Copertina

Accelerating Streaming Video Large Language Models via Hierarchical Token Compression

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Yiyu, Liu, Xuyang, Gui, Xiyan, Lin, Xinying, Yang, Boxue, Liao, Chenfei, Chen, Tailai, Zhang, Linfeng
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models
di: Liu, Xuyang, et al.
Pubblicazione: (2025)

EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant
di: Wen, Zichen, et al.
Pubblicazione: (2026)

Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Models
di: Liu, Xuyang, et al.
Pubblicazione: (2025)

V-CAST: Video Curvature-Aware Spatio-Temporal Pruning for Efficient Video Large Language Models
di: Lin, Xinying, et al.
Pubblicazione: (2026)

Flash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified Models
di: Ke, Junlong, et al.
Pubblicazione: (2026)

Variation-aware Vision Token Dropping for Faster Large Vision-Language Models
di: Chen, Junjie, et al.
Pubblicazione: (2025)

Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods
di: Liao, Chenfei, et al.
Pubblicazione: (2025)

Shifting AI Efficiency From Model-Centric to Data-Centric Compression
di: Liu, Xuyang, et al.
Pubblicazione: (2025)

AI for Service: Proactive Assistance with AI Glasses
di: Wen, Zichen, et al.
Pubblicazione: (2025)

Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models
di: Han, Yuhang, et al.
Pubblicazione: (2026)

KiToke: Kernel-based Interval-aware Token Compression for Video Large Language Models
di: Huang, Haifeng, et al.
Pubblicazione: (2026)

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

Accelerating Diffusion Transformers with Token-wise Feature Caching
di: Zou, Chang, et al.
Pubblicazione: (2024)

TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models
di: Tan, Xudong, et al.
Pubblicazione: (2025)

HieraVid: Hierarchical Token Pruning for Fast Video Large Language Models
di: Guo, Yansong, et al.
Pubblicazione: (2026)

Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration
di: Han, Yuhang, et al.
Pubblicazione: (2024)

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

StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding
di: Wang, Junxi, et al.
Pubblicazione: (2026)

Streaming Long Video Understanding with Large Language Models
di: Qian, Rui, et al.
Pubblicazione: (2024)

Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
di: Liu, Xuyang, et al.
Pubblicazione: (2025)

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

EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
di: Yang, Yantai, et al.
Pubblicazione: (2025)

Language-Guided Token Compression with Reinforcement Learning in Large Vision-Language Models
di: Cao, Sihan, et al.
Pubblicazione: (2026)

VideoLLM-online: Online Video Large Language Model for Streaming Video
di: Chen, Joya, et al.
Pubblicazione: (2024)

TokenSeg: Efficient 3D Medical Image Segmentation via Hierarchical Visual Token Compression
di: Zeng, Sen, et al.
Pubblicazione: (2026)

HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models
di: Zhou, Ziqin, et al.
Pubblicazione: (2025)

A Survey of Token Compression for Efficient Multimodal Large Language Models
di: Shao, Kele, et al.
Pubblicazione: (2025)

Open-ended Hierarchical Streaming Video Understanding with Vision Language Models
di: Kang, Hyolim, et al.
Pubblicazione: (2025)

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

OTT-Vid: Optimal Transport Temporal Token Compression for Video Large Language Models
di: Kang, Minseok, et al.
Pubblicazione: (2026)

HPC: Hierarchical Point-based Latent Representation for Streaming Dynamic Gaussian Splatting Compression
di: Ma, Yangzhi, et al.
Pubblicazione: (2026)

Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation
di: Lyu, Yuanhuiyi, et al.
Pubblicazione: (2025)

VidCompress: Memory-Enhanced Temporal Compression for Video Understanding in Large Language Models
di: Lan, Xiaohan, et al.
Pubblicazione: (2024)

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model
di: Liu, Ting, et al.
Pubblicazione: (2024)

4DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming
di: Zheng, Zihan, et al.
Pubblicazione: (2025)

Vision-centric Token Compression in Large Language Model
di: Xing, Ling, et al.
Pubblicazione: (2025)

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

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

Aligning Effective Tokens with Video Anomaly in Large Language Models
di: Chen, Yingxian, et al.
Pubblicazione: (2025)

Hierarchical Frequency-based Upsampling and Refining for Compressed Video Quality Enhancement
di: Zhang, Qianyu, et al.
Pubblicazione: (2024)