Code
FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
Why Lacuna links this resource
Linked from the paper
\textbf{10$\times$}$ increase in video frame input to Qwen2.5-VL, resulting in a relative improvement of $\textbf{8.6}$% within the same computational budget. Code is available at https://github.com/Fanziyang-v/FlashVID.