English
Related papers

Related papers: DP$^2$O-SR: Direct Perceptual Preference Optimizat…

200 papers

Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has…

Computer Vision and Pattern Recognition · Computer Science 2023-11-23 Bram Wallace , Meihua Dang , Rafael Rafailov , Linqi Zhou , Aaron Lou , Senthil Purushwalkam , Stefano Ermon , Caiming Xiong , Shafiq Joty , Nikhil Naik

The practical applications of diffusion models have been limited by the misalignment between generated images and corresponding text prompts. Recent studies have introduced direct preference optimization (DPO) to enhance the alignment of…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Zijing Hu , Fengda Zhang , Kun Kuang

The popularization of Text-to-Image (T2I) diffusion models enables the generation of high-quality images from text descriptions. However, generating diverse customized images with reference visual attributes remains challenging. This work…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Brian Nlong Zhao , Yuhang Xiao , Jiashu Xu , Xinyang Jiang , Yifan Yang , Dongsheng Li , Laurent Itti , Vibhav Vineet , Yunhao Ge

Memory-efficient personalization is critical for adapting text-to-image diffusion models while preserving user privacy and operating within the limited computational resources of edge devices. To this end, we propose a selective…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Seokeon Choi , Sunghyun Park , Hyoungwoo Park , Jeongho Kim , Sungrack Yun

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Machine Learning · Computer Science 2025-03-04 Adam Fisch , Jacob Eisenstein , Vicky Zayats , Alekh Agarwal , Ahmad Beirami , Chirag Nagpal , Pete Shaw , Jonathan Berant

Aligning large language models with human preferences is crucial for their safe deployment. While Direct Preference Optimization (DPO) offers an efficient alternative to reinforcement learning from human feedback, traditional DPO methods…

Artificial Intelligence · Computer Science 2025-07-30 Mengyang Li , Zhong Zhang

Text-to-Image (T2I) diffusion models have achieved remarkable success in image generation. Despite their progress, challenges remain in both prompt-following ability, image quality and lack of high-quality datasets, which are essential for…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Jingkun An , Yinghao Zhu , Zongjian Li , Enshen Zhou , Haoran Feng , Xijie Huang , Bohua Chen , Yemin Shi , Chengwei Pan

Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Junyi Wu , Weijian Luo , Haoyang Zheng , Ruizhe Zhang , Guang Lin

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

Aligning text-to-video diffusion models with human preferences is crucial for generating high-quality videos. Existing Direct Preference Otimization (DPO) methods rely on multi-sample ranking and task-specific critic models, which is…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Zitong Huang , Kaidong Zhang , Yukang Ding , Chao Gao , Rui Ding , Ying Chen , Wangmeng Zuo

Diffusion-based image super-resolution (SR) has recently attracted significant attention by leveraging the expressive power of large pre-trained text-to-image diffusion models (DMs). A central practical challenge is resolving the trade-off…

Image and Video Processing · Electrical Eng. & Systems 2026-01-26 Maxence Noble , Gonzalo Iñaki Quintana , Benjamin Aubin , Clément Chadebec

Single-image super-resolution (SISR) networks trained with perceptual and adversarial losses provide high-contrast outputs compared to those of networks trained with distortion-oriented losses, such as L1 or L2. However, it has been shown…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Seung Ho Park , Young Su Moon , Nam Ik Cho

We present Diffusion-KTO, a novel approach for aligning text-to-image diffusion models by formulating the alignment objective as the maximization of expected human utility. Since this objective applies to each generation independently,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Shufan Li , Konstantinos Kallidromitis , Akash Gokul , Yusuke Kato , Kazuki Kozuka

Diffusion models are widely used for generative tasks across domains. Given a pre-trained diffusion model, it is often desirable to fine-tune it further either to correct for errors in learning or to align with downstream applications.…

Despite the success of Reinforcement Learning from Human Feedback (RLHF) in language reasoning, its application to autoregressive Text-to-Image (T2I) generation is often constrained by the limited availability of human preference data. This…

Artificial Intelligence · Computer Science 2026-02-02 Yihang Chen , Yuanhao Ban , Yunqi Hong , Cho-Jui Hsieh

Image super-resolution pursuits reconstructing high-fidelity high-resolution counterpart for low-resolution image. In recent years, diffusion-based models have garnered significant attention due to their capabilities with rich prior…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Aiwen Jiang , Zhi Wei , Long Peng , Feiqiang Liu , Wenbo Li , Mingwen Wang

Omnidirectional image super-resolution (ODISR) aims to upscale low-resolution (LR) omnidirectional images (ODIs) to high-resolution (HR), catering to the growing demand for detailed visual content across a $ 180^{\circ}\times360^{\circ}$…

Image and Video Processing · Electrical Eng. & Systems 2026-03-04 Xuhan Sheng , Runyi Li , Bin Chen , Weiqi Li , Xu Jiang , Jian Zhang

Efficient text-to-image generation remains a challenging task due to the high computational costs associated with the multi-step sampling in diffusion models. Although distillation of pre-trained diffusion models has been successful in…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Jeeyung Kim , Ze Wang , Qiang Qiu

Efficiently aligning large-scale video diffusion models with human intent requires a scalable and trajectory-aware pathway that bridges the inherent discrepancy between training noise distributions and practical inference trajectories.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Jingyuan Zhu , Biaolong Chen , Le Zhang , Aixi Zhang , Hao Jiang , Pipei Huang

Diffusion models excel at capturing the natural design spaces of images, molecules, DNA, RNA, and protein sequences. However, rather than merely generating designs that are natural, we often aim to optimize downstream reward functions while…

‹ Prev 1 4 5 6 7 8 10 Next ›