Jailbreaking on Text-to-Video Models via Scene Splitting Strategy
通过场景分割策略对文本到视频模型进行劫持
Wonjun Lee, Haon Park, Doehyeon Lee, Bumsub Ham, Suhyun Kim
机构
*
Yonsei University(延世大学)
;
Korea Institute of Science and Technology(韩国科学技术院)
;
AIM Intelligence(AIM智能)
;
Seoul National University(首尔国立大学)
;
Kyung Hee University(庆熙大学)
机构
*
School of Physics Science and Technology, Beijing University of Posts and Telecommunications(北京邮电大学物理科学与技术学院)
;
Guangdong Institute of Intelligence Science and Technology(广东智能科学技术研究院)
;
Beijing Chaoyang Hospital, Capital Medical University(北京朝阳医院)
;
Sleep Medical Center, Huzhou Third Municipal Hospital, Affiliated Hospital of Wenzhou Medical University(湖州第三人民医院睡眠医学中心,温州医科大学附属医院)
;
University of Macau(澳门大学)
;
Renyixun Health Technology Co., Ltd(仁颐讯健康科技有限公司)
;
Academy for Advanced Interdisciplinary Studies, Peking University(北京大学交叉学科研究院)
Eunsu Baek, Sunghwan Han, Taesik Gong, Hyung-Sin Kim
机构
*
Graduate School of Data Science(数据科学研究生院)
;
Seoul National University(首尔国立大学)
;
Department of Computer Science & Engineering(计算机科学与工程系)
;
Seogang University(世宗大学)
;
Ulsan National Institute of Science and Technology(乌山国立科学技术研究院)
DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics
DiffWind: 基于物理的可微风驱物体动力学建模
Yuanhang Lei, Boming Zhao, Zesong Yang, Xingxuan Li, Tao Cheng, Haocheng Peng, Ru Zhang, Yang Yang, Siyuan Huang, Yujun Shen, Ruizhen Hu, Hujun Bao, Zhaopeng Cui
机构
*
State Key Laboratory of CAD & CG(CAD与计算机图形学国家重点实验室)
;
State Key Laboratory of General Artificial Intelligence(通用人工智能国家重点实验室)
;
Ant Group(蚂蚁集团)
;
Shenzhen University(深圳大学)
Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning
在可以的时候使用在线网络:迈向快速且稳定的强化学习
Ahmed Hendawy, Henrik Metternich, Théo Vincent, Mahdi Kallel, Jan Peters, Carlo D'Eramo
机构
*
Technical University of Darmstadt(德累斯顿技术大学)
;
German Research Center for AI (DFKI)(德国人工智能研究中心(DFKI))
;
Robotics Institute Germany (RIG)(德国机器人研究所(RIG))
;
University of Würzburg(弗赖堡大学)
New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions
零阶硬阈值化中方差减少的新见解:缓解梯度误差和扩张性矛盾
Xinzhe Yuan, William de Vazelhes, Bin Gu, Huan Xiong
机构
*
IASM, Harbin Institute of Technology(哈尔滨工业大学人工智能研究所,哈尔滨工业大学)
;
Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
;
School of Artificial Intelligence, Jilin University(吉林大学人工智能学院)
CommentsPublished as a conference paper at ICLR 2024. 9 pages main paper, 24 pages appendix, 11 figures, 7 tables. Correspondence to Bin Gu and Huan Xiong
Journal refInternational Conference on Learning Representations (ICLR), 2024
CommentsA preliminary conference version is accepted at ICLR 2026. This full version includes the formal statements of lower bounds and their proofs. v3: fixed some typos
Parameterized Hardness of Zonotope Containment and Neural Network Verification
参数化的Zonotope包含与神经网络验证的难度
Vincent Froese, Moritz Grillo, Christoph Hertrich, Moritz Stargalla
机构
*
Technische Universität Berlin(柏林技术大学)
;
Max Planck Institute for Mathematics in the Sciences(马克斯·普朗克数学研究所)
;
University of Technology Nuremberg(纽伦堡技术大学)
Accelerating Inference for Multilayer Neural Networks with Quantum Computers
利用量子计算机加速多层神经网络推理
Arthur G. Rattew, Po-Wei Huang, Naixu Guo, Lirandë Pira, Patrick Rebentrost
机构
*
Department of Materials, University of Oxford(牛津大学材料系)
;
Mathematical Institute, University of Oxford(牛津大学数学研究所)
;
Quantum Motion(Quantum Motion公司)
;
Centre for Quantum Technologies, National University of Singapore(新加坡国立大学量子中心)
;
Department of Computer Science, National University of Singapore(新加坡国立大学计算机科学系)