Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models
The paper presents a novel approach to optimizing Diffusion Multi-Modal Large Language Models (dMLLMs) using Hierarchical Reinforcement Learning. It addresses challenges in reward assignment during the image generation process by introducing a Sketch-Then-Paint training scheme. Experimental results indicate significant improvements in image quality and user preference metrics.
- ▪The proposed method, Hierarchical Token GRPO (HT-GRPO), integrates hierarchical generation into the policy optimization process.
- ▪HT-GRPO organizes updates into three stages: global, structure, and refinement.
- ▪Experiments show substantial gains on the GenEval and DPG benchmarks using two dMLLM backbones.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.16842 |
| Publication time | Tue, 19 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-19T04:04:57.272Z |
| Last seen | 2026-05-19T04:04:57.272Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | vHalhwRKINOG |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.16842 (cs) [Submitted on 16 May 2026] Title: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, Yihao Liu, Guangtao Zhai, Yuewen Cao, Xiaohong Liu View a PDF of the paper titled Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models, by Siqi Luo and 11 other authors View PDF HTML (experimental) Abstract:Diffusion Multi-Modal Large Language Models (dMLLMs) are powerful for image generation, but optimizing them through reinforcement learning (RL) remains a major challenge.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
