Year: 2026
Type: review
Study design: Systematic Review
Abstract: Large Vision-Language Models (LVLMs) excel at visual understanding but face severe computational bottlenecks when processing high-resolution images and long videos due to massive visual token counts. Token pruning mitigates this by selectively removing less informative tokens while maintaining performance. However, existing methods vary widely in pruning location (vision encoder vs. LLM decoder), importance criteria (attention vs. similarity vs. learned scores), and application strategy, lacking systematic comparison. This survey presents the first comprehensive review of token pruning for LVLMs. We propose a taxonomy categorizing methods into vision-side, LLM-side, and hybrid paradigms, systematically analyze token selection mechanisms and pruning strategy. We further discuss evaluation protocols and identify key challenges including prompt-adaptive pruning and hardware-aware design. Our survey provides a structured foundation for this rapidly growing research area.
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: Collaborative Research: III: Small: Physics Guided Graph Networks for Modeling Water Dynamics in Freshwater Ecosystems, Collaborative Research: CPS: Medium: Multi-Scale Sensing and Control for Optimizing Crop Production and Energy Efficiency in Controlled-Environment Agriculture, G8876996369, Online Adaptive Proton Therapy
OpenAlex ID: W7166847097