AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Mesh-Pro: Asynchronous Advantage-guided Ranking Preference Optimization for Artist-style Quadrilateral Mesh Generation

Zhen Zhou, Jian Liu, Biwen Lei, Jing Xu, Haohan Weng, Yiling Zhu, Zhuo Chen, Junfeng Fan, Yunkai Ma, Dazhao Du, Song Guo, Fengshui Jing and 1 more

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Preference optimization for diffusion · 1 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 ARPO instead of GRPO (ablation)Async RL post-training · Async RL algorithm comparisonquad ratio: 68% -> 81%Improved
use ARPO instead of DPO (ablation)Async RL post-training · Async RL algorithm comparisonquad ratio: 75% -> 81%Improved
use GRPO instead of pretrained model (no RL) (ablation)Mesh-Pro · Async RL algorithm comparisonuser study score: 0.4 -> 1.3Improved
add advantage guidance to ranking preference (ablation)ARPO (group 4) · Async ARPO component ablationuser study score: 2.4 -> 2.9Improved
increase group size from 2 to 4 (ablation)ARPO · Async ARPO component ablationuser study score: 2.1 -> 2.4Improved
asynchronous online instead of synchronous RL (ablation)RL post-training · training timespeedup: 3.75x fasterImproved
asynchronous online instead of offline RL (ablation)ARPO · Async ARPO component ablationCD/HD/BR/QR/USImproved
add pre-start stage (ablation)async ARPO · Async ARPO component ablationstability / user study: 2.7 -> 3.5Improved
diagonal-aware tokenizer instead of previous tokenizer (ablation)Mesh-Pro · Tokenizer comparison (no RL)broken ratio: 38% -> 24%Improved
apply async ARPO to previous tokenizer (ablation)QuadGPT-style tokenizer · Tokenizer comparisonbroken ratio: 38% -> 46%Hurt
apply async ARPO to diagonal-aware tokenizer (ablation)Mesh-Pro · Tokenizer comparisonbroken ratio: 24% -> 22%Improved
increase ARPO training data 400 to 1000 meshes (ablation)async ARPO · Data scale in async ARPObroken ratio: 22.35% -> 21.83%Improved

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