arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

高校专区

University of Science and Technology of China(中国科学技术大学)

2026-02-12 至 2026-02-12 共收录 5
2602.11066 2026-02-12 cs.CV

PuriLight: A Lightweight Shuffle and Purification Framework for Monocular Depth Estimation

PuriLight: 一种轻量级的洗牌与净化框架用于单目深度估计

Yujie Chen, Li Zhang, Xiaomeng Chu, Tian Zhang

机构 * Department of Mathematics, Hefei University of Technology, Hefei, China(数学系,合肥工业大学) Department of Computer Science and Technology, University of Science and Technology of China, Hefei, China(计算机科学与技术系,中国科学技术大学)

AI总结 PuriLight通过三种创新模块实现轻量级且结构精确的单目深度估计,提升计算效率与细节保留能力。

Comments 8 pages, 6figures, accepted by European Conference on Artificial Intelligence (ECAI2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.01304 2026-02-12 cs.AI cs.CL

Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models

代理拼图交互学习:提升视觉感知与推理能力在视觉-语言模型中

Yu Zeng, Wenxuan Huang, Shiting Huang, Xikun Bao, Yukun Qi, Yiming Zhao, Qiuchen Wang, Lin Chen, Zehui Chen, Huaian Chen, Wanli Ouyang, Feng Zhao

机构 * University of Science and Technology of China(中国科学技术大学) Shanghai AI Laboratory(上海人工智能实验室) East China Normal University(华东师范大学) The Chinese University of Hong Kong(香港中文大学)

AI总结 AGILE通过代理拼图交互学习提升视觉-语言模型的感知与推理能力,显著提高拼图任务性能并增强多模态模型的泛化能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.10161 2026-02-12 cs.CR cs.AI cs.CL

Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment

跨模态冲突下的全方位安全:漏洞、动态机制和高效对齐

Kun Wang, Zherui Li, Zhenhong Zhou, Yitong Zhang, Yan Mi, Kun Yang, Yiming Zhang, Junhao Dong, Zhongxiang Sun, Qiankun Li, Yang Liu

机构 * Nanyang Technological University(南洋理工大学) Beijing University of Posts and Telecommunications(北京邮电大学) Tsinghua University(清华大学) Fudan University(复旦大学) University of Science and Technology of China(中国科学技术大学) Renmin University of China(中国人民大学)

AI总结 本文提出OmniSteer方法,通过提取黄金拒绝向量和轻量级适配器提升多模态模型的安全性与通用能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.07262 2026-02-12 cs.CV

TwistNet-2D: Learning Second-Order Channel Interactions via Spiral Twisting for Texture Recognition

TwistNet-2D: 通过螺旋扭转学习第二阶通道交互用于纹理识别

Junbo Jacob Lian, Feng Xiong, Yujun Sun, Kaichen Ouyang, Zong Ke, Mingyang Yu, Shengwei Fu, Zhong Rui, Zhang Yujun, Huiling Chen

机构 * McCormick School of Engineering, Northwestern University(西北大学工程学院) School of Mathematics, University of Science and Technology of China(中国科学技术大学数学学院) National University of Singapore(新加坡国立大学) College of Artificial Intelligence, Nankai University(南开大学人工智能学院) Guizhou University(贵州大学) Information Initiative Center, Hokkaido University(北海道大学信息初始化中心) School of New Energy, Jingchu University of Technology(荆楚科技大学新能源学院) Wenzhou University(温州大学)

AI总结 TwistNet-2D通过螺旋扭转学习第二阶通道交互,提升纹理识别性能,参数高效且超越多种基线模型。

Comments Code is available at https://github.com/junbolian/TwistNet-2D

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.01330 2026-02-12 cs.AI

Beyond Gemini-3-Pro: Revisiting LLM Routing and Aggregation at Scale

超越Gemini-3-Pro:大规模LLM路由与聚合的再审视

Shengji Tang, Weihao Lin, Peng Ye, Jingqi Ye, Hao Li, Yiqun Zhang, Xiaosong Wang, Bo Zhang, Shuyue Hu, Tao Chen, Lei Bai, Wanli Ouyang

机构 * Shanghai AI Lab(上海人工智能实验室) The Chinese University of Hong Kong(香港中文大学) Fudan University(复旦大学) University of Science and Technology of China(中国科学技术大学) Northwestern Polytechnical University(西北工业大学) Northeastern University(东北大学)

AI总结 本文提出JiSi框架,通过混合路由、支持集聚合选择和自适应切换技术,实现开源LLM协作超越Gemini-3-Pro。

Comments 21 pages

详情

展开后加载摘要…

URL PDF HTML 收藏