AI RESEARCH
Fre-Res: Frequency-Residual Video Token Compression for Efficient Video MLLMs
arXiv CS.CV
•
ArXi:2605.16366v1 Announce Type: new Video MLLMs face a persistent tension between spatial fidelity and temporal coverage: preserving fine-grained visual details requires many spatial tokens, while capturing short-lived events requires dense temporal sampling. We propose \textbf{Fre-Res}, a budget-adaptive dual-track video-token compression framework that separates these two forms of evidence. Fre-Res preserves sparse high-fidelity spatial anchors and represents dense temporal evolution through compact residual-frequency tokens.