Copertina

HieraVid: Hierarchical Token Pruning for Fast Video Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Guo, Yansong, Zhu, Chaoyang, Ji, Jiayi, Lin, Jianghang, Cao, Liujuan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

VidCoM: Fast Video Comprehension through Large Language Models with Multimodal Tools
di: Qi, Ji, et al.
Pubblicazione: (2023)

PruneVid: Visual Token Pruning for Efficient Video Large Language Models
di: Huang, Xiaohu, et al.
Pubblicazione: (2024)

Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models
di: Ye, Weihao, et al.
Pubblicazione: (2024)

Pseudo-Label Quality Decoupling and Correction for Semi-Supervised Instance Segmentation
di: Lin, Jianghang, et al.
Pubblicazione: (2025)

GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane
di: Qu, Yansong, et al.
Pubblicazione: (2024)

AnomalyPainter: Vision-Language-Diffusion Synergy for Zero-Shot Realistic and Diverse Industrial Anomaly Synthesis
di: Lai, Zhangyu, et al.
Pubblicazione: (2025)

Evolving, Not Training: Zero-Shot Reasoning Segmentation via Evolutionary Prompting
di: Ye, Kai, et al.
Pubblicazione: (2025)

Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection
di: Lu, Yilin, et al.
Pubblicazione: (2025)

Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?
di: Wen, Zichen, et al.
Pubblicazione: (2025)

Understanding What Is Not Said:Referring Remote Sensing Image Segmentation with Scarce Expressions
di: Ye, Kai, et al.
Pubblicazione: (2025)

FastVGGT: Training-Free Acceleration of Visual Geometry Transformer
di: Shen, You, et al.
Pubblicazione: (2025)

Active-SAOOD: Active Sparsely Annotated Oriented Object Detection in Remote Sensing Images
di: Lin, Yu, et al.
Pubblicazione: (2026)

WildSeg3D: Segment Any 3D Objects in the Wild from 2D Images
di: Guo, Yansong, et al.
Pubblicazione: (2025)

VidLA: Video-Language Alignment at Scale
di: Rizve, Mamshad Nayeem, et al.
Pubblicazione: (2024)

Depth-Guided Semi-Supervised Instance Segmentation
di: Chen, Xin, et al.
Pubblicazione: (2024)

HUWSOD: Holistic Self-training for Unified Weakly Supervised Object Detection
di: Cao, Liujuan, et al.
Pubblicazione: (2024)

ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models
di: Ye, Xubing, et al.
Pubblicazione: (2024)

CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models
di: Poppi, Tobia, et al.
Pubblicazione: (2026)

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

Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models
di: Li, Yue, et al.
Pubblicazione: (2025)

What You Perceive Is What You Conceive: A Cognition-Inspired Framework for Open Vocabulary Image Segmentation
di: Lin, Jianghang, et al.
Pubblicazione: (2025)

HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba Pooling
di: An, Joungbin, et al.
Pubblicazione: (2025)

Referring Industrial Anomaly Segmentation
di: Yue, Pengfei, et al.
Pubblicazione: (2026)

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models
di: Liu, Jizhihui, et al.
Pubblicazione: (2025)

SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning
di: Ji, Yicheng, et al.
Pubblicazione: (2025)

CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
di: Tang, Zicong, et al.
Pubblicazione: (2025)

UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking
di: Wu, Hao, et al.
Pubblicazione: (2026)

S$^2$Teacher: Step-by-step Teacher for Sparsely Annotated Oriented Object Detection
di: Lin, Yu, et al.
Pubblicazione: (2025)

MIHBench: Benchmarking and Mitigating Multi-Image Hallucinations in Multimodal Large Language Models
di: Li, Jiale, et al.
Pubblicazione: (2025)

Test-Time Computing for Referring Multimodal Large Language Models
di: Wu, Mingrui, et al.
Pubblicazione: (2026)

HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit
di: Wu, Hao, et al.
Pubblicazione: (2026)

VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models
di: Wang, Wenhao, et al.
Pubblicazione: (2024)

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

HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation
di: Chen, Cong, et al.
Pubblicazione: (2025)

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

HieraFashDiff: Hierarchical Fashion Design with Multi-stage Diffusion Models
di: Xie, Zhifeng, et al.
Pubblicazione: (2024)

From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models
di: Shang, Yuying, et al.
Pubblicazione: (2024)

Video Understanding with Large Language Models: A Survey
di: Tang, Yolo Y., et al.
Pubblicazione: (2023)

Efficient Vision-Language Reasoning via Adaptive Token Pruning
di: Li, Xue, et al.
Pubblicazione: (2025)

Index-Preserving Lightweight Token Pruning for Efficient Document Understanding in Vision-Language Models
di: Son, Jaemin, et al.
Pubblicazione: (2025)