arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

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

2026-06-18 至 2026-06-18 共收录 8
2606.18644 2026-06-18 cs.CV 新提交

Spiking Pyramid Wavelet Transformation for High-efficient and Low-energy Image Restoration

尖峰金字塔小波变换用于高效低能耗图像恢复

Chen Zhao, Xiantao Hu, Song Wu, Qian Wang, Chen Wu, Rui Xie, Jian Yang, Ying Tai

机构 * Nanjing University(南京大学) Nanjing University of Science and Technology(南京理工大学) University of Science and Technology of China(中国科学技术大学) China Mobile Institute(中国移动研究院)

AI总结 提出基于尖峰神经网络和金字塔小波变换的SPWM模型,通过SDPW块建模长程依赖并利用小波域退化特性,在保持图像质量的同时显著降低计算和能耗。

Comments Accepted by Pattern Recognition

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.18632 2026-06-18 cs.RO 新提交

ROBOSHACKLES: A Safety Dataset for Human-Injury Prevention in Embodied Foundation Models

ROBOSHACKLES: 面向具身基础模型中人体伤害预防的安全数据集

Zhuowen Yin, Chongyang Liu, Wenzhang Yang, Renjue Li, Yinxing Xue

机构 * Institute of Al for Industries, Chinese Academy of Sciences(工业人工智能研究所,中国科学院) University of Science and Technology of China(中国科学技术大学)

AI总结 为解决机器人伤害人类数据难以安全收集的问题,提出基于真实观测的安全数据构建流水线,生成包含1万条视频的ROBOSHACKLES数据集,涵盖直接和间接伤害类别,评估发现现有模型在安全关键场景下100%产生不安全动作。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.18257 2026-06-18 cs.HC cs.AI 新提交

From Memorization to Creation: Evaluating the Cognitive Depth of LLM-Generated Educational Questions

从记忆到创造:评估LLM生成的教育问题的认知深度

Xiaolong Wang, Zhe Zhao, Song Lai, Chaoli Zhang, Zijie Geng, Yu Tong, Ye Wei, Qingsong Wen

机构 * City University of Hong Kong(香港城市大学) Zhejiang Normal University(浙江师范大学) Squirrel Ai Learning University of Science and Technology of China(中国科学技术大学) Wuhan University(武汉大学)

AI总结 通过布鲁姆认知分类学评估六种LLM生成问题的认知层次,提出细粒度提示策略减少重复性并提升高阶认知比例,引入认知转移强度和类别漂移指标,揭示链式思维提示的可解释性。

Comments Accepted by KDD 2026

Journal ref KDD 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.21626 2026-06-18 cs.LG cs.AI 版本更新

HeRo-Q: A General Framework for Stable Low Bit Quantization via Hessian Conditioning

HeRo-Q: 通过Hessian条件化实现稳定低比特量化的通用框架

Jinhao Zhang, Yunquan Zhang, Zicheng yan, Boyang Zhang, Jun Sun, Daning Cheng

机构 * Beijing University of Posts and Telecommunications(北京邮电大学) Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所) University of Science and Technology of China(中国科学技术大学) Zhejiang Lab(浙江实验室) Peng Cheng Laboratory(鹏城实验室)

AI总结 针对后训练量化中“低误差、高损失”的矛盾,提出HeRo-Q算法,通过轻量可学习的旋转压缩矩阵重塑损失景观,降低最大Hessian特征值,增强对量化噪声的鲁棒性,在Llama和Qwen模型上优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.14968 2026-06-18 cs.LG cs.AI 版本更新

InstructTime++: Time Series Classification with Multimodal Language Modeling via Implicit Feature Enhancement

InstructTime++: 通过隐式特征增强的多模态语言建模进行时间序列分类

Mingyue Cheng, Xiaoyu Tao, Huajian Zhang, Qi Liu, Zhiding Liu, Yucong Luo, Yiheng Chen, Enhong Chen

机构 * State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China(中国科学技术大学认知智能国家重点实验室)

AI总结 提出将时间序列分类转化为多模态生成任务,通过离散化模块和对齐投影层弥合模态差距,并利用隐式特征建模提升语言模型性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.09191 2026-06-18 cs.LG cs.AI 版本更新

From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization

从数值到标记:一种基于符号离散化的LLM驱动上下文感知时间序列预测框架

Xiaoyu Tao, Shilong Zhang, Mingyue Cheng, Daoyu Wang, Tingyue Pan, Bokai Pan, Changqing Zhang, Shijin Wang

机构 * State Key Laboratory of Cognitive Intelligence(认知智能国家重点实验室) University of Science and Technology of China(中国科学技术大学) College of Intelligence and Computing(智能科学与计算学院) iFLYTEK Research(iFLYTEK研究院)

AI总结 提出TokenCast框架,利用大语言模型通过符号离散化将连续时间序列转化为标记,与上下文文本对齐,实现上下文感知的预测,实验证明有效。

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.16439 2026-06-18 cs.CV

Continual Test-Time Adaptation for Object Detection with Adaptive Monitoring and Randomized Restoration

持续测试时间适应用于目标检测的自适应监控与随机恢复

Shilei Cao, Juepeng Zheng, Yan Liu, Baoquan Zhao, Ziqi Yuan, Weijia Li, Runmin Dong, Haohuan Fu

机构 * School of Artificial Intelligence, Sun Yat-Sen University(中山大学人工智能学院) School of Information Science and Technology, University of Science and Technology of China(中国科学技术大学信息科学与技术学院) State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University(清华大学智能技术与系统国家重点实验室) Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生学院) National Supercomputing Center in Shenzhen(深圳国家超算中心) Ministry of Education Key Laboratory for Earth System Modeling and the Department of Earth System Science, Tsinghua University(清华大学地球系统模型教育部重点实验室)

AI总结 本文提出AMROD方法,通过对比学习、自适应监控和随机恢复机制提升持续测试时间适应的目标检测性能,实验证明其在多个任务中优于现有方法,尤其在Cityscapes-to-Cityscapes-C任务中提升3.2 mAP并提高20%效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.08038 2026-06-18 cs.LG cs.AI cs.CV 版本更新

Generalized Kullback-Leibler Divergence Loss

广义Kullback-Leibler散度损失

Jiequan Cui, Beier Zhu, Qingshan Xu, Zhuotao Tian, Xiaojuan Qi, Bei Yu, Hanwang Zhang, Richang Hong

机构 * Hefei University of Technology(合肥工业大学) University of Science and Technology of China(中国科学技术大学) Nanyang Technological University(南洋理工大学) The Chinese University of Hong Kong(香港中文大学) The University of Hong Kong(香港大学) Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳))

AI总结 本文提出广义KL散度损失,通过解耦KL损失为加权MSE和交叉熵损失,并引入非对称优化修正和类别全局信息,在对抗训练和知识蒸馏中取得SOTA性能。

Comments TPAMI 2026, extension of our NeurIPS paper "Decoupled Kullback-Leibler Divergence Loss". arXiv admin note: substantial text overlap with arXiv:2305.13948

详情

展开后加载摘要…

URL PDF HTML 收藏