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。

2025-09-19 至 2025-09-19 共收录 4 篇信号源：cs.CV, cs.GR, cs.MM

1. 可控生成 4 篇

2509.15185 2025-09-19 cs.CV 79%

Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation

Xiaoyu Yue, Zidong Wang, Yuqing Wang, Wenlong Zhang, Xihui Liu, Wanli Ouyang, Lei Bai, Luping Zhou

机构 * Shanghai AI Laboratory（上海人工智能实验室）； University of Sydney（悉尼大学）； Chinese University of Hong Kong（香港中文大学）； University of Hong Kong（香港大学）

专题命中可控生成：image generation(title,abstract)；分类 cs.CV

Comments Accepted by NeurIPS 2025

2508.11277 2025-09-19 cs.CV cs.LG 57%

Probing the Representational Power of Sparse Autoencoders in Vision Models

Matthew Lyle Olson, Musashi Hinck, Neale Ratzlaff, Changbai Li, Phillip Howard, Vasudev Lal, Shao-Yen Tseng

机构 * Oracle ； Intel Labs（英特尔实验室）； Oregon State University（俄勒冈州立大学）； Thoughtworks

专题命中可控生成：diffusion(abstract)；分类 cs.CV

Comments ICCV 2025 Findings

2509.14495 2025-09-19 math.OC 50%

A Time-Inconsistent Stochastic Optimal Control Problem in an Infinite Time Horizon

Qingmeng Wei, Jiongmin Yong

专题命中可控生成：diffusion(abstract)

2404.17236 2025-09-19 math.AP math.PR 50%

Stochastic optimal control problems with measurable coefficients and $L_d$-drift

David Criens

专题命中可控生成：diffusion(abstract)

Comments The paper is fully rewritten, covering more general settings with merely measurable coefficients, an $L_d$-drift and any dimension $d \geq 2$. Further, it discusses more cost functions and includes a discussion of the semigroup connection