arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Northeastern University(东北大学)

2026-06-04 至 2026-06-04 共收录 6
2606.05161 2026-06-04 cs.SD cs.CL

Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models

超越文本跟随:音频-语言模型中的可修复仲裁反转

Yichen Gao, Yiqun Zhang, Zijing Wang, Yujia Li, Heng Guo, Xi Wu, Xiaocui Yang, Shi Feng, Yifei Zhang, Daling Wang

机构 * Northeastern University, China(东北大学) Shanghai Artificial Intelligence Laboratory, China(上海人工智能实验室)

AI总结 本文通过同音频反事实实验发现,音频-语言模型在冲突任务中常因文本主导而忽略音频证据,并提出无训练解码规则GACL,通过插值联合分数与同音频分数来修复仲裁反转,显著提升忠实度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.04442 2026-06-04 cs.CL cs.AI

MemoryDocDataSet: A Benchmark for Joint Conversational Memory and Long Document Reasoning

MemoryDocDataSet: 联合对话记忆与长文档推理的基准测试

Qiyang Xie, Jialun Wu, Xinjie He, Su Liu, Shuai Xiao, Zhiyuan Lin, Weikai Zhou

机构 * Northeastern University(东北大学) Johns Hopkins University(约翰霍普金斯大学) Columbia University(哥伦比亚大学) Independent Researcher(独立研究者)

AI总结 提出MemoryDocDataSet合成基准,包含50个微世界和1000个QA对,评估系统同时处理多轮对话历史和长文档阅读理解的能力,其中75.1%的问题需要混合推理(先导航对话历史再提取文档答案),实验显示联合检索存在明显差距。

Comments 17 pages, 2 figures, 8 tables. Submitted for peer review

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.04301 2026-06-04 cs.CV

XSSR: Cross-Domain Self-Supervised Representative Selection for Efficient Annotation in Medical Image Segmentation

XSSR: 跨域自监督代表性选择用于医学图像分割中的高效标注

Byunghyun Ko, Aleksei Anisimov, Kobe Ke, Suhas Bharthepude, Jeongkyu Lee

机构 * Northeastern University, San Jose, CA 95113, USA(东北大学,旧金山,CA 95113,美国) Northeastern University, New York, NY 10021, USA(东北大学,纽约,NY 10021,美国)

AI总结 提出XSSR框架,通过自监督学习在目标域中自动选择代表性样本进行标注,在仅使用5%标注预算时达到接近全数据性能。

Comments Accepted to the Third International Conference on AI in Healthcare (AIiH 2026). This is the preprint version of the paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.03564 2026-06-04 cs.CV cs.AI

CR-Seg: Attention-Guided and CoT-Enhanced Coarse-to-Refined Reasoning Segmentation

CR-Seg:注意力引导与CoT增强的由粗到精推理分割

Yifan Cao, Xiaocui Yang, Faxian Wan, Shi Feng, Daling Wang, Yifei Zhang

机构 * School of Computer Science and Engineering, Northeastern University(东北大学计算机科学与工程学院)

AI总结 提出CR-Seg两阶段框架,通过注意力图提取和全局到局部思维链,实现由粗到精的推理分割,解决跨模态对齐和推理-答案不一致问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.01770 2026-06-04 cs.LG cs.AI

Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams

自适应自动框架:面向开放式任务流的智能体系统部署的持续自我改进

Zewen Liu, Zhan Shi, Yisi Sang, Bing He, Minhua Lin, Tianxin Wei, Dakuo Wang, Benoit Dumoulin, Wei Jin, Hanqing Lu

机构 * Emory University(埃默里大学) Amazon(亚马逊) The Pennsylvania State University(宾夕法尼亚州立大学) UIUC(伊利诺伊大学香槟分校) Northeastern University(东北大学)

AI总结 提出自适应自动框架(Adaptive Auto-Harness),通过状态化多智能体进化器、带求解时路由的框架树和人工引导机制,解决开放式任务流中自动框架性能退化问题,在多个流上超越现有基线。

详情

展开后加载摘要…

URL PDF HTML 收藏
1403.3320 2026-06-04 math.NA cs.CV cs.NA

Numerical Approaches for Linear Left-invariant Diffusions on SE(2), their Comparison to Exact Solutions, and their Applications in Retinal Imaging

在SE(2)上的线性左不变扩散的数值方法,其与精确解的比较及其在视网膜成像中的应用

Jiong Zhang, Remco Duits, Gonzalo Sanguinetti, Bart M. ter Haar Romeny

机构 * Department of Biomedical Engineering, Biomedical Image Analysis (BMIA)(生物医学工程系,生物医学影像分析(BMIA)) Department of Mathematics and Computer Science, Image Science and Technology (IST/e)(数学与计算机科学系,图像科学与技术(IST/e)) Eindhoven University of Technology(埃因霍温理工大学) Northeastern University(东北大学)

AI总结 本文比较了SE(2)上左不变扩散的多种数值方法,并提供了精确解的分析,展示了傅里叶方法在精度上的优势,并在视网膜成像中应用了结合左不变PDE演化的可逆方向分数。

Comments A final and corrected version of the manuscript is Published in Numerical Mathematics: Theory, Methods and Applications (NM-TMA), vol. (9), p.1-50, 2016

Journal ref Numerical Mathematics: Theory, Methods and Applications (NM-TMA), vol. (9), p.1-50, 2016

详情

展开后加载摘要…

URL PDF HTML 收藏