[0] SEMU-Net: A Segmentation-based Corrector for Fabrication Process Variations of Nanophotonics with Microscopic Images[cs.CV] 标题：SEMU-Net：基于分割的纳光子制造工艺变化的显微镜图像校正器 作者：Rambod Azimi, Yijian Kong, Dusan Gostimirovic, James J. Clark, Odile Liboiron-Ladouceur 链接：http://arxiv.org/abs/2411.16973 备注：Accepted to WACV 2025
[1] D$^2$-World: An Efficient World Model through Decoupled Dynamic Flow[cs.CV] 标题：D$^2$-World：通过解耦动态流的效率世界模型 作者：Haiming Zhang, Xu Yan, Ying Xue, Zixuan Guo, Shuguang Cui, Zhen Li, Bingbing Liu 链接：http://arxiv.org/abs/2411.17027 代码：https://github.com/zhanghm1995/D2-World 备注：The 2nd Place and Innovation Award Solution of Predictive World Model at the CVPR 2024 Autonomous Grand Challenge
[2] LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual Watermarks[cs.CV] 标题：LampMark：基于无训练的地标感知水印的主动深度伪造检测 作者：Tianyi Wang, Mengxiao Huang, Harry Cheng, Xiao Zhang, Zhiqi Shen 链接：http://arxiv.org/abs/2411.17209 备注：Accepted to ACM MM 2024
[3] SAM-MPA: Applying SAM to Few-shot Medical Image Segmentation using Mask Propagation and Auto-prompting[cs.CV] 标题：SAM-MPA：利用掩码传播和自动提示将SAM应用于少量样本医学图像分割 作者：Jie Xu, Xiaokang Li, Chengyu Yue, Yuanyuan Wang, Yi Guo 链接：http://arxiv.org/abs/2411.17363 备注：Accepted as an oral presentation at NeurIPS 2024 AIM-FM Workshop
[4] Dual-Representation Interaction Driven Image Quality Assessment with Restoration Assistance[cs.CV] 标题：双重表示交互驱动的图像质量评估及修复辅助 作者：Jingtong Yue, Xin Lin, Zijiu Yang, Chao Ren 链接：http://arxiv.org/abs/2411.17390 备注：8 pages,6 figures, published to WACV
[5] Adversarial Bounding Boxes Generation (ABBG) Attack against Visual Object Trackers[cs.CV] 标题：对抗性边界框生成（ABBG）攻击面向视觉目标追踪器 作者：Fatemeh Nourilenjan Nokabadi, Jean-Francois Lalonde, Christian Gagné 链接：http://arxiv.org/abs/2411.17468 备注：Accepted in The 3rd New Frontiers in Adversarial Machine Learning (AdvML Frontiers @NeurIPS2024)
[6] Box for Mask and Mask for Box: weak losses for multi-task partially supervised learning[cs.CV] 标题：盒子与盒子中的面具：多任务部分监督学习的弱损失 作者：Hoàng-Ân Lê, Paul Berg, Minh-Tan Pham 链接：http://arxiv.org/abs/2411.17536 代码：https://github.com/lhoangan/multas 备注：Accepted for publishing in BMVC 2024
[7] Modality-Incremental Learning with Disjoint Relevance Mapping Networks for Image-based Semantic Segmentation[cs.CV] 标题：基于断开相关映射网络的模态增量学习在图像语义分割中的应用 作者：Niharika Hegde, Shishir Muralidhara, René Schuster, Didier Stricker 链接：http://arxiv.org/abs/2411.17610 备注：Accepted at WACV 2025
自然语言处理会议: 2篇
[0] "Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks[cs.CL] 标题：道德化多步越狱提示：用于言语攻击的大型语言模型护栏的黑盒测试 作者：Libo Wang 链接：http://arxiv.org/abs/2411.16730 代码：https://github.com/brucewang123456789/GeniusTrail.git 备注：This paper has been submitted to ICLR 2025 BlogPosts and OpenReview preprints. It has 9 pages of text, 4 figures, and 3 tables
[1] Different Bias Under Different Criteria: Assessing Bias in LLMs with a Fact-Based Approach[cs.CL] 标题：不同标准下的不同偏差：基于事实方法的LLMs偏差评估 作者：Changgeon Ko, Jisu Shin, Hoyun Song, Jeongyeon Seo, Jong C. Park 链接：http://arxiv.org/abs/2411.17338 备注：Accepted in NeurIPS 2024 Workshop on Socially Responsible Language Modelling Research (SoLaR)
