图像生成 - arXivDaily 专题

2404.10176 2024-04-17 cs.LG cs.NE 50%

Multi-objective evolutionary GAN for tabular data synthesis

Nian Ran, Bahrul Ilmi Nasution, Claire Little, Richard Allmendinger, Mark Elliot

专题命中文生图：image synthesis(abstract)

2404.00551 2024-04-02 stat.ML cs.LG 50%

Convergence of Continuous Normalizing Flows for Learning Probability Distributions

Yuan Gao, Jian Huang, Yuling Jiao, Shurong Zheng

专题命中文生图：image synthesis(abstract)

Comments 60 pages, 3 tables, and 3 figures

2403.09374 2024-03-15 cs.HC 50%

Machine Learning Processes as Sources of Ambiguity: Insights from AI Art

Christian Sivertsen, Guido Salimbeni, Anders Sundnes Løvlie, Steve Benford, Jichen Zhu

专题命中文生图：image synthesis(abstract)

2403.08137 2024-03-14 cs.HC cs.AI cs.CL 50%

From Paper to Card: Transforming Design Implications with Generative AI

Donghoon Shin, Lucy Lu Wang, Gary Hsieh

专题命中文生图：text-to-image(abstract)

Journal ref In Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI '24), May 11-16, 2024, Honolulu, HI, USA. ACM, New York, NY, USA

2403.07182 2024-03-13 cs.NE 50%

MAP-Elites with Transverse Assessment for Multimodal Problems in Creative Domains

Marvin Zammit, Antonios Liapis, Georgios N. Yannakakis

专题命中文生图：text-to-image(abstract)

Comments 18 pages, 5 figures To be published in the proceedings of the 13th International Conference on Artificial Intelligence in Music, Sound, Art and Design (EvoMUSART) 2024

2310.09985 2024-03-04 cs.HC 50%

Prompting for Discovery: Flexible Sense-Making for AI Art-Making with Dreamsheets

Shm Garanganao Almeda, J. D. Zamfirescu-Pereira, Kyu Won Kim, Pradeep Mani Rathnam, Bjoern Hartmann

专题命中文生图：text-to-image(abstract)

Comments 13 pages, 14 figures, currently under review

2402.13442 2024-02-22 cs.RO 50%

CoFRIDA: Self-Supervised Fine-Tuning for Human-Robot Co-Painting

Peter Schaldenbrand, Gaurav Parmar, Jun-Yan Zhu, James McCann, Jean Oh

专题命中文生图：text-to-image(abstract)

2305.18671 2024-02-15 stat.ML cs.LG 50%

Perturbation-Assisted Sample Synthesis: A Novel Approach for Uncertainty Quantification

Yifei Liu, Rex Shen, Xiaotong Shen

专题命中文生图：image synthesis(abstract)

2306.01820 2024-01-17 cs.LG 50%

Concurrent Classifier Error Detection (CCED) in Large Scale Machine Learning Systems

Pedro Reviriego, Ziheng Wang, Alvaro Alonso, Zhen Gao, Farzad Niknia, Shanshan Liu, Fabrizio Lombardi

专题命中文生图：text-to-image(abstract)

Journal ref IEEE Transactions on Reliability, 2024

2401.00023 2024-01-08 eess.IV cs.LG 50%

CycleGAN Models for MRI Image Translation

Cassandra Czobit, Reza Samavi

专题命中文生图：image synthesis(abstract)

Comments Accepted and presented in ACML PRHA 2023 workshop

2306.12028 2023-12-21 cs.SE 50%

Prompt Sapper: A LLM-Empowered Production Tool for Building AI Chains

Yu Cheng, Jieshan Chen, Qing Huang, Zhenchang Xing, Xiwei Xu, Qinghua Lu

专题命中文生图：text-to-image(abstract)

Comments 23 pages, 5 figures, accepted to TOSEM 2023

2305.10512 2023-12-19 cs.CL cs.HC 50%

IMAD: IMage-Augmented multi-modal Dialogue

Viktor Moskvoretskii, Anton Frolov, Denis Kuznetsov

专题命中文生图：text-to-image(abstract)

Comments Main part contains 6 pages, 4 figures. It was accepted on AINL. We wait the publication and DOI

2308.06385 2023-12-15 cs.CL cs.AI 50%

ZYN: Zero-Shot Reward Models with Yes-No Questions for RLAIF

Victor Gallego

专题命中文生图：text-to-image(abstract)

Comments pre-print, work in progress

2311.14735 2023-11-28 q-fin.ST cs.LG 50%

Generative Machine Learning for Multivariate Equity Returns

Ruslan Tepelyan, Achintya Gopal

专题命中文生图：text-to-image(abstract)

Comments 13 pages, 2-column format, presented at ICAIF'23

2311.12131 2023-11-22 cs.CL 50%

Human Learning by Model Feedback: The Dynamics of Iterative Prompting with Midjourney

Shachar Don-Yehiya, Leshem Choshen, Omri Abend

专题命中文生图：text-to-image(abstract)

Comments EMNLP23

2302.00111 2023-11-21 cs.AI 50%

Learning Universal Policies via Text-Guided Video Generation

Yilun Du, Mengjiao Yang, Bo Dai, Hanjun Dai, Ofir Nachum, Joshua B. Tenenbaum, Dale Schuurmans, Pieter Abbeel

专题命中文生图：image synthesis(abstract)

Comments NeurIPS 2023, Project Website: https://universal-policy.github.io/

2310.16730 2023-10-26 cs.LG 50%

MultiPrompter: Cooperative Prompt Optimization with Multi-Agent Reinforcement Learning

Dong-Ki Kim, Sungryull Sohn, Lajanugen Logeswaran, Dongsub Shim, Honglak Lee

专题命中文生图：text-to-image(abstract)

2307.02106 2023-08-08 cs.CR cs.DB cs.LG 50%

SoK: Privacy-Preserving Data Synthesis

Yuzheng Hu, Fan Wu, Qinbin Li, Yunhui Long, Gonzalo Munilla Garrido, Chang Ge, Bolin Ding, David Forsyth, Bo Li, Dawn Song

专题命中文生图：image synthesis(abstract)

Comments Accepted at IEEE S&P (Oakland) 2024

2306.06135 2023-06-13 cs.LG cs.AI 50%

Safety and Fairness for Content Moderation in Generative Models

Susan Hao, Piyush Kumar, Sarah Laszlo, Shivani Poddar, Bhaktipriya Radharapu, Renee Shelby

专题命中文生图：text-to-image(abstract)

Comments CVPR Workshop Paper

2305.04810 2023-05-09 cs.SD eess.AS q-bio.QM 50%

Synthesizing Cough Audio with GAN for COVID-19 Detection

Yahya Saleh

专题命中文生图：image synthesis(abstract)

Comments Bachelor's thesis

2304.13742 2023-04-28 cs.LG cs.AI stat.ML 50%

TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation

Zhaoyan Liu, Noel Vouitsis, Satya Krishna Gorti, Jimmy Ba, Gabriel Loaiza-Ganem

专题命中文生图：text-to-image(abstract)

Comments Accepted at ICML 2023

2304.12725 2023-04-26 q-bio.QM 50%

Quantitative analysis of collagen remodeling in pancreatic lesions using computationally translated collagen images derived from brightfield microscopy images

Varun Nair, Gavish Uppal, Saurav Bharadwaj, Ruchi Sinha, Manjit Kaur, Rajesh Kumar, .

专题命中文生图：image synthesis(abstract)

2103.04794 2023-04-03 cs.CR 50%

Packet-Level Adversarial Network Traffic Crafting using Sequence Generative Adversarial Networks

Qiumei Cheng, Shiying Zhou, Yi Shen, Dezhang Kong, Chunming Wu

专题命中文生图：image synthesis(abstract)

Comments The authors agreed to withdraw the manuscript due to privacy reason

2303.14811 2023-03-28 cs.LG stat.ML 50%

Learning Generative Models with Goal-conditioned Reinforcement Learning

Mariana Vargas Vieyra, Pierre Ménard

专题命中文生图：image synthesis(abstract)

2303.12647 2023-03-23 cs.HC 50%

A Word is Worth a Thousand Pictures: Prompts as AI Design Material

Chinmay Kulkarni, Stefania Druga, Minsuk Chang, Alex Fiannaca, Carrie Cai, Michael Terry

专题命中文生图：text-to-image(abstract)

Comments 22 pages, 5 figures

2303.05497 2023-03-20 cs.LG 50%

Learning Stationary Markov Processes with Contrastive Adjustment

Ludvig Bergenstråhle, Jens Lagergren, Joakim Lundeberg

专题命中文生图：image synthesis(abstract)

2303.09395 2023-03-17 cs.CL cs.LG eess.SP 50%

Text-to-ECG: 12-Lead Electrocardiogram Synthesis conditioned on Clinical Text Reports

Hyunseung Chung, Jiho Kim, Joon-myoung Kwon, Ki-Hyun Jeon, Min Sung Lee, Edward Choi

专题命中文生图：text-to-image(abstract)

Comments Accepted to ICASSP 2023 (5 pages, 3 figures, 4 tables)

2110.05887 2023-03-08 stat.ML cs.LG 50%

Discovery of Single Independent Latent Variable

Uri Shaham, Jonathan Svirsky, Ori Katz, Ronen Talmon

专题命中文生图：image synthesis(abstract)

Comments Published as a conference paper at Neurips 2022. In the current version the proof of the lemma is modified

Journal ref Advances in Neural Information Processing Systems 2022

2303.02957 2023-03-07 stat.ML cs.LG math.OC 50%

Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems

Atsushi Nitanda, Kazusato Oko, Denny Wu, Nobuhito Takenouchi, Taiji Suzuki

专题命中文生图：image synthesis(abstract)

2301.09545 2023-01-24 cs.HC cs.AI cs.LG 50%

The Entoptic Field Camera as Metaphor-Driven Research-through-Design with AI Technologies

Jesse Josua Benjamin, Heidi Biggs, Arne Berger, Julija Rukanskaitė, Michael Heidt, Nick Merrill, James Pierce, Joseph Lindley

专题命中文生图：image synthesis(abstract)

Comments To be published in Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI '23), April 23--28, 2023, Hamburg, Germany

1. 文生图 3490 篇

Multi-objective evolutionary GAN for tabular data synthesis

Convergence of Continuous Normalizing Flows for Learning Probability Distributions

Machine Learning Processes as Sources of Ambiguity: Insights from AI Art

From Paper to Card: Transforming Design Implications with Generative AI

MAP-Elites with Transverse Assessment for Multimodal Problems in Creative Domains

Prompting for Discovery: Flexible Sense-Making for AI Art-Making with Dreamsheets

CoFRIDA: Self-Supervised Fine-Tuning for Human-Robot Co-Painting

Perturbation-Assisted Sample Synthesis: A Novel Approach for Uncertainty Quantification

Concurrent Classifier Error Detection (CCED) in Large Scale Machine Learning Systems

CycleGAN Models for MRI Image Translation

Prompt Sapper: A LLM-Empowered Production Tool for Building AI Chains

IMAD: IMage-Augmented multi-modal Dialogue

ZYN: Zero-Shot Reward Models with Yes-No Questions for RLAIF

Generative Machine Learning for Multivariate Equity Returns

Human Learning by Model Feedback: The Dynamics of Iterative Prompting with Midjourney

Learning Universal Policies via Text-Guided Video Generation

MultiPrompter: Cooperative Prompt Optimization with Multi-Agent Reinforcement Learning

SoK: Privacy-Preserving Data Synthesis

Safety and Fairness for Content Moderation in Generative Models

Synthesizing Cough Audio with GAN for COVID-19 Detection

TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation

Quantitative analysis of collagen remodeling in pancreatic lesions using computationally translated collagen images derived from brightfield microscopy images

Packet-Level Adversarial Network Traffic Crafting using Sequence Generative Adversarial Networks

Learning Generative Models with Goal-conditioned Reinforcement Learning

A Word is Worth a Thousand Pictures: Prompts as AI Design Material

Learning Stationary Markov Processes with Contrastive Adjustment

Text-to-ECG: 12-Lead Electrocardiogram Synthesis conditioned on Clinical Text Reports

Discovery of Single Independent Latent Variable

Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems

The Entoptic Field Camera as Metaphor-Driven Research-through-Design with AI Technologies