The Year in AI Papers
The year/Independent research

Paper 2511.09611

MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation

Ye Tian, Ling Yang, Jiongfan Yang, Anran Wang, Yu Tian, Jiani Zheng, Haochen Wang, Zhiyang Teng, Zhuochen Wang, Yinjie Wang, Yunhai Tong, Mengdi Wang, et al.

Published
Nov 2025
Research lab
Independent
Citations
8
GitHub
306 stars

01 In brief

Summary

The paper introduces MMaDA-Parallel, a parallel multimodal diffusion framework for thinking-aware image editing and generation.

The authors identify a failure mode in sequential autoregressive approaches where pre-generation reasoning can degrade performance due to error propagation.

They propose ParaBench, a benchmark evaluating both text and image outputs, and find that performance degradation correlates with poor alignment between generated reasoning and the final image.

MMaDA-Parallel enables continuous bidirectional interaction between text and images throughout the denoising trajectory, trained with supervised fine-tuning and further optimized by Parallel Reinforcement Learning (ParaRL), which applies semantic rewards along the trajectory to enforce cross-modal consistency.

Experiments show a 6.9% improvement in Output Alignment on ParaBench compared to the state-of-the-art model Bagel, establishing a more robust paradigm for thinking-aware image synthesis.

02 From the paper

Abstract

While thinking-aware generation aims to improve performance on complex tasks, we identify a critical failure mode where existing sequential, autoregressive approaches can paradoxically degrade performance due to error propagation. To systematically analyze this issue, we propose ParaBench, a new benchmark designed to evaluate both text and image output modalities. Our analysis using ParaBench reveals that this performance degradation is strongly correlated with poor alignment between the generated reasoning and the final image. To resolve this, we propose a parallel multimodal diffusion framework, MMaDA-Parallel, that enables continuous, bidirectional interaction between text and images throughout the entire denoising trajectory. MMaDA-Parallel is trained with supervised finetuning and then further optimized by Parallel Reinforcement Learning (ParaRL), a novel strategy that applies semantic rewards along the trajectory to enforce cross-modal consistency. Experiments validate that our model significantly improves cross-modal alignment and semantic consistency, achieving a 6.9\% improvement in Output Alignment on ParaBench compared to the state-of-the-art model, Bagel, establishing a more robust paradigm for thinking-aware image synthesis. Our code is open-sourced at https://github.com/tyfeld/MMaDA-Parallel