咨询与建议

限定检索结果

文献类型

  • 90 篇 期刊文献
  • 42 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

  • 98 篇 工学
    • 90 篇 计算机科学与技术...
    • 71 篇 软件工程
    • 15 篇 信息与通信工程
    • 12 篇 控制科学与工程
    • 4 篇 电气工程
    • 4 篇 土木工程
    • 4 篇 交通运输工程
    • 4 篇 安全科学与工程
    • 4 篇 网络空间安全
    • 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 生物工程
  • 39 篇 管理学
    • 32 篇 图书情报与档案管...
    • 11 篇 管理科学与工程(可...
  • 23 篇 理学
    • 11 篇 数学
    • 5 篇 物理学
    • 5 篇 统计学(可授理学、...
    • 4 篇 生物学
    • 2 篇 化学
    • 1 篇 天文学
  • 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
  • 1 篇 农学

主题

  • 9 篇 semantics
  • 8 篇 computational li...
  • 5 篇 generative adver...
  • 5 篇 benchmarking
  • 5 篇 training
  • 3 篇 modeling languag...
  • 3 篇 recommender syst...
  • 3 篇 large datasets
  • 3 篇 adversarial mach...
  • 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 digital elevatio...
  • 2 篇 knowledge graph
  • 2 篇 contrastive lear...
  • 2 篇 graph neural net...
  • 2 篇 computational mo...

机构

  • 74 篇 university of ch...
  • 30 篇 cas key laborato...
  • 17 篇 cas key laborato...
  • 11 篇 cas key laborato...
  • 9 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 baidu inc.
  • 4 篇 cas key laborato...
  • 3 篇 key lab of ai sa...

作者

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

语言

  • 98 篇 英文
  • 33 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11-20 订阅
排序:
Generative Ghost: Investigating Ranking Bias Hidden in ai-Generated Videos
arXiv
收藏 引用
arXiv 2025年
作者: Gao, Haowen Pang, Liang Xu, Shicheng Qu, Leigang Chua, Tat-Seng Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences China Sea-NExT Joint Lab National University of Singapore Singapore CAS Key Laboratory of AI Security Institute of Computing Technology Chinese Academy of Sciences China
With the rapid development of ai-generated content (aiGC), the creation of high-quality ai-generated videos has become faster and easier, resulting in the Internet being flooded with all kinds of video content. Howeve... 详细信息
来源: 评论
The Mirage of Model Editing: Revisiting Evaluation in the Wild
arXiv
收藏 引用
arXiv 2025年
作者: Yang, Wanli Sun, Fei Tan, Jiajun Ma, Xinyu Cao, Qi Yin, Dawei Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology CAS China University of Chinese Academy of Sciences China Baidu Inc. China
Despite near-perfect results in artificial evaluations, the effectiveness of model editing in real-world applications remains unexplored. To bridge this gap, we propose to study model editing in question answering (QA...
来源: 评论
CLIPURE: PURIFICATION IN LATENT SPACE VIA CLIP FOR ADVERSARIALLY ROBUST ZERO-SHOT CLASSIFICATION
arXiv
收藏 引用
arXiv 2025年
作者: Zhang, Mingkun Bi, Keping Chen, Wei Guo, Jiafeng Cheng, Xueqi State Key Lab of AI Safety CAS Key Lab of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China
In this paper, we aim to build an adversarially robust zero-shot image classifier. We ground our work on CLIP, a vision-language pre-trained encoder model that can perform zero-shot classification by matching an image... 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
MIGE: A Unified Framework for Multimodal Instruction-Based Image Generation and Editing
arXiv
收藏 引用
arXiv 2025年
作者: Tian, Xueyun Li, Wei Xu, Bingbing Yuan, Yige Wang, Yuanzhuo Shen, Huawei CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China
Despite significant progress in diffusion-based image generation, subject-driven generation and instruction-based editing remain challenging. Existing methods typically treat them separately, struggling with limited h... 详细信息
来源: 评论
Synthetic View Augmentation for Sign Language Recognition  25
Synthetic View Augmentation for Sign Language Recognition
收藏 引用
Companion Proceedings of the ACM on Web Conference 2025
作者: Yuting Peng Peiqi Jiao Honggang Zou Yuecong Min Xilin Chen State Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing China and University of Chinese Academy of Sciences Beijing China State Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing China
Sign language, as a visual language, is inherently spatial and dynamic, characterized by various hand shapes, movements, facial expressions, and body postures. In real-world scenarios, sign language recognition (SLR) ... 详细信息
来源: 评论
Agent-SiMT: Agent-Assisted Simultaneous Translation With Large Language Models
IEEE Transactions on Audio, Speech and Language Processing
收藏 引用
IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 2074-2083页
作者: Shoutao Guo Shaolei Zhang Zhengrui Ma Min Zhang Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (ICT/CAS) Beijing China University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology Soochow University Suzhou China Key Laboratory of AI Safety Chinese Academy of Sciences Beijing China
Simultaneous Machine Translation (SiMT) generates target translations in real-time while reading the source sentence. It relies on a policy to determine the optimal timing for producing translations, aiming to achieve... 详细信息
来源: 评论
Revisiting Robust RAG: Do We Still Need Complex Robust Training in the Era of Powerful LLMs?
arXiv
收藏 引用
arXiv 2025年
作者: Ding, Hanxing Tao, Shuchang Pang, Liang Wei, Zihao Chen, Liwei Xu, Kun Shen, Huawei Cheng, Xueqi Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Kuaishou Technology China
Retrieval-augmented generation (RAG) systems often suffer from performance degradation when encountering noisy or irrelevant documents, driving researchers to develop sophisticated training strategies to enhance their...
来源: 评论
Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment
arXiv
收藏 引用
arXiv 2025年
作者: Deng, Jingcheng Jiang, Zhongtao Pang, Liang Chen, Liwei Xu, Kun Wei, Zihao Shen, Huawei Cheng, Xueqi Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Kuaishou Technology China
A new trend uses LLMs as dense text encoders via contrastive learning. However, since LLM embeddings predict the probability distribution of the next token, they are inherently generative and distributive, conflicting... 详细信息
来源: 评论
PERPLEXITY-TRAP: PLM-BASED RETRIEVERS OVERRATE LOW PERPLEXITY DOCUMENTS
arXiv
收藏 引用
arXiv 2025年
作者: Wang, Haoyu Dai, Sunhao Zhao, Haiyuan Pang, Liang Zhang, Xiao Wang, Gang Dong, Zhenhua Xu, Jun Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China Beijing China CAS Key Laboratory of AI Safety Institute of Computing Technology Beijing China Huawei Noah’s Ark Lab Shenzhen China
Previous studies have found that PLM-based retrieval models exhibit a preference for LLM-generated content, assigning higher relevance scores to these documents even when their semantic quality is comparable to human-... 详细信息
来源: 评论