中文
相关论文

相关论文: PSR: Scaling Multi-Subject Personalized Image Gene…

200 篇论文

Recent advancements in multimodal reward models (RMs) have significantly propelled the development of visual generation. Existing frameworks typically adopt Bradley-Terry-style preference modeling or leverage generative VLMs as judges, and…

计算机视觉与模式识别 · 计算机科学 2026-02-11 Yibin Wang , Yuhang Zang , Feng Han , Jiazi Bu , Yujie Zhou , Cheng Jin , Jiaqi Wang

Text-to-image generative models have recently attracted considerable interest, enabling the synthesis of high-quality images from textual prompts. However, these models often lack the capability to generate specific subjects from given…

计算机视觉与模式识别 · 计算机科学 2024-12-24 Yanting Miao , William Loh , Suraj Kothawade , Pascal Poupart , Abdullah Rashwan , Yeqing Li

Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single optimizeable objective. We seek to answer what it would take to simultaneously align a model…

机器学习 · 计算机科学 2025-10-02 Yiran Shen , Yu Xia , Jonathan Chang , Prithviraj Ammanabrolu

Subject-driven generation has garnered significant interest recently due to its ability to personalize text-to-image generation. Typical works focus on learning the new subject's private attributes. However, an important fact has not been…

计算机视觉与模式识别 · 计算机科学 2024-03-12 Pengchong Qiao , Lei Shang , Chang Liu , Baigui Sun , Xiangyang Ji , Jie Chen

Building upon large language models (LLMs), recent large multimodal models (LMMs) unify cross-model understanding and generation into a single framework. However, LMMs still struggle to achieve accurate vision-language alignment, prone to…

人工智能 · 计算机科学 2025-09-09 Jixiang Hong , Yiran Zhang , Guanzhong Wang , Yi Liu , Ji-Rong Wen , Rui Yan

Reward models (RMs) are crucial for aligning large language models (LLMs) with human preferences. They are trained using preference datasets where each example consists of one input prompt, two responses, and a preference label. As curating…

计算与语言 · 计算机科学 2025-03-18 Jiaming Shen , Ran Xu , Yennie Jun , Zhen Qin , Tianqi Liu , Carl Yang , Yi Liang , Simon Baumgartner , Michael Bendersky

Personalized text-to-image generation methods can generate customized images based on the reference images, which have garnered wide research interest. Recent methods propose a finetuning-free approach with a decoupled cross-attention…

计算机视觉与模式识别 · 计算机科学 2024-12-19 Qihan Huang , Siming Fu , Jinlong Liu , Hao Jiang , Yipeng Yu , Jie Song

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

计算与语言 · 计算机科学 2024-02-20 Meng Cao , Lei Shu , Lei Yu , Yun Zhu , Nevan Wichers , Yinxiao Liu , Lei Meng

Personalized search plays a crucial role in improving user search experience owing to its ability to build user profiles based on historical behaviors. Previous studies have made great progress in extracting personal signals from the query…

信息检索 · 计算机科学 2021-11-25 Yujia Zhou , Zhicheng Dou , Yutao Zhu , Ji-Rong Wen

Recent advancements in the text-rendering capabilities of image generation models have made the end-to-end creation of graphic design content, such as posters, increasingly feasible. However, existing reward models fall short of accurately…

Weakly supervised person search aims to jointly detect and match persons with only bounding box annotations. Existing approaches typically focus on improving the features by exploring relations of persons. However, scale variation problem…

计算机视觉与模式识别 · 计算机科学 2024-01-04 Benzhi Wang , Yang Yang , Jinlin Wu , Guo-jun Qi , Zhen Lei

Diffusion-based text-to-image generation has advanced significantly, yet customizing scenes with multiple distinct subjects while maintaining fine-grained control over their interactions remains challenging. Existing methods often struggle…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Pengxiang Cai , Mengyang Li

Recent advances in text-to-image diffusion models spurred research on personalization, i.e., a customized image synthesis, of subjects within reference images. Although existing personalization methods are able to alter the subjects'…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Yongjin Choi , Chanhun Park , Seung Jun Baek

Although subject-driven generation has been extensively explored in image generation due to its wide applications, it still has challenges in data scalability and subject expansibility. For the first challenge, moving from curating…

计算机视觉与模式识别 · 计算机科学 2025-04-04 Shaojin Wu , Mengqi Huang , Wenxu Wu , Yufeng Cheng , Fei Ding , Qian He

The rapid advancement in self-supervised representation learning has highlighted its potential to leverage unlabeled data for learning rich visual representations. However, the existing techniques, particularly those employing different…

计算机视觉与模式识别 · 计算机科学 2024-12-18 Sana Ayromlou , Vahid Reza Khazaie , Fereshteh Forghani , Arash Afkanpour

Recent advancements in generative models have significantly facilitated the development of personalized content creation. Given a small set of images with user-specific concept, personalized image generation allows to create images that…

计算机视觉与模式识别 · 计算机科学 2025-02-19 Yuxiang Wei , Yiheng Zheng , Yabo Zhang , Ming Liu , Zhilong Ji , Lei Zhang , Wangmeng Zuo

Personalized image synthesis has emerged as a pivotal application in text-to-image generation, enabling the creation of images featuring specific subjects in diverse contexts. While diffusion models have dominated this domain,…

计算机视觉与模式识别 · 计算机科学 2025-04-18 Kaiyue Sun , Xian Liu , Yao Teng , Xihui Liu

High-quality training triplets (instruction, original image, edited image) are essential for instruction-based image editing. Predominant training datasets (e.g., InsPix2Pix) are created using text-to-image generative models (e.g., Stable…

计算机视觉与模式识别 · 计算机科学 2025-03-21 Xin Gu , Ming Li , Libo Zhang , Fan Chen , Longyin Wen , Tiejian Luo , Sijie Zhu

Subject-driven text-to-image (T2I) generation aims to produce images that align with a given textual description, while preserving the visual identity from a referenced subject image. Despite its broad downstream applicability - ranging…

Recent progress in personalized image generation using diffusion models has been significant. However, development in the area of open-domain and non-fine-tuning personalized image generation is proceeding rather slowly. In this paper, we…

计算机视觉与模式识别 · 计算机科学 2024-05-21 Jian Ma , Junhao Liang , Chen Chen , Haonan Lu