Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models
Authors: Siqi Luo, Jianghan Shen, Yi Xin, Huayu Zheng, Haoxing Chen, Yan Tai, Yue Li, Junjun He, +4 more
Organizations: 1Shanghai Jiao Tong University · 2Shanghai Artificial Intelligence Laboratory · 3Nanjing University · 4Shanghai Innovation Institute · 5Peking University
Diffusion Multi-Modal Large Language Models (dMLLMs) are powerful for image generation, but optimizing them through reinforcement learning (RL) remains a major challenge. One primary difficulty is that a single image can be generated through many different unmasking sequences, which makes calculating importance ratios often intractable. Additionally, existing methods tend to ignore the hierarchical generation process of dMLLMs, where early tokens define the global layout and later tokens focus on local details. By assigning uniform rewards to all tokens, these current methods fail to reflect the actual contribution of each token to the final image. To address these issues, we propose Hierarchical Token GRPO (HT-GRPO), which integrates this hierarchy directly into the policy optimization process. Our approach features a Sketch-Then-Paint training scheme that organizes updates into three distinct stages: global, structure, and refinement. We also use a prompt-conditioned estimator to calculate importance ratios starting from a fully masked state. Furthermore, we introduce a Hierarchical Credit Assignment mechanism that prioritizes key structural tokens to ensure accurate reward propagation. Experiments using two popular dMLLM backbones, MMaDA and Lumina-DiMOO, demonstrate that HT-GRPO achieves substantial gains on the GenEval and DPG benchmarks. Evaluations across six additional metrics confirm significant improvements in image quality, aesthetics, and human preference.
Diffusion Language Models (DLMs) have recently achieved substantial progress in natural language generation tasks. Recent research demonstrates that adaptive token generation ordering can significantly improve performance in mathematical reasoning and code synthesis applications. In this work, we investigate the optimization of generation order for both text-to-image synthesis and multimodal understanding. We first establish that, unlike structured problems in language generation such as Sudoku puzzles, model logits alone are insufficient for determining optimal generation sequences in text-to-image generation and multimodal understanding. To address this challenge, we introduce a learnable control module trained via Group Relative Policy Optimization (GRPO) to determine the generation order. Our results demonstrate that learning this control block substantially improves both text-to-image alignment and multimodal understanding in DLMs. In particular, it enhances the model's ability to capture fine-grained spatial relationships in generated images while also strengthening performance on multimodal reasoning and comprehension tasks. We evaluate our framework on GenEval, an object-focused benchmark for text-to-image alignment, where it achieves 4.08% relative improvements. In addition, experiments on VLMEvalKit confirm 4.85% relative improvements in multimodal understanding, highlighting the broad effectiveness of our approach.
Reinforcement learning (RL) holds immense promise for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, progress is fundamentally constrained by a dual misalignment between authentic generation trajectory and the gradient update process: (i) Process-reward misalignment. Sparse, terminal rewards are indiscriminately assigned to all intermediate steps of the generation process, failing to provide discriminative credit assignment. (ii) State-trajectory misalignment. Policy updates are often diverted toward artificial, out-of-trajectory states, squandering gradients on less informative samples. To address these limitations, we introduce Process Aligned Policy Optimization (PAPO), a novel framework that holistically aligns the RL update with the dLLM's generative trajectory via Step-Aware Process Rewards (SPR) that transform sparse terminal rewards into dense, step-wise credit, and Entropy-Guided Historical Re-enactment (EHR) that replays authentic trajectories at high-uncertainty steps. Extensive experiments on four benchmarks demonstrate that PAPO significantly outperforms baselines, achieving gains of up to 4.5% on GSM8K, 4.8% on MATH500, 42.2% on Countdown and 16.1% on Sudoku.
Distribution Matching Distillation (DMD) facilitates efficient inference by distilling multi-step diffusion models into few-step variants. Concurrently, Reinforcement Learning (RL) has emerged as a vital tool for aligning generative models with human preferences. While both represent critical post-training stages for large-scale diffusion models, existing studies typically treat them as independent, sequential processes, leaving a systematic framework for their unification largely unexplored. In this work, we demonstrate that jointly optimizing these two objectives yields mutual benefits: RL enables more preference-aware and controllable distillation rather than uniformly compressing the full data distribution, while DMD serves as an effective regularizer to mitigate reward hacking during RL training. Building on these insights, we propose DMDR, a unified framework that incorporates Reward-Tilted Distribution Matching optimization alongside two dynamic distillation training strategies in the initial stage, followed by the joint DMD and RL optimization in the second stage. Extensive experiments demonstrate that DMDR achieves state-of-the-art visual quality and prompt adherence among few-step generation methods, even surpassing the performance of its multi-step teacher model.