跳到正文
arXiv cs.AI· Bingjun Luo, Jialin Guo, Siqi Li·· 2 小时前AI 评分22

FrameRouter:面向长视频理解的帧预算路由框架

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

AI 导读

一项 NeurIPS 2026 论文提出 FrameRouter,一个免训练的测试时框架,通过证据需求路由器、预算约束分配规则和冻结的帧采样策略库,为 Video-MME-v2 中每个问题分配不同的帧预算,同时保持与统一采样相同的平均预算。

正文 · 原文

View PDF HTML (experimental)

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 this https URL.
Comments: Accepted to NeurIPS 2026
Subjects: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
Cite as: arXiv:2611.23055 [cs.AI]
  (or arXiv:2611.23055v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.23055

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Bingjun Luo [view email]
[v1] Tue, 17 Nov 2026 16:49:21 UTC (618 KB)

来源:arXiv cs.AI · arxiv.org