Cover Image

How Many Visual Tokens Do Multimodal Language Models Need? Scaling Visual Token Pruning with F^3A

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, YiJie, Zhang, Yiqun, Jia, Zhuoyue, Yang, Xiaocui, Huang, Junzhao, Wang, Zihan, Feng, Shi, Wang, Daling, Zhang, Yifei, Liu, Yongkang
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

Muse: A Multimodal Conversational Recommendation Dataset with Scenario-Grounded User Profiles
by: Wang, Zihan, et al.
Published: (2024)

Enhancing LLM-based Recommendation through Semantic-Aligned Collaborative Knowledge
by: Wang, Zihan, et al.
Published: (2025)

ES4R: Speech Encoding Based on Prepositive Affective Modeling for Empathetic Response Generation
by: Gao, Zhuoyue, et al.
Published: (2026)

Can LLMs Beat Humans in Debating? A Dynamic Multi-agent Framework for Competitive Debate
by: Zhang, Yiqun, et al.
Published: (2024)

TOOL-ED: Enhancing Empathetic Response Generation with the Tool Calling Capability of LLM
by: Cao, Huiying, et al.
Published: (2024)

MoLAN: A Unified Modality-Aware Noise Dynamic Editing Framework for Multimodal Sentiment Analysis
by: Xu, Xingle, et al.
Published: (2025)

MEKiT: Multi-source Heterogeneous Knowledge Injection Method via Instruction Tuning for Emotion-Cause Pair Extraction
by: Mu, Shiyi, et al.
Published: (2025)

Generative Emotion Cause Explanation in Multimodal Conversations
by: Wang, Lin, et al.
Published: (2024)

TrimTokenator-LC: Towards Adaptive Visual Token Pruning for Large Multimodal Models with Long Contexts
by: Zhang, Hao, et al.
Published: (2025)

Why Do More Experts Fail? A Theoretical Analysis of Model Merging
by: Wang, Zijing, et al.
Published: (2025)

PsyDraw: A Multi-Agent Multimodal System for Mental Health Screening in Left-Behind Children
by: Zhang, Yiqun, et al.
Published: (2024)

TrimTokenator: Towards Adaptive Visual Token Pruning for Large Multimodal Models
by: Zhang, Hao, et al.
Published: (2025)

DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models
by: Alvar, Saeed Ranjbar, et al.
Published: (2025)

GRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification
by: Wan, Faxian, et al.
Published: (2026)

Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation
by: Shangguan, Haonan, et al.
Published: (2025)

HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models
by: Zhu, Qihui, et al.
Published: (2026)

Pixel-Level Reasoning Segmentation via Multi-turn Conversations
by: Cai, Dexian, et al.
Published: (2025)

PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs
by: Wang, Zijing, et al.
Published: (2026)

NEAT: Neuron-Based Early Exit for Large Reasoning Models
by: Liu, Kang, et al.
Published: (2026)

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

From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning
by: Wang, Xiao, et al.
Published: (2026)

Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering
by: Zhang, Xiaoming, et al.
Published: (2024)

What Kind of Visual Tokens Do We Need? Training-free Visual Token Pruning for Multi-modal Large Language Models from the Perspective of Graph
by: Jiang, Yutao, et al.
Published: (2025)

On the Role of Discrete Tokenization in Visual Representation Learning
by: Du, Tianqi, et al.
Published: (2024)

Fast-Slow Efficient Training for Multimodal Large Language Models via Visual Token Pruning
by: Zhang, Dingkun, et al.
Published: (2026)

EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models
by: Wang, Yahong, et al.
Published: (2026)

Geometry-Guided 3D Visual Token Pruning for Video-Language Models
by: Li, Han, et al.
Published: (2026)

Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing
by: Zhao, Yinzhi, et al.
Published: (2026)

Is Mamba Effective for Time Series Forecasting?
by: Wang, Zihan, et al.
Published: (2024)

CIRAG: Construction-Integration Retrieval and Adaptive Generation for Multi-hop Question Answering
by: Wei, Zili, et al.
Published: (2026)

TokenPacker: Efficient Visual Projector for Multimodal LLM
by: Li, Wentong, et al.
Published: (2024)

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

MTRouter: Cost-Aware Multi-Turn LLM Routing with History-Model Joint Embeddings
by: Zhang, Yiqun, et al.
Published: (2026)

ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance
by: Li, Duo, et al.
Published: (2025)

IDPruner: Harmonizing Importance and Diversity in Visual Token Pruning for MLLMs
by: Tan, Yifan, et al.
Published: (2026)

DEEPMED: Building a Medical DeepResearch Agent via Multi-hop Med-Search Data and Turn-Controlled Agentic Training & Inference
by: Wang, Zihan, et al.
Published: (2026)

Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response
by: Liu, Yongkang, et al.
Published: (2023)

ChatZero:Zero-shot Cross-Lingual Dialogue Generation via Pseudo-Target Language
by: Liu, Yongkang, et al.
Published: (2024)

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
by: Zhang, Qizhe, et al.
Published: (2024)

HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy
by: Liu, Yongkang, et al.
Published: (2024)