arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Columbia University(哥伦比亚大学)

2025-12-02 至 2025-12-02 共收录 7
2512.01922 2025-12-02 cs.CV

Med-VCD: Mitigating Hallucination for Medical Large Vision Language Models through Visual Contrastive Decoding

Med-VCD: 通过视觉对比解码缓解医疗大视觉语言模型的幻觉问题

Zahra Mahdavi, Zahra Khodakaramimaghsoud, Hooman Khaloo, Sina Bakhshandeh Taleshani, Erfan Hashemi, Javad Mirzapour Kaleybar, Omid Nejati Manzari

机构 * Department of computer science, University of Central Florida, Orlando, USA(计算机科学系,中央佛罗里达大学) Department of Bioengineering, University of Pennsylvania, Philadelphia, PA, USA(生物工程系,宾夕法尼亚大学) Department of electrical engineering, Columbia university, New York, NY, USA(电气工程系,哥伦比亚大学) Technical University of Applied Sciences Regensburg, Regensburg, Germany(应用科学技术大学(雷根斯堡)) Department of Surgery, University of Calgary, Calgary, Alberta, Canada(外科系,卡尔加里大学) University College of Nabi Akram, Tabriz, Iran(纳比阿克兰大学) School of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran(电气工程学院,伊朗科学技术大学)

AI总结 Med-VCD通过视觉对比解码方法提升医疗大视觉语言模型的事实准确性与幻觉准确性,减少幻觉输出并提高推理效率。

Journal ref Computers in Biology and Medicine (2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.01509 2025-12-02 quant-ph cs.LG hep-ex

Learning Reduced Representations for Quantum Classifiers

学习量子分类器的降维表示

Patrick Odagiu, Vasilis Belis, Lennart Schulze, Panagiotis Barkoutsos, Michele Grossi, Florentin Reiter, Günther Dissertori, Ivano Tavernelli, Sofia Vallecorsa

机构 * Institute for Particle Physics and Astrophysics, ETH Zurich(粒子物理与天体物理研究所,苏黎世联邦理工学院) Columbia University(哥伦比亚大学) IBM Quantum, IBM Research – Zurich(IBM量子,IBM瑞士研究) European Organization for Nuclear Research (CERN)(欧洲核子研究中心) Institute for Quantum Electronics, ETH Zurich(量子电子研究所,苏黎世联邦理工学院) Fraunhofer Institute for Applied Solid State Physics IAF(应用固态物理研究所(IAF))

AI总结 本文提出Sinkclass自编码器,通过降维提升量子分类器性能,实现对高维数据集的有效处理。

Journal ref Odagiu, P., Belis, V., Schulze, L. et al. Learning reduced representations for quantum classifiers. Quantum Mach. Intell. 7, 113 (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.01366 2025-12-02 cs.CV cs.HC cs.LG

BlinkBud: Detecting Hazards from Behind via Sampled Monocular 3D Detection on a Single Earbud

BlinkBud: 通过单个耳塞上的采样单目3D检测检测后方危险

Yunzhe Li, Jiajun Yan, Yuzhou Wei, Kechen Liu, Yize Zhao, Chong Zhang, Hongzi Zhu, Li Lu, Shan Chang, Minyi Guo

机构 * Shanghai Jiao Tong University(上海交通大学) Columbia University(哥伦比亚大学) University of Electronic Science and Technology of China(电子科技大学) Southwest Petroleum University(西南石油大学) Donghua University(东华大学)

AI总结 BlinkBud通过单耳塞和手机实现后方危险检测,采用3D跟踪算法和强化学习优化功耗与精度。

Comments This is the author-accepted version of the paper published in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), Vol. 9, No. 4, Article 191, 2025. Final published version: https://doi.org/10.1145/3770707

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.01199 2025-12-02 cs.LG q-bio.NC

Know Thyself by Knowing Others: Learning Neuron Identity from Population Context

通过了解他人来认识自己:从群体上下文学习神经元身份

Vinam Arora, Divyansha Lachi, Ian J. Knight, Mehdi Azabou, Blake Richards, Cole L. Hurwitz, Josh Siegle, Eva L. Dyer

机构 * University of Pennsylvania(宾夕法尼亚大学) Columbia University(哥伦比亚大学) McGill University(麦吉尔大学) Mila(Mila研究所) Allen Institute for Neural Dynamics(神经动态阿伦研究所)

AI总结 NuCLR通过自监督学习从群体上下文中的神经活动区分神经元身份,实现了细胞类型和大脑区域解码的最新成果。

Comments Accepted at Neurips 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21526 2025-12-02 cs.LG cs.CV

TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised Learning

TRiCo:三元博弈协同训练用于鲁棒半监督学习

Hongyang He, Xinyuan Song, Yangfan He, Zeyu Zhang, Yanshu Li, Haochen You, Lifan Sun, Wenqiao Zhang

机构 * University of Warwick(沃里克大学) Emory University(埃默里大学) University of Minnesota – Twin Cities(明尼苏达大学双城分校) ANU(澳大利亚国立大学) Brown University(布朗大学) Columbia University(哥伦比亚大学) UCSD(加州大学圣地亚哥分校) Zhejiang University(浙江大学)

AI总结 TRiCo通过三元博弈协同训练框架提升半监督学习的鲁棒性和性能,实现更稳健的伪标签选择和决策边界优化。

Comments Accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.20793 2025-12-02 cs.CV cs.AI

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

面向渲染的强化学习用于矢量图形生成

Juan A. Rodriguez, Haotian Zhang, Abhay Puri, Aarash Feizi, Rishav Pramanik, Pascal Wichmann, Arnab Mondal, Mohammad Reza Samsami, Rabiul Awal, Perouz Taslakian, Spandana Gella, Sai Rajeswar, David Vazquez, Christopher Pal, Marco Pedersoli

机构 * ServiceNow Research(ServiceNow研究机构) Mila ÉTS Montréal(蒙特利尔ÉTS) Polytechnique Montréal(蒙特利尔Polytechnique) Columbia University(哥伦比亚大学) Stony Brook University(石溪大学) Apple(苹果公司) Google Research(谷歌研究) Canada CIFAR AI Chair(加拿大CIFAR人工智能主席) McGill University(麦吉尔大学)

AI总结 本文提出RLRF方法,通过利用渲染反馈提升自回归VLMs中SVG生成的准确性和效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.17320 2025-12-02 cs.CL cs.SD eess.AS

Comparative Evaluation of Expressive Japanese Character Text-to-Speech with VITS and Style-BERT-VITS2

表达性日语字符文本到语音的比较评估:VITS与Style-BERT-VITS2 JP Extra

Zackary Rackauckas, Julia Hirschberg

机构 * Columbia University, RoleGaku(哥伦比亚大学、RoleGaku) Columbia University(哥伦比亚大学)

AI总结 本文比较了VITS和Style-BERT-VITS2 JP Extra在生成表达性日语字符语音中的表现,发现SBV2JE在自然度和可懂度方面表现更优,适用于语言学习和角色对话生成。

Comments Accepted to IEEE UEMCON 2025

详情

展开后加载摘要…

URL PDF HTML 收藏