中文
相关论文

相关论文: Subject-driven Text-to-Image Generation via Prefer…

200 篇论文

RLHF techniques like DPO can significantly improve the generation quality of text-to-image diffusion models. However, these methods optimize for a single reward that aligns model generation with population-level preferences, neglecting the…

机器学习 · 计算机科学 2025-01-14 Meihua Dang , Anikait Singh , Linqi Zhou , Stefano Ermon , Jiaming Song

Model-based reinforcement learning (MBRL) has gained much attention for its ability to learn complex behaviors in a sample-efficient way: planning actions by generating imaginary trajectories with predicted rewards. Despite its success, we…

机器学习 · 计算机科学 2024-02-20 Vint Lee , Pieter Abbeel , Youngwoon Lee

In subject-driven text-to-image generation, recent works have achieved superior performance by training the model on synthetic datasets containing numerous image pairs. Trained on these datasets, generative models can produce text-aligned…

计算机视觉与模式识别 · 计算机科学 2024-08-09 Yufan Zhou , Ruiyi Zhang , Kaizhi Zheng , Nanxuan Zhao , Jiuxiang Gu , Zichao Wang , Xin Eric Wang , Tong Sun

Due to the demand for personalizing image generation, subject-driven text-to-image generation method, which creates novel renditions of an input subject based on text prompts, has received growing research interest. Existing methods often…

计算机视觉与模式识别 · 计算机科学 2025-01-08 Shang Chai , Zihang Lin , Min Zhou , Xubin Li , Liansheng Zhuang , Houqiang Li

Text-to-image generation has advanced rapidly, yet aligning complex textual prompts with generated visuals remains challenging, especially with intricate object relationships and fine-grained details. This paper introduces Fast Prompt…

计算与语言 · 计算机科学 2024-12-12 Khalil Mrini , Hanlin Lu , Linjie Yang , Weilin Huang , Heng Wang

A common approach for aligning language models to human preferences is to first learn a reward model from preference data, and then use this reward model to update the language model. We study two closely related problems that arise in this…

计算与语言 · 计算机科学 2024-07-22 Zihao Wang , Chirag Nagpal , Jonathan Berant , Jacob Eisenstein , Alex D'Amour , Sanmi Koyejo , Victor Veitch

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…

人工智能 · 计算机科学 2026-02-02 Yihang Chen , Yuanhao Ban , Yunqi Hong , Cho-Jui Hsieh

Evaluating the pedagogical quality of AI tutors remains challenging: standard NLG metrics do not determine whether responses identify mistakes, scaffold reasoning, or avoid revealing the answers. For the task of mistake remediation, we…

计算与语言 · 计算机科学 2026-03-26 Kseniia Petukhova , Ekaterina Kochmar

Impressive advances in text-to-image (T2I) generative models have yielded a plethora of high performing models which are able to generate aesthetically appealing, photorealistic images. Despite the progress, these models still struggle to…

计算机视觉与模式识别 · 计算机科学 2024-03-27 Oscar Mañas , Pietro Astolfi , Melissa Hall , Candace Ross , Jack Urbanek , Adina Williams , Aishwarya Agrawal , Adriana Romero-Soriano , Michal Drozdzal

Recent Text-to-Image (T2I) generation models such as Stable Diffusion and Imagen have made significant progress in generating high-resolution images based on text descriptions. However, many generated images still suffer from issues such as…

Aligning large language models (LLMs) with human values and safety constraints is challenging, especially when objectives like helpfulness, truthfulness, and avoidance of harm conflict. Reinforcement Learning from Human Feedback (RLHF) has…

计算与语言 · 计算机科学 2025-03-31 Xuying Li , Zhuo Li , Yuji Kosuga , Victor Bian

This paper explores advancements in high-fidelity personalized image generation through the utilization of pre-trained text-to-image diffusion models. While previous approaches have made significant strides in generating versatile scenes…

计算机视觉与模式识别 · 计算机科学 2023-12-04 Zhonghao Wang , Wei Wei , Yang Zhao , Zhisheng Xiao , Mark Hasegawa-Johnson , Humphrey Shi , Tingbo Hou

Personalized text-to-image models allow users to generate varied styles of images (specified with a sentence) for an object (specified with a set of reference images). While remarkable results have been achieved using diffusion-based…

计算机视觉与模式识别 · 计算机科学 2024-07-19 Fanyue Wei , Wei Zeng , Zhenyang Li , Dawei Yin , Lixin Duan , Wen Li

Previous work on augmenting large multimodal models (LMMs) for text-to-image (T2I) generation has focused on enriching the input space of in-context learning (ICL). This includes providing a few demonstrations and optimizing image…

计算与语言 · 计算机科学 2025-01-14 Yongyu Mu , Hengyu Li , Junxin Wang , Xiaoxuan Zhou , Chenglong Wang , Yingfeng Luo , Qiaozhi He , Tong Xiao , Guocheng Chen , Jingbo Zhu

Recent text-to-image (T2I) models have benefited from large-scale and high-quality data, demonstrating impressive performance. However, these T2I models still struggle to produce images that are aesthetically pleasing, geometrically…

计算机视觉与模式识别 · 计算机科学 2024-03-28 Jianshu Guo , Wenhao Chai , Jie Deng , Hsiang-Wei Huang , Tian Ye , Yichen Xu , Jiawei Zhang , Jenq-Neng Hwang , Gaoang Wang

Text-to-image (T2I) models achieve high-fidelity generation through extensive training on large datasets. However, these models may unintentionally pick up undesirable biases of their training data, such as over-representation of particular…

计算机视觉与模式识别 · 计算机科学 2024-07-01 Shufan Li , Harkanwar Singh , Aditya Grover

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…

计算机视觉与模式识别 · 计算机科学 2025-11-26 Jeongeun Lee , Ryang Heo , Dongha Lee

Text-to-image generative models have made significant advancements in recent years; however, accurately capturing intricate details in textual prompts-such as entity missing, attribute binding errors, and incorrect relationships remains a…

Content safety is a fundamental challenge for text-to-image (T2I) models, yet prevailing methods enforce a debilitating trade-off between safety and generation quality. We argue that mitigating this trade-off hinges on addressing systemic…

计算机视觉与模式识别 · 计算机科学 2025-11-18 Shouwei Ruan , Zhenyu Wu , Yao Huang , Ruochen Zhang , Yitong Sun , Caixin Kang , Shiji Zhao , Xingxing Wei

Reinforcement learning (RL) has improved guided image generation with diffusion models by directly optimizing rewards that capture image quality, aesthetics, and instruction following capabilities. However, the resulting generative policies…

计算机视觉与模式识别 · 计算机科学 2024-06-25 Owen Oertell , Jonathan D. Chang , Yiyi Zhang , Kianté Brantley , Wen Sun