arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

大模型对齐与安全

大模型对齐、安全、越狱、红队、提示注入和可信评测。

共收录 8057 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 其他安全 8057 篇

2410.05767 2024-11-15 cs.CV cs.AI cs.MM 57%

Grounding is All You Need? Dual Temporal Grounding for Video Dialog

You Qin, Wei Ji, Xinze Lan, Hao Fei, Xun Yang, Dan Guo, Roger Zimmermann, Lizi Liao

机构 * National University of Singapore(新加坡国立大学) University of Science and Technology of China(中国科学技术大学) Hefei University of Technology(合肥工业大学) Singapore Management University(新加坡管理大学)

专题命中 其他安全 :alignment(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.08664 2024-11-14 cs.LG cond-mat.mtrl-sci 57%

UniMat: Unifying Materials Embeddings through Multi-modal Learning

Janghoon Ock, Joseph Montoya, Daniel Schweigert, Linda Hung, Santosh K. Suram, Weike Ye

专题命中 其他安全 :alignment(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.06538 2024-11-12 cs.AI cs.CE 57%

A Next-Generation Approach to Airline Reservations: Integrating Cloud Microservices with AI and Blockchain for Enhanced Operational Performance

Biman Barua, M. Shamim Kaiser

专题命中 其他安全 :safety(abstract);分类 cs.AI

Comments 25 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.11436 2024-11-12 q-bio.NC cs.CV cs.LG 57%

Layerwise complexity-matched learning yields an improved model of cortical area V2

Nikhil Parthasarathy, Olivier J. Hénaff, Eero P. Simoncelli

机构 * New York University(纽约大学) Flatiron Institute(弗拉铁隆研究所) Google DeepMind(谷歌DeepMind)

专题命中 其他安全 :alignment(abstract);分类 cs.LG

Comments 31 pages, 13 figures

Journal ref Transactions on Machine Learning Research, Jun 2024. Featured Article certification

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.06142 2024-11-12 cs.CV cs.AI 57%

Aquila-plus: Prompt-Driven Visual-Language Models for Pixel-Level Remote Sensing Image Understanding

Kaixuan Lu

专题命中 其他安全 :alignment(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.06074 2024-11-12 cs.CV cs.AI 57%

Aquila: A Hierarchically Aligned Visual-Language Model for Enhanced Remote Sensing Image Comprehension

Kaixuan Lu, Ruiqian Zhang, Xiao Huang, Yuxing Xie

专题命中 其他安全 :alignment(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.05898 2024-11-12 cs.CV cs.AI cs.RO 57%

Integrating Object Detection Modality into Visual Language Model for Enhanced Autonomous Driving Agent

Linfeng He, Yiming Sun, Sihao Wu, Jiaxu Liu, Xiaowei Huang

机构 * University of Liverpool(利物浦大学) University of Nottingham(诺丁汉大学)

专题命中 其他安全 :safety(abstract);分类 cs.AI

Comments accepted by SafeGenAI workshop of NeurIPS 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.05831 2024-11-12 cs.AI cs.CV 57%

To Ask or Not to Ask? Detecting Absence of Information in Vision and Language Navigation

Savitha Sam Abraham, Sourav Garg, Feras Dayoub

机构 * Australian Institute for Machine Learning(澳大利亚机器学习研究所) The University of Adelaide(阿德莱德大学)

专题命中 其他安全 :alignment(abstract);分类 cs.AI

Comments Accepted at WACV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.05586 2024-11-11 cs.RO cs.AI cs.SY eess.SY 57%

Tangled Program Graphs as an alternative to DRL-based control algorithms for UAVs

Hubert Szolc, Karol Desnos, Tomasz Kryjak

机构 * AGH University of Krakow(克拉科夫AGH科技大学) Univ Rennes(雷恩大学) INSA Rennes(雷恩国立应用科学学院) CNRS(法国国家科学研究中心) IETR(电子与电信研究所)

专题命中 其他安全 :safety(abstract);分类 cs.AI

Comments The papers was accepted for the 2024 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) conference in Poznan, Poland

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.05079 2024-11-11 cs.CV cs.CL 57%

Precision or Recall? An Analysis of Image Captions for Training Text-to-Image Generation Model

Sheng Cheng, Maitreya Patel, Yezhou Yang

机构 * Arizona State University(亚利桑那州立大学)

专题命中 其他安全 :alignment(abstract);分类 cs.CL

Comments EMNLP 2024 Findings. Code: https://github.com/shengcheng/Captions4T2I

详情

展开后加载摘要…

URL PDF HTML 收藏
2310.10108 2024-11-11 cs.IR cs.AI 57%

On Generative Agents in Recommendation

An Zhang, Yuxin Chen, Leheng Sheng, Xiang Wang, Tat-Seng Chua

机构 * National University of Singapore(新加坡国立大学) Tsinghua University(清华大学) University of Science and Technology of China(中国科学技术大学)

专题命中 其他安全 :alignment(abstract);分类 cs.AI

Comments SIGIR 2024 perspective paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.01345 2024-11-07 cs.CL 57%

The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights

Wenhao Zhu, Shujian Huang, Fei Yuan, Cheng Chen, Jiajun Chen, Alexandra Birch

机构 * National Key Laboratory for Novel Software Technology(计算机软件新技术国家重点实验室) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) School of Informatics, University of Edinburgh(爱丁堡大学信息学院)

专题命中 其他安全 :alignment(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.03038 2024-11-06 cs.LG 57%

Can Transformers Smell Like Humans?

Farzaneh Taleb, Miguel Vasco, Antônio H. Ribeiro, Mårten Björkman, Danica Kragic

机构 * KTH Royal Institute of Technology(瑞典皇家理工学院) Uppsala University(乌普萨拉大学)

专题命中 其他安全 :alignment(abstract);分类 cs.LG

Comments Spotlight paper at NeurIPS 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.03034 2024-11-06 cs.AI cs.MM 57%

HumanVLM: Foundation for Human-Scene Vision-Language Model

Dawei Dai, Xu Long, Li Yutang, Zhang Yuanhui, Shuyin Xia

机构 * Chongqing University of Posts and Telecommunications(重庆邮电大学)

专题命中 其他安全 :alignment(abstract);分类 cs.AI

Comments 34 pages,11 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.23074 2024-11-06 cs.SE cs.CL 57%

Multi-Programming Language Sandbox for LLMs

Shihan Dou, Jiazheng Zhang, Jianxiang Zang, Yunbo Tao, Weikang Zhou, Haoxiang Jia, Shichun Liu, Yuming Yang, Zhiheng Xi, Shenxi Wu, Shaoqing Zhang, Muling Wu, Changze Lv, Limao Xiong, Wenyu Zhan, Lin Zhang, Rongxiang Weng, Jingang Wang, Xunliang Cai, Yueming Wu, Ming Wen, Rui Zheng, Tao Ji, Yixin Cao, Tao Gui, Xipeng Qiu, Qi Zhang, Xuanjing Huang

机构 * Fudan University(复旦大学) Peking University(北京大学) Nanyang Technological University(南洋理工大学) Huazhong University of Science and Technology(华中科技大学) Harbin Institute of Technology(哈尔滨工业大学) Meituan Inc(美团公司)

专题命中 其他安全 :safety(abstract);分类 cs.CL

Comments 25 pages, 14 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.17717 2024-11-05 cs.CL 57%

AmbigNLG: Addressing Task Ambiguity in Instruction for NLG

Ayana Niwa, Hayate Iso

机构 * Megagon Labs(美嘉根实验室) Recruit Co., Ltd.(Recruit公司) MBZUAI(穆罕默德·本·扎耶德人工智能大学)

专题命中 其他安全 :alignment(abstract);分类 cs.CL

Comments EMNLP 2024 (main)

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.01765 2024-11-05 cs.CL 57%

Towards Pedagogical LLMs with Supervised Fine Tuning for Computing Education

Alexandra Vassar, Jake Renzella, Emily Ross, Andrew Taylor

机构 * The University of New South Wales(新南威尔士大学)

专题命中 其他安全 :alignment(abstract);分类 cs.CL

Comments 3 pages, 1 table, conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.16229 2024-11-05 cs.CL 57%

Building A Coding Assistant via the Retrieval-Augmented Language Model

Xinze Li, Hanbin Wang, Zhenghao Liu, Shi Yu, Shuo Wang, Yukun Yan, Yukai Fu, Yu Gu, Ge Yu

专题命中 其他安全 :alignment(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.07536 2024-11-05 cs.CV cs.LG 57%

LaB-GATr: geometric algebra transformers for large biomedical surface and volume meshes

Julian Suk, Baris Imre, Jelmer M. Wolterink

机构 * University of Twente(特文特大学)

专题命中 其他安全 :alignment(abstract);分类 cs.LG

Comments First published in "Medical Image Computing and Computer Assisted Intervention" (MICCAI), pp 185-195, 2024 by Springer Nature

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.00168 2024-11-04 cs.HC cs.AI 57%

Creativity in the Age of AI: Evaluating the Impact of Generative AI on Design Outputs and Designers' Creative Thinking

Yue Fu, Han Bin, Tony Zhou, Marx Wang, Yixin Chen, Zelia Gomes Da Costa Lai, Jacob O. Wobbrock, Alexis Hiniker

专题命中 其他安全 :alignment(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.23870 2024-11-01 cs.CR cs.LG 57%

Noise as a Double-Edged Sword: Reinforcement Learning Exploits Randomized Defenses in Neural Networks

Steve Bakos, Pooria Madani, Heidar Davoudi

机构 * Ontario Tech University(安大略理工大学)

专题命中 其他安全 :safety(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.19542 2024-11-01 q-bio.NC cs.AI 57%

Brain-like Functional Organization within Large Language Models

Haiyang Sun, Lin Zhao, Zihao Wu, Xiaohui Gao, Yutao Hu, Mengfei Zuo, Wei Zhang, Junwei Han, Tianming Liu, Xintao Hu

机构 * School of Automation, Northwestern Polytechnical University(西北工业大学自动化学院) School of Computing, University of Georgia(佐治亚大学计算学院) School of Computer and Cyber Sciences, Augusta University(奥古斯塔大学计算机与网络科学学院)

专题命中 其他安全 :alignment(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.22888 2024-10-31 cs.CV cs.CL cs.CR 57%

Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector

Youcheng Huang, Fengbin Zhu, Jingkun Tang, Pan Zhou, Wenqiang Lei, Jiancheng Lv, Tat-Seng Chua

机构 * Sichuan University(四川大学) National University of Singapore(新加坡国立大学) Singapore Management University(新加坡管理大学)

专题命中 其他安全 :safety(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.22459 2024-10-31 cs.AI 57%

Predicting Future Actions of Reinforcement Learning Agents

Stephen Chung, Scott Niekum, David Krueger

机构 * University of Cambridge(剑桥大学) University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校) Mila(米拉研究所)

专题命中 其他安全 :safety(abstract);分类 cs.AI

Comments 16 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.22315 2024-10-30 cs.CL cs.CV 57%

Natural Language Inference Improves Compositionality in Vision-Language Models

Paola Cascante-Bonilla, Yu Hou, Yang Trista Cao, Hal Daumé, Rachel Rudinger

机构 * University of Maryland, College Park(马里兰大学学院公园分校) Stony Brook University(石溪大学) University of Texas at Austin(德克萨斯大学奥斯汀分校)

专题命中 其他安全 :alignment(abstract);分类 cs.CL

Comments Project page: https://cece-vlm.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.12137 2024-10-30 cs.AI 57%

IDs for AI Systems

Alan Chan, Noam Kolt, Peter Wills, Usman Anwar, Christian Schroeder de Witt, Nitarshan Rajkumar, Lewis Hammond, David Krueger, Lennart Heim, Markus Anderljung

专题命中 其他安全 :safety(abstract);分类 cs.AI

Comments Under review; accepted to RegML workshop at NeurIPS 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.20678 2024-10-29 eess.SP cs.LG 57%

A Machine Learning-Driven Wireless System for Structural Health Monitoring

Marius Pop, Mihai Tudose, Daniel Visan, Mircea Bocioaga, Mihai Botan, Cesar Banu, Tiberiu Salaoru

专题命中 其他安全 :safety(abstract);分类 cs.LG

Comments 16 pages, 14 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.16536 2024-10-29 cs.CL 57%

C-LLM: Learn to Check Chinese Spelling Errors Character by Character

Kunting Li, Yong Hu, Liang He, Fandong Meng, Jie Zhou

专题命中 其他安全 :alignment(abstract);分类 cs.CL

Comments Accepted to EMNLP 2024 Main

详情

展开后加载摘要…

URL PDF HTML 收藏
2112.07313 2024-10-28 cs.LG 57%

Autonomous Navigation and Configuration of Integrated Access Backhauling for UAV Base Station Using Reinforcement Learning

Hongyi Zhang, Jingya Li, Zhiqiang Qi, Xingqin Lin, Anders Aronsson, Jan Bosch, Helena Holmström Olsson

专题命中 其他安全 :safety(abstract);分类 cs.LG

Comments This work has been submitted to the IEEE for possible publication

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.19722 2024-10-28 cs.SD cs.LG eess.AS 57%

Temporal Convolution-based Hybrid Model Approach with Representation Learning for Real-Time Acoustic Anomaly Detection

Sahan Dissanayaka, Manjusri Wickramasinghe, Pasindu Marasinghe

专题命中 其他安全 :safety(abstract);分类 cs.LG

Comments 10 pages, 10 figures, ICMLC2024

Journal ref ICMLC'24: Proceedings of the 2024 16th International Conference on Machine Learning and Computing, Pages 218 - 227

详情

展开后加载摘要…

URL PDF HTML 收藏