视觉与机器人

图像生成

图像生成、文生图、图像编辑、扩散模型和可控生成。

2025-10-27 至 2025-10-27 共收录 7 篇信号源：cs.CV, cs.GR, cs.MM

1. 文生图 7 篇

2412.06771 2025-10-27 cs.AI cs.CV cs.LG 86%

Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty

Meera Hahn, Wenjun Zeng, Nithish Kannen, Rich Galt, Kartikeya Badola, Been Kim, Zi Wang

机构 * Google DeepMind（谷歌DeepMind）

专题命中文生图：text-to-image(title,abstract)；image generation(title)；分类 cs.CV

Journal ref International Conference on Machine Learning, 2025

2510.21363 2025-10-27 cs.LG cs.CL cs.CV 85%

FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models

Zihao Fu, Ryan Brown, Shun Shao, Kai Rawal, Eoin Delaney, Chris Russell

机构 * The Chinese University of Hong Kong（香港中文大学）； University of Oxford（牛津大学）； University of Cambridge（剑桥大学）； Trinity College Dublin（都柏林大学三一学院）

专题命中文生图：text-to-image(title,abstract)；image generation(abstract)；diffusion(abstract)；分类 cs.CV

Comments Neurips 2025

2510.21512 2025-10-27 cs.CV 70%

Towards a Golden Classifier-Free Guidance Path via Foresight Fixed Point Iterations

Kaibo Wang, Jianda Mao, Tong Wu, Yang Xiang

机构 * Department of Mathematics, The Hong Kong University of Science and Technology（香港科技大学数学系）； Shenzhen-Hong Kong Collaborative Innovation Research Institute, HKUST（深圳-香港协同创新研究院）

专题命中文生图：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments Accepted at NeurIPS 2025 (Spotlight)

2506.09538 2025-10-27 cs.CV 70%

AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant T2I Adversarial Patches

Wenjun Ji, Yuxiang Fu, Luyang Ying, Deng-Ping Fan, Yuyi Wang, Ming-Ming Cheng, Ivor Tsang, Qing Guo

机构 * NKIARI, Shenzhen Futian（深圳福田NKIARI）； VCIP, CS, Nankai University（南开大学VCIP研究所）； CRRC Zhuzhou Institute（株洲CRRC研究所）； CFAR and IHPC, Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局CFAR和IHPC）

专题命中文生图：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

2510.20350 2025-10-27 cs.CY cs.AI 67%

What Do AI-Generated Images Want?

Amanda Wasielewski

专题命中文生图：image generation(abstract)；text-to-image(abstract)

2507.07207 2025-10-27 cs.LG cs.NE 67%

Scaling can lead to compositional generalization

Florian Redhardt, Yassir Akram, Simon Schug

机构 * ETH Zurich（苏黎世联邦理工学院）； Princeton University（普林斯顿大学）

专题命中文生图：image generation(abstract)；text-to-image(abstract)

Comments NeurIPS 2025 (Spotlight); Code available at https://github.com/smonsays/scale-compositionality

2509.15551 2025-10-27 cs.LG 50%

PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image Detectors

Sepehr Dehdashtian, Mashrur M. Morshed, Jacob H. Seidman, Gaurav Bharaj, Vishnu Naresh Boddeti

机构 * Michigan State University（密歇根州立大学）； Reality Defender

专题命中文生图：text-to-image(abstract)

Comments Accepted as NeurIPS 2025 poster