QCPruner: Query-Conditioned Population Coverage for Visual Token Pruning
cs.CV
Submitted: 2026-09-17
Updated: 2026-09-17
Code: https://github.com/haotian-liu/LLaVA
Terminology
Sources
- Qwen2.5-VL Technical Report
- Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity
- MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
- Similarity-Aware Token Pruning: Your VLM but Faster
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities
- SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
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