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 8017 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 其他安全 8017 篇

2512.24383 2026-01-01 math.AP math.PR 78%

Mean-Field Limits of Deterministic and Stochastic Flocking Models with Nonlinear Velocity Alignment

确定性和随机 flocking 模型的均场极限:非线性速度对齐

Vinh Nguyen, Roman Shvydkoy, Changhui Tan

专题命中 其他安全 :alignment(title,abstract)

AI总结 本文研究了具有非线性速度对齐的 flocking 模型的均场极限,扩展了 Cucker-Smale 理论到非线性框架,并在确定性和随机性情况下提供了收敛率的改进。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.18910 2025-12-23 cs.CV 78%

Delta-LLaVA: Base-then-Specialize Alignment for Token-Efficient Vision-Language Models

Delta-LLaVA: 基于令牌效率的视觉-语言模型对齐方法

Mohamad Zamini, Diksha Shukla

机构 * University of Wyoming(怀俄明大学)

专题命中 其他安全 :alignment(title,abstract)

AI总结 Delta-LLaVA通过低秩Delta投影和轻量级Transformer块实现视觉-语言模型的高效对齐,提升推理速度和训练效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.08930 2025-12-23 cs.CV cs.GR 78%

Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment

Selfi: 通过3D几何特征对齐实现自改进的重建引擎

Youming Deng, Songyou Peng, Junyi Zhang, Kathryn Heal, Tiancheng Sun, John Flynn, Steve Marschner, Lucy Chai

机构 * Cornell University(康奈尔大学) Google(谷歌) UC Berkeley(加州大学伯克利分校)

专题命中 其他安全 :alignment(title,abstract)

AI总结 Selfi通过特征对齐提升3D重建精度,利用VGGT输出作为伪地面真实值,实现NVS和姿态估计的高性能表现。

Comments Project Page: https://denghilbert.github.io/selfi/

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.17154 2025-12-22 cs.SD 78%

InstructDubber: Instruction-based Alignment for Zero-shot Movie Dubbing

InstructDubber:基于指令的零样本电影配音对齐

Zhedong Zhang, Liang Li, Gaoxiang Cong, Chunshan Liu, Yuhan Gao, Xiaowan Wang, Tao Gu, Yuankai Qi

机构 * VIPL group, ICT, CAS(中国科学院信息科技研究所VIPL小组)

专题命中 其他安全 :alignment(title,abstract)

AI总结 InstructDubber通过指令生成和持续时间蒸馏模块,实现鲁棒的领域内和零样本电影配音对齐。

Comments Accepted by AAAI2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.17117 2025-12-22 cs.HC 78%

Alignment, Exploration, and Novelty in Human-AI Interaction

对齐、探索与新颖性在人机交互中的体现

Halfdan Nordahl Fundal, Johannes Eide Rambøll, Karsten Olsen

专题命中 其他安全 :alignment(title,abstract)

AI总结 本研究探讨了人类与AI在协作叙事中的情感对齐、语义探索和创新贡献,发现人类输入在塑造叙事方向和创造性分歧中起关键作用。

Comments 28 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.15080 2025-12-18 cs.RO 78%

NAP3D: NeRF Assisted 3D-3D Pose Alignment for Autonomous Vehicles

NAP3D: 通过NeRF辅助的3D-3D姿态对齐用于自动驾驶车辆

Gaurav Bansal

机构 * MIT THINK Scholars Program(MIT THINK学者计划) Archbishop Mitty High School(阿奇博尔特·米蒂高中)

专题命中 其他安全 :alignment(title,abstract)

AI总结 NAP3D通过NeRF辅助的3D-3D对应关系,提升自动驾驶车辆在长视距下的姿态估计精度,实现优于传统2D-3D方法的鲁棒性。

Comments 10 pages, 5 figures, 2 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.13974 2025-12-17 cs.RO 78%

Autonomous Construction-Site Safety Inspection Using Mobile Robots: A Multilayer VLM-LLM Pipeline

基于移动机器人的自主施工工地安全检查:一种多层VLM-LLM流水线

Hossein Naderi, Alireza Shojaei, Philip Agee, Kereshmeh Afsari, Abiola Akanmu

专题命中 其他安全 :safety(title,abstract)

AI总结 本文提出一种多层VLM-LLM流水线,通过机器人自主导航与人工智能结合,实现施工工地安全检查的自动化报告生成。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13201 2025-12-17 cs.IR 78%

Cog-RAG: Cognitive-Inspired Dual-Hypergraph with Theme Alignment Retrieval-Augmented Generation

Cog-RAG: 基于认知的双超图主题对齐检索增强生成

Hao Hu, Yifan Feng, Ruoxue Li, Rundong Xue, Xingliang Hou, Zhiqiang Tian, Yue Gao, Shaoyi Du

专题命中 其他安全 :alignment(title,abstract)

AI总结 Cog-RAG通过双超图结构和主题对齐策略,提升检索增强生成的语义对齐与生成一致性。

Comments Accepted by AAAI 2026 main conference

Journal ref AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.13169 2025-12-16 cs.MM 78%

Integrated Semantic and Temporal Alignment for Interactive Video Retrieval

集成语义与时间对齐用于交互式视频检索

Thanh-Danh Luu, Le-Vu Nguyen Dinh, Duc-Thien Tran, Duy-Bao Bui, Nam-Tien Le, Tinh-Anh Nguyen Nhu

专题命中 其他安全 :alignment(title,abstract)

AI总结 本文提出集成语义与时间对齐的交互式视频检索框架,通过QUEST和DANTE组件解决复杂现实查询问题,提升视频检索性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.07128 2025-12-16 cs.CV 78%

MulCLIP: A Multi-level Alignment Framework for Enhancing Fine-grained Long-context CLIP

MulCLIP: 一种多级对齐框架,用于增强细粒度长上下文CLIP

Chau Truong, Hieu Ta Quang, Dung D. Le

机构 * FPT Software AI Center(FPT软件人工智能中心) VinUniversity(文大学)

专题命中 其他安全 :alignment(title,abstract)

AI总结 MulCLIP通过多级对齐框架提升细粒度长上下文CLIP的性能,采用标记重建和子描述聚合策略增强语义连接与上下文提取。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.17982 2025-12-15 cs.CV 78%

Few-Shot Learning from Gigapixel Images via Hierarchical Vision-Language Alignment and Modeling

通过层次化视觉-语言对齐和建模实现高像素图像的少样本学习

Bryan Wong, Jong Woo Kim, Huazhu Fu, Mun Yong Yi

机构 * KAIST(韩国科学技术院) IHPC, A*STAR(A*STAR研究院)

专题命中 其他安全 :alignment(title,abstract)

AI总结 HiVE-MIL通过层次化视觉-语言对齐和建模,提升高像素图像的少样本学习性能,实现4.1%的宏F1提升。

Comments Accepted at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.05815 2025-12-08 cs.RO 78%

Optimal Safety-Aware Scheduling for Multi-Agent Aerial 3D Printing with Utility Maximization under Dependency Constraints

多智能体空中3D打印的最优安全意识调度与效用最大化在依赖约束下

Marios-Nektarios Stamatopoulos, Shridhar Velhal, Avijit Banerjee, George Nikolakopoulos

机构 * Robotics and AI Group, Luleå University of Technology(机器人与人工智能组,卢勒奥技术大学)

专题命中 其他安全 :safety(title,abstract)

AI总结 本文提出了一种基于效用最大化的优化框架,用于在依赖约束下实现多智能体空中3D打印的最优安全调度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.16832 2025-12-08 cs.CV 78%

Joint Self-Supervised Video Alignment and Action Segmentation

联合自监督视频对齐与动作分割

Ali Shah Ali, Syed Ahmed Mahmood, Mubin Saeed, Andrey Konin, M. Zeeshan Zia, Quoc-Huy Tran

机构 * Retrocausal, Inc.(Retrocausal公司)

专题命中 其他安全 :alignment(title,abstract)

AI总结 本文提出了一种统一最优传输框架,用于联合自监督视频对齐与动作分割,实现了高效训练和更优的分割性能。

Comments Accepted to ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.04483 2025-12-05 cs.CV 78%

DeRA: Decoupled Representation Alignment for Video Tokenization

DeRA: 解耦表示对齐用于视频标记化

Pengbo Guo, Junke Wang, Zhen Xing, Chengxu Liu, Daoguo Dong, Xueming Qian, Zuxuan Wu

机构 * Xi’an Jiaotong University(西安交通大学) Shanghai Innovation Institute(上海创新研究院) Institute of Trustworthy Embodied AI, Fudan University(复旦大学可信具身人工智能研究院)

专题命中 其他安全 :alignment(title,abstract)

AI总结 DeRA通过解耦时空表示学习,提升视频标记化效率和性能,并在视频生成任务中取得新突破。

详情

展开后加载摘要…

URL PDF HTML 收藏
2305.19478 2025-12-03 cs.CV 78%

Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment

通过无监督帧到段对齐实现感知-aware的动作分割

Quoc-Huy Tran, Ahmed Mehmood, Muhammad Ahmed, Muhammad Naufil, Anas Zafar, Andrey Konin, M. Zeeshan Zia

机构 * Retrocausal, Inc.(Retrocausal公司)

专题命中 其他安全 :alignment(title,abstract)

AI总结 本文提出一种无监督框架,通过帧到段对齐实现感知-aware的动作分割,利用变换器模型和伪标签提升分割性能。

Comments Accepted to WACV 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.20614 2025-11-26 cs.CV 78%

The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment

一致性批评者:通过参考引导的注意对齐纠正生成图像中的不一致

Ziheng Ouyang, Yiren Song, Yaoli Liu, Shihao Zhu, Qibin Hou, Ming-Ming Cheng, Mike Zheng Shou

机构 * VCIP, Nankai University Show Lab, National University of Singapore State Key Laboratory of CAD\&CG, Zhejiang University

专题命中 其他安全 :alignment(title,abstract)

AI总结 本文提出ImageCritic,通过参考引导的注意力对齐方法纠正生成图像中的不一致问题,提升细粒度细节的一致性。

Comments Project page: https://ouyangziheng.github.io/ImageCritic-Page/

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13909 2025-11-19 cs.CV 78%

Mind the Gap: Evaluating LLM Understanding of Human-Taught Road Safety Principles

Chalamalasetti Kranti

机构 * uni-potsdam(波恩大学)

专题命中 其他安全 :safety(title,abstract)

Comments Preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06009 2025-11-19 cs.CV 78%

Continual Learning for Image Captioning through Improved Image-Text Alignment

Bertram Taetz, Gal Bordelius

机构 * IT & Engineering International University of Applied Sciences(IT与工程国际应用科学大学)

专题命中 其他安全 :alignment(title,abstract)

Comments 11 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.07334 2025-11-17 cs.CV 78%

Unleashing the Potential of Large Language Models for Text-to-Image Generation through Autoregressive Representation Alignment

Xing Xie, Jiawei Liu, Ziyue Lin, Huijie Fan, Zhi Han, Yandong Tang, Liangqiong Qu

专题命中 其他安全 :alignment(title,abstract)

Comments Accepted by AAAI 2026 Oral

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.10334 2025-11-14 cs.CV 78%

Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment

Wenti Yin, Huaxin Zhang, Xiang Wang, Yuqing Lu, Yicheng Zhang, Bingquan Gong, Jialong Zuo, Li Yu, Changxin Gao, Nong Sang

专题命中 其他安全 :alignment(title,abstract)

Comments Accepted to AAAI 2026. Code is available at https://github.com/lessiYin/DSANet

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.10211 2025-11-14 cs.CV 78%

HeatV2X: Scalable Heterogeneous Collaborative Perception via Efficient Alignment and Interaction

Yueran Zhao, Zhang Zhang, Chao Sun, Tianze Wang, Chao Yue, Nuoran Li

机构 * Beijing Institute of Technology(北京理工大学)

专题命中 其他安全 :alignment(title,abstract)

Comments 10 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.04601 2025-11-07 cs.CV cs.MM 78%

PixCLIP: Achieving Fine-grained Visual Language Understanding via Any-granularity Pixel-Text Alignment Learning

Yicheng Xiao, Yu Chen, Haoxuan Ma, Jiale Hong, Caorui Li, Lingxiang Wu, Haiyun Guo, Jinqiao Wang

专题命中 其他安全 :alignment(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.19739 2025-11-04 cs.CV 78%

FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion

Pihai Sun, Junjun Jiang, Yuanqi Yao, Youyu Chen, Wenbo Zhao, Kui Jiang, Xianming Liu

机构 * Faculty of Computing, Harbin Institute of Technology(计算机学院,哈尔滨工业大学) Zhengzhou Research Institute, Harbin Institute of Technology(郑州研究院,哈尔滨工业大学)

专题命中 其他安全 :alignment(title,abstract)

Comments [IROS 2025, camera ready version]: 8 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.26580 2025-10-31 cs.CV 78%

Dynamic Context-Aware Scene Reasoning Using Vision-Language Alignment in Zero-Shot Real-World Scenarios

Manjunath Prasad Holenarasipura Rajiv, B. M. Vidyavathi

专题命中 其他安全 :alignment(title,abstract)

Comments Preprint under review at IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.26464 2025-10-31 cs.CV 78%

Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detection

Yuanting Fan, Jun Liu, Xiaochen Chen, Bin-Bin Gao, Jian Li, Yong Liu, Jinlong Peng, Chengjie Wang

机构 * Tencent Youtu Lab(腾讯优图实验室)

专题命中 其他安全 :alignment(title,abstract)

Comments 12 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.05696 2025-10-31 cs.CV 78%

MoralCLIP: Contrastive Alignment of Vision-and-Language Representations with Moral Foundations Theory

Ana Carolina Condez, Diogo Tavares, João Magalhães

机构 * NOVA LINCS, NOVA School of Science and Technology(NOVA LINCS,NOVA科学与技术学院)

专题命中 其他安全 :alignment(title,abstract)

Comments Updated version: corresponds to the ACM MM '25 published paper and includes full appendix material

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.11194 2025-10-27 cs.CE 78%

Prot2Text-V2: Protein Function Prediction with Multimodal Contrastive Alignment

Xiao Fei, Michail Chatzianastasis, Sarah Almeida Carneiro, Hadi Abdine, Lawrence P. Petalidis, Michalis Vazirgiannis

专题命中 其他安全 :alignment(title,abstract)

Comments 24 pages, 11 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.12718 2025-10-23 cs.CV cs.MM 78%

ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding

Zhenxing Zhang, Yaxiong Wang, Lechao Cheng, Zhun Zhong, Dan Guo, Meng Wang

机构 * School of Computer Science and Information Engineering, Hefei University of Technology, China(计算机科学与信息工程学院,合肥工业大学,中国) Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, China(人工智能研究所,合肥综合性国家科学中心,中国)

专题命中 其他安全 :alignment(title,abstract)

Comments 12 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.14359 2025-10-22 cs.CV 78%

Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable

Ruoxin Chen, Junwei Xi, Zhiyuan Yan, Ke-Yue Zhang, Shuang Wu, Jingyi Xie, Xu Chen, Lei Xu, Isabel Guan, Taiping Yao, Shouhong Ding

机构 * Tencent YouTu Lab(腾讯优图实验室) East China University of Science and Technology(东华大学) Peking University(北京大学) Renmin University of China(中国人民大学) Shenzhen University(深圳大学) Hong Kong University of Science and Technology(香港科技大学)

专题命中 其他安全 :alignment(title,abstract)

Comments NeurIPS 2025 Spotlight. 13 Pages, 10 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17598 2025-10-21 cs.AI cs.CL cs.LG 78%

Reasoning Distillation and Structural Alignment for Improved Code Generation

Amir Jalilifard, Anderson de Rezende Rocha, Marcos Medeiros Raimundo

机构 * Universidade Estadual de Campinas(坎皮纳斯州立大学)

专题命中 其他安全 :alignment(title);分类 cs.CL、cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏