4 papers · 1 filter
Watch and Learn: Teaching Visual In-Context Learning by Removing Textual Shortcuts
Nimrod Shabtay, Asaf Yehudai, Avihu Dekel +2
Vision-language models (VLMs) struggle with in context learning compared to their textual counterparts. Our preliminary study shows that VLMs rely on textual shortcuts and underuti…
Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs
Nimrod Shabtay, Moshe Kimhi, Artem Spector +5
Vision-language models (VLMs) typically process images at a native high-resolution, forcing a trade-off between accuracy and computational efficiency: high-resolution inputs captur…
CARES: Context-Aware Resolution Selector for VLMs
Moshe Kimhi, Nimrod Shabtay, Raja Giryes +2
Large vision-language models (VLMs) commonly process images at native or high resolution to remain effective across tasks. This inflates visual tokens ofter to 97-99% of total toke…
WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIP
Moshe Kimhi, Erez Koifman, Ehud Rivlin +2
We introduce WAVECLIP, a single unified model for adaptive resolution inference in CLIP, enabled by wavelet-based tokenization. WAVECLIP replaces standard patch embeddings with a m…