English
Related papers

Related papers: DyCoRM: Dynamic Criterion-Aware Reward Modeling fo…

200 papers

The task of layout-to-image generation involves synthesizing images based on the captions of objects and their spatial positions. Existing methods still struggle in complex layout generation, where common bad cases include object missing,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-21 Bo Cheng , Yuhang Ma , Liebucha Wu , Shanyuan Liu , Ao Ma , Xiaoyu Wu , Dawei Leng , Yuhui Yin

The ability to collect a large dataset of human preferences from text-to-image users is usually limited to companies, making such datasets inaccessible to the public. To address this issue, we create a web app that enables text-to-image…

Computer Vision and Pattern Recognition · Computer Science 2023-11-27 Yuval Kirstain , Adam Polyak , Uriel Singer , Shahbuland Matiana , Joe Penna , Omer Levy

A critical bottleneck in deep reinforcement learning (DRL) is sample inefficiency, as training high-performance agents often demands extensive environmental interactions. Model-based reinforcement learning (MBRL) mitigates this by building…

Machine Learning · Computer Science 2025-09-30 Boxuan Zhang , Runqing Wang , Wei Xiao , Weipu Zhang , Jian Sun , Gao Huang , Jie Chen , Gang Wang

Text-to-Image (T2I) generation has achieved remarkable progress in recent years. Meanwhile, reinforcement learning methods, particularly those based on Group Relative Policy Optimization (GRPO), have attracted widespread attention and been…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Baoteng Li , Xianghao Zang , Xinran Wang , Xiangyu Na , Zhixiang He , Hao Sun , Chi Zhang , Zhongjiang He , Tianwei Cao , Kongming Liang , Zhanyu Ma

Recent studies extend the autoregression paradigm to text-to-image generation, achieving performance comparable to diffusion models. However, our new PairComp benchmark -- featuring test cases of paired prompts with similar syntax but…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Kaihang Pan , Wendong Bu , Yuruo Wu , Yang Wu , Kai Shen , Yunfei Li , Hang Zhao , Juncheng Li , Siliang Tang , Yueting Zhuang

The recent success of denoising diffusion models has significantly advanced text-to-image generation. While these large-scale pretrained models show excellent performance in general image synthesis, downstream objectives often require…

Computer Vision and Pattern Recognition · Computer Science 2024-11-27 Maorong Wang , Jiafeng Mao , Xueting Wang , Toshihiko Yamasaki

Recent advances in text-to-video generation have produced increasingly realistic and diverse content, yet evaluating such videos remains a fundamental challenge due to their multi-faceted nature encompassing visual quality, semantic…

Machine unlearning in text-to-image diffusion models aims to remove targeted concepts while preserving overall utility. Prior diffusion unlearning methods typically rely on supervised weight edits or global penalties; reinforcement-learning…

Machine Learning · Computer Science 2026-02-17 Mykola Vysotskyi , Zahar Kohut , Mariia Shpir , Taras Rumezhak , Volodymyr Karpiv

Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values. While benchmarks for general response…

Computation and Language · Computer Science 2026-04-09 Qiyao Ma , Dechen Gao , Rui Cai , Boqi Zhao , Hanchu Zhou , Junshan Zhang , Zhe Zhao

Text-to-image (T2I) generation has greatly enhanced creative expression, yet achieving preference-aligned generation in a real-time and training-free manner remains challenging. Previous methods often rely on static, pre-collected…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Yang Li , Songlin Yang , Xiaoxuan Han , Wei Wang , Jing Dong , Yueming Lyu , Ziyu Xue

Reward models play a critical role in guiding large language models toward outputs that align with human expectations. However, an open challenge remains in effectively utilizing test-time compute to enhance reward model performance. In…

Computation and Language · Computer Science 2025-05-21 Jiaxin Guo , Zewen Chi , Li Dong , Qingxiu Dong , Xun Wu , Shaohan Huang , Furu Wei

Reinforcement learning (RL) can improve the prompt following capability of text-to-image (T2I) models, yet obtaining high-quality reward signals remains challenging: CLIP Score is too coarse-grained, while VLM-based reward models (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Jinlong Liu , Wanggui He , Peng Zhang , Mushui Liu , Hao Jiang , Pipei Huang

Image-text retrieval, as a fundamental and important branch of information retrieval, has attracted extensive research attentions. The main challenge of this task is cross-modal semantic understanding and matching. Some recent works focus…

Computer Vision and Pattern Recognition · Computer Science 2023-04-24 Weijing Chen , Linli Yao , Qin Jin

Recent text-to-image (T2I) generative models allow for high-quality synthesis following either text instructions or visual examples. Despite their capabilities, these models face limitations in creating new, detailed creatures within…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Kam Woh Ng , Xiatian Zhu , Yi-Zhe Song , Tao Xiang

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…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Yanting Miao , William Loh , Suraj Kothawade , Pascal Poupart , Abdullah Rashwan , Yeqing Li

Image-to-poster generation is a high-demand task requiring not only local adjustments but also high-level design understanding. Models must generate text, layout, style, and visual elements while preserving semantic fidelity and aesthetic…

Computer Vision and Pattern Recognition · Computer Science 2026-02-13 Sixiang Chen , Jianyu Lai , Jialin Gao , Hengyu Shi , Zhongying Liu , Tian Ye , Junfeng Luo , Xiaoming Wei , Lei Zhu

Visual Text Rendering (VTR) remains a critical challenge in text-to-image generation, where even advanced models frequently produce text with structural anomalies such as distortion, blurriness, and misalignment. However, we find that…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Hanshen Zhu , Yuliang Liu , Xuecheng Wu , An-Lan Wang , Hao Feng , Dingkang Yang , Chao Feng , Can Huang , Jingqun Tang , Xiang Bai

In this paper, we make the first attempt to align diffusion models for image inpainting with human aesthetic standards via a reinforcement learning framework, significantly improving the quality and visual appeal of inpainted images.…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Kendong Liu , Zhiyu Zhu , Chuanhao Li , Hui Liu , Huanqiang Zeng , Junhui Hou

Text-to-image (T2I) diffusion models have achieved strong performance in semantic alignment, yet they still struggle with generating the correct number of objects specified in prompts. Existing approaches typically incorporate auxiliary…

Computer Vision and Pattern Recognition · Computer Science 2025-10-23 Nobline Yoo , Olga Russakovsky , Ye Zhu

The emergence of generative models enables the creation of texts and images tailored to users' preferences. Existing personalized generative models have two critical limitations: lacking a dedicated paradigm for accurate preference…

Information Retrieval · Computer Science 2026-04-23 Yuting Zhang , Ying Sun , Dazhong Shen , Ziwei Xie , Feng Liu , Changwang Zhang , Xiang Liu , Jun Wang , Hui Xiong