Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Reinforcing VLMs to Use Tools for Detailed Visual Reasoning Under Resource Constraints
Sunil Kumar, Bowen Zhao, Leo Dirac +1
Despite tremendous recent advances in large model reasoning ability, vision-language models (VLMs) still struggle with detailed visual reasoning, especially when compute resources…
cs.LG2024
Fine-tuning Vision Classifiers On A Budget
Sunil Kumar, Ted Sandler, Paulina Varshavskaya
Fine-tuning modern computer vision models requires accurately labeled data for which the ground truth may not exist, but a set of multiple labels can be obtained from labelers of v…