# RealDPO: Real or Not Real, that is the Preference

arXiv: https://arxiv.org/abs/2510.14955 · HTML: https://mlsanity.com/paper/2510.14955/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 34 of its 38 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Placed in

- 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 34)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors](https://mlsanity.com/paper/2310.12190/) (2023)
- [Directly Fine-Tuning Diffusion Models on Differentiable Rewards](https://mlsanity.com/paper/2309.17400/) (2023)
- [Aligning Text-to-Image Models using Human Feedback](https://mlsanity.com/paper/2302.12192/) (2023)
- [I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models](https://mlsanity.com/paper/2311.04145/) (2023)
- [Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding](https://mlsanity.com/paper/2405.08748/) (2024)
- [Open-Sora Plan: Open-Source Large Video Generation Model](https://mlsanity.com/paper/2412.00131/) (2024)
- [Improving Video Generation with Human Feedback](https://mlsanity.com/paper/2501.13918/) (2025)
- [Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model](https://mlsanity.com/paper/2311.13231/) (2023)
- [Unified Reward Model for Multimodal Understanding and Generation](https://mlsanity.com/paper/2503.05236/) (2025)
- [VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation](https://mlsanity.com/paper/2412.21059/) (2024)
- [Rich Human Feedback for Text-to-Image Generation](https://mlsanity.com/paper/2312.10240/) (2023)
- [VideoDPO: Omni-Preference Alignment for Video Diffusion Generation](https://mlsanity.com/paper/2412.14167/) (2024)
- [InstructVideo: Instructing Video Diffusion Models with Human Feedback](https://mlsanity.com/paper/2312.12490/) (2023)
- [LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment](https://mlsanity.com/paper/2412.04814/) (2024)
- [OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization](https://mlsanity.com/paper/2412.15159/) (2024)
- [DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models](https://mlsanity.com/paper/2506.03517/) (2025)
- [VPO: Aligning Text-to-Video Generation Models with Prompt Optimization](https://mlsanity.com/paper/2503.20491/) (2025)
- [Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences](https://mlsanity.com/paper/2506.02095/) (2025)

## Built on by (most cited first, 6 of 6)

- [Simulating the Visual World with Artificial Intelligence: A Roadmap](https://mlsanity.com/paper/2511.08585/) (2025)
- [Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence](https://mlsanity.com/paper/2607.07675/) (2026)
- [Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning](https://mlsanity.com/paper/2601.04153/) (2026)
- [VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning](https://mlsanity.com/paper/2608.26105/) (2026)
- [NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning](https://mlsanity.com/paper/2606.27771/) (2026)
- [Temporal Concentration from Rollout Errors: Implicit Preference Optimization for Text-to-Video Diffusion](https://mlsanity.com/paper/2607.28058/) (2026)

## Abstract (arXiv)

Video generative models have recently achieved notable advancements in synthesis quality. However, generating complex motions remains a critical challenge, as existing models often struggle to produce natural, smooth, and contextually consistent movements. This gap between generated and real-world motions limits their practical applicability. To address this issue, we introduce RealDPO, a novel alignment paradigm that leverages real-world data as positive samples for preference learning, enabling more accurate motion synthesis. Unlike traditional supervised fine-tuning (SFT), which offers limited corrective feedback, RealDPO employs Direct Preference Optimization (DPO) with a tailored loss function to enhance motion realism. By contrasting real-world videos with erroneous model outputs, RealDPO enables iterative self-correction, progressively refining motion quality. To support post-training in complex motion synthesis, we propose RealAction-5K, a curated dataset of high-quality videos capturing human daily activities with rich and precise motion details. Extensive experiments demonstrate that RealDPO significantly improves video quality, text alignment, and motion realism compared to state-of-the-art models and existing preference optimization techniques.