English
Related papers

Related papers: Sparse Autoencoder as a Zero-Shot Classifier for C…

200 papers

Text-to-image (T2I) diffusion models have achieved widespread success due to their ability to generate high-resolution, photorealistic images. These models are trained on large-scale datasets, like LAION-5B, often scraped from the internet.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Korada Sri Vardhana , Shrikrishna Lolla , Soma Biswas

As text-to-image diffusion models grow increasingly prevalent, the ability to remove specific concepts-mostly explicit content and many copyrighted characters or styles-has become essential for safety and compliance. Existing unlearning…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Junyeong Ahn , Seojin Yoon , Sungyong Baik

Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the $L_1$ penalty, which hinders reconstruction and scalability, and a lack…

Artificial Intelligence · Computer Science 2026-05-19 Ouns El Harzli , Hugo Wallner , Yoonsoo Nam , Haixuan Xavier Tao

We propose DeCoDi, a debiasing procedure for text-to-image diffusion-based models that changes the inference procedure, does not significantly change image quality, has negligible compute overhead, and can be applied in any diffusion-based…

Recent advances in text-to-image (T2I) diffusion models have seen rapid and widespread adoption. However, their powerful generative capabilities raise concerns about potential misuse for synthesizing harmful, private, or copyrighted…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Uichan Lee , Jeonghyeon Kim , Sangheum Hwang

Modern Text-to-Image (T2I) Diffusion models have revolutionized image editing by enabling the generation of high-quality photorealistic images. While the de facto method for performing edits with T2I models is through text instructions,…

Computer Vision and Pattern Recognition · Computer Science 2024-11-07 Ashutosh Srivastava , Tarun Ram Menta , Abhinav Java , Avadhoot Jadhav , Silky Singh , Surgan Jandial , Balaji Krishnamurthy

Diffusion models (DMs) have become the new trend of generative models and have demonstrated a powerful ability of conditional synthesis. Among those, text-to-image diffusion models pre-trained on large-scale image-text pairs are highly…

Computer Vision and Pattern Recognition · Computer Science 2023-03-06 Wenliang Zhao , Yongming Rao , Zuyan Liu , Benlin Liu , Jie Zhou , Jiwen Lu

Sparse Autoencoders (SAEs) have been successfully used to probe Large Language Models (LLMs) and extract interpretable concepts from their internal representations. These concepts are linear combinations of neuron activations that…

Computation and Language · Computer Science 2026-02-23 Mathis Le Bail , Jérémie Dentan , Davide Buscaldi , Sonia Vanier

Recent text-to-image models have achieved impressive results in generating high-quality images. However, when tasked with multi-concept generation creating images that contain multiple characters or objects, existing methods often suffer…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Yang Zhang , Rui Zhang , Xuecheng Nie , Haochen Li , Jikun Chen , Yifan Hao , Xin Zhang , Luoqi Liu , Ling Li

Text-to-image (T2I) models exhibit a significant yet under-explored "brand bias", a tendency to generate contents featuring dominant commercial brands from generic prompts, posing ethical and legal risks. We propose CIDER, a novel,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Fangjian Shen , Zifeng Liang , Chao Wang , Wushao Wen

Unsupervised approaches to large language model (LLM) interpretability, such as sparse autoencoders (SAEs), offer a way to decode LLM activations into interpretable and, ideally, controllable concepts. On the one hand, these approaches…

Machine Learning · Computer Science 2026-03-03 Shruti Joshi , Andrea Dittadi , Sébastien Lachapelle , Dhanya Sridhar

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,…

Machine Learning · Computer Science 2026-05-12 Nicola Novello , Andrea M. Tonello

Existing unlearning algorithms in text-to-image generative models often fail to preserve the knowledge of semantically related concepts when removing specific target concepts: a challenge known as adjacency. To address this, we propose FADE…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Kartik Thakral , Tamar Glaser , Tal Hassner , Mayank Vatsa , Richa Singh

In this paper we propose a new generative model of text, Step-unrolled Denoising Autoencoder (SUNDAE), that does not rely on autoregressive models. Similarly to denoising diffusion techniques, SUNDAE is repeatedly applied on a sequence of…

Computation and Language · Computer Science 2022-04-20 Nikolay Savinov , Junyoung Chung , Mikolaj Binkowski , Erich Elsen , Aaron van den Oord

Diffusion models have demonstrated remarkable image generation capabilities, but also pose risks in privacy and fairness by memorizing sensitive concepts or perpetuating biases. We propose a novel \textbf{concept erasure} method for…

Computer Vision and Pattern Recognition · Computer Science 2025-07-17 Zixuan Fu , Yan Ren , Finn Carter , Chenyue Wang , Ze Niu , Dacheng Yu , Emily Davis , Bo Zhang

Due to the recent success of diffusion models, text-to-image generation is becoming increasingly popular and achieves a wide range of applications. Among them, text-to-image editing, or continuous text-to-image generation, attracts lots of…

Computer Vision and Pattern Recognition · Computer Science 2024-01-05 Zihao Yu , Haoyang Li , Fangcheng Fu , Xupeng Miao , Bin Cui

Continual learning enables large language models to adapt to evolving tasks without retraining from scratch, yet catastrophic forgetting remains a central obstacle. Among continual learning methods, regularization-based approaches are…

Machine Learning · Computer Science 2026-05-26 Mingxu Zhang , Yuhan Li , Lujundong Li , Dazhong Shen , Hui Xiong , Ying Sun

Large-scale text-to-image models have demonstrated amazing ability to synthesize diverse and high-fidelity images. However, these models are often violated by several limitations. Firstly, they require the user to provide precise and…

Computer Vision and Pattern Recognition · Computer Science 2023-05-09 Yupei Lin , Sen Zhang , Xiaojun Yang , Xiao Wang , Yukai Shi

Sparse autoencoders (SAEs) are used to analyze embeddings, but their role and practical value are debated. We propose a new perspective on SAEs by demonstrating that they can be naturally understood as topic models. We propose a continuous…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Leander Girrbach , Zeynep Akata

Text-to-Image (T2I) has been prevalent in recent years, with most common condition tasks having been optimized nicely. Besides, counterfactual Text-to-Image is obstructing us from a more versatile AIGC experience. For those scenes that are…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Sifan Li , Ming Tao , Hao Zhao , Ling Shao , Hao Tang