← 研踪 PaperTrailCVF · CVPR 2026:cvf:8ae27c66cf2b73fdb8aec2ac82d9f64a · 记录 #1
ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative Decoding
来源日期（仅到年份） 2026
来源记录日期 2026
雷达观测 2026-11-05 02:54
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 incorporates 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 1.6-1.8x with high accepted lengths, and accelerates various video understanding benchmarks by 3.36x on LLaVA-Onevision-72B and 2.42x on Qwen2.5-VL-32B compared with vanilla autoregressive decoding.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026 · 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 incorporates 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 1.6-1.8x with high accepted lengths, and accelerates various video understanding benchmarks by 3.36x on LLaVA-Onevision-72B and 2.42x on Qwen2.5-VL-32B compared with vanilla autoregressive decoding.
查看此版本解读 →查看此版本原文 ↗