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。

2025-08-26 至 2025-08-26 共收录 5 篇信号源：cs.CV, cs.GR, cs.MM

1. 效率与蒸馏 5 篇

2508.17868 2025-08-26 cs.SD cs.AI cs.LG eess.AS stat.ML 78%

FasterVoiceGrad: Faster One-step Diffusion-Based Voice Conversion with Adversarial Diffusion Conversion Distillation

Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo

机构 * NTT, Inc.（日本NTT公司）

专题命中效率与蒸馏：diffusion(title,abstract)

Comments Accepted to Interspeech 2025. Project page: https://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/fastervoicegrad/

2508.16939 2025-08-26 cs.LG math.PR stat.ML 78%

Sig-DEG for Distillation: Making Diffusion Models Faster and Lighter

Lei Jiang, Wen Ge, Niels Cariou-Kotlarek, Mingxuan Yi, Po-Yu Chen, Lingyi Yang, Francois Buet-Golfouse, Gaurav Mittal, Hao Ni

机构 * University College London（伦敦大学学院）； JPMorganChase（摩根大通）； University of Oxford（牛津大学）； AIML Global Markets, Barclays（巴克莱证券AIML全球市场）

专题命中效率与蒸馏：diffusion(title,abstract)

2508.17426 2025-08-26 cs.LG 67%

Modular MeanFlow: Towards Stable and Scalable One-Step Generative Modeling

Haochen You, Baojing Liu, Hongyang He

机构 * Graduate School of Arts and Sciences, Columbia University, New York, USA（哥伦比亚大学艺术与科学研究生院）； Department of Computer Science, University of Warwick, Coventry, UK（沃里克大学计算机科学系）

专题命中效率与蒸馏：diffusion(abstract)；image synthesis(abstract)

Comments Accepted as a conference paper at PRCV 2025

2501.15420 2025-08-26 cs.CV cs.AI cs.LG 57%

Visual Generation Without Guidance

Huayu Chen, Kai Jiang, Kaiwen Zheng, Jianfei Chen, Hang Su, Jun Zhu

机构 * Department of Computer Science \& Technology, Tsinghua University

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

Comments Accepted to ICML 2025

2508.16917 2025-08-26 cs.CV 57%

Structural Energy-Guided Sampling for View-Consistent Text-to-3D

Qing Zhang, Jinguang Tong, Jie Hong, Jing Zhang, Xuesong Li

机构 * The Australian National University（澳大利亚国立大学）； CSIRO（澳大利亚联邦科学与工业研究组织）； The University of Hong Kong（香港大学）

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