English
Related papers

Related papers: Reward-Agnostic Prompt Optimization for Text-to-Im…

200 papers

Text-to-audio (T2A) generation has advanced considerably in recent years, yet existing methods continue to face challenges in accurately rendering complex text prompts, particularly those involving intricate audio effects, and achieving…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-03 Yi Gu , Yanqing Liu , Chen Yang , Sheng Zhao

Reinforcement learning (RL) has become a standard approach for post-training large language models and, more recently, for improving image generation models, which uses reward functions to enhance generation quality and human preference…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Yunqi Hong , Kuei-Chun Kao , Hengguang Zhou , Cho-Jui Hsieh

Differentiable reinforcement learning (RL) frameworks like DiffRO offer a powerful approach for controllable text-to-speech (TTS), but are vulnerable to reward hacking, particularly for nuanced tasks like emotion control. The policy model…

Sound · Computer Science 2026-02-17 Cong Wang , Changfeng Gao , Yang Xiang , Zhihao Du , Keyu An , Han Zhao , Qian Chen , Xiangang Li , Yingming Gao , Ya Li

Automatic prompt optimization has recently emerged as a strategy for improving the quality of prompts used in Large Language Models (LLMs), with the goal of generating more accurate and useful responses. However, most prior work focuses on…

Computation and Language · Computer Science 2025-10-06 Juhyeon Lee , Wonduk Seo , Hyunjin An , Seunghyun Lee , Yi Bu

Recently, diffusion-based deep generative models (e.g., Stable Diffusion) have shown impressive results in text-to-image synthesis. However, current text-to-image models often require multiple passes of prompt engineering by humans in order…

Computation and Language · Computer Science 2023-11-14 Tingfeng Cao , Chengyu Wang , Bingyan Liu , Ziheng Wu , Jinhui Zhu , Jun Huang

Policy optimization for large language models often suffers from sparse reward signals in multi-step reasoning tasks. Critic-free methods like GRPO assign a single normalized outcome reward to all tokens, providing limited guidance for…

Machine Learning · Computer Science 2026-02-04 Ruiyi Ding , Yongxuan Lv , Xianhui Meng , Jiahe Song , Chao Wang , Chen Jiang , Yuan Cheng

Diffusion models have emerged as a dominant paradigm for generative modeling across a wide range of domains, including prompt-conditional generation. The vast majority of samplers, however, rely on forward discretization of the reverse…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Zhenghan Fang , Jian Zheng , Qiaozi Gao , Xiaofeng Gao , Jeremias Sulam

Aligning text-to-image (T2I) diffusion models with human preferences has emerged as a critical research challenge. While recent advances in this area have extended preference optimization techniques from large language models (LLMs) to the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-25 Junyong Kang , Seohyun Lim , Kyungjune Baek , Hyunjung Shim

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

Despite recent progress, reinforcement learning (RL)-based fine-tuning of diffusion models often struggles with generalization, composability, and robustness against reward hacking. Recent studies have explored prompt refinement as a…

Machine Learning · Computer Science 2026-03-26 Suhyeon Lee , Jong Chul Ye

Reward finetuning has emerged as a promising approach to aligning foundation models with downstream objectives. Remarkable success has been achieved in the language domain by using reinforcement learning (RL) to maximize rewards that…

Machine Learning · Computer Science 2024-03-29 Fei Deng , Qifei Wang , Wei Wei , Matthias Grundmann , Tingbo Hou

Large language models (LLMs) demonstrate impressive performance but lack the flexibility to adapt to human preferences quickly without retraining. In this work, we introduce Test-time Preference Optimization (TPO), a framework that aligns…

Computation and Language · Computer Science 2025-01-23 Yafu Li , Xuyang Hu , Xiaoye Qu , Linjie Li , Yu Cheng

Flow matching models (FMs) have revolutionized text-to-image (T2I) generation, with reinforcement learning (RL) serving as a critical post-training strategy for alignment with reward objectives. In this research, we show that current RL…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Fu-Yun Wang , Han Zhang , Michael Gharbi , Hongsheng Li , Taesung Park

Text-to-image generation models are powerful but difficult to use. Users craft specific prompts to get better images, though the images can be repetitive. This paper proposes a Prompt Expansion framework that helps users generate…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Siddhartha Datta , Alexander Ku , Deepak Ramachandran , Peter Anderson

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). In this paper, we propose a novel and enhanced version of DPO based on curriculum…

Computer Vision and Pattern Recognition · Computer Science 2025-05-12 Florinel-Alin Croitoru , Vlad Hondru , Radu Tudor Ionescu , Nicu Sebe , Mubarak Shah

As Text-to-Image (T2I) generation becomes widespread, third-party platforms increasingly integrate multiple model APIs for convenient image creation. However, false claims of using official models can mislead users and harm model owners'…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Zidong Zhao , Yihao Huang , Qing Guo , Tianlin Li , Anran Li , Kailong Wang , Jin Song Dong , Geguang Pu

The rapid progress in diffusion-based text-to-image (T2I) generation has created an urgent need for interpretable automatic evaluation methods that can assess the quality of generated images, therefore reducing the human annotation burden.…

Artificial Intelligence · Computer Science 2025-05-26 Zi-Ao Ma , Tian Lan , Rong-Cheng Tu , Shu-Hang Liu , Heyan Huang , Zhijing Wu , Chen Xu , Xian-Ling Mao

Recent advancements highlight the importance of GRPO-based reinforcement learning methods and benchmarking in enhancing text-to-image (T2I) generation. However, current methods using pointwise reward models (RM) for scoring generated images…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Yibin Wang , Zhimin Li , Yuhang Zang , Yujie Zhou , Jiazi Bu , Chunyu Wang , Qinglin Lu , Cheng Jin , Jiaqi Wang

The performance of text-to-image diffusion models may be improved at test-time by scaling computation to search for a generated image that maximizes a given reward function. While existing trajectory level exploration methods improve the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Qingtao Yu , Changlin Song , Minghao Sun , Zhengyang Yu , Vinay Kumar Verma , Soumya Roy , Sumit Negi , Hongdong Li , Dylan Campbell

Test-time alignment (TTA) aims to adapt models to specific rewards during inference. However, existing methods tend to either under-optimise or over-optimise (reward hack) the target reward function. We propose Null-Text Test-Time Alignment…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Taehoon Kim , Henry Gouk , Timothy Hospedales