图像生成

Supercharged One-step Text-to-Image Diffusion Models with Negative Prompts

Viet Nguyen, Anh Nguyen, Trung Dao, Khoi Nguyen, Cuong Pham, Toan Tran, Anh Tran

机构 * Qualcomm AI Research（高通人工智能研究） 纠错

专题命中 效率与蒸馏 ：diffusion(title,abstract)；text-to-image(title)；image synthesis(abstract)；分类 cs.CV

Comments Accepted at ICCV 2025

Energy based diffusion generator for efficient sampling of Boltzmann distributions

Yan Wang, Ling Guo, Hao Wu, Tao Zhou

机构 * School of Mathematical Sciences, Tongji University（同济大学数学科学学院） ； Department of Mathematics, Shanghai Normal University（上海师范大学数学系） ； Institute of Computational Mathematics and Scientific/Engineering Computing, AMSS, Chinese Academy of Sciences（中国科学院数学与系统科学研究院） 纠错

专题命中 效率与蒸馏 ：diffusion(title,abstract)

SD3.5-Flash: Distribution-Guided Distillation of Generative Flows

Hmrishav Bandyopadhyay, Rahim Entezari, Jim Scott, Reshinth Adithyan, Yi-Zhe Song, Varun Jampani

机构 * Stability AI ； SketchX, University of Surrey（SketchX，大学） 纠错

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

Comments Project Page: https://hmrishavbandy.github.io/sd35flash/

KeyWorld: Key Frame Reasoning Enables Effective and Efficient World Models

Sibo Li, Qianyue Hao, Yu Shang, Yong Li

机构 * Department of Electronic Engineering, BNRist, Tsinghua University（电子工程系、北京理工大学、清华大学） 纠错

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

Parallel Thinking, Sequential Answering: Bridging NAR and AR for Efficient Reasoning

Qihang Ai, Haiyun Jiang

机构 * Nanyang Technological University（南洋理工大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

专题命中 效率与蒸馏 ：diffusion(abstract)

Comments 4 pages