# UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning

arXiv: https://arxiv.org/abs/2505.23380 · HTML: https://mlsanity.com/paper/2505.23380/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 42 of its 48 references that are in the map.
- First posted on arXiv 29 May 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)
- Synthetic data and self-improvement for LLMs / [Self-improving MLLMs and synthetic data](https://mlsanity.com/synth/self-improving-mllms-and-synthetic-data/)

## Builds on (most cited first, 30 of 42)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [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)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [Emu3: Next-Token Prediction is All You Need](https://mlsanity.com/paper/2409.18869/) (2024)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model](https://mlsanity.com/paper/2408.11039/) (2024)
- [Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2410.13848/) (2024)
- [SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation](https://mlsanity.com/paper/2404.14396/) (2024)
- [DreamLLM: Synergistic Multimodal Comprehension and Creation](https://mlsanity.com/paper/2309.11499/) (2023)
- [VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation](https://mlsanity.com/paper/2409.04429/) (2024)
- [SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models](https://mlsanity.com/paper/2504.11468/) (2025)
- [MetaMorph: Multimodal Understanding and Generation via Instruction Tuning](https://mlsanity.com/paper/2412.14164/) (2024)
- [Imagine while Reasoning in Space: Multimodal Visualization-of-Thought](https://mlsanity.com/paper/2501.07542/) (2025)
- [JourneyDB: A Benchmark for Generative Image Understanding](https://mlsanity.com/paper/2307.00716/) (2023)
- [Any-to-Any Generation via Composable Diffusion](https://mlsanity.com/paper/2305.11846/) (2023)

## Built on by (most cited first, 24 of 24)

- [Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding](https://mlsanity.com/paper/2510.06308/) (2025)
- [Reconstruction Alignment Improves Unified Multimodal Models](https://mlsanity.com/paper/2509.07295/) (2025)
- [SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models](https://mlsanity.com/paper/2510.12784/) (2025)
- [The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation](https://mlsanity.com/paper/2511.20256/) (2025)
- [Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding](https://mlsanity.com/paper/2603.13366/) (2026)
- [Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward](https://mlsanity.com/paper/2511.20561/) (2025)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in Reinforcement Learning](https://mlsanity.com/paper/2511.14760/) (2025)
- [Toward Native Multimodal Modeling: A Roadmap](https://mlsanity.com/paper/2605.25343/) (2026)
- [Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards](https://mlsanity.com/paper/2606.27376/) (2026)
- [Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models](https://mlsanity.com/paper/2603.06043/) (2026)
- [Self-Improving World Modelling with Latent Actions](https://mlsanity.com/paper/2602.06130/) (2026)
- [AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward](https://mlsanity.com/paper/2605.12495/) (2026)
- [Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning](https://mlsanity.com/paper/2512.06835/) (2025)
- [Self-Corrected Image Generation with Explainable Latent Rewards](https://mlsanity.com/paper/2603.24965/) (2026)
- [LatentUMM: Dual Latent Alignment for Unified Multimodal Models](https://mlsanity.com/paper/2605.17766/) (2026)
- [Enhancing Alignment for Unified Multimodal Models via Semantically-Grounded Supervision](https://mlsanity.com/paper/2603.19807/) (2026)
- [Towards Customized Multimodal Role-Play](https://mlsanity.com/paper/2605.08129/) (2026)
- [Model Guides You How to Draw: Adaptive Visual Gating for Unified Multimodal Reasoning](https://mlsanity.com/paper/2607.10004/) (2026)
- [STBridge: Shared-Target Alignment for Bridging Understanding and Generation in UMMs](https://mlsanity.com/paper/2607.17140/) (2026)
- [Where a New Concept Must Enter: Entry Point Gates Cross-Task Usability in Unified Multimodal Models](https://mlsanity.com/paper/2608.17564/) (2026)
- [Beyond Generation and Accuracy: Diagnosing and Enhancing Visual Chain-of-Thought for Geometry Problem Solving](https://mlsanity.com/paper/2609.12606/) (2026)
- [Mutually Adversarial Self-Training with Evolving Data for Unified Multimodal Models](https://mlsanity.com/paper/2609.36224/) (2026)
- [Recursive Self-Improvement in Unified Multimodal Models](https://mlsanity.com/paper/2610.03002/) (2026)

## Abstract (arXiv)

Unified multimodal large language models such as Show-o and Janus have achieved strong performance across both generation and understanding tasks. However, these models typically rely on large-scale datasets and require substantial computation during the pretraining stage. In addition, several post-training methods have been proposed, but they often depend on external data or are limited to task-specific customization. In this work, we introduce UniRL, a self-improving post-training approach. Our approach enables the model to generate images from prompts and use them as training data in each iteration, without relying on any external image data. Moreover, it enables the two tasks to enhance each other: the generated images are used for understanding, and the understanding results are used to supervise generation. We explore supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO) to optimize the models. UniRL offers three key advantages: (1) it requires no external image data, as all training samples are generated by the model itself during training; (2) it not only improves individual task performance, but also reduces the imbalance between generation and understanding; and (3) it requires only several additional training steps during the post-training stage. We evaluate UniRL on top of Show-o and Janus, achieving a GenEval score of 0.77 for Show-o and 0.65 for Janus. Code and models will be released in https://github.com/showlab/UniRL.