English
Related papers

Related papers: HP-Edit: A Human-Preference Post-Training Framewor…

200 papers

Text-to-image diffusion models deliver high-quality images, yet aligning them with human preferences remains challenging. We revisit diffusion-based Direct Preference Optimization (DPO) for these models and identify a critical pathology:…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Minghao Fu , Guo-Hua Wang , Tianyu Cui , Qing-Guo Chen , Zhao Xu , Weihua Luo , Kaifu Zhang

Instruction-guided image editing has achieved remarkable progress, yet current models still face challenges with complex instructions and often require multiple samples to produce a desired result. Reinforcement Learning (RL) offers a…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Xin Luo , Jiahao Wang , Chenyuan Wu , Shitao Xiao , Xiyan Jiang , Defu Lian , Jiajun Zhang , Dong Liu , Zheng liu

Recent advances in diffusion models enable many powerful instruments for image editing. One of these instruments is text-driven image manipulations: editing semantic attributes of an image according to the provided text description. %…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Nikita Starodubcev , Dmitry Baranchuk , Valentin Khrulkov , Artem Babenko

We propose a method for editing images from human instructions: given an input image and a written instruction that tells the model what to do, our model follows these instructions to edit the image. To obtain training data for this…

Computer Vision and Pattern Recognition · Computer Science 2023-01-19 Tim Brooks , Aleksander Holynski , Alexei A. Efros

Our goal is to develop fine-grained real-image editing methods suitable for real-world applications. In this paper, we first summarize four requirements for these methods and propose a novel diffusion-based image editing framework with…

Computer Vision and Pattern Recognition · Computer Science 2023-06-01 Naoki Matsunaga , Masato Ishii , Akio Hayakawa , Kenji Suzuki , Takuya Narihira

The goal of aligning language models to human preferences requires data that reveal these preferences. Ideally, time and money can be spent carefully collecting and tailoring bespoke preference data to each downstream application. However,…

Artificial Intelligence · Computer Science 2024-09-17 Judy Hanwen Shen , Archit Sharma , Jun Qin

Current mainstream methods of aligning diffusion models with human preferences typically employ VLM-based reward models. However, these reward models, pre-trained for semantic alignment, struggle to capture the essential perceptual…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Jaxon Zhang , Binxin Yang , Hubery Yin , Chen Li , Jing Lyu

Graphic layouts serve as an important and engaging medium for visual communication across different channels. While recent layout generation models have demonstrated impressive capabilities, they frequently fail to align with nuanced human…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Varun Gopal , Rishabh Jain , Aradhya Mathur , Nikitha SR , Sohan Patnaik , Sudhir Yarram , Mayur Hemani , Balaji Krishnamurthy , Mausoom Sarkar

Retouching can significantly elevate the visual appeal of photos, but many casual photographers lack the expertise to do this well. To address this problem, previous works have proposed automatic retouching systems based on supervised…

Graphics · Computer Science 2018-02-09 Yuanming Hu , Hao He , Chenxi Xu , Baoyuan Wang , Stephen Lin

Image retouching aims to enhance the visual quality of photos. Considering the different aesthetic preferences of users, the target of retouching is subjective. However, current retouching methods mostly adopt deterministic models, which…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Zheng-Peng Duan , Jiawei zhang , Zheng Lin , Xin Jin , Dongqing Zou , Chunle Guo , Chongyi Li

Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm in artificial intelligence to align large models with human preferences. In this paper, we propose a novel statistical framework to simultaneously conduct the…

Machine Learning · Statistics 2026-05-01 Nan Lu , Ethan Lee , Ethan X. Fang , Junwei Lu

Diffusion models have demonstrated strong capabilities in generating high-fidelity 3D human poses, yet their iterative nature and multi-hypothesis requirements incur substantial computational cost. In this paper, we propose an Efficient…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Yuquan Bi , Hongsong Wang , Xinli Shi , Zhipeng Gui , Jie Gui , Yuan Yan Tang

The increasing availability of image-text pairs has largely fueled the rapid advancement in vision-language foundation models. However, the vast scale of these datasets inevitably introduces significant variability in data quality, which…

Computer Vision and Pattern Recognition · Computer Science 2024-09-05 Lei Zhang , Fangxun Shu , Tianyang Liu , Sucheng Ren , Hao Jiang , Cihang Xie

Diffusion models have opened the path to a wide range of text-based image editing frameworks. However, these typically build on the multi-step nature of the diffusion backwards process, and adapting them to distilled, fast-sampling methods…

Computer Vision and Pattern Recognition · Computer Science 2024-08-02 Gilad Deutch , Rinon Gal , Daniel Garibi , Or Patashnik , Daniel Cohen-Or

A critical component of the current generation of language models is preference alignment, which aims to precisely control the model's behavior to meet human needs and values. The most notable among such methods is Reinforcement Learning…

Artificial Intelligence · Computer Science 2024-10-22 Oh Joon Kwon , Daiki E. Matsunaga , Kee-Eung Kim

While reinforcement learning (RL) has become a more popular approach for robotics, designing sufficiently informative reward functions for complex tasks has proven to be extremely difficult due their inability to capture human intent and…

Robotics · Computer Science 2022-12-08 Joey Hejna , Dorsa Sadigh

Video diffusion alignment has been heavily relied on scalar rewards. These rewards are typically derived from learned reward models in human preference datasets, requiring additional training and extensive collection. Moreover, scalar…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Yifan Wang , Yanyu Li , Gordon Guocheng Qian , Sergey Tulyakov , Yun Fu , Anil Kag

Fine-tuning large language models (LLMs) on human preferences, typically through reinforcement learning from human feedback (RLHF), has proven successful in enhancing their capabilities. However, ensuring the safety of LLMs during…

Artificial Intelligence · Computer Science 2025-04-09 Wenxuan Zhang , Philip H. S. Torr , Mohamed Elhoseiny , Adel Bibi

Current metrics for text-to-image models typically rely on statistical metrics which inadequately represent the real preference of humans. Although recent work attempts to learn these preferences via human annotated images, they reduce the…

Computer Vision and Pattern Recognition · Computer Science 2024-05-24 Sixian Zhang , Bohan Wang , Junqiang Wu , Yan Li , Tingting Gao , Di Zhang , Zhongyuan Wang

To design rewards that align with human goals, Reinforcement Learning from Human Feedback (RLHF) has emerged as a prominent technique for learning reward functions from human preferences and optimizing policies via reinforcement learning…

Machine Learning · Computer Science 2025-05-14 Taehyun Cho , Seokhun Ju , Seungyub Han , Dohyeong Kim , Kyungjae Lee , Jungwoo Lee