arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Huazhong University of Science and Technology(华中科技大学)

共收录 702
2603.28130 2026-03-31 cs.CV cs.AI

MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios

MDPBench:多语言文档解析的实际场景基准

Zhang Li, Zhibo Lin, Qiang Liu, Ziyang Zhang, Shuo Zhang, Zidun Guo, Jiajun Song, Jiarui Zhang, Xiang Bai, Yuliang Liu

机构 * Huazhong University of Science and Technology(华中科技大学) Kingsoft Office(金山办公)

AI总结 本文提出MDPBench,首个多语言数字和照片文档解析基准,包含17种语言的3400张文档图像,揭示闭源模型在非拉丁文和真实场景下的性能优势,开放源代码以促进更包容的解析系统发展。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.27993 2026-03-31 cs.CV

Progressive Prompt-Guided Cross-Modal Reasoning for Referring Image Segmentation

逐步引导的跨模态推理用于指代图像分割

Jiachen Li, Hongyun Wang, Jinyu Xu, Wenbo Jiang, Yanchun Ma, Yongjian Liu, Qing Xie, Bolong Zheng

机构 * School of Computer Science and Artificial Intelligence, Wuhan University of Technology(武汉理工大学计算机科学与人工智能学院) School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(华中科技大学人工智能与自动化学院) University of Electronic Science and Technology of China(电子科技大学) Wuhan Vocational College of Software and Engineering(武汉软件工程职业学院)

AI总结 本文提出PPCR框架,通过语义理解-空间定位-实例分割流程,改进指代图像分割中语言描述与视觉表示的连接,提升分割精度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.27969 2026-03-31 cs.CV

Hg-I2P: Bridging Modalities for Generalizable Image-to-Point-Cloud Registration via Heterogeneous Graphs

Hg-I2P:通过异构图实现通用的图像到点云配准

Pei An, Junfeng Ding, Jiaqi Yang, Yulong Wang, Jie Ma, Liangliang Nan

机构 * Huazhong University of Science and Technology(华中科技大学) Northwestern Polytechnical University(西北工业大学) Huazhong Agricultural University(华中农业大学) Delft University of Technology(代尔夫特理工大学)

AI总结 本文提出Hg-I2P方法,通过异构图融合多模态特征,提升图像与点云配准的泛化能力和精度。

Comments Accepted to CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.14255 2026-03-31 cs.CV

Identity-Preserving Image-to-Video Generation via Reward-Guided Optimization

通过奖励引导优化实现身份保持的图像到视频生成

Liao Shen, Wentao Jiang, Yiran Zhu, Jiahe Li, Tiezheng Ge, Zhiguo Cao, Bo Zheng

机构 * Huazhong University of Science and Technology(华中科技大学) Taobao & Tmall Group of Alibaba(阿里巴巴淘宝天猫集团) Alibaba Group(阿里巴巴集团)

AI总结 本文提出IPRO框架,通过强化学习优化扩散模型,提升身份一致性。引入面部评分机制和KL散度正则化,改进性能并加速收敛。

Comments accepted by CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.27734 2026-03-31 cs.LG cs.AI

Robust Smart Contract Vulnerability Detection via Contrastive Learning-Enhanced Granular-ball Training

通过对比学习增强的细粒度球训练实现鲁棒的智能合约漏洞检测

Zeli Wang, Qingxuan Yang, Shuyin Xia, Yueming Wu, Bo Liu, Longlong Lin

机构 * Chongqing Key Laboratory of Computational Intelligence(重庆计算智能重点实验室) Key Laboratory of Cyberspace Big Data Intelligent Security, Ministry of Education(教育部网络空间大数据智能安全重点实验室) Key Laboratory of Big Data Intelligent Computing(大数据智能计算重点实验室) Chongqing University of Posts and Telecommunications(重庆邮电大学) School of Cyber Science and Engineering, Huazhong University of Science and Technology(华中科技大学网络空间安全学院) School of Computer Science and Artificial Intelligence, Zhengzhou University(郑州大学计算机与人工智能学院) College of Computer and Information Science, Southwest University(西南大学计算机与信息科学学院)

AI总结 本文提出CGBC方法,通过细粒度球训练和对比学习增强智能合约漏洞检测的鲁棒性,解决标签噪声问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.27169 2026-03-31 cs.AI

Aligning LLMs with Graph Neural Solvers for Combinatorial Optimization

对齐大语言模型与图神经求解器以解决组合优化问题

Shaodi Feng, Zhuoyi Lin, Yaoxin Wu, Haiyan Yin, Yan Jin, Senthilnath Jayavelu, Xun Xu

机构 * National Yang Ming Chiao Tung University(国立阳明交通大学) Eindhoven University of Technology(埃因霍温理工大学) Centre for Frontier AI Research, A*STAR(前沿人工智能研究中心,新加坡科技研究局) Huazhong University of Science and Technology(华中科技大学) National University of Singapore(新加坡国立大学)

AI总结 本文提出AlignOPT方法,通过结合大语言模型与图神经求解器,提升组合优化问题的求解能力,实现语义与结构表示的对齐,实验显示其在多种优化问题中表现优异。

Comments 18 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.27159 2026-03-31 cs.LG cs.SY eess.SY math.OC

Online Learning of Kalman Filtering: From Output to State Estimation

在线学习卡尔曼滤波:从输出到状态估计

Lintao Ye, Ankang Zhang, Ming Chi, Bin Du, Jianghai Hu

机构 * School of Artificial Intelligence and Automation at the Huazhong University of Science and Technology(华中科技大学人工智能与自动化学院) College of Automation Engineering at Nanjing University of Aeronautics and Astronautics(南京航空航天大学自动化工程学院) Elmore Family School of Electrical and Computer Engineering at Purdue University(普渡大学埃尔莫尔家族电气与计算机工程学院)

AI总结 本文研究了在部分观测线性动态系统中学习未知系统模型的卡尔曼滤波问题,提出了一种基于在线优化的统一算法框架,解决输出估计和状态估计场景。通过分析估计误差成本函数的性质,证明算法在输出估计场景中达到logT regret,同时解决更挑战性的状态估计问题,揭示了算法在有限观测下的权衡。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.27138 2026-03-31 cs.LG

ScoutAttention: Efficient KV Cache Offloading via Layer-Ahead CPU Pre-computation for LLM Inference

ScoutAttention:通过层前CPU预计算实现高效的KV缓存卸载以用于LLM推理

Qiuyang Zhang, Kai Zhou, Ding Tang, Kai Lu, Cheng Li, Zhenyu Yang, Peng Xu, Jiguang Wan

机构 * Huazhong University of Science and Technology(华中科技大学) Huawei Technologies(华为技术有限公司)

AI总结 本文提出ScoutAttention框架,通过GPU-CPU协作计算加速LLM推理,采用层前CPU预计算和异步召回机制,减少CPU负载,实验表明在保持2.4%准确率的同时,比现有方法快2.1倍。

Comments Accepted at the 63rd Design Automation Conference (DAC 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.25716 2026-03-31 cs.CV cs.AI

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

视线之外但未被遗忘:动态视频世界模型的混合记忆

Kaijin Chen, Dingkang Liang, Xin Zhou, Yikang Ding, Xiaoqiang Liu, Pengfei Wan, Xiang Bai

机构 * Huazhong University of Science and Technology(华中科技大学) Kling Team, Kuaishou Technology(快手科技Kling团队)

AI总结 本文提出混合记忆机制,解决动态主体消失后重现时的连续性问题,通过HM-World数据集和HyDRA架构提升视频世界模型的动态一致性与生成质量。

Comments Project Page: https://kj-chen666.github.io/Hybrid-Memory-in-Video-World-Models/ Code: https://github.com/H-EmbodVis/HyDRA

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.26781 2026-03-31 cs.CR cs.LG

Efficient Encrypted Computation in Convolutional Spiking Neural Networks with TFHE

在卷积脉冲神经网络中实现高效的加密计算:TFHE

Longfei Guo, Pengbo Li, Ting Gao, Yonghai Zhong, Haojie Fan, Jinqiao Duan

机构 * School of Cyber Science and Engineering, Huazhong University of Science and Technology(华中科技大学网络空间安全学院) School of Mathematics and Statistics, Huazhong University of Science and Technology(华中科技大学数学与统计学院) Center for Mathematical Science, Huazhong University of Science and Technology(华中科技大学数学中心) Steklov-Wuhan Institute for Mathematical Exploration, Huazhong University of Science and Technology(华中科技大学斯捷克洛夫-武汉数学探索研究所) Department of Mathematics and Department of Physics, Great Bay University(大湾区大学数学与物理学院) Guangdong Provincial Key Laboratory of Mathematical and Neural Dynamical Systems(广东省数学与神经动力系统重点实验室)

AI总结 本文提出FHE-DiCSNN框架,利用脉冲神经网络的离散特性实现安全高效的加密计算,结合卷积方法提升准确率并减少模拟时间,实验验证其在MNIST和FashionMNIST上的有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.26328 2026-03-30 cs.CV

Verify Claimed Text-to-Image Models via Boundary-Aware Prompt Optimization

通过边界感知提示优化验证声称的文本到图像模型

Zidong Zhao, Yihao Huang, Qing Guo, Tianlin Li, Anran Li, Kailong Wang, Jin Song Dong, Geguang Pu

机构 * Zhejiang University(浙江大学) East China Normal University(华东师范大学) Nankai University(南开大学) Beihang University(北京航空航天大学) University of Science and Technology of China(中国科学技术大学) Huazhong University of Science and Technology(华中科技大学) National University of Singapore(新加坡国立大学)

AI总结 本文提出边界感知提示优化方法,通过识别模型特定的边界相邻提示来验证文本到图像模型的真实性,实验显示其验证准确率优越。

Comments Accepted to CVPR 2026 (Findings)

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.18940 2026-03-30 cs.CL cs.LG

Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought

熵轨迹形状预测LLM推理可靠性:对不确定性动态的诊断研究

Xinghao Zhao

机构 * Huazhong University of Science and Technology(华中科技大学)

AI总结 研究通过分析推理过程中熵轨迹形状来预测大语言模型的推理可靠性,提出了一种基于轨迹形状而非标量大小的诊断方法,展示了其在黑盒环境中的实用性与鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.24636 2026-03-27 cs.LG cs.AI

DyMRL: Dynamic Multispace Representation Learning for Multimodal Event Forecasting in Knowledge Graph

DyMRL: 动态多空间表征学习用于知识图谱中的多模态事件预测

Feng Zhao, Kangzheng Liu, Teng Peng, Yu Yang, Guandong Xu

机构 * Huazhong University of Science and Technology(华中科技大学) Centre for Learning, Teaching and Technology(学习、教学与技术中心) The Education University of Hong Kong(香港教育大学)

AI总结 DyMRL通过动态多空间表征学习,解决多模态知识动态获取与融合问题,提升事件预测性能。

Comments Accepted to The ACM Web Conference 2026 (WWW '26). This version is published under a CC BY license

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.24322 2026-03-26 cs.CV

Heuristic Self-Paced Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions

启发式自适应学习用于恶劣条件下域自适应语义分割

Shiqin Wang, Haoyang Chen, Huaizhou Huang, Yinkan He, Dongfang Sun, Xiaoqing Chen, Xingyu Liu, Zheng Wang, Kaiyan Zhao

机构 * National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, School of Computer Science, Wuhan University(国家多媒体软件工程研究中心、人工智能研究院、计算机科学学院、武汉大学) Hubei Key Laboratory of Multimedia and Network Communication Engineering(湖北省多媒体与网络通信工程重点实验室) Zhongguancun Academy, Beijing, China(中关村学院,北京,中国) School of Computer Science, Wuhan University, Wuhan, China(武汉大学计算机科学学院,武汉,中国) School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(华中科技大学人工智能与自动化学院)

AI总结 本文提出自适应学习方法,通过动态调整语义类别学习顺序,提升恶劣天气下域自适应语义分割性能,实现类别平衡与动态学习。

Comments Accepted by CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2304.01184 2026-03-26 cs.CV

WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation

WeakTr: 探索纯视觉变换器用于弱监督语义分割

Lianghui Zhu, Yingyue Li, Jiemin Fang, Yan Liu, Hao Xin, Wenyu Liu, Xinggang Wang

机构 * School of Electronic Information and Communications, Huazhong University of Science and Technology(华中科技大学电子信息与通讯学院) Alipay Tian Qian Security Lab(支付宝天泉安全实验室)

AI总结 本文提出WeakTr方法,利用纯视觉变换器的多层多头自注意力图进行弱监督语义分割和CAM生成,通过自适应融合提升CAM质量,并提出基于ViT的梯度裁剪解码器实现高效重训练。

Comments Accepted by IEEE Transactions on Image Processing, TIP. Source code and checkpoints are available at https://github.com/hustvl/WeakTr

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.22874 2026-03-25 cs.CV

Template-Based Feature Aggregation Network for Industrial Anomaly Detection

基于模板的特征聚合网络用于工业异常检测

Wei Luo, Haiming Yao, Wenyong Yu

机构 * State Key Laboratory of Precision Measurement Technology and Instruments(精密测量技术与仪器国家重点实验室) Tsinghua University(清华大学) State Key Laboratory of Digital Manufacturing Equipment and Technology(数字制造装备与技术国家重点实验室) Huazhong University of Science and Technology(华中科技大学)

AI总结 本文提出TFA-Net,通过模板特征聚合过滤异常特征,提升工业异常检测性能,实现高效率和实时性。

Comments Accepted by Engineering Applications of Artificial Intelligence

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.22840 2026-03-25 cs.CV cs.AI

URA-Net: Uncertainty-Integrated Anomaly Perception and Restoration Attention Network for Unsupervised Anomaly Detection

URA-Net:一种集成不确定性异常感知与恢复注意力网络用于无监督异常检测

Wei Luo, Peng Xing, Yunkang Cao, Haiming Yao, Weiming Shen, Zechao Li

机构 * State Key Laboratory of Precision Measurement Technology and Instruments, Department of Precision Instrument, Tsinghua University(精密测量技术与仪器国家重点实验室,清华大学精密仪器系) State Key Laboratory of Intelligent Manufacturing Equipment and Technology, Huazhong University of Science and Technology(智能制造装备与技术国家重点实验室,华中科技大学) School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院)

AI总结 URA-Net通过引入不确定性集成的异常感知模块和恢复注意力机制,有效解决传统方法在异常检测中的过泛化问题,提升检测性能。

Comments Accepted by IEEE TCSVT

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.11336 2026-03-25 cs.CV

UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models

UFVideo:迈向统一的细粒度视频协作理解的大型语言模型

Hewen Pan, Cong Wei, Dashuang Liang, Zepeng Huang, Pengfei Gao, Ziqi Zhou, Lulu Xue, Pengfei Yan, Xiaoming Wei, Minghui Li, Shengshan Hu

机构 * Huazhong University of Science and Technology(华中科技大学) Meituan(美团)

AI总结 UFVideo通过统一多粒度协作理解能力,实现视频理解的全面覆盖,展示了其在多粒度视频任务中的灵活性和优势。

Comments CVPR 2026 Camera Ready, Github Code: https://github.com/Heven-Pan/UFVideo

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.22271 2026-03-24 cs.CV

DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution

DUO-VSR:双流蒸馏用于一步视频超分辨率

Zhengyao Lv, Menghan Xia, Xintao Wang, Kwan-Yee K. Wong

机构 * The University of Hong Kong(香港大学) Huazhong University of Science and Technology(华中科技大学) Kling Team, Kuaishou Technology(快手科技 Kling 团队)

AI总结 DUO-VSR提出双流蒸馏策略,通过轨迹保留蒸馏、双流优化和偏好引导细化,解决视频超分辨率中训练不稳定和监督不足的问题,提升视觉质量和效率。

Comments Accepted to CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.21547 2026-03-24 cs.CV

PROBE: Diagnosing Residual Concept Capacity in Erased Text-to-Video Diffusion Models

PROBE: 诊断 erased 文本到视频扩散模型中的残余概念容量

Yiwei Xie, Zheng Zhang, Ping Liu

机构 * School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(华中科技大学人工智能与自动化学院) Department of Computer Science and Engineering, University of Nevada(内华达大学计算机科学与工程系)

AI总结 PROBE 通过多级评估框架揭示文本到视频扩散模型中被擦除概念的残余容量,发现所有测试方法留有可测量的残余能力,且其鲁棒性与干预深度相关,指出当前擦除方法仅实现输出级抑制而非表征移除。

Comments This preprint was posted after submission to IEEE Transactions

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.21295 2026-03-24 cs.CV

Text-Image Conditioned 3D Generation

文本-图像条件的3D生成

Jiazhong Cen, Jiemin Fang, Sikuang Li, Guanjun Wu, Chen Yang, Taoran Yi, Zanwei Zhou, Zhikuan Bao, Lingxi Xie, Wei Shen, Qi Tian

机构 * MoE Key Lab of Artificial Intelligence, AI Institute, School of Computer Science, Shanghai Jiao Tong University(人工智能大模型重点实验室、人工智能学院、计算机科学学院、上海交通大学) Huawei Inc.(华为公司) Huazhong University of Science and Technology(华中科技大学)

AI总结 本文提出结合文本和图像条件的3D生成方法,通过跨模态互补性提升生成质量,引入TIGON模型实现高效融合。

Comments CVPR 2026. Project page: https://jumpat.github.io/tigon-page Code: https://github.com/Jumpat/tigon

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.21229 2026-03-24 cs.CV

Plant Taxonomy Meets Plant Counting: A Fine-Grained, Taxonomic Dataset for Counting Hundreds of Plant Species

植物分类与植物计数:一个细粒度、分类学数据集,用于计数数百种植物物种

Jinyu Xu, Tianqi Hu, Xiaonan Hu, Letian Zhou, Songliang Cao, Meng Zhang, Hao Lu

机构 * Huazhong University of Science and Technology(华中科技大学)

AI总结 本文提出TPC-268数据集,用于细粒度、分类学-aware的植物计数,包含10,000张图像和678,050个点注释,涵盖268种可计数的植物类别,推动了细粒度类无关计数的发展。

Comments Accepted by CVPR 2026. Project page: https://github.com/tiny-smart/TPC-268

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.21134 2026-03-24 cs.RO cs.CV

Anatomical Prior-Driven Framework for Autonomous Robotic Cardiac Ultrasound Standard View Acquisition

基于解剖先验的自主机器人心脏超声标准视图采集框架

Zhiyan Cao, Zhengxi Wu, Yiwei Wang, Pei-Hsuan Lin, Li Zhang, Zhen Xie, Huan Zhao, Han Ding

机构 * State Key Laboratory of Intelligent Manufacturing Equipment and Technology, Huazhong University of Science and Technology(华中科技大学智能制造装备与技术国家重点实验室) School of Biomedical Engineering, Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳)生物医学工程学院) Information Intelligence Lab, Department of Electrical Engineering, National Chung Hsing University(中原大学电子工程系信息智能实验室) Institute of Medical Equipment Science and Engineering, Huazhong University of Science and Technology(华中科技大学医学装备科学与工程研究院) Department of Ultrasound Medicine, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology(华中科技大学同济医学院附属同济医院超声医学科) Institute of Systems Science (ISS), National University of Singapore (NUS)(新加坡国立大学系统科学研究所)

AI总结 本文提出结合心脏结构分割与自主探头调整的框架,通过解剖先验引导提升超声标准视图采集的自动化水平,实验表明其在分割精度和探头调整成功率上均有显著提升。

Comments Accepted for publication at the IEEE ICRA 2026. 8 pages, 5 figures, 3 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.20708 2026-03-24 cs.CV

High-Quality and Efficient Turbulence Mitigation with Events

高质高效湍流抑制方法

Xiaoran Zhang, Jian Ding, Yuxing Duan, Haoyue Liu, Gang Chen, Yi Chang, Luxin Yan

机构 * State Key Laboratory of Multispectral Information Intelligent Processing Technology(多谱信息智能处理技术国家重点实验室) School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(华中科技大学人工智能与自动化学院) School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院)

AI总结 本文提出EHETM方法,利用事件相机的特性,通过事件极性变化和事件管约束实现高效湍流抑制,提升恢复质量并减少数据开销和系统延迟。

Comments Accepted by CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.17655 2026-03-24 cs.CV cs.AI

Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment

可解释的跨领域少样本学习与修正的目标域局部对齐

Yaze Zhao, Yixiong Zou, Yuhua Li, Ruixuan Li

机构 * School of Computer Science and Technology, Huazhong University of Science and Technology(华中科技大学计算机科学与技术学院)

AI总结 本文提出CC-CDFSL方法,通过循环一致性解决CLIP-based CDFSL中的局部对齐问题,提升局部视觉语言对齐和可解释性,实现SOTA性能。

Comments Accepted to CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.23306 2026-03-24 cs.CV

ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding

ThinkOmni: 通过指导解码将文本推理提升到多模态场景

Yiran Guan, Sifan Tu, Dingkang Liang, Linghao Zhu, Jianzhong Ju, Zhenbo Luo, Jian Luan, Yuliang Liu, Xiang Bai

机构 * Huazhong University of Science and Technology(华中科技大学) MiLM Plus, Xiaomi Inc.(小米公司)

AI总结 ThinkOmni提出一种无需训练和数据的框架,通过指导解码将文本推理扩展到多模态场景,实验显示在多个多模态推理基准上取得显著提升。

Comments Accept by ICLR 2026, Code: https://github.com/1ranGuan/thinkomni

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.00596 2026-03-24 cs.IT cs.CR cs.DC cs.LG math.IT

Information-Theoretic Decentralized Secure Aggregation with Passive Collusion Resilience

信息论视角下的去中心化安全聚合与被动合谋鲁棒性

Xiang Zhang, Zhou Li, Shuangyang Li, Kai Wan, Derrick Wing Kwan Ng, Giuseppe Caire

机构 * Department of Electrical Engineering and Computer Science, Technical University of Berlin(技术大学柏林电气工程与计算机科学系) Guangxi Key Laboratory of Multimedia Communications and Network Technology, Guangxi University(广西多媒体通信与网络技术重点实验室,广西大学) School of Electronic Information and Communications, Huazhong University of Science and Technology(华中科技大学电子信息与通信学院) School of Electrical Engineering and Telecommunications, University of New South Wales(新南威尔士大学电子工程与电信学院)

AI总结 研究去中心化安全聚合的理论极限,提出在合谋情况下保证输入总和安全计算的通信与密钥使用最优界限。

Comments Accepted by IEEE JSAC

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.11289 2026-03-24 cs.CV cs.MM

UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer

UniAnimate-DiT:基于大规模视频扩散变换器的人像图像动画

Xiang Wang, Shiwei Zhang, Longxiang Tang, Yingya Zhang, Changxin Gao, Yuehuan Wang, Nong Sang

机构 * Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(华中科技大学图像处理与智能控制重点实验室,人工智能与自动化学院) Alibaba Group(阿里巴巴集团) Tsinghua University(清华大学)

AI总结 本文提出UniAnimate-DiT,利用Wan2.1模型实现一致的人像动画,通过LoRA技术优化参数,设计轻量姿态编码器并整合参考外观,实验表明其能生成高质量且时间一致的动画,支持从480p到720P的超分辨率。

Comments The training and inference code (based on Wan2.1) is available at https://github.com/ali-vilab/UniAnimate-DiT

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.20005 2026-03-23 cs.CV

NEC-Diff: Noise-Robust Event-RAW Complementary Diffusion for Seeing Motion in Extreme Darkness

NEC-Diff: 用于极端黑暗中感知运动的噪声鲁棒事件-RAW互补扩散

Haoyue Liu, Jinghan Xu, Luxin Feng, Hanyu Zhou, Haozhi Zhao, Yi Chang, Luxin Yan

机构 * National Key Lab of Multispectral Information Intelligent Processing Technology(多谱信息智能处理技术国家级重点实验室) School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(华中科技大学人工智能与自动化学院) School of Computing, National University of Singapore(新加坡国立大学计算机学院)

AI总结 NEC-Diff通过结合RAW图像的线性光响应和事件的亮度变化特性,提出一种新型扩散框架,以在极低光照条件下实现高保真视觉重建。

Comments Accepted by CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.19762 2026-03-23 cs.CV

PCSTracker: Long-Term Scene Flow Estimation for Point Cloud Sequences

PCSTracker: 点云序列的长期场景流估计

Min Lin, Gangwei Xu, Xianqi Wang, Yuyi Peng, Xin Yang

机构 * Huazhong University of Science and Technology(华中科技大学) Optics Valley Laboratory(光谷实验室)

AI总结 本文提出PCSTracker,通过引入IGMO和STTU模块,解决点云序列中长期场景流估计的时序一致性问题,实现实时32.5 FPS性能,优于RGB-D方法。

Comments Accepted in CVPR 2026 (Findings)

详情

展开后加载摘要…

URL PDF HTML 收藏