Representation Dynamics Reveal Semantic Saliency and Similarity for Visual Token Pruning in MLLMs

arXiv:2609.36916 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-30

Code: https://github.com/liweixuan-hitsz/MSDG-Prune

Terminology

• Pruning — 42× in this paper · explained in 4 episodes
• Benchmark — 20× in this paper · explained in 2 episodes
• Cosine Similarity — 16× in this paper · explained in 3 episodes
• Ablation — 12× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition — 10× in this paper
• Redundancy — 7× in this paper · explained in 2 episodes
• Aggregation — 6× in this paper · explained in 1 episode
• Consistency — 4× in this paper · explained in 3 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• F1 Score — 4× in this paper · explained in 3 episodes
• Hallucination — 3× in this paper · explained in 3 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Clustering — 2× in this paper · explained in 2 episodes
• Generalizability — 2× in this paper · explained in 6 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Vision-language models — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• CVF International Conference on Computer Vision — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Guided attention — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Positional Bias — 1× in this paper · explained in 2 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Training-Free Framework — 1× in this paper · explained in 2 episodes

Sources

• GPT-4 Technical Report
• Qwen2.5-VL Technical Report
• Token Merging: Your ViT But Faster
• SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension
• EvoCut: Multi-Layer Evolution-Aware Visual Token Compression for Efficient Large Vision-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