AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation

Tingrui Shen, Yiheng Zhang, Chen Tang, Chuan Ping, Zixing Zhao, Le Wan, Yuwang Wang, Ronggang Wang, Shengfeng He

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Next-scale and token autoregressive images · 3 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
add SP-Block only (coordinate-level speculation) (ablation)Meshtron 1B · Mesh generation ablation (Meshtron 1B)Tokens per second: 95.5 -> 109.7Improved
add HF-Block to SP-Block (ablation)FlashMesh (Meshtron 1B) · Mesh generation ablation (Meshtron 1B)Tokens per second: 109.7 -> 176.5Improved
add correction mechanism (ablation)FlashMesh (Meshtron 1B) · Mesh generation ablation (Meshtron 1B)Tokens per second: 176.5 -> 180.4Improved
add correction mechanism (ablation)FlashMesh (Meshtron 1B) · Mesh generation ablation (Meshtron 1B)Chamfer Distance: 0.120 -> 0.120No clear effect
increase draft tokens from 18-18 to 27-27 (ablation)FlashMesh (Meshtron 1B) · Draft token count (Meshtron 1B)Tokens per second: 179.9 -> 114.4Hurt
increase draft tokens from 18-18 to 27-27 (ablation)FlashMesh (Meshtron 1B) · Draft token count (Meshtron 1B)Chamfer Distance: 0.120 -> 0.127Hurt
use 9-9 draft tokens instead of 18-18 (ablation)FlashMesh (Meshtron 1B) · Draft token count (Meshtron 1B)Tokens per second: 179.9 -> 139.9Hurt
apply FlashMesh to 0.5B backboneMeshtron 0.5B · Model size (Meshtron backbone)Chamfer Distance: 0.137 -> 0.140Hurt
apply FlashMesh to 2B backboneMeshtron 2B · ShapeNetV2+gObjaverse test (1000 meshes)Chamfer Distance: 0.092 -> 0.089Improved
apply FlashMesh to Meshtron 1BMeshtron 1B · ShapeNetV2+gObjaverse test (1000 meshes)Tokens per second: 98.6 -> 180.4Improved
vary loss weight gamma (0.1, 0.3, 0.5) (ablation)FlashMesh (Meshtron 1B) · Mesh generation ablation (Meshtron 1B)Chamfer Distance: 0.120 for all gammaNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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