arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Fudan University(复旦大学)

2026-04-23 至 2026-04-23 共收录 8
2604.20393 2026-04-23 cs.CV

MLG-Stereo: ViT Based Stereo Matching with Multi-Stage Local-Global Enhancement

MLG-Stereo: 基于ViT的立体匹配方法与多阶段局部-全局增强

Haoyu Zhang, Jingyi Zhou, Peng Ye, Jiakang Yuan, Lin Zhang, Feng Xu, Tao Chen

机构 * Embedded Deep Learning and Visual Analysis Laboratory, College of Future Information Technology, Fudan University(嵌入式深度学习与视觉分析实验室,未来信息技术学院,复旦大学) Key Laboratory for Information Science of Electromagnetic Waves, Ministry of Education, Fudan University(电磁波信息科学重点实验室,教育部,复旦大学)

AI总结 本文提出MLG-Stereo,通过多粒度特征网络、局部-全局成本体积和局部-全局引导递归单元,提升ViT在处理任意分辨率图像时的细节预测能力,实验表明其在Middlebury和KITTI-2015等基准上表现优异。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.20225 2026-04-23 cs.CL

The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models

高 Yao 基准:评估大型语言模型多语言和多文化能力的综合框架

Yilun Liu, Chunguang Zhao, Mengyao Piao, Lingqi Miao, Shimin Tao, Minggui He, Chenxin Liu, Li Zhang, Hongxia Ma, Jiaxin Guo, Chen Liu, Liqun Deng, Jiansheng Wei, Xiaojun Meng, Fanyi Du, Daimeng Wei, Yanghua Xiao

机构 * Huawei, China(华为,中国) Fudan University, China(复旦大学,中国)

AI总结 本文提出GaoYao基准,通过182300个样本、26种语言和51个地区,评估大型语言模型的多语言和多文化能力,揭示地理性能差异和任务间差距。

Comments Accepted by ACL 2026 main

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.19502 2026-04-23 cs.CL

Beyond Rating: A Comprehensive Evaluation and Benchmark for AI Reviews

超越评分:AI评论的全面评估与基准

Bowen Li, Haochen Ma, Yuxin Wang, Jie Yang, Yining Zheng, Xinchi Chen, Xuanjing Huang, Xipeng Qiu

机构 * College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China(复旦大学计算机科学与人工智能学院) Shanghai Innovation Institute, Shanghai, China(上海创新研究院)

AI总结 本文提出Beyond Rating框架,通过五个维度评估AI评论,引入Max-Recall策略和高质量数据集,证明文本中心指标与评分准确性的强相关性。

Comments 38 pages,8 figures,4 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.16914 2026-04-23 cs.CV eess.IV

Unified Ultrasound Intelligence Toward an End-to-End Agentic System

统一超声智能:面向端到端代理系统

Chen Ma, Yunshu Li, Junhu Fu, Shuyu Liang, Yuanyuan Wang, Yi Guo

机构 * College of Biomedical Engineering, Fudan University, Shanghai, China(复旦大学生物医学工程学院,上海,中国)

AI总结 本文提出USTri框架,通过三阶段方法实现多器官多任务统一分析,提升跨设备和协议的泛化能力,生成可解释的临床报告。

Comments Accepted by ISBI2026. 5 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.12456 2026-04-23 eess.AS cs.AI

X-VC: Zero-shot Streaming Voice Conversion in Codec Space

X-VC:在编码空间中实现零样本语音转换

Qixi Zheng, Yuxiang Zhao, Tianrui Wang, Wenxi Chen, Kele Xu, Yikang Li, Qinyuan Chen, Xipeng Qiu, Kai Yu, Xie Chen

机构 * Shanghai Jiao Tong University Shanghai China Tianjin University Tianjin China Shanghai Jiao Tong University, Shanghai Innovation Institute Shanghai China State Key Laboratory of Complex \& Critical Software Environment Changsha China Shanghai Innovation Institute Shanghai China Fudan University, Shanghai Innovation Institute Shanghai China Shanghai Jiao Tong University Tianjin University Shanghai Jiao Tong University, Shanghai Innovation Institute State Key Laboratory of Complex \& Critical Software Environment Shanghai Innovation Institute Fudan University, Shanghai Innovation Institute

AI总结 X-VC提出一种在编码空间中进行零样本语音转换的系统,通过双条件声学转换器和自适应归一化技术,在保持语言内容的同时实现高质量低延迟的语音转换。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.20806 2026-04-23 cs.CV cs.AI cs.CL

OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model

OMIBench:用于大型视觉-语言模型在奥林匹克级多图像推理中的基准测试

Qiguang Chen, Chengyu Luan, Jiajun Wu, Qiming Yu, Yi Yang, Yizhuo Li, Jingqi Tong, Xiachong Feng, Libo Qin, Wanxiang Che

机构 * Research Center for Social Computing and Interactive Robotics(社会计算与交互机器人研究室) Harbin Institute of Technology(哈尔滨工业大学) Central South University(中南大学) Fudan University(复旦大学) The University of Hong Kong(香港大学) Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳)) Text Computing and Cognitive Intelligence Ministry of Education Engineering Research Center(教育部文本计算与认知智能工程研究中心) Guizhou University(贵州大学)

AI总结 OMIBench旨在评估多图像推理能力,包含生物、化学、数学和物理奥林匹克问题,提供精确和语义答案匹配的评估协议,实验显示现有模型性能存在显著差距。

Comments ACL 2026 Camera Ready

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.20721 2026-04-23 cs.RO

ALAS: Adaptive Long-Horizon Action Synthesis via Async-pathway Stream Disentanglement

ALAS: 通过异步路径流解构实现自适应长时域动作合成

Yutong Shen, Hangxu Liu, Lei Zhang, Penghui Liu, Yinqi Liu, Liuxiang Yang, Tongtong Feng

机构 * Beijing University of Technology(北京理工大学) Fudan University(复旦大学) University of Hamburg(汉堡大学) Hubei University of Chinese Medicine(湖北中医药大学) Tsinghua University(清华大学)

AI总结 本文提出ALAS框架,通过生物启发的双流解构方法,解决长时域任务中环境与技能耦合问题,提升跨域任务执行效率与成功率。

Comments 10 pages, 7 figures. arXiv admin note: substantial text overlap with arXiv:2508.07842

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.01621 2026-04-23 cs.LG q-bio.QM stat.ME stat.ML

Deciphering interventional dynamical causality from non-intervention complex systems

从非干预复杂系统中解码干预性动力学因果性

Jifan Shi, Yang Li, Juan Zhao, Siyang Leng, Rui Bao, Kazuyuki Aihara, Luonan Chen, Wei Lin

机构 * Research Institute of Intelligent Complex Systems & CISOR, Fudan University(智能复杂系统研究所及CISOR,复旦大学) International Research Center for Neurointelligence, The University of Tokyo Institutes for Advanced Study, The University of Tokyo(神经智能国际研究中心,东京大学先进研究所,东京大学) School of Pharmacy, Shanghai University of Traditional Chinese Medicine(上海中医药大学药学院) Institute of AI and Robotics, College of Intelligent Robotics and Advanced Manufacturing, Fudan University(人工智能与机器人研究所,智能机器人与先进制造学院,复旦大学) Frontiers Science Center for Deep Ocean Multispheres and Earth System, Key Laboratory of Marine Chemistry Theory and Technology, Ministry of Education, Ocean University of China(深海多球体与地球系统前沿科学中心,海洋化学理论与技术重点实验室,教育部,中国海洋大学) School of Mathematical Sciences and School of AI, Shanghai Jiao Tong University(数学科学学院和人工智能学院,上海交通大学) Key Laboratory of Systems Health Science of Zhejiang Province, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Chinese Academy of Sciences(浙江省系统健康科学重点实验室,杭州高级研究所,中国科学院大学,中国科学院)

AI总结 本文提出IntDC框架和IEE算法,通过延迟嵌入空间在不需干预或动力学模型的情况下,从观测数据中解码因果性,验证了其在因果分析中的有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏