English
Related papers

Related papers: A Minimalist Method for Fine-tuning Text-to-Image …

200 papers

We introduce Random Reward Perturbation (RRP), a novel exploration strategy for reinforcement learning (RL). Our theoretical analyses demonstrate that adding zero-mean noise to environmental rewards effectively enhances policy diversity…

Machine Learning · Computer Science 2025-06-11 Haozhe Ma , Guoji Fu , Zhengding Luo , Jiele Wu , Tze-Yun Leong

Offline reinforcement learning (RL) optimizes a policy using only a fixed dataset, making it a practical approach in scenarios where interaction with the environment is costly. Due to this limitation, generalization ability is key to…

Machine Learning · Computer Science 2025-07-04 JunHyeok Oh , Byung-Jun Lee

Recent advancements in generative models have sparked a significant interest within the machine learning community. Particularly, diffusion models have demonstrated remarkable capabilities in synthesizing images and speech. Studies such as…

Machine Learning · Computer Science 2024-11-19 Jingyi Chen , Ju-Seung Byun , Micha Elsner , Andrew Perrault

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

Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has…

Computer Vision and Pattern Recognition · Computer Science 2023-11-23 Bram Wallace , Meihua Dang , Rafael Rafailov , Linqi Zhou , Aaron Lou , Senthil Purushwalkam , Stefano Ermon , Caiming Xiong , Shafiq Joty , Nikhil Naik

Diffusion models recently emerged as a powerful paradigm for recommender systems, offering state-of-the-art performance by modeling the generative process of user-item interactions. However, training such models from scratch is both…

Information Retrieval · Computer Science 2025-11-11 Yu Hou , Hua Li , Ha Young Kim , Won-Yong Shin

Group Relative Policy Optimization (GRPO) is highly effective for post-training autoregressive (AR) language models, yet its direct application to diffusion large language models (dLLMs) often triggers reward collapse. We identify two…

Machine Learning · Computer Science 2026-03-10 Jianyuan Zhong , Kaibo Wang , Ding Ding , Zijin Feng , Haoli Bai , Yang Xiang , Jiacheng Sun , Qiang Xu

Reinforcement learning (RL) has been successfully applied to autoregressive (AR) and diffusion models. However, extending RL to hybrid AR-diffusion frameworks remains challenging due to interleaved inference and noisy log-probability…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Xiaoxiao Ma , Jiachen Lei , Tianfei Ren , Jie Huang , Siming Fu , Aiming Hao , Jiahong Wu , Xiangxiang Chu , Feng Zhao

Recently, reinforcement learning (RL) has been shown to greatly enhance the reasoning capabilities of large language models (LLMs), and RL-based approaches have been progressively applied to visual multimodal tasks. However, the audio…

Sound · Computer Science 2025-05-15 Gang Li , Jizhong Liu , Heinrich Dinkel , Yadong Niu , Junbo Zhang , Jian Luan

Diffusion models generate highly realistic images but often struggle with precise text-image alignment. While recent post-training methods improve alignment using external rewards or human preference signals, their performance heavily…

Machine Learning · Computer Science 2026-05-29 Jaa-Yeon Lee , Yeobin Hong , Taesung Kwon , Jong Chul Ye

Recent advances in diffusion models have led to impressive image generation capabilities, but aligning these models with human preferences remains challenging. Reward-based fine-tuning using models trained on human feedback improves…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Dmitrii Sorokin , Maksim Nakhodnov , Andrey Kuznetsov , Aibek Alanov

Without using explicit reward, direct preference optimization (DPO) employs paired human preference data to fine-tune generative models, a method that has garnered considerable attention in large language models (LLMs). However, exploration…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Yunhong Lu , Qichao Wang , Hengyuan Cao , Xierui Wang , Xiaoyin Xu , Min Zhang

Self-rewarding have emerged recently as a powerful tool in the field of Natural Language Processing (NLP), allowing language models to generate high-quality relevant responses by providing their own rewards during training. This innovative…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Safouane El Ghazouali , Arnaud Gucciardi , Umberto Michelucci

GRPO is a standard approach to endowing pretrained LLMs with reasoning capabilities. It estimates the advantage of an outcome from a group of $K$ outcomes, and promotes those with positive advantages inside a trust region. Since GRPO…

Machine Learning · Computer Science 2026-02-02 Wenzheng Zhang , Karl Stratos

This paper introduces a novel approach to aesthetic quality improvement in pre-trained text-to-image diffusion models when given a simple prompt. Our method, dubbed Prompt Embedding Optimization (PEO), leverages a pre-trained text-to-image…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Hovhannes Margaryan , Bo Wan , Tinne Tuytelaars

Post-training alignment of diffusion models relies on simplified signals, such as scalar rewards or binary preferences. This limits alignment with complex human expertise, which is hierarchical and fine-grained. To address this, we first…

Computer Vision and Pattern Recognition · Computer Science 2026-01-09 Chenye Meng , Zejian Li , Zhongni Liu , Yize Li , Changle Xie , Kaixin Jia , Ling Yang , Huanghuang Deng , Shiying Ding , Shengyuan Zhang , Jiayi Li , Lingyun Sun

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…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Amir Mohammad Izadi , Seyed Mohammad Hadi Hosseini , Soroush Vafaie Tabar , Ali Abdollahi , Armin Saghafian , Mahdieh Soleymani Baghshah

Reinforcement learning from human feedback (RLHF) has been popular for aligning text-to-image (T2I) diffusion models with human preferences. As a mainstream branch of RLHF, Direct Preference Optimization (DPO) offers a computationally…

Machine Learning · Computer Science 2026-05-07 Jiaming Hu , Jiamu Bai , Haoyu Wang , Debarghya Mukherjee , Ioannis Ch. Paschalidis

With the advancement of pre-trained vision-language (VL) models, enhancing the alignment between visual and linguistic modalities in downstream tasks has emerged as a critical challenge. Different from existing fine-tuning methods that add…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Sida Huang , Hongyuan Zhang , Xuelong Li

The rapid adoption of text-to-image diffusion models in society underscores an urgent need to address their biases. Without interventions, these biases could propagate a skewed worldview and restrict opportunities for minority groups. In…

Machine Learning · Computer Science 2024-03-18 Xudong Shen , Chao Du , Tianyu Pang , Min Lin , Yongkang Wong , Mohan Kankanhalli