Cover Image

VideoRouter: Query-Adaptive Dual Routing for Efficient Long-Video Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Kuanwei, Zhang, Wenhao, Li, Ge
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

VideoCuRL: Video Curriculum Reinforcement Learning with Orthogonal Difficulty Decomposition
by: Jin, Hongbo, et al.
Published: (2025)

SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation
by: Tan, Shanwen, et al.
Published: (2026)

Video Panels for Long Video Understanding
by: Doorenbos, Lars, et al.
Published: (2025)

Adaptive Greedy Frame Selection for Long Video Understanding
by: Huang, Yuning, et al.
Published: (2026)

Query-Conditioned Evidential Keyframe Sampling for MLLM-Based Long-Form Video Understanding
by: Wang, Yiheng, et al.
Published: (2026)

AdaFocus: Adaptive Relevance-Diversity Sampling with Zero-Cache Look-back for Efficient Long Video Understanding
by: Yang, Xiao, et al.
Published: (2026)

VCA: Video Curious Agent for Long Video Understanding
by: Yang, Zeyuan, et al.
Published: (2024)

Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding
by: Li, Jialuo, et al.
Published: (2025)

Adaptive Keyframe Sampling for Long Video Understanding
by: Tang, Xi, et al.
Published: (2025)

SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis
by: Kim, Junho, et al.
Published: (2024)

VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks
by: Jang, Lawrence, et al.
Published: (2024)

Iterative Zoom-In: Temporal Interval Exploration for Long Video Understanding
by: Li, Chenglin, et al.
Published: (2025)

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction
by: Man, Yuanbin, et al.
Published: (2024)

AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation
by: Tan, Haoyue, et al.
Published: (2026)

Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understanding
by: Chen, Houlun, et al.
Published: (2026)

Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos
by: Fei, Jiajun, et al.
Published: (2024)

VideoExplorer: Think With Videos For Agentic Long-Video Understanding
by: Yuan, Huaying, et al.
Published: (2025)

LVBench: An Extreme Long Video Understanding Benchmark
by: Wang, Weihan, et al.
Published: (2024)

Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding
by: Zhang, Xiaoyi, et al.
Published: (2025)

TimeSearch: Hierarchical Video Search with Spotlight and Reflection for Human-like Long Video Understanding
by: Pan, Junwen, et al.
Published: (2025)

AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding
by: Qi, Haozhe, et al.
Published: (2026)

ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding
by: Lu, Hao, et al.
Published: (2025)

VideoWeave: A Data-Centric Approach for Efficient Video Understanding
by: Durante, Zane, et al.
Published: (2026)

HLV-1K: A Large-scale Hour-Long Video Benchmark for Time-Specific Long Video Understanding
by: Zou, Heqing, et al.
Published: (2025)

StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding
by: Yang, Yanlai, et al.
Published: (2025)

Enhancing Long Video Question Answering with Scene-Localized Frame Grouping
by: Yang, Xuyi, et al.
Published: (2025)

Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding
by: Wang, Yun, et al.
Published: (2025)

VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority
by: Qiu, Chenhao, et al.
Published: (2026)

TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability
by: Chen, Shimin, et al.
Published: (2024)

VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG
by: Fu, Honghao, et al.
Published: (2026)

Event-VStream: Event-Driven Real-Time Understanding for Long Video Streams
by: Guo, Zhenghui, et al.
Published: (2026)

FOCUS: Efficient Keyframe Selection for Long Video Understanding
by: Zhu, Zirui, et al.
Published: (2025)

TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning
by: Pan, Junwen, et al.
Published: (2025)

HaploOmni: Unified Single Transformer for Multimodal Video Understanding and Generation
by: Xiao, Yicheng, et al.
Published: (2025)

M-LLM Based Video Frame Selection for Efficient Video Understanding
by: Hu, Kai, et al.
Published: (2025)

QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design
by: Schneider, Benjamin, et al.
Published: (2025)

Localizing Events in Videos with Multimodal Queries
by: Zhang, Gengyuan, et al.
Published: (2024)

TIR-Flow: Active Video Search and Reasoning with Frozen VLMs
by: Jin, Hongbo, et al.
Published: (2026)

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding
by: Wang, Ziyang, et al.
Published: (2025)

FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding
by: Cho, Janghoon, et al.
Published: (2025)