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 41 篇信号源：cs.CV, cs.GR, cs.MM

1. 扩散模型 29 篇

2509.14298 2025-09-19 eess.AS cs.LG 50%

SpeechOp: Inference-Time Task Composition for Generative Speech Processing

Justin Lovelace, Rithesh Kumar, Jiaqi Su, Ke Chen, Kilian Q Weinberger, Zeyu Jin

机构 * Cornell University（康奈尔大学）； Adobe Research（Adobe研究）

专题命中扩散模型：diffusion(abstract)

2508.04287 2025-09-19 math.ST stat.TH 50%

Parameter Estimation for Weakly Interacting Hypoelliptic Diffusions

Yuga Iguchi, Alexandros Beskos, Grigorios A. Pavliotis

专题命中扩散模型：diffusion(abstract)

2508.01442 2025-09-19 cs.RO 50%

Physically-based Lighting Generation for Robotic Manipulation

Shutong Jin, Lezhong Wang, Ben Temming, Florian T. Pokorny

机构 * KTH Royal Institute of Technology（皇家理工学院）； Technical University of Denmark（丹麦技术大学）

专题命中扩散模型：diffusion(abstract)

2502.06405 2025-09-19 math.NA cs.NA 50%

Hybrid Schwarz preconditioners for linear systems arising from hp-discontinuous Galerkin method

Vit Dolejsi, Tomas Hammerbauer

专题命中扩散模型：diffusion(abstract)

2308.09218 2025-09-19 math.PR 50%

Fixation and stationary times for the $Λ$-Wright-Fisher process

Airam Blancas, Adrián González Casanova, Sebastian Hummel, Sandra Palau

专题命中扩散模型：diffusion(abstract)

2. 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

3. 个性化与一致性 1 篇

2509.06499 2025-09-19 cs.CV 89%

TIDE: Achieving Balanced Subject-Driven Image Generation via Target-Instructed Diffusion Enhancement

Jibai Lin, Bo Ma, Yating Yang, Xi Zhou, Rong Ma, Turghun Osman, Ahtamjan Ahmat, Rui Dong, Lei Wang

机构 * Xinjiang Technical Institute of Physics & Chemistry（新疆物理化学技术研究所）； University of Chinese Academy of Sciences（中国科学院大学）； Xinjiang Laboratory of Minority Speech and Language Information Processing（新疆少数民族语言信息处理实验室）

专题命中个性化与一致性：image generation(title,abstract)；diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

4. 效率与蒸馏 1 篇

2509.15076 2025-09-19 cs.LG cs.CV 57%

Forecasting and Visualizing Air Quality from Sky Images with Vision-Language Models

Mohammad Saleh Vahdatpour, Maryam Eyvazi, Yanqing Zhang

机构 * Georgia State University（佐治亚州立大学）； Savannah College of Art and Design（萨凡纳艺术与设计学院）

专题命中效率与蒸馏：image generation(abstract)；分类 cs.CV

Comments Published at ICCVW 2025