提升视觉生成模型推理速度，通过静态树草案让长序列更易被接受。
LANTERN++: Enhancing Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models
- 用静态树草案替代动态树，避免低置信度词导致的筛选失败。
- 在多个视觉自回归模型上实现最高2.56倍加速，图像质量保持不变。
- 适合需要高效生成高分辨率图像的研究者和开发者。
自回归（AR）文本生成中，推测解码已被广泛用于加速。然而，由于标记选择模糊性——多个标记具有相似的低概率——其在视觉自回归模型中的效果受限，导致接受率下降。近期提出的宽松推测解码结合动态树草案虽有所改善，但我们发现标记选择模糊性仍影响动态树草案，导致草稿树过浅、加速有限。为此，本文提出LANTERN++，将静态树草案与定制化的宽松接受条件相结合，使草稿选择不再依赖低置信度预测。这使得更深层序列可被接受，提升了解码效率并保持图像质量。在主流视觉自回归模型上的大量实验表明，LANTERN++相比标准自回归解码最高实现×2.56的加速，同时维持高质量输出。代码已公开于https://github.com/jadohu/LANTERN。
原文摘要 · Abstract (English)
Speculative decoding has been widely used to accelerate auto-regressive (AR) text generation. However, its effectiveness for visual AR models remains limited due to token selection ambiguity, where multiple tokens share similarly low probabilities and thus reduce acceptance rates. Recently, relaxed speculative decoding with dynamic tree drafting was proposed to mitigate this ambiguity, demonstrating promising results in accelerating visual AR models. However, we observe that token selection ambiguity still negatively affects dynamic tree drafting, resulting in shallow draft trees and limited acceleration. To overcome this issue, we introduce LANTERN++, a refined framework that integrates static tree drafting with a tailored relaxed acceptance condition, allowing drafts to be selected independently of low-confidence predictions. This enables the acceptance of deeper sequences, improving decoding efficiency while preserving image quality. Extensive experiments on state-of-the-art visual AR models demonstrate that LANTERN++ significantly accelerates inference, achieving up to $\mathbf{\times 2.56}$ speedup over standard AR decoding while maintaining high image quality. The code is publicly available at https://github.com/jadohu/LANTERN.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。