# Pareto-Guided Optimal Transport for Multi-Reward Alignment

arXiv: https://arxiv.org/abs/2605.13155 · HTML: https://mlsanity.com/paper/2605.13155/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 33 of its 40 references that are in the map.
- First posted on arXiv 13 May 2026.

## 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 33)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [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)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [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)
- [Directly Fine-Tuning Diffusion Models on Differentiable Rewards](https://mlsanity.com/paper/2309.17400/) (2023)
- [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://mlsanity.com/paper/2210.14896/) (2022)
- [ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization](https://mlsanity.com/paper/2406.04312/) (2024)
- [Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism](https://mlsanity.com/paper/2305.18438/) (2023)
- [PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models](https://mlsanity.com/paper/2402.08714/) (2024)
- [Calibrated Multi-Preference Optimization for Aligning Diffusion Models](https://mlsanity.com/paper/2502.02588/) (2025)
- [TextCraftor: Your Text Encoder Can be Image Quality Controller](https://mlsanity.com/paper/2403.18978/) (2024)
- [Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs](https://mlsanity.com/paper/2505.10425/) (2025)
- [Reinforcement Learning for Joint Optimization of Multiple Rewards](https://mlsanity.com/paper/1909.02940/) (2019)
- [Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment](https://mlsanity.com/paper/2507.19002/) (2025)
- [Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation](https://mlsanity.com/paper/2402.14146/) (2024)
- [Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning](https://mlsanity.com/paper/2407.06642/) (2024)
- [BalancedDPO: Adaptive Multi-Metric Alignment](https://mlsanity.com/paper/2503.12575/) (2025)
- [Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction](https://mlsanity.com/paper/2508.04216/) (2025)
- [Learning User Preferences for Image Generation Model](https://mlsanity.com/paper/2508.08220/) (2025)
- [Group Causal Policy Optimization for Post-Training Large Language Models](https://mlsanity.com/paper/2508.05428/) (2025)

## Abstract (arXiv)

Text-to-image generation models have achieved remarkable progress in preference optimization, yet achieving robust alignment across diverse reward models remains a significant challenge. Existing multi-reward fusion approaches rely on weighted summation, which is costly to tune and insufficient for balancing conflicting objectives. More critically, optimization with reward models is highly susceptible to reward hacking, where reward scores increase while the perceived quality of generated images deteriorates. We demonstrate that optimizing against a unified global target under heterogeneous reward upper bounds can induce reward hacking, a risk further exacerbated by the inherent instability of weak reward models. To mitigate this, we propose a Pareto Frontier-Guided Optimal Transport (PG-OT) framework. Our method constructs a prompt-specific Pareto frontier and maps dominated samples toward it via distribution-aware optimal transport. Furthermore, we develop both online and offline optimization strategies tailored to diverse reward signal characteristics. To provide a more rigorous assessment, we introduce the Joint Domination Rate (JDR) and Joint Collapse Rate (JCR) as principled metrics to quantify multi-reward synergy and reward hacking. Experimental results show that our approach outperforms strong baselines with an 11% gain in JDR and achieves a near 80% win rate in human evaluations.