# Curriculum Direct Preference Optimization for Diffusion and Consistency Models

arXiv: https://arxiv.org/abs/2405.13637 · HTML: https://mlsanity.com/paper/2405.13637/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 67 of its 83 references that are in the map.
- First posted on arXiv 22 May 2024.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 30 of 67)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)

## Built on by (most cited first, 30 of 36)

- [Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples](https://mlsanity.com/paper/2502.09650/) (2025)
- [Alignment of Diffusion Models: Fundamentals, Challenges, and Future](https://mlsanity.com/paper/2409.07253/) (2024)
- [PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation](https://mlsanity.com/paper/2512.24551/) (2025)
- [Boost Your Human Image Generation Model via Direct Preference Optimization](https://mlsanity.com/paper/2405.20216/) (2024)
- [Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models](https://mlsanity.com/paper/2601.20354/) (2026)
- [Aligning Few-Step Diffusion Models with Dense Reward Difference Learning](https://mlsanity.com/paper/2411.11727/) (2024)
- [Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances](https://mlsanity.com/paper/2508.10316/) (2025)
- [Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization](https://mlsanity.com/paper/2410.05255/) (2024)
- [MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety](https://mlsanity.com/paper/2504.15241/) (2025)
- [Dual-Difficulty Curriculum Learning for Direct Preference Optimization](https://mlsanity.com/paper/2504.07856/) (2025)
- [Drifting Preference Optimization for One-Step Generative Models](https://mlsanity.com/paper/2606.02521/) (2026)
- [From Fragments to Facts: A Curriculum-Driven DPO Approach for Generating Hindi News Veracity Explanations](https://mlsanity.com/paper/2507.05179/) (2025)
- [Improving LLMs for Machine Translation Using Synthetic Preference Data](https://mlsanity.com/paper/2508.14951/) (2025)
- [Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation](https://mlsanity.com/paper/2511.01450/) (2025)
- [Test-Time Preference Optimization for Image Restoration](https://mlsanity.com/paper/2511.19169/) (2025)
- [Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision](https://mlsanity.com/paper/2512.23426/) (2025)
- [Human detectors are surprisingly powerful reward models](https://mlsanity.com/paper/2601.14037/) (2026)
- [Small-Margin Preferences Still Matter-If You Train Them Right](https://mlsanity.com/paper/2602.00954/) (2026)
- [Diffusion Controller: Framework, Algorithms and Parameterization](https://mlsanity.com/paper/2603.06981/) (2026)
- [SyncDPO: Enhancing Temporal Synchronization in Video-Audio Joint Generation via Preference Learning](https://mlsanity.com/paper/2605.12179/) (2026)
- [When Preferences Diverge: Aligning Diffusion Models with Minority-Aware Adaptive DPO](https://mlsanity.com/paper/2503.16921/) (2025)
- [Sell It Before You Make It: Revolutionizing E-Commerce with Personalized AI-Generated Items](https://mlsanity.com/paper/2503.22182/) (2025)
- [CLewR: Curriculum Learning with Restarts for Machine Translation Preference Learning](https://mlsanity.com/paper/2601.05858/) (2026)
- [POCA: Pareto-Optimal Curriculum Alignment for Visual Text Generation](https://mlsanity.com/paper/2604.24171/) (2026)
- [Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs](https://mlsanity.com/paper/2605.09433/) (2026)
- [g-DPO: Scalable Preference Optimization for Protein Language Models](https://mlsanity.com/paper/2510.19474/) (2025)
- [SP^2DPO: An LLM-assisted Semantic Per-Pair DPO Generalization](https://mlsanity.com/paper/2601.22385/) (2026)
- [Region-Normalized DPO for Medical Image Segmentation under Noisy Judges](https://mlsanity.com/paper/2601.23222/) (2026)
- [Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation](https://mlsanity.com/paper/2602.13055/) (2026)
- [Learning Hierarchical and Geometry-Aware Graph Representations for Text-to-CAD](https://mlsanity.com/paper/2604.10075/) (2026)

## Abstract (arXiv)

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.