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。

2025-10-14 至 2025-10-14 共收录 2 篇信号源：cs.CV, cs.GR, cs.MM

1. 效率与蒸馏 2 篇

2505.18809 2025-10-14 cs.CV 79%

VORTA: Efficient Video Diffusion via Routing Sparse Attention

Wenhao Sun, Rong-Cheng Tu, Yifu Ding, Zhao Jin, Jingyi Liao, Shunyu Liu, Dacheng Tao

机构 * College of Computing and Data Science, Nanyang Technological University, Singapore（计算与数据科学学院，南洋理工大学，新加坡）

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

Comments Accepted by NeurIPS 2025. The code is available at https://github.com/wenhao728/VORTA

2503.12067 2025-10-14 cs.CV 57%

A Comprehensive Survey on Knowledge Distillation

Amir M. Mansourian, Rozhan Ahmadi, Masoud Ghafouri, Amir Mohammad Babaei, Elaheh Badali Golezani, Zeynab Yasamani Ghamchi, Vida Ramezanian, Alireza Taherian, Kimia Dinashi, Amirali Miri, Shohreh Kasaei

机构 * Sharif University of Technology（谢里夫科技大学）

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

Comments Published at TMLR (102 pages, 10 figures, 17 tables)