跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2603.19610 · v3

ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative Decoding

首次提交 2026-03-20 11:30
版本更新 2026-11-17 21:21
雷达观测 2026-11-18 19:41
arXiv ↗PDF ↗

摘要

Although current Video-LLMs achieve impressive performance in video understanding tasks, their autoregressive decoding efficiency remains constrained by the massive number of video tokens. Visual token pruning can partially ease this bottleneck, yet existing approaches still suffer from information loss and yield only modest acceleration in decoding. In this paper, we propose ParallelVLM, a training-free draft-then-verify speculative decoding framework that overcomes both mutual waiting and limited speedup-ratio problems between draft and target models in long-video settings. ParallelVLM features two parallelized stages that maximize hardware utilization and incorporate an Unbiased Verifier-Guided Pruning strategy to better align the draft and target models by eliminating the positional bias in attention-guided pruning. Extensive experiments demonstrate that ParallelVLM effectively expands the draft window by 1.6∼1.8×1.6\sim1.8\times with high accepted lengths, and accelerates various video understanding benchmarks by 3.36×\times on LLaVA-Onevision-72B and 2.42×\times on Qwen2.5-VL-32B compared with vanilla autoregressive decoding.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v3,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v3 · 2026-11-17 21:21 · 最新观测版本

ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative Decoding

Although current Video-LLMs achieve impressive performance in video understanding tasks, their autoregressive decoding efficiency remains constrained by the massive number of video tokens. Visual token pruning can partially ease this bottleneck, yet existing approaches still suffer from information loss and yield only modest acceleration in decoding. In this paper, we propose ParallelVLM, a training-free draft-then-verify speculative decoding framework that overcomes both mutual waiting and limited speedup-ratio problems between draft and target models in long-video settings. ParallelVLM features two parallelized stages that maximize hardware utilization and incorporate an Unbiased Verifier-Guided Pruning strategy to better align the draft and target models by eliminating the positional bias in attention-guided pruning. Extensive experiments demonstrate that ParallelVLM effectively expands the draft window by 1.6∼1.8×1.6\sim1.8\times with high accepted lengths, and accelerates various video understanding benchmarks by 3.36×\times on LLaVA-Onevision-72B and 2.42×\times on Qwen2.5-VL-32B compared with vanilla autoregressive decoding.

查看此版本解读 →查看此版本原文 ↗