国立大学) Tianjin University of Technology(天津工业大学) Beihang University(北航) State Key Laboratory of CNS/ATM(国家空管重大科技专项实验室) Aviation Data Communication Corporation(航空数据通信公司)

AI总结 CRANE通过双图学习和递归注意力机制,解决多模态推荐中的浅层融合和不对称特征处理问题,提升推荐性能。

Comments Accepted to ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.08687 2026-01-19 cs.LG cs.AI

AC-PKAN: Attention-Enhanced and Chebyshev Polynomial-Based Physics-Informed Kolmogorov-Arnold Networks

AC-PKAN:基于注意力机制和切比雪夫多项式的物理信息柯莫戈罗夫-阿诺德网络

Hangwei Zhang, Zhimu Huang, Yan Wang

机构 * Institute for AI Industry Research, Tsinghua University(清华人工智能产业研究院) Beihang University(北航) Beijing Institute of Technology(北京理工大学)

AI总结 AC-PKAN通过结合注意力机制和切比雪夫多项式,提升物理信息神经网络在求解偏微分方程中的性能与稳定性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.13347 2026-01-19 cs.CV

TriDF: Triplane-Accelerated Density Fields for Few-Shot Remote Sensing Novel View Synthesis

TriDF: 三平面加速密度场用于少样本遥感新视角合成

Jiaming Kang, Keyan Chen, Zhengxia Zou, Zhenwei Shi

机构 * Beihang University(北航大学)

AI总结 TriDF通过高效混合3D表示,实现少样本遥感新视角合成,提升速度与渲染质量

Comments Corrected metadata formatting

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.10589 2026-01-16 cs.CR cs.CL

Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay

做自己的红队:通过自play和反思经验回放实现安全对齐

Hao Wang, Yanting Wang, Hao Li, Rui Li, Lei Sha

机构 * Beihang University(北京航空航天大学) Peking University(北京大学) Zhongguancun Laboratory(中关村实验室)

AI总结 通过自play和反思经验回放机制,使模型自主进化防御能力,提升安全对齐效果。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.10015 2026-01-16 cs.LG

CAFEDistill: Learning Personalized and Dynamic Models through Federated Early-Exit Network Distillation

CAFEDistill: 通过联邦早退网络蒸馏学习个性化和动态模型

Boyi Liu, Zimu Zhou, Yongxin Tong

机构 * DS, City University of Hong Kong(DS,香港城市大学) SKLCCSE, Beihang University(SKLCCSE,北京航空航天大学)

AI总结 CAFEDistill通过冲突感知的联邦退出蒸馏框架,解决PFL中客户端异质性和深度干扰问题,提升模型准确性和降低推理成本。

Comments 12 pages, conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.21357 2026-01-16 cs.CV cs.LG

AgriFM: A Multi-source Temporal Remote Sensing Foundation Model for Agriculture Mapping

AgriFM:一种多源时序遥感基础模型用于农业制图

Wenyuan Li, Shunlin Liang, Keyan Chen, Yongzhe Chen, Han Ma, Jianglei Xu, Yichuan Ma, Shikang Guan, Husheng Fang, Zhenwei Shi

机构 * Jockey Club STEM Lab of Quantitative Remote Sensing, Department of Geography, The University of Hong Kong, Hong Kong, China(香港大学地理系金钟STEM实验室) Department of Aerospace Intelligent Science and Technology, School of Astronautics, Beihang University, Beijing, China(北航航天智能科学与技术学院) School of Remote Sensing and Information Engineering, Wuhan University, China(武汉大学遥感与信息工程学院)

AI总结 AgriFM是一种多源时序遥感基础模型,通过改进的Video Swin Transformer架构实现多尺度时空特征提取,提升农业制图的准确性和效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.09665 2026-01-15 cs.CV

SCE-SLAM: Scale-Consistent Monocular SLAM via Scene Coordinate Embeddings

SCE-SLAM:通过场景坐标嵌入实现尺度一致的单目SLAM

Yuchen Wu, Jiahe Li, Xiaohan Yu, Lina Yu, Jin Zheng, Xiao Bai

机构 * School of Computer Science and Engineering, State Key Laboratory of Complex & Critical Software Environment, Jiangxi Research Institute, Beihang University(计算机科学与工程学院、复杂与关键软件环境国家重点实验室、江西研究院、北航) Macquarie University(麦考瑞大学) Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology(北京半导体神经网络智能感知与计算技术重点实验室)

AI总结 SCE-SLAM通过场景坐标嵌入实现单目SLAM的尺度一致性,实验显示在KITTI上轨迹误差减少8.36米,同时保持36 FPS。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.09613 2026-01-15 cs.CV cs.AI

CogRail: Benchmarking VLMs in Cognitive Intrusion Perception for Intelligent Railway Transportation Systems

CogRail: 对智能铁路运输系统中认知入侵感知的视觉语言模型进行基准测试

Yonglin Tian, Qiyao Zhang, Wei Xu, Yutong Wang, Yihao Wu, Xinyi Li, Xingyuan Dai, Hui Zhang, Zhiyong Cui, Baoqing Guo, Zujun Yu, Yisheng Lv

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences(多模态人工智能系统国家重点实验室,自动化研究所,中国科学院) School of Automation, Beijing Institute of Technology(自动化学院,北京理工大学) Signal & Communication Research Institute, China Academy of Railway Sciences(信号与通信研究所,中国铁路科学研究院) Beijing Huairou Academy of Parallel Sensing(北京怀柔平行感知院) School of Computer Science and Technology, Beijing Jiaotong University(计算机科学与技术学院,北京交通大学) State Key Lab of Intelligent Transportation Systems, School of Transportation Science and Engineering, Beihang University(智能交通系统国家重点实验室,交通科学与工程学院,北京航空航天大学)

AI总结 CogRail提出一个用于评估视觉语言模型在认知入侵感知任务中性能的基准,通过联合微调框架提升模型在时空推理和威胁分析中的表现。

详情

展开后加载摘要…

URL PDF HTML 收藏