FlashMesh：通过结构化推测实现更快更好的自回归网格合成
FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation
把推测解码（speculative decoding）引入自回归网格生成，利用网格 token 在面/点/坐标层级上的结构相关性做多 token 并行预测，可直接迁移到其他自回归式 3D 生成器（如 MeshGPT 类模型）做免训练或轻训练加速。
原文依据 introducing a speculative decoding scheme tailored to the commonly used hourglass transformer architecture
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论自回归模型能够通过依次生成顶点与面来生成高质量三维网格，但其逐 token 解码导致推理缓慢，限制了在交互式与大规模应用中的实际使用。我们提出 FlashMesh，一个快速且高保真的网格生成框架，通过「预测—校正—验证」范式重新思考自回归解码。其核心洞见在于：网格 token 具有强烈的结构与几何相关性，从而支持高置信度的多 token 推测。FlashMesh 据此引入一种面向常用沙漏型 Transformer 架构定制的推测解码方案，在面、点与坐标三个层级上实现并行预测。大量实验表明，FlashMesh 相较标准自回归模型最高可实现 2 倍加速，同时提升生成保真度。我们的结果说明，网格数据中的结构先验可以被系统地利用，以加速并增强自回归生成。
英文原文摘要 1020 字符
Autoregressive models can generate high-quality 3D meshes by sequentially producing vertices and faces, but their token-by-token decoding results in slow inference, limiting practical use in interactive and large-scale applications.We present FlashMesh, a fast and high-fidelity mesh generation framework that rethinks autoregressive decoding through a predict-correct-verify paradigm. The key insight is that mesh tokens exhibit strong structural and geometric correlations that enable confident multi-token speculation. FlashMesh leverages this by introducing a speculative decoding scheme tailored to the commonly used hourglass transformer architecture, enabling parallel prediction across face, point, and coordinate levels.Extensive experiments show that FlashMesh achieves up to a 2xspeedup over standard autoregressive models while also improving generation fidelity. Our results demonstrate that structural priors in mesh data can be systematically harnessed to accelerate and enhance autoregressive generation.