咨询与建议

限定检索结果

文献类型

  • 89 篇 期刊文献
  • 43 篇 会议

馆藏范围

  • 132 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 94 篇 工学
    • 87 篇 计算机科学与技术...
    • 71 篇 软件工程
    • 12 篇 信息与通信工程
    • 9 篇 控制科学与工程
    • 4 篇 土木工程
    • 3 篇 电气工程
    • 3 篇 电子科学与技术(可...
    • 3 篇 建筑学
    • 2 篇 机械工程
    • 2 篇 材料科学与工程(可...
    • 2 篇 测绘科学与技术
    • 2 篇 化学工程与技术
    • 2 篇 环境科学与工程(可...
    • 2 篇 安全科学与工程
    • 2 篇 网络空间安全
    • 1 篇 交通运输工程
  • 36 篇 管理学
    • 29 篇 图书情报与档案管...
    • 9 篇 管理科学与工程(可...
  • 20 篇 理学
    • 10 篇 数学
    • 4 篇 物理学
    • 4 篇 统计学(可授理学、...
    • 2 篇 化学
    • 2 篇 生物学
    • 1 篇 天文学
    • 1 篇 系统科学
  • 4 篇 法学
    • 4 篇 社会学
  • 4 篇 文学
    • 4 篇 中国语言文学
    • 4 篇 外国语言文学
  • 2 篇 教育学
    • 2 篇 教育学
  • 1 篇 经济学
    • 1 篇 应用经济学

主题

  • 9 篇 semantics
  • 8 篇 computational li...
  • 6 篇 training
  • 5 篇 generative adver...
  • 5 篇 benchmarking
  • 3 篇 modeling languag...
  • 3 篇 large datasets
  • 3 篇 adversarial mach...
  • 3 篇 benchmark testin...
  • 3 篇 decoding
  • 3 篇 machine learning
  • 2 篇 query processing
  • 2 篇 rendering (compu...
  • 2 篇 deep learning
  • 2 篇 computer archite...
  • 2 篇 recommender syst...
  • 2 篇 digital elevatio...
  • 2 篇 knowledge graph
  • 2 篇 contrastive lear...
  • 2 篇 graph neural net...

机构

  • 74 篇 university of ch...
  • 30 篇 cas key laborato...
  • 18 篇 cas key laborato...
  • 11 篇 cas key laborato...
  • 8 篇 gaoling school o...
  • 8 篇 cas key laborato...
  • 8 篇 university of ca...
  • 7 篇 kuaishou technol...
  • 7 篇 key laboratory o...
  • 7 篇 cas key laborato...
  • 7 篇 cas key laborato...
  • 6 篇 university of ca...
  • 6 篇 key laboratory o...
  • 5 篇 key laboratory o...
  • 5 篇 cas key laborato...
  • 5 篇 institute for ai...
  • 4 篇 idea research in...
  • 4 篇 school of artifi...
  • 4 篇 baidu inc.
  • 4 篇 cas key laborato...

作者

  • 68 篇 cheng xueqi
  • 54 篇 shen huawei
  • 34 篇 pang liang
  • 18 篇 sun fei
  • 15 篇 cao qi
  • 13 篇 bi baolong
  • 12 篇 xu shicheng
  • 11 篇 wang yiwei
  • 11 篇 liu shenghua
  • 11 篇 mei lingrui
  • 9 篇 zhang kaike
  • 9 篇 wu yunfan
  • 8 篇 guo jiafeng
  • 8 篇 xu jun
  • 8 篇 guo fangda
  • 8 篇 xu bingbing
  • 7 篇 wang yuanzhuo
  • 7 篇 yuan yige
  • 6 篇 shan shiguang
  • 6 篇 xueqi cheng

语言

  • 100 篇 英文
  • 31 篇 其他
  • 1 篇 中文
检索条件"机构=CAS Key Laboratory of AI Safety Institute of Computing Technology"
132 条 记 录,以下是41-50 订阅
排序:
CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense
arXiv
收藏 引用
arXiv 2024年
作者: Zhang, Mingkun Bi, Keping Chen, Wei Chen, Quanrun Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology CAS China Key Laboratory of Network Data Science and Technology Institute of Computing Technology CAS China School of Statistics University of International Business and Economics China CAS stands for Chinese Academy of Sciences China
Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated by subtle manipulations, since we ma... 详细信息
来源: 评论
Disentangled Graph Representation with Contrastive Learning for Rumor Detection
Disentangled Graph Representation with Contrastive Learning ...
收藏 引用
International Conference on Acoustics, Speech, and Signal Processing (IcasSP)
作者: Haoyu Liu Yuanhai Xue Xiaoming Yu CAS Key Laboratory of AI Safety and Security Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences
With many social problems nowadays, rumor detection in social media has become increasingly important. Previous works proposed classical and deep learning methods to extract information from features or rumor propagat...
来源: 评论
Rethinking the evaluation of out-of-distribution detection: a sorites paradox  24
Rethinking the evaluation of out-of-distribution detection: ...
收藏 引用
Proceedings of the 38th International Conference on Neural Information Processing Systems
作者: Xingming Long Jie Zhang Shiguang Shan Xilin Chen Key Laboratory of AI Safety of CAS Institute of Computing Technology Chinese Academy of Sciences (CAS) Beijing China and University of Chinese Academy of Sciences Beijing China
Most existing out-of-distribution (OOD) detection benchmarks classify samples with novel labels as the OOD data. However, some marginal OOD samples actually have close semantic contents to the in-distribution (ID) sam...
来源: 评论
TEA: Test-Time Energy Adaptation
TEA: Test-Time Energy Adaptation
收藏 引用
Conference on Computer Vision and Pattern Recognition (CVPR)
作者: Yige Yuan Bingbing Xu Liang Hou Fei Sun Huawei Shen Xueqi Cheng CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Kuaishou Technology
Test Time Adaptation (TTA) aims to improve model generalizability when test data diverges from training distribution, with the distinct advantage of not requiring access to training data and processes, especially valu... 详细信息
来源: 评论
Precise Integral in NeRFs: Overcoming the Approximation Errors of Numerical Quadrature
Precise Integral in NeRFs: Overcoming the Approximation Erro...
收藏 引用
IEEE Workshop on Applications of Computer Vision (WACV)
作者: Boyuan Zhang Zhenliang He Meina Kan Shiguang Shan Key Lab of AI Safety Institute of Computing Technology CAS China University of Chinese Academy of Sciences China
Neural Radiance Fields (NeRFs) use neural networks to translate spatial coordinates to corresponding volume density and directional radiance, enabling realistic novel view synthesis through volume rendering. Rendering... 详细信息
来源: 评论
Understanding the Collapse of LLMs in Model Editing
arXiv
收藏 引用
arXiv 2024年
作者: Yang, Wanli Sun, Fei Tan, Jiajun Ma, Xinyu Su, Du Yin, Dawei Shen, Huawei CAS Key Laboratory of AI Safety Institute of Computing Technology CAS China University of Chinese Academy of Sciences China Baidu Inc. China
Despite significant progress in model editing methods, their application in real-world scenarios remains challenging as they often cause large language models (LLMs) to collapse. Among them, ROME is particularly conce... 详细信息
来源: 评论
Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration
arXiv
收藏 引用
arXiv 2024年
作者: Wu, Kangxi Pang, Liang Shen, Huawei Cheng, Xueqi Key Laboratory of AI Safety Chinese Academy of Sciences Institute of Computing Technology CAS China University of Chinese Academy of Sciences China
The black-box nature of large language models (LLMs) poses challenges in interpreting results, impacting issues such as data intellectual property protection and hallucination tracing. Training data attribution (TDA) ... 详细信息
来源: 评论
Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement
arXiv
收藏 引用
arXiv 2024年
作者: Hou, Danyang Pang, Liang Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China
Video Corpus Moment Retrieval (VCMR) is a new video retrieval task aimed at retrieving a relevant moment from a large corpus of untrimmed videos using a text query. The relevance between the video and query is partial...
来源: 评论
ALiiCE: Evaluating Positional Fine-grained Citation Generation
arXiv
收藏 引用
arXiv 2024年
作者: Xu, Yilong Gao, Jinhua Yu, Xiaoming Bi, Baolong Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China
Large Language Model (LLM) can enhance its credibility and verifiability by generating text with citations. However, existing research on citation generation is predominantly limited to sentence-level statements, negl... 详细信息
来源: 评论
M3GIA: A Cognition Inspired Multilingual and Multimodal General Intelligence Ability Benchmark
arXiv
收藏 引用
arXiv 2024年
作者: Song, Wei Li, Yadong Xu, Jianhua Wu, Guowei Ming, Lingfeng Yi, Kexin Luo, Weihua Li, Houyi Du, Yi Guo, Fangda Yu, Kaicheng AutoLab Westlake University China AI Business Alibaba Group China Zhejiang University China Key Laboratory of Behavioral Science Institute of Psychology CAS China Key Laboratory of AI Safety Institute of Computing Technology CAS China
As recent multi-modality large language models (MLLMs) have shown formidable proficiency on various complex tasks, there has been increasing attention on debating whether these models could eventually mirror human int... 详细信息
来源: 评论