English
Related papers

Related papers: On Mechanistic Knowledge Localization in Text-to-I…

200 papers

Large Language Models store extensive factual knowledge acquired during large-scale pre-training. However, this knowledge is inherently static, reflecting only the state of the world at the time of training. Knowledge editing has emerged as…

Computation and Language · Computer Science 2025-10-14 Geunyeong Jeong , Juoh Sun , Seonghee Lee , Harksoo Kim

Understanding how knowledge is distributed across the layers of generative models is crucial for improving interpretability, controllability, and adaptation. While prior work has explored knowledge localization in UNet-based architectures,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Arman Zarei , Samyadeep Basu , Keivan Rezaei , Zihao Lin , Sayan Nag , Soheil Feizi

When automatically generating a sentence description for an image or video, it often remains unclear how well the generated caption is grounded, that is whether the model uses the correct image regions to output particular words, or if the…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Chih-Yao Ma , Yannis Kalantidis , Ghassan AlRegib , Peter Vajda , Marcus Rohrbach , Zsolt Kira

Text-to-Image models have introduced a remarkable leap in the evolution of machine learning, demonstrating high-quality synthesis of images from a given text-prompt. However, these powerful pretrained models still lack control handles that…

Computer Vision and Pattern Recognition · Computer Science 2022-11-28 Andrey Voynov , Kfir Aberman , Daniel Cohen-Or

Convolutional neural networks (CNNs) learn abstract features to perform object classification, but understanding these features remains challenging due to difficult-to-interpret results or high computational costs. We propose an automatic…

Computer Vision and Pattern Recognition · Computer Science 2024-09-26 Maren H. Wehrheim , Pamela Osuna-Vargas , Matthias Kaschube

Machine unlearning--the ability to remove designated concepts from a pre-trained model--has advanced rapidly, particularly for text-to-image diffusion models. However, existing methods typically assume that unlearning requests arrive all at…

Machine Learning · Computer Science 2026-03-04 Justin Lee , Zheda Mai , Jinsu Yoo , Chongyu Fan , Cheng Zhang , Wei-Lun Chao

Diffusion models have revolted the field of text-to-image generation recently. The unique way of fusing text and image information contributes to their remarkable capability of generating highly text-related images. From another…

Computer Vision and Pattern Recognition · Computer Science 2024-10-02 Changming Xiao , Qi Yang , Feng Zhou , Changshui Zhang

Text-guided diffusion models have significantly advanced image editing, enabling highly realistic and local modifications based on textual prompts. While these developments expand creative possibilities, their malicious use poses…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Valentina Bazyleva , Nicolo Bonettini , Gaurav Bharaj

Diffusion-based models have achieved state-of-the-art performance on text-to-image synthesis tasks. However, one critical limitation of these models is the low fidelity of generated images with respect to the text description, such as…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Qiucheng Wu , Yujian Liu , Handong Zhao , Trung Bui , Zhe Lin , Yang Zhang , Shiyu Chang

Knowledge editing, which aims to update the knowledge encoded in language models, can be deceptive. Despite the fact that many existing knowledge editing algorithms achieve near-perfect performance on conventional metrics, the models edited…

Computation and Language · Computer Science 2025-05-20 Jiakuan Xie , Pengfei Cao , Yubo Chen , Kang Liu , Jun Zhao

Despite the tremendous success in text-to-image generative models, localized text-to-image generation (that is, generating objects or features at specific locations in an image while maintaining a consistent overall generation) still…

Computer Vision and Pattern Recognition · Computer Science 2023-06-27 Yutong He , Ruslan Salakhutdinov , J. Zico Kolter

Recent text-to-image diffusion models have reached an unprecedented level in generating high-quality images. However, their exclusive reliance on textual prompts often falls short in precise control of image compositions. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2024-03-27 Peiang Zhao , Han Li , Ruiyang Jin , S. Kevin Zhou

Knowledge editing is a promising way to improve factuality in large language models, but recent studies have shown significant model degradation during sequential editing. In this paper, we formalize the popular locate-then-edit methods as…

Computation and Language · Computer Science 2025-05-22 Akshat Gupta , Phudish Prateepamornkul , Maochuan Lu , Ahmed Alaa , Thomas Hartvigsen , Gopala Anumanchipalli

Grounding textual phrases in visual content is a meaningful yet challenging problem with various potential applications such as image-text inference or text-driven multimedia interaction. Most of the current existing methods adopt the…

Computer Vision and Pattern Recognition · Computer Science 2018-05-03 Zhiyuan Fang , Shu Kong , Tianshu Yu , Yezhou Yang

Concept erasure in text-to-image diffusion models seeks to remove undesired concepts while preserving overall generative capability. Localized erasure methods aim to restrict edits to the spatial region occupied by the target concept.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Zhuan Shi , Alireza Dehghanpour Farashah , Rik de Vries , Golnoosh Farnadi

Unsupervised learning of keypoints and landmarks has seen significant progress with the help of modern neural network architectures, but performance is yet to match the supervised counterpart, making their practicability questionable. We…

Computer Vision and Pattern Recognition · Computer Science 2024-05-24 Eric Hedlin , Gopal Sharma , Shweta Mahajan , Xingzhe He , Hossam Isack , Abhishek Kar Helge Rhodin , Andrea Tagliasacchi , Kwang Moo Yi

Text-to-image diffusion models have achieved remarkable progress in generating diverse and realistic images from textual descriptions. However, they still struggle with personalization, which requires adapting a pretrained model to depict…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Seoyun Yang , Gihoon Kim , Taesup Kim

A basic aspiration for interpretability research in large language models is to "localize" semantically meaningful behaviors to particular components within the LLM. There are various heuristics for finding candidate locations within the…

Machine Learning · Computer Science 2025-02-20 Zihao Wang , Victor Veitch

Large language models often retain unintended content, prompting growing interest in knowledge unlearning. Recent approaches emphasize localized unlearning, restricting parameter updates to specific regions in an effort to remove target…

Computation and Language · Computer Science 2026-02-12 Hwiyeong Lee , Uiji Hwang , Hyelim Lim , Taeuk Kim

Text-guided image editing aims to modify specific regions of an image according to natural language instructions while maintaining the general structure and the background fidelity. Existing methods utilize masks derived from…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Achint Soni , Meet Soni , Sirisha Rambhatla