paper-with-me

홈 › Papers

Curriculum Direct Preference Optimization for Diffusion and Consistency Models

2024-05-22 · CVPR 2025 1 · Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, Nicu Sebe, Mubarak Shah

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 learning for text-to-image generation. Our method is divided into two training stages. First, a ranking of the examples generated for each prompt is obtained by employing a reward model. Then, increasingly difficult pairs of examples are sampled and provided to a text-to-image generative (diffusion or consistency) model. Generated samples that are far apart in the ranking are considered to form easy pairs, while those that are close in the ranking form hard pairs. In other words, we use the rank difference between samples as a measure of difficulty. The sampled pairs are split into batches according to their difficulty levels, which are gradually used to train the generative model. Our approach, Curriculum DPO, is compared against state-of-the-art fine-tuning approaches on nine benchmarks, outperforming the competing methods in terms of text alignment, aesthetics and human preference. Our code is available at https://github.com/CroitoruAlin/Curriculum-DPO.

📄 PDF Abstract BibTeX arXiv:2405.13637

Code (1)

croitorualin/curriculum-dpo 공식 구현 pytorch

Tasks

Image GenerationText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

DPO 설명 없음

Similar Papers 제목 키워드 기반

Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation

2026-02-13 · Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, Nicu Sebe 외 arxiv

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). However, neither RLHF nor DPO take into account the fact that learnin…

Text-to-Image GenerationReinforcement Learning

Towards Better Optimization For Listwise Preference in Diffusion Models

2025-10-02 · Jiamu Bai, Xin Yu, Meilong Xu, Weitao Lu 외 arxiv

Reinforcement learning from human feedback (RLHF) has proven effectiveness for aligning text-to-image (T2I) diffusion models with human preferences. Although Direct Preference Optimization (DPO) is widely adopted for its…

Text-to-Image GenerationComputational EfficiencyReinforcement LearningImage Editing

Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMs

2025-09-29 · Yuanshuai Li, Yuping Yan, Junfeng Tang, Yunxuan Li 외 arxiv

Multimodal Large Language Models (MLLMs) have significantly improved the performance of various tasks, but continue to suffer from visual hallucinations, a critical issue where generated responses contradict visual evide…

2D-Curri-DPO: Two-Dimensional Curriculum Learning for Direct Preference Optimization

2025-04-10 · Mengyang Li, Zhong Zhang

Aligning large language models with human preferences is crucial for their safe deployment. While Direct Preference Optimization (DPO) offers an efficient alternative to reinforcement learning from human feedback, tradit…

Model Optimization

PC-Diffusion: Aligning Diffusion Models with Human Preferences via Preference Classifier

2025-11-11 · Shaomeng Wang, He Wang, Xiaolu Wei, Longquan Dai 외 arxiv

Diffusion models have achieved remarkable success in conditional image generation, yet their outputs often remain misaligned with human preferences. To address this, recent work has applied Direct Preference Optimization…

Conditional Image Generation