XSpecMesh：通过多头投机解码实现保质量的自动回归网格生成加速
XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding
AI总结：
针对自动回归网格生成推理延迟高的问题，提出XSpecMesh方法，采用多头投机解码并行预测词元，结合验证重采样与蒸馏策略，实现1.7倍加速且不损失生成质量。
摘要：
当前的自动回归模型能够生成高质量、拓扑精确的网格；然而，它们在推理过程中需要数千次甚至数万次的下一词元预测，导致显著的延迟。我们引入了XSpecMesh，一种用于自动回归网格生成模型的保质量加速方法。XSpecMesh采用轻量级的多头投机解码方案，在单次前向传播中并行预测多个词元，从而加速推理。我们进一步提出了一种验证与重采样策略：骨干模型验证每个预测的词元，并对任何不符合质量标准的词元进行重采样。此外，我们提出了一种蒸馏策略，通过从骨干模型蒸馏来训练轻量级解码头，促使它们的预测分布对齐，并提高投机预测的成功率。大量实验表明，我们的方法在不牺牲生成质量的情况下实现了1.7倍的加速。我们的代码将发布。
英文摘要：
Current auto-regressive models can generate high-quality, topologically precise meshes; however, they necessitate thousands-or even tens of thousands-of next-token predictions during inference, resulting in substantial latency. We introduce XSpecMesh, a quality-preserving acceleration method for auto-regressive mesh generation models. XSpecMesh employs a lightweight, multi-head speculative decoding scheme to predict multiple tokens in parallel within a single forward pass, thereby accelerating inference. We further propose a verification and resampling strategy: the backbone model verifies each predicted token and resamples any tokens that do not meet the quality criteria. In addition, we propose a distillation strategy that trains the lightweight decoding heads by distilling from the backbone model, encouraging their prediction distributions to align and improving the success rate of speculative predictions. Extensive experiments demonstrate that our method achieves a 1.7x speedup without sacrificing generation quality. Our code will be released.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
