English
Related papers

Related papers: Let Triggers Control: Frequency-Aware Dropout for …

200 papers

Multi-subject image generation aims to synthesize images that faithfully preserve the identities of multiple reference subjects while following textual instructions. However, existing methods often suffer from identity inconsistency and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Yijia Xu , Zihao Wang , Jinshi Cui

The emergence of diffusion models has significantly advanced generative AI, improving the quality, realism, and creativity of image and video generation. Among them, Stable Diffusion (StableDiff) stands out as a key model for text-to-image…

Hardware Architecture · Computer Science 2025-07-03 Zhican Wang , Guanghui He , Hongxiang Fan

Regional prompting, or compositional generation, which enables fine-grained spatial control, has gained increasing attention for its practicality in real-world applications. However, previous methods either introduce additional trainable…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Zhennan Chen , Yajie Li , Haofan Wang , Zhibo Chen , Zhengkai Jiang , Jun Li , Qian Wang , Jian Yang , Ying Tai

Visual autoregressive (AR) generation offers a promising path toward unifying vision and language models, yet its performance remains suboptimal against diffusion models. Prior work often attributes this gap to tokenizer limitations and…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Qiyuan He , Yicong Li , Haotian Ye , Jinghao Wang , Xinyao Liao , Pheng-Ann Heng , Stefano Ermon , James Zou , Angela Yao

Recently, text-to-image models have been thriving. Despite their powerful generative capacity, our research has uncovered a lack of robustness in this generation process. Specifically, the introduction of small perturbations to the text…

Computer Vision and Pattern Recognition · Computer Science 2023-06-07 Chengbin Du , Yanxi Li , Zhongwei Qiu , Chang Xu

Recent advances in diffusion-based generative models have shown incredible promise for zero shot image-to-image translation and editing. Most of these approaches work by combining or replacing network-specific features used in the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Zeqi Gu , Ethan Yang , Abe Davis

Dropout is a widely used regularization technique in deep learning, but its effects are typically realized through stochastic masking rather than explicit optimization objectives. We propose a deterministic formulation that expresses…

Machine Learning · Computer Science 2026-04-23 Vidhi Agrawal , Illia Oleksiienko , Alexandros Iosifidis

Vision Transformers have demonstrated exceptional performance across various computer vision tasks, yet their quadratic computational complexity concerning token length remains a significant challenge. To address this, token reduction…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Dong-Jae Lee , Jiwan Hur , Jaehyun Choi , Jaemyung Yu , Junmo Kim

In human-centric content generation, the pre-trained text-to-image models struggle to produce user-wanted portrait images, which retain the identity of individuals while exhibiting diverse expressions. This paper introduces our efforts…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Renshuai Liu , Bowen Ma , Wei Zhang , Zhipeng Hu , Changjie Fan , Tangjie Lv , Yu Ding , Xuan Cheng

In text-to-image generation tasks, the advancements of diffusion models have facilitated the fidelity of generated results. However, these models encounter challenges when processing text prompts containing multiple entities and attributes.…

Computation and Language · Computer Science 2024-04-23 Yihang Wu , Xiao Cao , Kaixin Li , Zitan Chen , Haonan Wang , Lei Meng , Zhiyong Huang

Text-to-image (T2I) models excel on single-entity prompts but struggle with multi-entity scenes, often exhibiting attribute leakage, identity entanglement, and subject omissions. We present a principled theoretical framework that steers…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Eric Tillmann Bill , Enis Simsar , Thomas Hofmann

Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approaches. However, applying supervised fine-tuning (SFT) to diffusion models remains…

Computation and Language · Computer Science 2026-05-12 Guowei Xu , Wenxin Xu , Jiawang Zhao , Kaisheng Ma

Recent advancements in text-to-image models, such as Stable Diffusion, show significant demographic biases. Existing de-biasing techniques rely heavily on additional training, which imposes high computational costs and risks of compromising…

Artificial Intelligence · Computer Science 2025-03-28 Eunji Kim , Siwon Kim , Minjun Park , Rahim Entezari , Sungroh Yoon

Flexible image tokenizers aim to represent an image using an ordered 1D variable-length token sequence. This flexible tokenization is typically achieved through nested dropout, where a portion of trailing tokens is randomly truncated during…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Zixuan Fu , Lanqing Guo , Chong Wang , Binbin Song , Ding Liu , Bihan Wen

Prefix-based methods have emerged as a promising paradigm for Controllable Text Generation (CTG) due to their parameter efficiency. However, while effective in short sequences, their controllability tends to diminish as the generated…

Computation and Language · Computer Science 2026-05-19 Jiabing Yang , Yixiang Chen , Zichen Wen , Chenhang Cui , Peiyan Li , Yuan Xu , Bowen Fang , Tao Yu , Ruikang Lin , Yan Huang , Liang Wang

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

Diffusion models have recently become the dominant paradigm for image generation, yet existing systems struggle to interpret and follow numeric instructions for adjusting semantic attributes. In real-world creative scenarios, especially…

Computer Vision and Pattern Recognition · Computer Science 2026-01-12 Die Chen , Zhongjie Duan , Zhiwen Li , Cen Chen , Daoyuan Chen , Yaliang Li , Yingda Chen

Controllable text generation systems often leverage control codes to direct various properties of the output like style and length. Inspired by recent work on causal inference for NLP, this paper reveals a previously overlooked flaw in…

Computation and Language · Computer Science 2022-10-10 Junyi Chai , Reid Pryzant , Victor Ye Dong , Konstantin Golobokov , Chenguang Zhu , Yi Liu

Cross-domain few-shot learning (CD-FSL) requires models to generalize from limited labeled samples under significant distribution shifts. While recent methods enhance adaptability through lightweight task-specific modules, they operate…

Computer Vision and Pattern Recognition · Computer Science 2025-05-14 Ruixiao Shi , Fu Feng , Yucheng Xie , Jing Wang , Xin Geng

Text-to-image synthesis has achieved high-quality results with recent advances in diffusion models. However, text input alone has high spatial ambiguity and limited user controllability. Most existing methods allow spatial control through…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Yuki Endo