AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models

Yi Xin, Siqi Luo, Tianxiang Xu, Qi Qin, Haoxing Chen, Kaiwen Zhu, Zhiwei Zhang, Yangfan He, Rongchao Zhang, Jinbin Bai, Shuo Cao, Bin Fu and 4 more

CVPR 2026 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use hierarchical trajectory search instead of linear search (T=32,N=32) (ablation)dMLLM-TTS · GenEval overall (MMaDA)accuracy: 0.64 -> 0.66Improved
use hierarchical trajectory search instead of linear search (T=32,N=32) (ablation)dMLLM-TTS · GenEval overall (Lumina-DiMOO)accuracy: 0.91 -> 0.92Improved
HTS reaches equal scores with less compute (ablation)dMLLM-TTS · GenEvalNFE: 5x faster on Lumina-DiMOO, 6x on MMaDA and MudditImproved
apply test-time scaling (HTS+SVF, T=32,N=32)Lumina-DiMOO · GenEval overallaccuracy: 0.78 -> 0.92Improved
apply test-time scaling (HTS+SVF, T=32,N=32)MMaDA · GenEval overallaccuracy: 0.51 -> 0.66Improved
apply test-time scaling (HTS+SVF, T=32,N=32)Muddit · GenEval overallaccuracy: 0.53 -> 0.67Improved
scale trajectories N from 1 to 32 (ablation)dMLLM-TTS · GenEval overall (Lumina-DiMOO)accuracy: +8.8%Improved
scale refinement steps from 8 to 64 (ablation)dMLLM-TTS · GenEval overallaccuracyImproved
replace self-verified feedback with GPT-4o verifier (ablation)dMLLM-TTS · GenEval overall (Muddit)accuracy: 0.67 -> 0.74Improved
replace self-verified feedback with VILA-Judge verifier (ablation)dMLLM-TTS · GenEval overallaccuracy: Lumina-DiMOO 0.92 -> 0.90; MMaDA 0.66 -> 0.70; Muddit 0.67 -> 0.70Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy