# SEE-DPO: Self Entropy Enhanced Direct Preference Optimization

arXiv: https://arxiv.org/abs/2411.04712 · HTML: https://mlsanity.com/paper/2411.04712/

## Key facts

- Cited by 7 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 32 of its 41 references that are in the map.
- First posted on arXiv 6 Nov 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 32)

- [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)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (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)
- [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)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Is Conditional Generative Modeling all you need for Decision-Making?](https://mlsanity.com/paper/2211.15657/) (2022)
- [DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16381/) (2023)
- [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://mlsanity.com/paper/2210.14896/) (2022)
- [Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint](https://mlsanity.com/paper/2312.11456/) (2023)
- [Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study](https://mlsanity.com/paper/2404.10719/) (2024)
- [Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model](https://mlsanity.com/paper/2311.13231/) (2023)
- [From r to Q^*: Your Language Model is Secretly a Q-Function](https://mlsanity.com/paper/2404.12358/) (2024)
- [Structure-based Drug Design with Equivariant Diffusion Models](https://mlsanity.com/paper/2210.13695/) (2022)
- [Sample Efficient Reinforcement Learning with REINFORCE](https://mlsanity.com/paper/2010.11364/) (2020)
- [FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation](https://mlsanity.com/paper/2212.03741/) (2022)
- [MoELoRA: Contrastive Learning Guided Mixture of Experts on Parameter-Efficient Fine-Tuning for Large Language Models](https://mlsanity.com/paper/2402.12851/) (2024)

## Built on by (most cited first, 7 of 7)

- [A Survey of Direct Preference Optimization](https://mlsanity.com/paper/2503.11701/) (2025)
- [Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges](https://mlsanity.com/paper/2604.13602/) (2026)
- [LookAlike: Consistent Distractor Generation in Math MCQs](https://mlsanity.com/paper/2505.01903/) (2025)
- [ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning](https://mlsanity.com/paper/2506.07459/) (2025)
- [Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models](https://mlsanity.com/paper/2511.03317/) (2025)
- [ROCM: RLHF on consistency models](https://mlsanity.com/paper/2503.06171/) (2025)
- [Sem-DPO: Mitigating Semantic Inconsistency in Preference Optimization for Prompt Engineering](https://mlsanity.com/paper/2507.20133/) (2025)

## Abstract (arXiv)

Direct Preference Optimization (DPO) has been successfully used to align large language models (LLMs) according to human preferences, and more recently it has also been applied to improving the quality of text-to-image diffusion models. However, DPO-based methods such as SPO, Diffusion-DPO, and D3PO are highly susceptible to overfitting and reward hacking, especially when the generative model is optimized to fit out-of-distribution during prolonged training. To overcome these challenges and stabilize the training of diffusion models, we introduce a self-entropy regularization mechanism in reinforcement learning from human feedback. This enhancement improves DPO training by encouraging broader exploration and greater robustness. Our regularization technique effectively mitigates reward hacking, leading to improved stability and enhanced image quality across the latent space. Extensive experiments demonstrate that integrating human feedback with self-entropy regularization can significantly boost image diversity and specificity, achieving state-of-the-art results on key image generation metrics.