Cover Image

Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Xiangrui, Shu, Yan, Liu, Zheng, Li, Ao, Tian, Yang, Zhao, Bo
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification
by: Qin, Minghao, et al.
Published: (2025)

Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding
by: Shu, Yan, et al.
Published: (2024)

TimeScope: Towards Task-Oriented Temporal Grounding In Long Videos
by: Liu, Xiangrui, et al.
Published: (2025)

Task-Aware KV Compression For Cost-Effective Long Video Understanding
by: Qin, Minghao, et al.
Published: (2025)

One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding
by: Zhang, Zheyu, et al.
Published: (2026)

VideoPro: Adaptive Program Reasoning for Long Video Understanding
by: Li, Chenglin, et al.
Published: (2025)

FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding
by: Guo, Yanan, et al.
Published: (2025)

Video Token Merging for Long-form Video Understanding
by: Lee, Seon-Ho, et al.
Published: (2024)

Video-Browser: Towards Agentic Open-web Video Browsing
by: Liang, Zhengyang, et al.
Published: (2025)

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation
by: Ma, Wentao, et al.
Published: (2025)

VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models
by: Wang, Jiapeng, et al.
Published: (2024)

EarlyTom: Early Token Compression Completes Fast Video Understanding
by: Wang, Hesong, et al.
Published: (2026)

X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding
by: Zhou, Wenqi, et al.
Published: (2025)

STORM: Token-Efficient Long Video Understanding for Multimodal LLMs
by: Jiang, Jindong, et al.
Published: (2025)

MLVU: Benchmarking Multi-task Long Video Understanding
by: Zhou, Junjie, et al.
Published: (2024)

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

Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning
by: Ma, Yinchao, et al.
Published: (2026)

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
by: Shen, Xiaoqian, et al.
Published: (2024)

MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
by: Wu, Peiran, et al.
Published: (2025)

VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction
by: Wang, Shaobo, et al.
Published: (2025)

METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding
by: Wang, Mengyue, et al.
Published: (2025)

LVC: A Lightweight Compression Framework for Enhancing VLMs in Long Video Understanding
by: Wang, Ziyi, et al.
Published: (2025)

Memory-enhanced Retrieval Augmentation for Long Video Understanding
by: Yuan, Huaying, et al.
Published: (2025)

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
by: Song, Enxin, et al.
Published: (2023)

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

Extreme Video Compression with Pre-trained Diffusion Models
by: Li, Bohan, et al.
Published: (2024)

AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding
by: Li, Handong, et al.
Published: (2026)

VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges
by: Wang, Yuxuan, et al.
Published: (2024)

FlexSelect: Flexible Token Selection for Efficient Long Video Understanding
by: Zhang, Yunzhu, et al.
Published: (2025)

Dynamic Token Compression for Efficient Video Understanding through Reinforcement Learning
by: Wang, Shida, et al.
Published: (2026)

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

Motion Guided Token Compression for Efficient Masked Video Modeling
by: Feng, Yukun, et al.
Published: (2024)

ProTA: Probabilistic Token Aggregation for Text-Video Retrieval
by: Fang, Han, et al.
Published: (2024)

TokensGen: Harnessing Condensed Tokens for Long Video Generation
by: Ouyang, Wenqi, et al.
Published: (2025)

OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding
by: Zhao, Ruixiang, et al.
Published: (2026)

Progressive Video Condensation with MLLM Agent for Long-form Video Understanding
by: Yin, Yufei, et al.
Published: (2026)

VideoLucy: Deep Memory Backtracking for Long Video Understanding
by: Zuo, Jialong, et al.
Published: (2025)

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

VirtueBench: Evaluating Trustworthiness under Uncertainty in Long Video Understanding
by: Yu, Xueqing, et al.
Published: (2026)

An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes
by: Qi, Ji, et al.
Published: (2025)