English
Related papers

Related papers: MidSteer: Optimal Affine Framework for Steering Ge…

200 papers

Steering methods influence Large Language Model behavior by identifying semantic directions in hidden representations, but are typically realized through inference-time activation interventions that apply a fixed, global modification to the…

Computation and Language · Computer Science 2026-03-04 Chung-En Sun , Ge Yan , Zimo Wang , Tsui-Wei Weng

Recent advancements in GANs and diffusion models have enabled the creation of high-resolution, hyper-realistic images. However, these models may misrepresent certain social groups and present bias. Understanding bias in these models remains…

Computer Vision and Pattern Recognition · Computer Science 2023-02-23 Cristian Muñoz , Sara Zannone , Umar Mohammed , Adriano Koshiyama

The rapid proliferation of large-scale text-to-image diffusion (T2ID) models has raised serious concerns about their potential misuse in generating harmful content. Although numerous methods have been proposed for erasing undesired concepts…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Koushik Srivatsan , Fahad Shamshad , Muzammal Naseer , Vishal M. Patel , Karthik Nandakumar

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

Activation steering has emerged as a cost-effective paradigm for modifying large language model (LLM) behaviors. Existing methods typically intervene at the block level, steering the bundled activations of selected attention heads,…

Computation and Language · Computer Science 2026-02-05 Zijian Feng , Tianjiao Li , Zixiao Zhu , Hanzhang Zhou , Junlang Qian , Li Zhang , Jia Jim Deryl Chua , Lee Onn Mak , Gee Wah Ng , Kezhi Mao

Centred on content modification and style preservation, Scene Text Editing (STE) remains a challenging task despite considerable progress in text-to-image synthesis and text-driven image manipulation recently. GAN-based STE methods…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Weichao Zeng , Yan Shu , Zhenhang Li , Dongbao Yang , Yu Zhou

Activation steering methods were shown to be effective in conditioning language model generation by additively intervening over models' intermediate representations. However, the evaluation of these techniques has so far been limited to…

Computation and Language · Computer Science 2024-12-02 Daniel Scalena , Gabriele Sarti , Malvina Nissim

In recent years, diffusion models have been widely adopted for image inpainting tasks due to their powerful generative capabilities, achieving impressive results. Existing multimodal inpainting methods based on diffusion models often…

Computer Vision and Pattern Recognition · Computer Science 2025-07-30 Qimin Wang , Xinda Liu , Guohua Geng

Prevailing alignment methods induce opaque parameter changes, obscuring what models truly learn. To address this, we introduce Feature Steering with Reinforcement Learning (FSRL), a framework that trains a lightweight adapter to steer model…

Artificial Intelligence · Computer Science 2025-12-02 Jeremias Ferrao , Matthijs van der Lende , Ilija Lichkovski , Clement Neo

Diffusion probabilistic models have achieved enormous success in the field of image generation and manipulation. In this paper, we explore a novel paradigm of using the diffusion model and classifier guidance in the latent semantic space…

Computer Vision and Pattern Recognition · Computer Science 2023-05-25 Changhao Shi , Haomiao Ni , Kai Li , Shaobo Han , Mingfu Liang , Martin Renqiang Min

Remarkable progress in text-to-image diffusion models has brought a major concern about potentially generating images on inappropriate or trademarked concepts. Concept erasing has been investigated with the goals of deleting target concepts…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Byung Hyun Lee , Sungjin Lim , Seunggyu Lee , Dong Un Kang , Se Young Chun

Despite the tremendous success of diffusion generative models in text-to-image generation, replicating this success in the domain of image compression has proven difficult. In this paper, we demonstrate that diffusion can significantly…

Image and Video Processing · Electrical Eng. & Systems 2024-03-11 Emiel Hoogeboom , Eirikur Agustsson , Fabian Mentzer , Luca Versari , George Toderici , Lucas Theis

Instruction-based image editing exhibits heterogeneous difficulty not only across cases but also across regions of an image, motivating refinement approaches that allocate correction to where the model struggles. Existing refinement signals…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Weitai Kang , Xiaohang Zhan , Yizhou Wang , Mang Tik Chiu , Jason Kuen , Kangning Liu , Yan Yan

So-called implicit behavioral cloning with energy-based models has shown promising results in robotic manipulation tasks. We tested if the method's advantages carry on to controlling the steering of a real self-driving car with an…

Robotics · Computer Science 2023-06-27 Mikita Balesni , Ardi Tampuu , Tambet Matiisen

Discrete Diffusion Language Models (DLMs) offer a promising non-autoregressive alternative for text generation, yet effective mechanisms for inference-time control remain relatively underexplored. Existing approaches include sampling-level…

Computation and Language · Computer Science 2026-01-30 Eden Avrahami , Eliya Nachmani

Recent progress in Multimodal Large Language Models (MLLMs) has unlocked powerful cross-modal reasoning abilities, but also raised new safety concerns, particularly when faced with adversarial multimodal inputs. To improve the safety of…

Computation and Language · Computer Science 2025-09-24 Lyucheng Wu , Mengru Wang , Ziwen Xu , Tri Cao , Nay Oo , Bryan Hooi , Shumin Deng

Design inspiration is crucial for establishing the direction of a design as well as evoking feelings and conveying meanings during the conceptual design process. Many practice designers use text-based searches on platforms like Pinterest to…

Human-Computer Interaction · Computer Science 2024-07-18 Ye Wang , Nicole B. Damen , Thomas Gale , Voho Seo , Hooman Shayani

Text-to-Image diffusion models can produce undesirable content that necessitates concept erasure. However, existing methods struggle with under-erasure, leaving residual traces of targeted concepts, or over-erasure, mistakenly eliminating…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Yuyang Xue , Edward Moroshko , Feng Chen , Jingyu Sun , Steven McDonagh , Sotirios A. Tsaftaris

Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, unlike discriminative vision-and-language models, it is a non-trivial task to subject these…

Computer Vision and Pattern Recognition · Computer Science 2023-11-06 Benno Krojer , Elinor Poole-Dayan , Vikram Voleti , Christopher Pal , Siva Reddy

Controllable layout generation refers to the process of creating a plausible visual arrangement of elements within a graphic design (e.g., document and web designs) with constraints representing design intentions. Although recent…

Computer Vision and Pattern Recognition · Computer Science 2024-05-17 Jian Chen , Ruiyi Zhang , Yufan Zhou , Rajiv Jain , Zhiqiang Xu , Ryan Rossi , Changyou Chen