Skip to main content
CenXiv.org
This website is in trial operation, support us!
We gratefully acknowledge support from all contributors.
Contribute
Donate
cenxiv logo > cs

Help | Advanced Search

Computer Science

Authors and titles for recent submissions

  • Mon, 22 Sep 2025
  • Fri, 19 Sep 2025
  • Thu, 18 Sep 2025
  • Wed, 17 Sep 2025
  • Tue, 16 Sep 2025

See today's new changes

Total of 3114 entries : 1-50 51-100 101-150 151-200 ... 3101-3114
Showing up to 50 entries per page: fewer | more | all

Mon, 22 Sep 2025 (showing first 50 of 543 entries )

[1] arXiv:2509.16203 [cn-pdf, pdf, html, other]
Title: Inverting Trojans in LLMs
Title: 反转大模型中的特洛伊木马
Zhengxing Li, Guangmingmei Yang, Jayaram Raghuram, David J. Miller, George Kesidis
Subjects: Machine Learning (cs.LG)
[2] arXiv:2509.16198 [cn-pdf, pdf, html, other]
Title: RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
Title: RPG:用于统一和可扩展代码库生成的仓库规划图
Jane Luo, Xin Zhang, Steven Liu, Jie Wu, Yiming Huang, Yangyu Huang, Chengyu Yin, Ying Xin, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Qi Chen, Scarlett Li, Mao Yang
Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI) ; Software Engineering (cs.SE)
[3] arXiv:2509.16197 [cn-pdf, pdf, html, other]
Title: MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
Title: MANZANO:具有混合视觉分词器的简单且可扩展的统一多模态模型
Yanghao Li, Rui Qian, Bowen Pan, Haotian Zhang, Haoshuo Huang, Bowen Zhang, Jialing Tong, Haoxuan You, Xianzhi Du, Zhe Gan, Hyunjik Kim, Chao Jia, Zhenbang Wang, Yinfei Yang, Mingfei Gao, Zi-Yi Dou, Wenze Hu, Chang Gao, Dongxu Li, Philipp Dufter, Zirui Wang, Guoli Yin, Zhengdong Zhang, Chen Chen, Yang Zhao, Ruoming Pang, Zhifeng Chen
Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL) ; Machine Learning (cs.LG)
[4] arXiv:2509.16195 [cn-pdf, pdf, html, other]
Title: FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation
Title: FocalCodec-Stream:通过因果蒸馏实现低比特率语音编码的流式传输
Luca Della Libera, Cem Subakan, Mirco Ravanelli
Comments: 5 pages, 1 figure
Subjects: Sound (cs.SD) ; Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG) ; Audio and Speech Processing (eess.AS)
[5] arXiv:2509.16194 [cn-pdf, pdf, html, other]
Title: Clustering with Set Outliers and Applications in Relational Clustering
Title: 带有集合异常值的聚类及其在关系聚类中的应用
Vaishali Surianarayanan, Neeraj Kumar, Stavros Sintos
Subjects: Data Structures and Algorithms (cs.DS) ; Databases (cs.DB)
[6] arXiv:2509.16189 [cn-pdf, pdf, html, other]
Title: Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences
Title: 潜在学习:情景记忆通过促进经验的灵活再利用来补充参数学习
Andrew Kyle Lampinen, Martin Engelcke, Yuxuan Li, Arslan Chaudhry, James L. McClelland
Subjects: Machine Learning (cs.LG) ; Computation and Language (cs.CL)
[7] arXiv:2509.16188 [cn-pdf, pdf, html, other]
Title: CultureScope: A Dimensional Lens for Probing Cultural Understanding in LLMs
Title: 文化范围:用于探测大语言模型文化理解的维度透镜
Jinghao Zhang, Sihang Jiang, Shiwei Guo, Shisong Chen, Yanghua Xiao, Hongwei Feng, Jiaqing Liang, Minggui HE, Shimin Tao, Hongxia Ma
Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI)
[8] arXiv:2509.16187 [cn-pdf, pdf, html, other]
Title: MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair
Title: MatchFixAgent:语言无关的自主仓库级代码翻译验证与修复
Ali Reza Ibrahimzada, Brandon Paulsen, Reyhaneh Jabbarvand, Joey Dodds, Daniel Kroening
Subjects: Software Engineering (cs.SE) ; Machine Learning (cs.LG)
[9] arXiv:2509.16180 [cn-pdf, pdf, html, other]
Title: Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph
Title: 通过Scheffe图进行查询高效的局部私有假设选择
Gautam Kamath, Alireza F. Pour, Matthew Regehr, David P. Woodruff
Subjects: Data Structures and Algorithms (cs.DS) ; Machine Learning (cs.LG) ; Machine Learning (stat.ML)
[10] arXiv:2509.16179 [cn-pdf, pdf, html, other]
Title: Fast OTSU Thresholding Using Bisection Method
Title: 快速使用二分法的OTSU阈值处理
Sai Varun Kodathala
Comments: 12 pages, 7 tables
Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) ; Numerical Analysis (math.NA)
[11] arXiv:2509.16176 [cn-pdf, pdf, html, other]
Title: Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories
Title: 代理式空中摄影:从对话线索到电影轨迹
Yifan Lin, Sophie Ziyu Liu, Ran Qi, George Z. Xue, Xinping Song, Chao Qin, Hugh H.-T. Liu
Subjects: Robotics (cs.RO)
[12] arXiv:2509.16173 [cn-pdf, pdf, html, other]
Title: DIVEBATCH: Accelerating Model Training Through Gradient-Diversity Aware Batch Size Adaptation
Title: DIVEBATCH:通过梯度多样性感知的批量大小自适应加速模型训练
Yuen Chen, Yian Wang, Hari Sundaram
Subjects: Machine Learning (cs.LG)
[13] arXiv:2509.16172 [cn-pdf, pdf, html, other]
Title: Two Optimizations on the Stålmarck Procedure
Title: 对Stålmarck过程的两种优化
Sergei Leonov, Liam Davis
Comments: Presented at the FMCAD 2025 Student Forum. Not part of the official FMCAD proceedings
Subjects: Logic in Computer Science (cs.LO)
[14] arXiv:2509.16171 [cn-pdf, pdf, html, other]
Title: Analyzing and improving a classical Betti number estimation algorithm
Title: 分析和改进经典的贝蒂数估计算法
Julien Sorci
Subjects: Data Structures and Algorithms (cs.DS) ; Discrete Mathematics (cs.DM) ; Quantum Physics (quant-ph)
[15] arXiv:2509.16170 [cn-pdf, pdf, html, other]
Title: UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation
Title: UniMRSeg:通过分层自监督补偿的统一模态放松分割
Xiaoqi Zhao, Youwei Pang, Chenyang Yu, Lihe Zhang, Huchuan Lu, Shijian Lu, Georges El Fakhri, Xiaofeng Liu
Comments: Accepted by NeurIPS 2025
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[16] arXiv:2509.16163 [cn-pdf, pdf, html, other]
Title: Robust Vision-Language Models via Tensor Decomposition: A Defense Against Adversarial Attacks
Title: 通过张量分解的鲁棒视觉-语言模型:对抗攻击的防御
Het Patel, Muzammil Allie, Qian Zhang, Jia Chen, Evangelos E. Papalexakis
Comments: To be presented as a poster at the Workshop on Safe and Trustworthy Multimodal AI Systems (SafeMM-AI), 2025
Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL)
[17] arXiv:2509.16158 [cn-pdf, pdf, other]
Title: Designing Culturally Aligned AI Systems For Social Good in Non-Western Contexts
Title: 为非西方背景设计文化一致的AI系统以促进社会福祉
Deepak Varuvel Dennison, Mohit Jain, Tanuja Ganu, Aditya Vashistha
Subjects: Human-Computer Interaction (cs.HC)
[18] arXiv:2509.16157 [cn-pdf, pdf, other]
Title: Strategic Analysis of Just-In-Time Liquidity Provision in Concentrated Liquidity Market Makers
Title: 集中流动性做市商的即时流动性提供战略分析
Bruno Llacer Trotti, Weizhao Tang, Rachid El-Azouzi, Giulia Fanti, Daniel Sadoc Menasche
Comments: Advances in Financial Technologies 2025 (AFT 2025), Pittsburgh, USA
Subjects: Computer Science and Game Theory (cs.GT) ; Cryptography and Security (cs.CR)
[19] arXiv:2509.16151 [cn-pdf, pdf, html, other]
Title: Automated Cyber Defense with Generalizable Graph-based Reinforcement Learning Agents
Title: 基于通用图的强化学习代理的自动化网络防御
Isaiah J. King, Benjamin Bowman, H. Howie Huang
Subjects: Machine Learning (cs.LG) ; Cryptography and Security (cs.CR)
[20] arXiv:2509.16149 [cn-pdf, pdf, html, other]
Title: Pointing to a Llama and Call it a Camel: On the Sycophancy of Multimodal Large Language Models
Title: 指向一只羊驼并称其为骆驼:关于多模态大语言模型的谄媚性
Renjie Pi, Kehao Miao, Li Peihang, Runtao Liu, Jiahui Gao, Jipeng Zhang, Xiaofang Zhou
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[21] arXiv:2509.16146 [cn-pdf, pdf, html, other]
Title: Implicit Communication in Linear Quadratic Gaussian Control Systems
Title: 线性二次高斯控制系统中的隐式通信
Gongpu Chen, Deniz Gunduz
Comments: 27 pages, 3 figures
Subjects: Information Theory (cs.IT)
[22] arXiv:2509.16145 [cn-pdf, pdf, html, other]
Title: Modeling Elastic-Body Dynamics of Fish Swimming Using a Variational Framework
Title: 使用变分框架对鱼类游泳的弹性体动力学进行建模
Zhiheng Chen, Wei Wang
Comments: Under review at IEEE Robotics and Automation Letters (RA-L)
Subjects: Robotics (cs.RO)
[23] arXiv:2509.16143 [cn-pdf, pdf, html, other]
Title: On the Structural Parameterizations of 2-Club with Triangle Constraints
Title: 关于带有三角形约束的2-俱乐部的结构参数化
Ashwin Jacob, Diptapriyo Majumdar, Raghav Sakhuja
Comments: 1 figure, 31 pages
Subjects: Data Structures and Algorithms (cs.DS) ; Discrete Mathematics (cs.DM)
[24] arXiv:2509.16141 [cn-pdf, pdf, html, other]
Title: AcT2I: Evaluating and Improving Action Depiction in Text-to-Image Models
Title: AcT2I:评估和改进文本到图像模型中的动作描述
Vatsal Malaviya, Agneet Chatterjee, Maitreya Patel, Yezhou Yang, Chitta Baral
Comments: Project Page : https://vatsal-malaviya.github.io/AcT2I/
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[25] arXiv:2509.16140 [cn-pdf, pdf, html, other]
Title: When Bugs Linger: A Study of Anomalous Resolution Time Outliers and Their Themes
Title: 当错误持续存在:异常解决时间异常值及其主题的研究
Avinash Patil
Comments: 7 pages, 2 tables, 21 figures
Subjects: Software Engineering (cs.SE) ; Machine Learning (cs.LG)
[26] arXiv:2509.16139 [cn-pdf, pdf, html, other]
Title: Spatio-temporal, multi-field deep learning of shock propagation in meso-structured media
Title: 跨时空多场深度学习在介观结构介质中冲击传播的分析
M. Giselle Fernández-Godino, Meir H. Shachar, Kevin Korner, Jonathan L. Belof, Mukul Kumar, Jonathan Lind, William J. Schill
Comments: 16 pages, 10 figures
Subjects: Machine Learning (cs.LG)
[27] arXiv:2509.16136 [cn-pdf, pdf, html, other]
Title: Reward Evolution with Graph-of-Thoughts: A Bi-Level Language Model Framework for Reinforcement Learning
Title: 基于思维图的奖励演化:一种双层语言模型框架用于强化学习
Changwei Yao, Xinzi Liu, Chen Li, Marios Savvides
Subjects: Robotics (cs.RO)
[28] arXiv:2509.16135 [cn-pdf, pdf, html, other]
Title: Constant time enumeration of perfect bipartite matchings
Title: 完美二部图匹配的常数时间枚举
Jiří Fink
Comments: 40 pages, 6 figures
Subjects: Data Structures and Algorithms (cs.DS)
[29] arXiv:2509.16134 (cross-list from eess.SY) [cn-pdf, pdf, html, other]
Title: Polymatroidal Representations of Aggregate EV Flexibility Considering Network Constraints
Title: 聚合电动汽车灵活性的多子模表示方法考虑网络约束
Karan Mukhi, Alessandro Abate
Subjects: Systems and Control (eess.SY)
[30] arXiv:2509.16132 [cn-pdf, pdf, html, other]
Title: Recovering Parametric Scenes from Very Few Time-of-Flight Pixels
Title: 从非常少的飞行时间像素中恢复参数化场景
Carter Sifferman, Yiquan Li, Yiming Li, Fangzhou Mu, Michael Gleicher, Mohit Gupta, Yin Li
Comments: ICCV 2025
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[31] arXiv:2509.16131 [cn-pdf, pdf, html, other]
Title: Dynamic Classifier-Free Diffusion Guidance via Online Feedback
Title: 通过在线反馈的动态无分类器扩散指导
Pinelopi Papalampidi, Olivia Wiles, Ira Ktena, Aleksandar Shtedritski, Emanuele Bugliarello, Ivana Kajic, Isabela Albuquerque, Aida Nematzadeh
Subjects: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV)
[32] arXiv:2509.16129 [cn-pdf, pdf, html, other]
Title: Learning the Influence Graph of a Markov Process that Randomly Resets to Past
Title: 学习随机重置到过去的马尔可夫过程的影响图
Sudharsan Senthil, Avhishek Chatterjee
Comments: Sample complexity proof included
Subjects: Information Theory (cs.IT)
[33] arXiv:2509.16128 [cn-pdf, pdf, html, other]
Title: AnchoredAI: Contextual Anchoring of AI Comments Improves Writer Agency and Ownership
Title: AnchoredAI:AI评论的上下文锚定提高了作者的自主权和所有权
Martin Lou, Jackie Crowley, Samuel Dodson, Dongwook Yoon
Subjects: Human-Computer Interaction (cs.HC)
[34] arXiv:2509.16127 [cn-pdf, pdf, html, other]
Title: BaseReward: A Strong Baseline for Multimodal Reward Model
Title: BaseReward:一种多模态奖励模型的强基线
Yi-Fan Zhang, Haihua Yang, Huanyu Zhang, Yang Shi, Zezhou Chen, Haochen Tian, Chaoyou Fu, Haotian Wang, Kai Wu, Bo Cui, Xu Wang, Jianfei Pan, Haotian Wang, Zhang Zhang, Liang Wang
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[35] arXiv:2509.16126 [cn-pdf, pdf, html, other]
Title: Network-Based Detection of Autism Spectrum Disorder Using Sustainable and Non-invasive Salivary Biomarkers
Title: 基于网络的自闭症谱系障碍检测:使用可持续且非侵入性唾液生物标志物
Janayna M. Fernandes, Robinson Sabino-Silva, Murillo G. Carneiro
Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI)
[36] arXiv:2509.16122 [cn-pdf, pdf, html, other]
Title: Efficient Detection of Objects Near a Robot Manipulator via Miniature Time-of-Flight Sensors
Title: 通过微型飞行时间传感器高效检测机器人机械臂附近的物体
Carter Sifferman, Mohit Gupta, Michael Gleicher
Subjects: Robotics (cs.RO)
[37] arXiv:2509.16119 [cn-pdf, pdf, html, other]
Title: RadarGaussianDet3D: An Efficient and Effective Gaussian-based 3D Detector with 4D Automotive Radars
Title: RadarGaussianDet3D:一种基于高斯的高效且有效的三维检测器,适用于四维汽车雷达
Weiyi Xiong, Bing Zhu, Tao Huang, Zewei Zheng
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[38] arXiv:2509.16117 [cn-pdf, pdf, html, other]
Title: DiffusionNFT: Online Diffusion Reinforcement with Forward Process
Title: DiffusionNFT:带有前向过程的在线扩散强化
Kaiwen Zheng, Huayu Chen, Haotian Ye, Haoxiang Wang, Qinsheng Zhang, Kai Jiang, Hang Su, Stefano Ermon, Jun Zhu, Ming-Yu Liu
Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV)
[39] arXiv:2509.16114 (cross-list from eess.SY) [cn-pdf, pdf, html, other]
Title: Real-Time Thermal State Estimation and Forecasting in Laser Powder Bed Fusion
Title: 实时热状态估计与预测在激光粉末床熔融中的应用
Yukta Pareek, Abdul Malik Al Mardhouf Al Saadi, Amrita Basak, Satadru Dey
Subjects: Systems and Control (eess.SY)
[40] arXiv:2509.16112 [cn-pdf, pdf, html, other]
Title: CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion
Title: CodeRAG:为检索增强的仓库级代码补全寻找相关且必要的知识
Sheng Zhang, Yifan Ding, Shuquan Lian, Shun Song, Hui Li
Comments: EMNLP 2025
Subjects: Computation and Language (cs.CL) ; Information Retrieval (cs.IR) ; Software Engineering (cs.SE)
[41] arXiv:2509.16107 [cn-pdf, pdf, html, other]
Title: It Depends: Resolving Referential Ambiguity in Minimal Contexts with Commonsense Knowledge
Title: 它取决于:使用常识知识解决最小上下文中的指代歧义
Lukas Ellinger, Georg Groh
Comments: Accepted by UncertaiNLP workshop @ EMNLP 2025
Subjects: Computation and Language (cs.CL)
[42] arXiv:2509.16105 [cn-pdf, pdf, html, other]
Title: DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning
Title: DiEP:通过可微专家剪枝的自适应专家混合压缩
Sikai Bai, Haoxi Li, Jie Zhang, Zicong Hong, Song Guo
Comments: 18 pages
Subjects: Computation and Language (cs.CL)
[43] arXiv:2509.16101 [cn-pdf, pdf, html, other]
Title: Personalized Federated Learning with Heat-Kernel Enhanced Tensorized Multi-View Clustering
Title: 带有热核增强张量化多视图聚类的个性化联邦学习
Kristina P. Sinaga
Comments: 26 pages, 3 algorithms, and 3 figures
Subjects: Machine Learning (cs.LG) ; Distributed, Parallel, and Cluster Computing (cs.DC)
[44] arXiv:2509.16098 [cn-pdf, pdf, html, other]
Title: SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Features
Title: SegDINO3D:结合图像级和物体级2D特征的3D实例分割
Jinyuan Qu, Hongyang Li, Xingyu Chen, Shilong Liu, Yukai Shi, Tianhe Ren, Ruitao Jing, Lei Zhang
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[45] arXiv:2509.16095 [cn-pdf, pdf, html, other]
Title: AdaSports-Traj: Role- and Domain-Aware Adaptation for Multi-Agent Trajectory Modeling in Sports
Title: AdaSports-Traj:体育中多智能体轨迹建模的角色和领域感知适应
Yi Xu, Yun Fu
Comments: Accepted by ICDM 2025
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[46] arXiv:2509.16093 [cn-pdf, pdf, html, other]
Title: Beyond Pointwise Scores: Decomposed Criteria-Based Evaluation of LLM Responses
Title: 超越逐点评分:分解标准的LLM响应评估
Fangyi Yu, Nabeel Seedat, Dasha Herrmannova, Frank Schilder, Jonathan Richard Schwarz
Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI)
[47] arXiv:2509.16091 [cn-pdf, pdf, html, other]
Title: Blind-Spot Guided Diffusion for Self-supervised Real-World Denoising
Title: 盲点引导的扩散用于自监督的真实世界去噪
Shen Cheng, Haipeng Li, Haibin Huang, Xiaohong Liu, Shuaicheng Liu
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[48] arXiv:2509.16088 [cn-pdf, pdf, html, other]
Title: Randomized Smoothing Meets Vision-Language Models
Title: 随机平滑与视觉-语言模型
Emmanouil Seferis, Changshun Wu, Stefanos Kollias, Saddek Bensalem, Chih-Hong Cheng
Comments: EMNLP'25 full version, including appendix (proofs, additional experiments)
Subjects: Machine Learning (cs.LG)
[49] arXiv:2509.16087 [cn-pdf, pdf, html, other]
Title: See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model
Title: See&Trek:面向多模态大语言模型的无训练空间提示方法
Pengteng Li, Pinhao Song, Wuyang Li, Weiyu Guo, Huizai Yao, Yijie Xu, Dugang Liu, Hui Xiong
Comments: Accepted by NeurIPS 2025
Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI)
[50] arXiv:2509.16084 [cn-pdf, pdf, html, other]
Title: Rethinking Molecule Synthesizability with Chain-of-Reaction
Title: 用反应链重新思考分子可合成性
Seul Lee, Karsten Kreis, Srimukh Prasad Veccham, Meng Liu, Danny Reidenbach, Saee Paliwal, Weili Nie, Arash Vahdat
Subjects: Machine Learning (cs.LG)
Total of 3114 entries : 1-50 51-100 101-150 151-200 ... 3101-3114
Showing up to 50 entries per page: fewer | more | all
  • About
  • Help
  • contact arXivClick here to contact arXiv Contact
  • subscribe to arXiv mailingsClick here to subscribe Subscribe
  • Copyright
  • Privacy Policy
  • Web Accessibility Assistance
  • arXiv Operational Status
    Get status notifications via email or slack

京ICP备2025123034号