10 citations · 20 across the 5 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Decoder-Agnostic Token Merging for Vision Transformers: A Systematic Study of G2TM
Victor Bercy, Martyna Poreba, Michal Szczepanski +1
Vision Transformers (ViTs) have achieved state-of-the-art performance across a range of computer vision tasks, mainly thanks to the self-attention mechanism. However, its complexit…
cs.CV2026
Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Models
Yvon Apedo, Martyna Poreba, Michal Szczepanski +1
Vision-Language Models (VLMs) have revolutionized multi-modal learning by jointly processing visual and textual information. Yet, they face significant challenges due to the high c…