图像生成 - arXivDaily 专题

2506.16655 2025-06-23 cs.CL 50%

Arch-Router: Aligning LLM Routing with Human Preferences

Co Tran, Salman Paracha, Adil Hafeez, Shuguang Chen

机构 * Katanemo Labs, Inc.（Katanemo实验室）

专题命中图像生成评测：image editing(abstract)

2506.15903 2025-06-23 cs.LG 50%

VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics

Josef Kuchař, Marek Kadlčík, Michal Spiegel, Michal Štefánik

机构 * Kempelen Institute of Intelligent Technologies（智能技术研究所）； Language Technology, University of Helsinki（语言技术，赫尔辛基大学）

专题命中图像生成评测：image editing(abstract)

2211.05894 2025-06-17 math.PR math.AP math.SP 50%

Spectral bounds for exit times on metric measure Dirichlet spaces and applications

Phanuel Mariano, Jing Wang

专题命中图像生成评测：diffusion(abstract)

Comments 34 pages. Published in Stochastic Processes and their Applications

2506.10502 2025-06-13 cs.CR cs.LG 50%

A Crack in the Bark: Leveraging Public Knowledge to Remove Tree-Ring Watermarks

Junhua Lin, Marc Juarez

机构 * University of Edinburgh（爱丁堡大学）

专题命中图像生成评测：diffusion(abstract)

Comments 18 pages, to be published in the 34th USENIX Security Symposium

2506.08844 2025-06-11 cs.LG cs.CE 50%

IMAGIC-500: IMputation benchmark on A Generative Imaginary Country (500k samples)

Siyi Sun, David Antony Selby, Yunchuan Huang, Sebastian Vollmer, Seth Flaxman, Anisoara Calinescu

机构 * University of Oxford（牛津大学）； German Research Center for Artificial Intelligence（德国人工智能研究中心）

专题命中图像生成评测：diffusion(abstract)

2408.13805 2025-06-05 cs.LG 50%

Prior Learning in Introspective VAEs

Ioannis Athanasiadis, Fredrik Lindsten, Michael Felsberg

专题命中图像生成评测：image generation(abstract)

2412.00639 2025-06-03 cs.IR cs.DB 50%

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries

Mahdi Erfanian, Mohsen Dehghankar, Abolfazl Asudeh

专题命中图像生成评测：text-to-image(abstract)

2505.24418 2025-06-02 math.AP 50%

Front propagation on a general metric graph

Hiroshi Matano, Shuichi Jimbo

专题命中图像生成评测：diffusion(abstract)

Comments 47 pages, 17 figures

2505.23245 2025-05-30 math.NA cs.NA 50%

A posteriori error estimates and adaptivity for locally conservative methods. Inexpensive implementation and evaluation, polytopal meshes, iterative linearization and algebraic solvers, and applications to complex porous media flows

Martin Vohralík, Soleiman Yousef

专题命中图像生成评测：diffusion(abstract)

2505.09609 2025-05-29 math.ST math.MG stat.ME stat.TH 50%

Robust Representation and Estimation of Barycenters and Modes of Probability Measures on Metric Spaces

Washington Mio, Tom Needham

专题命中图像生成评测：diffusion(abstract)

Comments V2: Small edits

2505.17434 2025-05-26 cs.RO cs.AI 50%

Dynamic Manipulation of Deformable Objects in 3D: Simulation, Benchmark and Learning Strategy

Guanzhou Lan, Yuqi Yang, Anup Teejo Mathew, Feiping Nie, Rong Wang, Xuelong Li, Federico Renda, Bin Zhao

机构 * Northwestern Polytechnical University（西北工业大学）； Khalifa University（卡利法大学）； TeleAI

专题命中图像生成评测：diffusion(abstract)

Comments 11 pages,

2504.08859 2025-05-23 cond-mat.soft cs.AI 50%

PolyConf: Unlocking Polymer Conformation Generation through Hierarchical Generative Models

Fanmeng Wang, Wentao Guo, Qi Ou, Hongshuai Wang, Haitao Lin, Hongteng Xu, Zhifeng Gao

专题命中图像生成评测：diffusion(abstract)

Comments Accepted by the 42nd International Conference on Machine Learning (ICML 2025)

2505.13840 2025-05-21 cs.CL cs.AI cs.LG 50%

EfficientLLM: Efficiency in Large Language Models

Zhengqing Yuan, Weixiang Sun, Yixin Liu, Huichi Zhou, Rong Zhou, Yiyang Li, Zheyuan Zhang, Wei Song, Yue Huang, Haolong Jia, Keerthiram Murugesan, Yu Wang, Lifang He, Jianfeng Gao, Lichao Sun, Yanfang Ye

机构 * University of Notre Dame（诺丁汉大学）； Lehigh University（莱斯大学）； Imperial College London（伦敦帝国理工学院）； Rutgers University（罗格斯大学）； International Business Machines Corporation (IBM)（国际商业机器公司（IBM））； University of Illinois Chicago（伊利诺伊大学芝加哥分校）； Microsoft Research（微软研究院）

专题命中图像生成评测：diffusion(abstract)

2505.06276 2025-05-13 cs.RO 50%

SynSHRP2: A Synthetic Multimodal Benchmark for Driving Safety-critical Events Derived from Real-world Driving Data

Liang Shi, Boyu Jiang, Zhenyuan Yuan, Miguel A. Perez, Feng Guo

机构 * Virginia Tech Transportation Institute（弗吉尼亚理工运输研究所）； Department of Statistics, Virginia Tech（弗吉尼亚理工统计系）； Department of Biomedical Engineering and Mechanics, Virginia Tech（弗吉尼亚理工生物医学工程与力学系）

专题命中图像生成评测：diffusion(abstract)

Comments Accepted as a poster in CVPR 2025

2501.18972 2025-05-01 cs.LG cs.NA math.NA 50%

BCAT: A Block Causal Transformer for PDE Foundation Models for Fluid Dynamics

Yuxuan Liu, Jingmin Sun, Hayden Schaeffer

机构 * Department of Mathematics, UCLA（数学系，加州大学洛杉矶分校）； Department of Mathematical Sciences, Carnegie Mellon University（数学科学系，卡内基梅隆大学）

专题命中图像生成评测：image generation(abstract)

2503.12936 2025-04-16 eess.AS 50%

FNSE-SBGAN: Far-field Speech Enhancement with Schrodinger Bridge and Generative Adversarial Networks

Tong Lei, Qinwen Hu, Ziyao Lin, Andong Li, Rilin Chen, Meng Yu, Dong Yu, Jing Lu

专题命中图像生成评测：diffusion(abstract)

Comments 13 pages, 6 figures

2504.02917 2025-04-07 cs.CL cs.AI 50%

Bias in Large Language Models Across Clinical Applications: A Systematic Review

Thanathip Suenghataiphorn, Narisara Tribuddharat, Pojsakorn Danpanichkul, Narathorn Kulthamrongsri

专题命中图像生成评测：image generation(abstract)

2410.12138 2025-03-27 cs.LG cs.CL 50%

Preference Optimization with Multi-Sample Comparisons

Chaoqi Wang, Zhuokai Zhao, Chen Zhu, Karthik Abinav Sankararaman, Michal Valko, Xuefei Cao, Zhaorun Chen, Madian Khabsa, Yuxin Chen, Hao Ma, Sinong Wang

专题命中图像生成评测：diffusion(abstract)

Comments Code is available at https://github.com/alecwangcq/multi-sample-alignment

2503.16740 2025-03-24 cs.SE 50%

Automated Harmfulness Testing for Code Large Language Models

Honghao Tan, Haibo Wang, Diany Pressato, Yisen Xu, Shin Hwei Tan

专题命中图像生成评测：image generation(abstract)

2405.09818 2025-03-24 cs.CL 50%

Chameleon: Mixed-Modal Early-Fusion Foundation Models

Chameleon Team

专题命中图像生成评测：image generation(abstract)

2503.15092 2025-03-20 cs.CR cs.AI cs.CL 50%

Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings

Zonghao Ying, Guangyi Zheng, Yongxin Huang, Deyue Zhang, Wenxin Zhang, Quanchen Zou, Aishan Liu, Xianglong Liu, Dacheng Tao

专题命中图像生成评测：text-to-image(abstract)

2503.14827 2025-03-20 cs.CL cs.AI cs.CR 50%

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

Chejian Xu, Jiawei Zhang, Zhaorun Chen, Chulin Xie, Mintong Kang, Yujin Potter, Zhun Wang, Zhuowen Yuan, Alexander Xiong, Zidi Xiong, Chenhui Zhang, Lingzhi Yuan, Yi Zeng, Peiyang Xu, Chengquan Guo, Andy Zhou, Jeffrey Ziwei Tan, Xuandong Zhao, Francesco Pinto, Zhen Xiang, Yu Gai, Zinan Lin, Dan Hendrycks, Bo Li, Dawn Song

专题命中图像生成评测：text-to-image(abstract)

Comments ICLR 2025

2503.09964 2025-03-14 cs.CR cs.CL 50%

ExtremeAIGC: Benchmarking LMM Vulnerability to AI-Generated Extremist Content

Bhavik Chandna, Mariam Aboujenane, Usman Naseem

专题命中图像生成评测：image generation(abstract)

Comments Preprint

2503.09428 2025-03-13 physics.ins-det physics.comp-ph 50%

LHC Triggers using FPGA Image Recognition

James Brooke, Emyr Clement, Maciej Glowacki, Sudarshan Paramesvaran, Jeronimo Segal

专题命中图像生成评测：image generation(abstract)

Comments 12 pages, 6 figures. Submitted to Computing and Software for Big Science

2503.07293 2025-03-11 physics.med-ph eess.IV 50%

Is fitting error a reliable metric for assessing deformable motion correction in quantitative MRI?

Fanwen Wang, Ke Wen, Yaqing Luo, Yinzhe Wu, Jiahao Huang, Dudley J. Pennell, Pedro F. Ferreira, Andrew D. Scott, Sonia Nielles-Vallespin, Guang Yang

专题命中图像生成评测：diffusion(abstract)

Comments 5 pages, 5 figures. Accepted by ISBI 2025

2405.10311 2025-03-11 cs.IR 50%

UniRAG: Universal Retrieval Augmentation for Large Vision Language Models

Sahel Sharifymoghaddam, Shivani Upadhyay, Wenhu Chen, Jimmy Lin

专题命中图像生成评测：image generation(abstract)

Comments 14 pages, 6 figures

2305.07973 2025-02-20 cs.LG cs.AI math.OC quant-ph 50%

Stochastic Security as a Performance Metric for Quantum-enhanced Generative AI

Noah A. Crum, Leanto Sunny, Pooya Ronagh, Raymond Laflamme, Radhakrishnan Balu, George Siopsis

专题命中图像生成评测：diffusion(abstract)

2502.04297 2025-02-07 cs.LG math.OC math.PR math.ST stat.TH 50%

Statistical guarantees for continuous-time policy evaluation: blessing of ellipticity and new tradeoffs

Wenlong Mou

专题命中图像生成评测：diffusion(abstract)

2409.05798 2025-01-03 cs.LG cs.AI cs.HC econ.EM stat.ML 50%

Enhancing Preference-based Linear Bandits via Human Response Time

Shen Li, Yuyang Zhang, Zhaolin Ren, Claire Liang, Na Li, Julie A. Shah

专题命中图像生成评测：diffusion(abstract)

Comments NeurIPS 2024 (Oral) camera ready

2412.17544 2024-12-24 cs.AI 50%

Retention Score: Quantifying Jailbreak Risks for Vision Language Models

Zaitang Li, Pin-Yu Chen, Tsung-Yi Ho

专题命中图像生成评测：diffusion(abstract)

Comments 14 pages, 8 figures, AAAI 2025

Journal ref AAAI 2025

1. 图像生成评测 1207 篇

Arch-Router: Aligning LLM Routing with Human Preferences

VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics

Spectral bounds for exit times on metric measure Dirichlet spaces and applications

A Crack in the Bark: Leveraging Public Knowledge to Remove Tree-Ring Watermarks

IMAGIC-500: IMputation benchmark on A Generative Imaginary Country (500k samples)

Prior Learning in Introspective VAEs

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries

Front propagation on a general metric graph

A posteriori error estimates and adaptivity for locally conservative methods. Inexpensive implementation and evaluation, polytopal meshes, iterative linearization and algebraic solvers, and applications to complex porous media flows

Robust Representation and Estimation of Barycenters and Modes of Probability Measures on Metric Spaces

Dynamic Manipulation of Deformable Objects in 3D: Simulation, Benchmark and Learning Strategy

PolyConf: Unlocking Polymer Conformation Generation through Hierarchical Generative Models

EfficientLLM: Efficiency in Large Language Models

SynSHRP2: A Synthetic Multimodal Benchmark for Driving Safety-critical Events Derived from Real-world Driving Data

BCAT: A Block Causal Transformer for PDE Foundation Models for Fluid Dynamics

FNSE-SBGAN: Far-field Speech Enhancement with Schrodinger Bridge and Generative Adversarial Networks

Bias in Large Language Models Across Clinical Applications: A Systematic Review

Preference Optimization with Multi-Sample Comparisons

Automated Harmfulness Testing for Code Large Language Models

Chameleon: Mixed-Modal Early-Fusion Foundation Models

Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

ExtremeAIGC: Benchmarking LMM Vulnerability to AI-Generated Extremist Content

LHC Triggers using FPGA Image Recognition

Is fitting error a reliable metric for assessing deformable motion correction in quantitative MRI?

UniRAG: Universal Retrieval Augmentation for Large Vision Language Models

Stochastic Security as a Performance Metric for Quantum-enhanced Generative AI

Statistical guarantees for continuous-time policy evaluation: blessing of ellipticity and new tradeoffs

Enhancing Preference-based Linear Bandits via Human Response Time

Retention Score: Quantifying Jailbreak Risks for Vision Language Models