Layer-Aware Position Embeddings for Visual Token Pruning in Multimodal Large Language Models

arXiv:2609.23715 · cs.CV · Submitted 2026-09-20 · Read on arXiv

cs.CV

Submitted: 2026-09-20

Updated: 2026-09-20

Code: https://github.com/YahongWang1/LayerPos

Terminology

• Embeddings — 104× in this paper · explained in 2 episodes
• Pruning — 71× in this paper · explained in 4 episodes
• Grounding — 68× in this paper · explained in 3 episodes
• Accuracy — 17× in this paper · explained in 1 episode
• Benchmark — 17× in this paper · explained in 2 episodes
• Visual Grounding — 10× in this paper · explained in 2 episodes
• Large Language Model — 7× in this paper
• Conference on Computer Vision and Pattern Recognition — 5× in this paper
• Calibration — 4× in this paper · explained in 7 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Optimal Transport — 2× in this paper · explained in 5 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Adaptive Strategy — 1× in this paper · explained in 1 episode
• Alignment Problem — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• IEEE International Conference on Computer Vision — 1× in this paper
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Multimodal Inputs — 1× in this paper · explained in 2 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes

Sources

• Qwen Technical Report
• Qwen2.5-VL Technical Report
• Are We on the Right Way for Evaluating Large Vision-Language Models?
• OTPrune: Distribution-Aligned Visual Token Pruning via Optimal Transport
• Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning
• MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
• LLaVA-OneVision: Easy Visual Task Transfer
• RoFormer: Enhanced Transformer with Rotary Position Embedding
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models

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