图像生成

Visual Stereotypes of Autism Spectrum in Janus-Pro-7B, DALL-E, Stable Diffusion, SDXL, FLUX, and Midjourney

自闭症光谱的视觉刻板印象：Janus-Pro-7B、DALL-E、Stable Diffusion、SDXL、FLUX和Midjourney的视觉表现

Maciej Wodziński, Marcin Rządeczka, Anastazja Szuła, Kacper Dudzic, Marcin Moskalewicz

机构 * Maria Curie-Skłodowska University（玛丽·居里大学） ； IDEAS Research Institute（IDEAS研究机构） ； Adam Mickiewicz University（亚当·密茨凯维奇大学） ； AMU Center for Artificial Intelligence（AMU人工智能中心） ； Poznań University of Medical Sciences（波兹南医科大学） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)

AI总结 本研究评估了六个AI图像生成模型在自闭症相关图像中的刻板印象表现，发现尽管技术有所改进，但模型在再现潜在有害刻板印象方面无显著变化。

Comments Preprint of a publication accepted to Identity-Aware AI 2025 (ECAI 2025)

Journal ref CEUR Workshop proceeding, 2025, Vol-4136 urn:nbn:de:0074-4136-x; https://ceur-ws.org/Vol-4136/iaai15.pdf

SustainDiffusion: Optimising the Social and Environmental Sustainability of Stable Diffusion Models

SustainDiffusion: 优化稳定扩散模型的社会和环境可持续性

Giordano d'Aloisio, Tosin Fadahunsi, Jay Choy, Rebecca Moussa, Federica Sarro

机构 * University of L'Aquila（拉奎拉大学） ； University College London（伦敦大学学院） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)

AI总结 SustainDiffusion通过优化超参数和提示结构，减少稳定扩散模型的性别、种族偏见和能耗，提升其社会和环境可持续性。

Parameter-aware high-fidelity microstructure generation using stable diffusion

基于稳定扩散的参数感知高保真微结构生成

Hoang Cuong Phan, Minh Tien Tran, Chihun Lee, Hoheok Kim, Sehyeok Oh, Dong-Kyu Kim, Ho Won Lee

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)

AI总结 本文提出基于稳定扩散3.5大模型的参数感知微结构生成方法，通过数值感知嵌入和微调技术实现高保真微结构生成，验证了其在材料设计中的有效性。

Comments 46 pages, 27 figures, 6 tables, 3rd Word Congress on Artificial Intelligence in Materials & Manufacturing 2025

Journal ref Adv. Eng. Inform. (2025), 104080

On the Information-Theoretic Fragility of Robust Watermarking under Diffusion Editing

Yunyi Ni, Ziyu Yang, Ze Niu, Emily Davis, Finn Carter

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；image editing(abstract)

Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory

Hanru Bai, Weiyang Ding, Difan Zou

机构 * Fudan University（复旦大学） ； The University of Hong Kong（香港大学） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；image synthesis(abstract)

Comments NeurIPS 2025

Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurements

Brett Levac, Jon Tamir, Marcelo Pereyra, Julian Tachella

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；inpainting(abstract)

Rare Text Semantics Were Always There in Your Diffusion Transformer

Seil Kang, Woojung Han, Dayun Ju, Seong Jae Hwang

专题命中 扩散模型 ：diffusion(title,abstract)；text-to-image(abstract)；image editing(abstract)

Comments Accepted to NeurIPS 2025

TridentServe: A Stage-level Serving System for Diffusion Pipelines

Yifei Xia, Fangcheng Fu, Hao Yuan, Hanke Zhang, Xupeng Miao, Yijun Liu, Suhan Ling, Jie Jiang, Bin Cui

专题命中 扩散模型 ：diffusion(title,abstract)；text-to-image(abstract)；generative vision(abstract)

Learn to Guide Your Diffusion Model

Alexandre Galashov, Ashwini Pokle, Arnaud Doucet, Arthur Gretton, Mauricio Delbracio, Valentin De Bortoli

机构 * Google DeepMind（谷歌DeepMind） ； Gatsby Unit, University College London（Gatsby单位，伦敦大学学院） ； Google（谷歌） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)

Test-Time Scaling of Diffusion Models via Noise Trajectory Search

Vignav Ramesh, Morteza Mardani

机构 * Harvard University（哈佛大学） ； NVIDIA（NVIDIA公司） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)

A Survey on Pre-Trained Diffusion Model Distillations

Xuhui Fan, Zhangkai Wu, Hongyu Wu

专题命中 扩散模型 ：diffusion(title,abstract)；text-to-image(abstract)；image synthesis(abstract)

Exploring Palette based Color Guidance in Diffusion Models

Qianru Qiu, Jiafeng Mao, Xueting Wang

机构 * CyberAgent Inc.（CyberAgent公司） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV、cs.GR、cs.MM

Comments Accepted to ACM MM 2025

When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting

Xiaodong Wu, Tianyi Tang, Xiangman Li, Jianbing Ni, Yong Yu

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)

Comments arXiv admin note: text overlap with arXiv:2408.02035

SD-Acc: Accelerating Stable Diffusion through Phase-aware Sampling and Hardware Co-Optimizations

Zhican Wang, Guanghui He, Hongxiang Fan

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)

Comments Under Review

Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models

Vineet Jain, Kusha Sareen, Mohammad Pedramfar, Siamak Ravanbakhsh

机构 * School of Computer Science, McGill University（计算机科学系，麦吉尔大学） ； Mila - Quebec Artificial Intelligence Institute（魁北克人工智能研究所） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)

Angle Domain Guidance: Latent Diffusion Requires Rotation Rather Than Extrapolation

Cheng Jin, Zhenyu Xiao, Chutao Liu, Yuantao Gu

机构 * Department of Electronic Engineering, Tsinghua University, Beijing, China（清华大学电子工程系） ； Zhili College, Tsinghua University, Beijing, China（清华大学紫金学院） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)；text-to-image(abstract)；image synthesis(abstract)

Comments Accepted at ICML 2025

Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts

Marta Skreta, Tara Akhound-Sadegh, Viktor Ohanesian, Roberto Bondesan, Alán Aspuru-Guzik, Arnaud Doucet, Rob Brekelmans, Alexander Tong, Kirill Neklyudov

机构 * University of Toronto（多伦多大学） ； Vector Institute（向量研究所） ； McGill University（麦吉尔大学） ； Mila - Quebec AI Institute（魁北克AI研究所） ； Imperial College London（伦敦帝国学院） ； Google DeepMind（谷歌DeepMind） ； Duke University（杜克大学） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)

Comments Accepted as a Spotlight Presentation at the International Conference of Machine Learning 2025

MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible Cost

Sen Xing, Muyan Zhong, Zeqiang Lai, Liangchen Li, Jiawen Liu, Yaohui Wang, Jifeng Dai, Wenhai Wang

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)

Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models

Jiachen Ma, Yijiang Li, Zhiqing Xiao, Anda Cao, Jie Zhang, Chao Ye, Junbo Zhao

机构 * Zhejiang University（浙江大学） ； UC San Diego（加州大学圣地亚哥分校） ； ETH Zurich（苏黎世联邦理工学院） 纠错

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)

Journal ref NAACL2025

Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation

Jiantao Lin, Xin Yang, Meixi Chen, Yingjie Xu, Dongyu Yan, Leyi Wu, Xinli Xu, Lie XU, Shunsi Zhang, Ying-Cong Chen

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV、cs.GR、cs.MM

Comments The first three authors contributed equally to this work

d-Sketch: Improving Visual Fidelity of Sketch-to-Image Translation with Pretrained Latent Diffusion Models without Retraining

Prasun Roy, Saumik Bhattacharya, Subhankar Ghosh, Umapada Pal, Michael Blumenstein

专题命中 扩散模型 ：diffusion(title,abstract)；image synthesis(abstract)；分类 cs.CV、cs.GR、cs.MM

Comments Accepted in The International Conference on Pattern Recognition (ICPR) 2024

Imagine2Servo: Intelligent Visual Servoing with Diffusion-Driven Goal Generation for Robotic Tasks

Pranjali Pathre, Gunjan Gupta, M. Nomaan Qureshi, Mandyam Brunda, Samarth Brahmbhatt, K. Madhava Krishna

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；image editing(abstract)

Comments Published at 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

SwiftDiffusion: Efficient Diffusion Model Serving with Add-on Modules

Suyi Li, Lingyun Yang, Xiaoxiao Jiang, Hanfeng Lu, Dakai An, Zhipeng Di, Weiyi Lu, Jiawei Chen, Kan Liu, Yinghao Yu, Tao Lan, Guodong Yang, Lin Qu, Liping Zhang, Wei Wang

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)

BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion

Bo-Kyeong Kim, Hyoung-Kyu Song, Thibault Castells, Shinkook Choi

专题命中 扩散模型 ：diffusion(title,abstract)；text-to-image(abstract)；personalized generation(abstract)

Comments ECCV 2024 Camera-Ready Version

Accelerated Image-Aware Generative Diffusion Modeling

Tanmay Asthana, Yufang Bao, Hamid Krim

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；image synthesis(abstract)

Zero-Shot Uncertainty Quantification using Diffusion Probabilistic Models

Dule Shu, Amir Barati Farimani

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)

Accelerating Parallel Sampling of Diffusion Models

Zhiwei Tang, Jiasheng Tang, Hao Luo, Fan Wang, Tsung-Hui Chang

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)

Comments ICML 2024

Diffusion Models for Constrained Domains

Nic Fishman, Leo Klarner, Valentin De Bortoli, Emile Mathieu, Michael Hutchinson

专题命中 扩散模型 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)

Comments Published in Transactions on Machine Learning Research (07/2023)

Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models

Yuchen Wu, Minshuo Chen, Zihao Li, Mengdi Wang, Yuting Wei

专题命中 扩散模型 ：diffusion(title,abstract)；text-to-image(abstract)；image synthesis(abstract)

Comments 41 pages, 12 figures

Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation

Jinlong Xue, Yayue Deng, Yingming Gao, Ya Li

专题命中 扩散模型 ：diffusion(title,abstract)；text-to-image(abstract)；inpainting(abstract)

Comments Demo and implementation at https://auffusion.github.io