English
Related papers

Related papers: EditReward: A Human-Aligned Reward Model for Instr…

200 papers

Reward models are used throughout the post-training of language models to capture nuanced signals from preference data and provide a training target for optimization across instruction following, reasoning, safety, and more domains. The…

Computation and Language · Computer Science 2026-04-24 Saumya Malik , Valentina Pyatkin , Sander Land , Jacob Morrison , Noah A. Smith , Hannaneh Hajishirzi , Nathan Lambert

Reinforcement Learning from Human/AI Feedback (RLHF/RLAIF) has been extensively utilized for preference alignment of text-to-image models. Existing methods face certain limitations in terms of both data and algorithm. For training data,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Xingyu Lu , Yuhang Hu , YiFan Zhang , Kaiyu Jiang , Changyi Liu , Tianke Zhang , Jinpeng Wang , Chun Yuan , Bin Wen , Fan Yang , Tingting Gao , Di Zhang

Natural language instructions are a powerful interface for editing the outputs of text-to-image diffusion models. However, several challenges need to be addressed: 1) underspecification (the need to model the implicit meaning of…

Computation and Language · Computer Science 2023-10-31 Tuhin Chakrabarty , Kanishk Singh , Arkadiy Saakyan , Smaranda Muresan

Human image editing includes tasks like changing a person's pose, their clothing, or editing the image according to a text prompt. However, prior work often tackles these tasks separately, overlooking the benefit of mutual reinforcement…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Nannan Li , Qing Liu , Krishna Kumar Singh , Yilin Wang , Jianming Zhang , Bryan A. Plummer , Zhe Lin

Despite recent advances in inversion and instruction-based image editing, existing approaches primarily excel at editing single, prominent objects but significantly struggle when applied to complex scenes containing multiple entities. To…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Bimsara Pathiraja , Maitreya Patel , Shivam Singh , Yezhou Yang , Chitta Baral

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…

Diffusion models have emerged as the de facto paradigm for video generation. However, their reliance on web-scale data of varied quality often yields results that are visually unappealing and misaligned with the textual prompts. To tackle…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Hangjie Yuan , Shiwei Zhang , Xiang Wang , Yujie Wei , Tao Feng , Yining Pan , Yingya Zhang , Ziwei Liu , Samuel Albanie , Dong Ni

Single-view 3D human reconstruction has achieved remarkable progress through the adoption of multi-view diffusion models, yet the recovered 3D humans often exhibit unnatural poses. This phenomenon becomes pronounced when reconstructing 3D…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Seunguk Do , Minwoo Huh , Joonghyuk Shin , Jaesik Park

Recent advances in foundation models highlight a clear trend toward unification and scaling, showing emergent capabilities across diverse domains. While image generation and editing have rapidly transitioned from task-specific to unified…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Xuan Ju , Tianyu Wang , Yuqian Zhou , He Zhang , Qing Liu , Nanxuan Zhao , Zhifei Zhang , Yijun Li , Yuanhao Cai , Shaoteng Liu , Daniil Pakhomov , Zhe Lin , Soo Ye Kim , Qiang Xu

We introduce $\texttt{Complex-Edit}$, a comprehensive benchmark designed to systematically evaluate instruction-based image editing models across instructions of varying complexity. To develop this benchmark, we harness GPT-4o to…

Computer Vision and Pattern Recognition · Computer Science 2025-04-18 Siwei Yang , Mude Hui , Bingchen Zhao , Yuyin Zhou , Nataniel Ruiz , Cihang Xie

Recent advances in instruction-guided image editing underscore the need for effective automated evaluation. While Vision-Language Models (VLMs) have been explored as judges, open-source models struggle with alignment, and proprietary models…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Sherry X. Chen , Yi Wei , Luowei Zhou , Suren Kumar

A plethora of text-guided image editing methods have recently been developed by leveraging the impressive capabilities of large-scale diffusion-based generative models such as Imagen and Stable Diffusion. A standardized evaluation protocol,…

Computer Vision and Pattern Recognition · Computer Science 2023-10-05 Samyadeep Basu , Mehrdad Saberi , Shweta Bhardwaj , Atoosa Malemir Chegini , Daniela Massiceti , Maziar Sanjabi , Shell Xu Hu , Soheil Feizi

Recent advances in text-driven image editing have been significant, yet the task of accurately evaluating these edited images continues to pose a considerable challenge. Different from the assessment of text-driven image generation,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Bowen Qu , Shangkun Sun , Xiaoyu Liang , Wei Gao

3D content creation from text prompts has shown remarkable success recently. However, current text-to-3D methods often generate 3D results that do not align well with human preferences. In this paper, we present a comprehensive framework,…

Computer Vision and Pattern Recognition · Computer Science 2024-03-22 Junliang Ye , Fangfu Liu , Qixiu Li , Zhengyi Wang , Yikai Wang , Xinzhou Wang , Yueqi Duan , Jun Zhu

Reward models are critical for reinforcement learning from human feedback, as they determine the alignment quality and reliability of generative models. For complex tasks such as image editing, reward models are required to capture global…

Recent text-to-image (T2I) models generate semantically coherent images from textual prompts, yet evaluating how well they align with individual user preferences remains an open challenge. Conventional evaluation methods, general reward…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Jeongeun Lee , Ryang Heo , Dongha Lee

Human feedback plays a critical role in learning and refining reward models for text-to-image generation, but the optimal form the feedback should take for learning an accurate reward function has not been conclusively established. This…

In this paper, we introduce OneReward, a unified reinforcement learning framework that enhances the model's generative capabilities across multiple tasks under different evaluation criteria using only \textit{One Reward} model. By employing…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Yuan Gong , Xionghui Wang , Jie Wu , Shiyin Wang , Yitong Wang , Xinglong Wu

Visual-prompt-guided edit transfer aims to learn image transformations directly from example pairs, offering more precise and controllable editing than purely text-driven approaches. However, existing diffusion transformer-based methods…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Lan Chen , Qi Mao , Yiren Song , Yuchao Gu , Siwei Ma

Evaluation of text generation to date has primarily focused on content created sequentially, rather than improvements on a piece of text. Writing, however, is naturally an iterative and incremental process that requires expertise in…

Computation and Language · Computer Science 2022-09-28 Jane Dwivedi-Yu , Timo Schick , Zhengbao Jiang , Maria Lomeli , Patrick Lewis , Gautier Izacard , Edouard Grave , Sebastian Riedel , Fabio Petroni