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。

2025-10-20 至 2025-10-20 共收录 6 篇信号源：cs.CV, cs.GR, cs.MM

1. 文生图 6 篇

2504.00010 2025-10-20 cs.LG cs.GR cs.MA 89%

LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integration

Yuyao Zhang, Jinghao Li, Yu-Wing Tai

机构 * Dartmouth College（达特茅斯学院）； CUHK（香港大学）

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

Comments 26 pages

2510.15752 2025-10-20 cs.CV cs.AI 88%

NDM: A Noise-driven Detection and Mitigation Framework against Implicit Sexual Intentions in Text-to-Image Generation

Yitong Sun, Yao Huang, Ruochen Zhang, Huanran Chen, Shouwei Ruan, Ranjie Duan, Xingxing Wei

机构 * Institute of Artificial Intelligence, Beihang University（北航人工智能研究院）； College of AI, Tsinghua University（清华人工智能学院）； Security Group, Alibaba Group（阿里集团安全组）

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

Comments 10 pages, 8 figures, accepted by ACMMM 2025

2510.15857 2025-10-20 cs.CV 87%

BLIP3o-NEXT: Next Frontier of Native Image Generation

Jiuhai Chen, Le Xue, Zhiyang Xu, Xichen Pan, Shusheng Yang, Can Qin, An Yan, Honglu Zhou, Zeyuan Chen, Lifu Huang, Tianyi Zhou, Junnan Li, Silvio Savarese, Caiming Xiong, Ran Xu

机构 * Salesforce Research（Salesforce研究部）； University of Maryland（马里兰大学）； Virginia Tech（弗吉尼亚理工大学）； New York University（纽约大学）； UC Davis（加州大学戴维斯分校）

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

2510.15015 2025-10-20 cs.CV cs.AI cs.CL 83%

DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models

Mor Ventura, Michael Toker, Or Patashnik, Yonatan Belinkov, Roi Reichart

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

2503.10679 2025-10-20 cs.CL cs.AI 67%

LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss

Pau Rodriguez, Michal Klein, Eleonora Gualdoni, Valentino Maiorca, Arno Blaas, Luca Zappella, Marco Cuturi, Xavier Suau

机构 * Apple（苹果公司）； Sapienza（拉维尼恩大学）

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

Comments NeurIPS 2025

2510.15240 2025-10-20 cs.CV 57%

The Face of Persuasion: Analyzing Bias and Generating Culture-Aware Ads

Aysan Aghazadeh, Adriana Kovashka

机构 * University of Pittsburgh（匹兹堡大学）

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