English
Related papers

Related papers: A Dense Reward View on Aligning Text-to-Image Diff…

200 papers

Modern preference alignment methods, such as DPO, rely on divergence regularization to a reference model for training stability-but this creates a fundamental problem we call "reference mismatch." In this paper, we investigate the negative…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Jiwoo Hong , Sayak Paul , Noah Lee , Kashif Rasul , James Thorne , Jongheon Jeong

Preference optimization for diffusion models aims to align them with human preferences for images. Previous methods typically use Vision-Language Models (VLMs) as pixel-level reward models to approximate human preferences. However, when…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Tao Zhang , Cheng Da , Kun Ding , Huan Yang , Kun Jin , Yan Li , Tingting Gao , Di Zhang , Shiming Xiang , Chunhong Pan

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

In text-to-image generation tasks, the advancements of diffusion models have facilitated the fidelity of generated results. However, these models encounter challenges when processing text prompts containing multiple entities and attributes.…

Computation and Language · Computer Science 2024-04-23 Yihang Wu , Xiao Cao , Kaixin Li , Zitan Chen , Haonan Wang , Lei Meng , Zhiyong Huang

While recent advancements in generative modeling have significantly improved text-image alignment, some residual misalignment between text and image representations still remains. Some approaches address this issue by fine-tuning models in…

Computer Vision and Pattern Recognition · Computer Science 2025-12-11 Jaa-Yeon Lee , Byunghee Cha , Jeongsol Kim , Jong Chul Ye

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

Diffusion models have become the de-facto approach for generating visual data, which are trained to match the distribution of the training dataset. In addition, we also want to control generation to fulfill desired properties such as…

Machine Learning · Computer Science 2024-12-30 Dinghuai Zhang , Yizhe Zhang , Jiatao Gu , Ruixiang Zhang , Josh Susskind , Navdeep Jaitly , Shuangfei Zhai

Diffusion models have shown promising generative capabilities across diverse domains, yet aligning their outputs with desired reward functions remains a challenge, particularly in cases where reward functions are non-differentiable. Some…

Machine Learning · Computer Science 2025-06-04 Xiner Li , Masatoshi Uehara , Xingyu Su , Gabriele Scalia , Tommaso Biancalani , Aviv Regev , Sergey Levine , Shuiwang Ji

Text-to-image diffusion model alignment is critical for improving the alignment between the generated images and human preferences. While training-based methods are constrained by high computational costs and dataset requirements,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Xin Xie , Dong Gong

Recent text-to-image (T2I) diffusion and flow-matching models can produce highly realistic images from natural language prompts. In practical scenarios, T2I systems are often run in a ``generate--then--select'' mode: many seeds are sampled…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Huanlei Guo , Hongxin Wei , Bingyi Jing

Generative multimodal content is increasingly prevalent in much of the content creation arena, as it has the potential to allow artists and media personnel to create pre-production mockups by quickly bringing their ideas to life. The…

Recent text-to-image (T2I) diffusion models have achieved remarkable advancement, yet faithfully following complex textual descriptions remains challenging due to insufficient interactions between textual and visual features. Prior…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Binglei Li , Mengping Yang , Zhiyu Tan , Junping Zhang , Hao Li

Text-to-image diffusion models are a class of deep generative models that have demonstrated an impressive capacity for high-quality image generation. However, these models are susceptible to implicit biases that arise from web-scale…

Computer Vision and Pattern Recognition · Computer Science 2024-01-24 Yinan Zhang , Eric Tzeng , Yilun Du , Dmitry Kislyuk

Text-to-Image (T2I) diffusion/flow models have recently achieved remarkable progress in visual fidelity and text alignment. However, they remain limited when users need to precisely control image layouts, something that natural language…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Amadou S. Sangare , Adrien Maglo , Mohamed Chaouch , Bertrand Luvison

Text-to-image (T2I) diffusion models have the ability to build high-quality pictures from text prompts, but they pose safety concerns because they can generate offensive or disturbing imagery when provided with harmful inputs. Existing…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Chi Zhang , Changjia Zhu , Xiaowen Li , Yao Liu , Zhuo Lu

Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training…

Artificial Intelligence · Computer Science 2026-04-14 Shaoan Xie , Lingjing Kong , Xiangchen Song , Xinshuai Dong , Guangyi Chen , Eric P. Xing , Kun Zhang

Recent advancements in diffusion models (DMs) have been propelled by alignment methods that post-train models to better conform to human preferences. However, these approaches typically require computation-intensive training of a base model…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Zejian Li , Yize Li , Chenye Meng , Zhongni Liu , Yang Ling , Shengyuan Zhang , Guang Yang , Changyuan Yang , Zhiyuan Yang , Lingyun Sun

Reinforcement learning (RL) algorithms have been used recently to align diffusion models with downstream objectives such as aesthetic quality and text-image consistency by fine-tuning them to maximize a single reward function under a fixed…

Artificial Intelligence · Computer Science 2026-03-13 Min Cheng , Fatemeh Doudi , Dileep Kalathil , Mohammad Ghavamzadeh , Panganamala R. Kumar

The rapid advancement of text-to-image (T2I) diffusion models has enabled them to generate unprecedented results from given texts. However, as text inputs become longer, existing encoding methods like CLIP face limitations, and aligning the…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Luping Liu , Chao Du , Tianyu Pang , Zehan Wang , Chongxuan Li , Dong Xu

Diffusion models have achieved impressive results in generative tasks such as text-to-image synthesis, yet they often struggle to fully align outputs with nuanced user intent and maintain consistent aesthetic quality. Existing…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Dohyun Kim , Seungwoo Lyu , Seung Wook Kim , Paul Hongsuck Seo