arXiv Computer Vision
Neighbor-Aware Token Reduction via Hilbert Curve for Vision Transformers
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Jun 9
RAPID: Layer-Wise Redundancy-Aware Pruning and Importance-Driven Token Merging for Efficient ViT
arXiv:2606. 08156v1 Announce Type: cross Abstract: Vision Transformers (ViTs) achieve strong performance but suffer from high computational costs due to quadratic self-attention complexity.
arXiv AI
Jul 10
Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Models
arXiv:2604. 11530v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have revolutionized multi-modal learning by jointly processing visual and textual information.
arXiv Computer Vision
Sep 22
VPRune: Efficient Training-free Pre-LLM Visual Token Pruning
arXiv:2609.24485v1 Announce Type: new Abstract: Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction oft...
arXiv Machine Learning
Aug 21
Clustering and Token Denoising for Faster and More Robust VLMs
arXiv:2608. 19285v1 Announce Type: cross Abstract: Recent Visual-Language Models (VLMs) have enhanced the capabilities of pre-trained LLMs by adding vision tokens alongside text, with approaches like LLaVA showing impressive results.
arXiv AI
Sep 1
Centering before Pruning: Lightweight Geometry Correction for Diversity-Based Visual Token Pruning in LVLMs
arXiv:2608.30263v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) incur substantial inference costs due to their long and highly redundant visual-token sequences. Diversity-based...
arXiv AI
Jun 2
CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models
arXiv:2605. 13178v2 Announce Type: replace-cross Abstract: In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead.