cs.AINov 17, 2026

FrameRouter: Frame Budget Routing for Long-Video Understanding on Video-MME-v2 and Beyond

Authors: Bingjun Luo, Jialin Guo, Siqi Li

Organizations: Tsinghua University, Beijing, China · Harbin Engineering University, Harbin, China · BNRist, THUIBCS, School of Software, Tsinghua University, Beijing, China

Abstract

Long-video question answering benchmarks like Video-MME-v2 typically evaluate systems under a uniform frame budget for every question, despite stark variation in the evidence each query actually demands. We analyze this mismatch on Video-MME-v2 and find that different question subsets prefer different frozen frame-budget policies, while uniformly increasing the frame count does not reliably improve all metrics. These findings motivate fixed-mean frame-budget routing, a controlled inference setting in which each question may receive a different frame budget while the average budget matches a uniform reference. We introduce FrameRouter, a training-free test-time framework that combines an evidence-demand router, a budget-constrained allocation rule, and a frozen bank of frame-sampling policies. By controlling how much visual evidence each question receives while leaving the underlying samplers unchanged, FrameRouter is orthogonal to query-aware frame selection. Across Video-MME-v2 and several long-video understanding benchmarks, FrameRouter improves long-video question answering by using the same average visual budget more selectively across questions. Code is available at https://github.com/bingjunluo/FrameRouter.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. ReQuest: Rethinking-based Question-Aware Frame Selection for Long-Form Video QA

    Jul 2, 2026Minkuk Kim, Suyong Yun, Young Tae Kim +3Efficient VLM InferenceVideo Question Answering