LANTERN++：利用静态树草稿增强视觉自回归模型的宽松推测解码
LANTERN++: Enhancing Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models
AI总结：
针对视觉自回归模型中令牌选择模糊性导致的推测解码加速受限问题，提出LANTERN++框架，通过静态树草稿与宽松接受条件结合，实现高达2.56倍加速并保持图像质量。
摘要：
推测解码已被广泛用于加速自回归（AR）文本生成。然而，由于令牌选择模糊性，即多个令牌具有相似的低概率从而降低接受率，其对视觉AR模型的有效性仍然有限。最近，提出了具有动态树草稿的宽松推测解码来缓解这种模糊性，在加速视觉AR模型方面显示出有前景的结果。然而，我们观察到令牌选择模糊性仍然对动态树草稿产生负面影响，导致草稿树较浅且加速有限。为了克服这一问题，我们引入了LANTERN++，一个精炼的框架，它将静态树草稿与定制的宽松接受条件相结合，使得草稿的选择独立于低置信度的预测。这能够接受更深的序列，在保持图像质量的同时提高解码效率。在最先进的视觉AR模型上进行的大量实验表明，LANTERN++显著加速推理，与标准AR解码相比实现了高达2.56倍的加速，同时保持了高图像质量。代码可在https://github.com/jadohu/LANTERN公开获取。
英文摘要：
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.
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。
