Cover Image

EarlyTom: Early Token Compression Completes Fast Video Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Hesong, Jin, Xin, Lu, Lu, Li, Chenhaowen, Chen, Jian, Liu, Qiang, Wang, Huan
Format:	Preprint
Published:	2026
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

HoliTom: Holistic Token Merging for Fast Video Large Language Models
by: Shao, Kele, et al.
Published: (2025)

StreamingTOM: Streaming Token Compression for Efficient Video Understanding
by: Chen, Xueyi, et al.
Published: (2025)

QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer
by: Pan, Zhizhen, et al.
Published: (2026)

OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
by: Tao, Keda, et al.
Published: (2025)

DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
by: Tao, Keda, et al.
Published: (2024)

FCDFusion: a Fast, Low Color Deviation Method for Fusing Visible and Infrared Image Pairs
by: Li, Hesong, et al.
Published: (2024)

LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs
by: Tao, Keda, et al.
Published: (2026)

Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding
by: Liu, Xiangrui, et al.
Published: (2025)

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

UniCompress: Token Compression for Unified Vision-Language Understanding and Generation
by: Wang, Ziyao, et al.
Published: (2026)

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

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

Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM
by: Wang, Han, et al.
Published: (2024)

StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding
by: Jin, Xinqi, et al.
Published: (2025)

Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention
by: Du, Junhao, et al.
Published: (2026)

From Understanding to Erasing: Towards Complete and Stable Video Object Removal
by: Liu, Dingming, et al.
Published: (2026)

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

OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot
by: Zhu, Junhan, et al.
Published: (2025)

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

Towards Real-time Video Compressive Sensing on Mobile Devices
by: Cao, Miao, et al.
Published: (2024)

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

A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging
by: Cao, Miao, et al.
Published: (2024)

MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
by: Jin, Xin, et al.
Published: (2025)

DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding
by: Zhang, Hongzhi, et al.
Published: (2025)

Active Perception Agent for Omnimodal Audio-Video Understanding
by: Tao, Keda, et al.
Published: (2025)

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

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

PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models
by: Yang, Chenyu, et al.
Published: (2024)

SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding
by: Xu, Mingze, et al.
Published: (2025)

Video Patch Pruning: Efficient Video Instance Segmentation via Early Token Reduction
by: Glandorf, Patrick, et al.
Published: (2026)

InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models
by: Liu, Xinxin, et al.
Published: (2026)

ST$^3$: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming
by: Zhuang, Jiedong, et al.
Published: (2024)

Motion-aware Dynamic Graph Neural Network for Video Compressive Sensing
by: Lu, Ruiying, et al.
Published: (2022)

TempCompass: Do Video LLMs Really Understand Videos?
by: Liu, Yuanxin, et al.
Published: (2024)

FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-Resolution
by: Wang, Zhaoyang, et al.
Published: (2025)

Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
by: Wang, Yiyu, et al.
Published: (2025)

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

Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification
by: Jin, Xin, et al.
Published: (2026)

DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models
by: Yao, Linli, et al.
Published: (2024)

VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs
by: Zhu, Jiaying, et al.
Published: (2025)