V-CAST: training-free video token pruning keeps 97% accuracy with 51% faster prefill

量子位 · wechat · 2026-11-17

Researchers from Sun Yat-sen University, PolyU and others propose V-CAST, a training-free, plug-and-play spatio-temporal pruning method for video LLMs.

Design:

Results across Qwen3-VL, LLaVA and Qwen2.5-Omni (6 configs, 10 benchmarks):

Code and project page are open-sourced.

Related event: V-CAST: Training-Free Visual Token Pruning Speeds Up Long Video Understanding by 51%(2 posts)→

Original post →

More from Multimodal

Multimodal channel →