T2I Diffusion Models

T2I: Text-to-Image

Follow this topic Ask about this topic

Momentum

35 papers in the last four weeks, up 169% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 240

All topics

Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models
May 11, 2026Nicola Novello, Andrea M. TonelloCross-Attention Concept Erasure
University of Klagenfurt Klagenfurt, Austria
What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers
May 11, 2026Chenyu ZhangDiffusion Transformer T2I Generation
Tianjin University · Tianjin, China
Attention Sinks in Diffusion Transformers: A Causal Analysis
May 10, 2026Fangzheng Wu, Brian SummaTransformer Interpretability Diffusion Transformer
Department of Computer Science, Tulane University, New Orleans, LA, USA.
simpleposter: a simple baseline for product poster generation
May 9, 2026Benlei Cui, Fangao Zeng, Weitao Jiang +6Image Generation Image Inpainting
1Alibaba Group · 2Taobao & Tmall Group of Alibaba
Flow-OPD: On-Policy Distillation for Flow Matching Models
May 8, 2026Zhen Fang, Wenxuan Huang, Yu Zeng +8Diffusion Model Alignment Flow Matching
University of Science and Technology of China · University of California, Los Angeles · 3The Chinese University of Hong Kong +1
HEART: Hyperspherical Embedding Alignment via Kent-Representation Traversal in Diffusion Models
May 8, 2026Arani Roy, Shristi Das Biswas, Kaushik RoyRepresentation Geometry Diffusion-Based Image Editing
Purdue University
Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models
May 7, 2026Zhikai Li, Yue Zhao, Edward Zhongwei Zhang +4Diffusion Model Alignment Preference Optimization
Institute of Automation, Chinese Academy of Sciences · University of California, Berkeley · University of California, Santa Barbara
Taming Outlier Tokens in Diffusion Transformers
May 6, 2026Xiaoyu Wu, Yifei Wang, Tsu-Jui Fu +3Diffusion Transformer Activation Outliers
Rice University · Apple
Advancing Aesthetic Image Generation via Composition Transfer
May 6, 2026Kai Zou, Zhiwei Zhao, Bin Liu +1Image Generation Compositional Image Generation
School of Cyber Science and Technology, University of Science and Technology of China, Anhui Province Key Laboratory of Digital Security, 96 Jinzhai Road, Hefei, 230026, Anhui, China. · School of Computer Science and Information Engineering, Hefei University of Technology, 193 Tunxi Road, Hefei, 230009, Anhui, China.
Towards General Preference Alignment: Diffusion Models at Nash Equilibrium
May 6, 2026Jiaming Hu, Jiamu Bai, Haoyu Wang +2Diffusion Model Alignment Preference Optimization
Boston University · Penn State University · University at Albany
Linearizing Vision Transformer with Test-Time Training
May 4, 2026Yining Li, Dongchen Han, Zeyu Liu +3Efficient Transformer Inference Self-Attention
Tsinghua University, Beijing, China
SteeringDiffusion: A Bottlenecked Activation Control Interface for Diffusion Models
May 3, 2026Fangzheng Wu, Brian SummaDiffusion Model Fine-Tuning Activation Steering
Department of Computer Science Tulane University
Disciplined Diffusion: Text-to-Image Diffusion Model against NSFW Generation
May 1, 2026Chi Zhang, Changjia Zhu, Xiaowen Li +2Adversarial Robustness Safe T2I Generation
Bellini College of Artificial Intelligence, Cybersecurity and Computing, University of South Florida, Tampa, FL, USA · Department of Electrical and Computer Engineering, College of Engineering, University of South Florida, Tampa, FL, USA
Colorful-Noise: Training-Free Low-Frequency Noise Manipulation for Color-Based Conditional Image Generation
May 1, 2026Nadav Z. Cohen, Ofir Abramovich, Ariel ShamirConditional Image Generation Controllable Image Generation
Reichman University, Israel
When Do Diffusion Models learn to Generate Multiple Objects?
Apr 30, 2026Yujin Jeong, Arnas Uselis, Iro Laina +2T2I Generation Compositional Image Generation
TU Darmstadt & hessian.AI · University of Tübingen · Visual Geometry Group, University of Oxford +1
AdvDMD: Adversarial Reward Meets DMD For High-Quality Few-Step Generation
Apr 29, 2026Xu Wang, Zexian Li, Litong Gong +2Diffusion Model Distillation Few-Step Diffusion Sampling
Shanghai Jiao Tong University · Alimama Tech
Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization
Apr 26, 2026Haosen Li, Wenshuo Chen, Lei Wang +3Diffusion Model Alignment Text-Image Alignment
1The Hong Kong University of Science and Technology (Guangzhou) · 2Griffith University & Data61/CSIRO
V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think
Apr 25, 2026Bingda Tang, Yuhui Zhang, Xiaohan Wang +3Diffusion Model Alignment Group Relative Policy Optimization
Stanford University · Tsinghua University · Amazon FAR +1
Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks
Apr 22, 2026Aljalila Aladawi, Mohammed Talha Alam, Fakhri KarrayDiffusion Model Fine-Tuning Diffusion Model Unlearning
Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE. · University of Waterloo, Ontario, Canada.
Who Defines Fairness? Target-Based Prompting for Demographic Representation in Generative Models
Apr 22, 2026Marzia Binta Nizam, James DavisSocial Bias in Language Models Algorithmic Fairness
University of California, Santa Cruz, USA
Hallucination Early Detection in Diffusion Models
Apr 22, 2026Federico Betti, Lorenzo Baraldi, Lorenzo Baraldi +2Compositional T2I Generation T2I Generation Evaluation
University of Trento, Italy. · Universit`a di Pisa, Italy. · University of Modena and Reggio Emilia, Italy.
Diff-SBSR: Learning Multimodal Feature-Enhanced Diffusion Models for Zero-Shot Sketch-Based 3D Shape Retrieval
Apr 21, 2026Hang Cheng, Fanhe Dong, Long Zeng3D Representation Learning T2I Diffusion Models
Tsinghua Shenzhen International Graduate School, Tsinghua University · Shenzhen, Guangdong, China
Long-Text-to-Image Generation via Compositional Prompt Decomposition
Apr 20, 2026Jen-Yuan Huang, Tong Lin, Yilun DuT2I Generation Compositional T2I Generation
Peking University · State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology. · Harvard University
Embedding Arithmetic: A Lightweight, Tuning-Free Framework for Post-hoc Bias Mitigation in Text-to-Image Models
Apr 20, 2026Venkatesh Thirugnana Sambandham, Torsten SchönT2I Generation Algorithmic Bias
AIMotion Bavaria, Technische Hochschule Ingolstadt, Esplanade 10, 85049 Ingolstadt, Germany
Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration
Apr 17, 2026Jun Li, Lizhi Xiong, Ziqiang Li +4Safe T2I Generation Controllable Image Generation
Nanjing University of Information Science and Technology · Southeast University · Nanjing University of Science and Technology
Correlation-Weighted Multi-Reward Optimization for Compositional Generation
Mar 19, 2026Jungmyung Wi, Hyunsoo Kim, Donghyun KimCompositional T2I Generation RL for Generative Models
Korea University · Korea Institute of Science and Technology
Q-Drift: Quantization-Aware Drift Correction for Diffusion Model Sampling
Mar 18, 2026Sooyoung Ryu, Mathieu Salzmann, Saqib JavedDiffusion Model Quantization Diffusion Model Sampling
Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea · School of Computer and Communication Sciences, EPFL, Lausanne, Switzerland · Meta Reality Labs, Redmond, USA
Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models
Mar 15, 2026Niklas Schweiger, Daniel Cremers, Karnik RamDiffusion Model Alignment Black-Box Optimization
Technical University of Munich, Germany · Munich Center for Machine Learning, Germany
Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models
Mar 13, 2026David McAllister, Miika Aittala, Tero Karras +4RL for Image Generation RL for Diffusion Models
UC Berkeley · NVIDIA
AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation
Mar 13, 2026Xuanhua Yin, Chuanzhi Xu, Haoxian Zhou +2Diffusion Transformer Image Generation
School of Computer Science, The University of Sydney, NSW 2006, Australia

May 11, 2026, cs.LGJ/K move · Enter open · S save

Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models

Nicola Novello, Andrea M. Tonello

University of Klagenfurt Klagenfurt, Austria

Cross-Attention Concept Erasure T2I Diffusion Models

Open paper AskPDF arXiv

Erasing specific concepts from text-to-image diffusion models is essential for avoiding the generation of copyrighted and explicit content. Closed-form concept erasure methods offer a fast alternative to backpropagation-based techniques, but they become less effective when scaling from smaller models such as Stable Diffusion 1.5 to larger models like Stable Diffusion XL. To maintain erasure effectiveness in these larger-scale architectures, we propose SParse cross-Attention-based Concept Erasure (SPACE). SPACE iteratively modifies the cross-attention parameters of a model with a closed-form update that jointly induces sparsity and erases target concepts. By concentrating the concept mapping to a lower-dimensional subspace, SPACE achieves superior erasure efficacy compared to dense baselines. Extensive experimental results show improvements in erasure effectiveness and robustness against adversarial prompts. Furthermore, SPACE achieves 80%-90% cross-attention sparsity, reducing the storage requirements for saving the modified parameters by 70%, demonstrating its memory efficiency.

Momentum

Related topics

Latest papers 240