# SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models

arXiv: https://arxiv.org/abs/2510.12784 · HTML: https://mlsanity.com/paper/2510.12784/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Self-improving MLLMs and synthetic data, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 82 of its 91 references that are in the map.
- First posted on arXiv 14 Oct 2025.

## Placed in

- 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 82)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [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)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [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)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)

## Built on by (most cited first, 22 of 22)

- [Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback](https://mlsanity.com/paper/2510.16888/) (2025)
- [Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward](https://mlsanity.com/paper/2511.20561/) (2025)
- [Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning](https://mlsanity.com/paper/2512.09924/) (2025)
- [UReason: Benchmarking Reasoning-to-Generation Alignment in Unified Multimodal Models](https://mlsanity.com/paper/2602.08336/) (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)
- [CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation](https://mlsanity.com/paper/2603.08652/) (2026)
- [MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation](https://mlsanity.com/paper/2606.05031/) (2026)
- [ReBind: Multi-Reference Video Editing via Structured Instructions with Explicit Reference Relationships](https://mlsanity.com/paper/2607.14681/) (2026)
- [Dreaming in Flow: Generative Grounding Feedback for Self-Evolving Unified Multimodal Models](https://mlsanity.com/paper/2609.08282/) (2026)
- [Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation](https://mlsanity.com/paper/2606.29941/) (2026)
- [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)
- [Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation](https://mlsanity.com/paper/2607.11886/) (2026)
- [TILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic Reward](https://mlsanity.com/paper/2607.21606/) (2026)
- [Generative Residual Factorization](https://mlsanity.com/paper/2609.34824/) (2026)
- [Mutually Adversarial Self-Training with Evolving Data for Unified Multimodal Models](https://mlsanity.com/paper/2609.36224/) (2026)
- [UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement](https://mlsanity.com/paper/2609.38721/) (2026)
- [Recursive Self-Improvement in Unified Multimodal Models](https://mlsanity.com/paper/2610.03002/) (2026)
- [Self-Verifier Capture in Unified Visual Generators: Diagnosing and Repairing Closed-Loop Self-Reward](https://mlsanity.com/paper/2610.16500/) (2026)
- [RSIgen: Reciprocal Self-Improvement for Agentic Visual Generation](https://mlsanity.com/paper/2610.18688/) (2026)

## Abstract (arXiv)

Recently, remarkable progress has been made in Unified Multimodal Models (UMMs), which integrate vision-language generation and understanding capabilities within a single framework. However, a model's strong visual understanding often fails to transfer to visual generation: it may correctly judge prompt-image alignment while failing to generate a faithful image from the same prompt. This raises a compelling question: Can a model improve itself by using its understanding module to reward its generation module? We introduce SRUM, a self-rewarding post-training framework directly applicable to existing UMMs of various designs. SRUM creates a feedback loop where the model's own understanding module acts as an internal ``evaluator'', providing corrective signals to improve generation without additional human-labeled data or external reward models. To provide comprehensive feedback, SRUM uses a global-local dual reward system: a global reward ensures overall visual semantics and layout, while a local reward refines fine-grained, object-level fidelity. SRUM shows strong generalization, boosting performance on T2I-CompBench from 82.18 to 88.37 and on T2I-ReasonBench from 43.82 to 46.75. Overall, our work establishes a powerful paradigm for enabling a UMM's understanding module to guide and enhance its own generation via self-rewarding.