English
Related papers

Related papers: DETONATE: A Benchmark for Text-to-Image Alignment …

200 papers

This paper introduces V2A-DPO, a novel Direct Preference Optimization (DPO) framework tailored for flow-based video-to-audio generation (V2A) models, incorporating key adaptations to effectively align generated audio with human preferences.…

Sound · Computer Science 2026-03-13 Nolan Chan , Timmy Gang , Yongqian Wang , Yuzhe Liang , Dingdong Wang

While recent text-to-image (T2I) models show impressive capabilities in synthesizing images from brief descriptions, their performance significantly degrades when confronted with long, detail-intensive prompts required in professional…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Qirui Jiao , Daoyuan Chen , Yilun Huang , Xika Lin , Ying Shen , Yaliang Li

Reinforcement learning from human feedback (RLHF) has proven effectiveness for aligning text-to-image (T2I) diffusion models with human preferences. Although Direct Preference Optimization (DPO) is widely adopted for its computational…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Jiamu Bai , Xin Yu , Meilong Xu , Weitao Lu , Xin Pan , Kiwan Maeng , Daniel Kifer , Jian Wang , Yu Wang

Text-to-Image (T2I) generative models are becoming increasingly crucial due to their ability to generate high-quality images, but also raise concerns about social biases, particularly in human image generation. Sociological research has…

Computer Vision and Pattern Recognition · Computer Science 2025-04-02 Hanjun Luo , Haoyu Huang , Ziye Deng , Xinfeng Li , Hewei Wang , Yingbin Jin , Yang Liu , Wenyuan Xu , Zuozhu Liu

Preference learning extends the performance of Code LLMs beyond traditional supervised fine-tuning by leveraging relative quality comparisons. In existing approaches, a set of n candidate solutions is evaluated based on test case success…

Computation and Language · Computer Science 2025-10-10 Jie Wu , Haoling Li , Xin Zhang , Xiao Liu , Yangyu Huang , Jianwen Luo , Yizhen Zhang , Zuchao Li , Ruihang Chu , Yujiu Yang , Scarlett Li

Radiography Report Generation (RRG) has gained significant attention in medical image analysis as a promising tool for alleviating the growing workload of radiologists. However, despite numerous advancements, existing methods have yet to…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Valentin Samokhin , Boris Shirokikh , Mikhail Goncharov , Dmitriy Umerenkov , Maksim Bobrin , Ivan Oseledets , Dmitry Dylov , Mikhail Belyaev

Generative modeling is widely regarded as one of the most essential problems in today's AI community, with text-to-image generation having gained unprecedented real-world impacts. Among various approaches, diffusion models have achieved…

Computer Vision and Pattern Recognition · Computer Science 2026-01-26 Xuyang Guo , Jiayan Huo , Yingyu Liang , Zhenmei Shi , Zhao Song , Jiahao Zhang , Zhen Zhuang

Text-to-Image(T2I) models have achieved remarkable success in image generation and editing, yet these models still have many potential issues, particularly in generating inappropriate or Not-Safe-For-Work(NSFW) content. Strengthening…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Sensen Gao , Xiaojun Jia , Yihao Huang , Ranjie Duan , Jindong Gu , Yang Bai , Yang Liu , Qing Guo

Text-to-Image (T2I) models have recently gained significant attention due to their ability to generate high-quality images and are consequently used in a wide range of applications. However, there are concerns about the gender bias of these…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Yunbo Lyu , Zhou Yang , Yuqing Niu , Jing Jiang , David Lo

Text-to-image diffusion models (T2I DMs) have achieved remarkable success in generating high-quality and diverse images from text prompts, yet recent studies have revealed their vulnerability to backdoor attacks. Existing attack methods…

Cryptography and Security · Computer Science 2025-08-05 Haoran Dai , Jiawen Wang , Ruo Yang , Manali Sharma , Zhonghao Liao , Yuan Hong , Binghui Wang

Direct preference optimization (DPO) methods have shown strong potential in aligning text-to-image diffusion models with human preferences by training on paired comparisons. These methods improve training stability by avoiding the REINFORCE…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Yi-Lun Wu , Bo-Kai Ruan , Chiang Tseng , Hong-Han Shuai

Text-to-image diffusion models often struggle to achieve accurate semantic alignment between generated images and text prompts while maintaining efficiency for deployment on resource-constrained hardware. Existing approaches either incur…

Computer Vision and Pattern Recognition · Computer Science 2025-07-02 Ziji Lu

Preference optimization has become a central paradigm for aligning large language models with human feedback. Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback by directly optimizing pairwise…

Machine Learning · Computer Science 2026-05-05 Inoussa Mouiche

Recent advancements in diffusion models trained on large-scale data have enabled the generation of indistinguishable human-level images, yet they often produce harmful content misaligned with human values, e.g., social bias, and offensive…

Computer Vision and Pattern Recognition · Computer Science 2024-10-17 Xingqi Wang , Xiaoyuan Yi , Xing Xie , Jia Jia

Recent studies have demonstrated significant progress in aligning text-to-image diffusion models with human preference via Reinforcement Learning from Human Feedback. However, while existing methods achieve high scores on automated reward…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Chubin Chen , Sujie Hu , Jiashu Zhu , Meiqi Wu , Jintao Chen , Yanxun Li , Nisha Huang , Chengyu Fang , Jiahong Wu , Xiangxiang Chu , Xiu Li

The rapid development of large language model (LLM) alignment algorithms has resulted in a complex and fragmented landscape, with limited clarity on the effectiveness of different methods and their inter-connections. This paper introduces…

Large language models (LLMs) require careful alignment to balance competing objectives - factuality, safety, conciseness, proactivity, and diversity. Existing studies focus on individual techniques or specific dimensions, lacking a holistic…

Machine Learning · Computer Science 2025-09-17 Denis Janiak , Julia Moska , Dawid Motyka , Karolina Seweryn , Paweł Walkowiak , Bartosz Żuk , Arkadiusz Janz

This paper develops a unified framework for image-to-image translation based on conditional diffusion models and evaluates this framework on four challenging image-to-image translation tasks, namely colorization, inpainting, uncropping, and…

Computer Vision and Pattern Recognition · Computer Science 2022-05-05 Chitwan Saharia , William Chan , Huiwen Chang , Chris A. Lee , Jonathan Ho , Tim Salimans , David J. Fleet , Mohammad Norouzi

Personalized text-to-image (T2I) generation has emerged as a key application for creating user-specific concepts from a few reference images. The core challenge is concept disentanglement: separating the target concept from irrelevant…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Minseo Kim , Minchan Kwon , Dongyeun Lee , Yunho Jeon , Junmo Kim

Human image generation is a key focus in image synthesis due to its broad applications, but even slight inaccuracies in anatomy, pose, or details can compromise realism. To address these challenges, we explore Direct Preference Optimization…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Sanghyeon Na , Yonggyu Kim , Hyunjoon Lee