ACPruner: Visual Token Pruning as Biased Attention Coverage Maximization in LVLMs
cs.CV
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Qwen2.5-VL Technical Report
- FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
- HERO: Rethinking Visual Token Early Dropping in High-Resolution Large Vision-Language Models
- Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language Models
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model
- ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention
- Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More
- HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit
- UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models