Vision and Interpretability Lab
We advance computer vision and trustworthy machine learning. Our team builds models that see the world, and tools that explain how and why they work.
Our research focus
We study perception, generalization, and explanation in modern AI systems. From robust recognition and segmentation to attribution, saliency, and concept-based explanations, we aim to make AI more reliable and interpretable.
Computer Vision
Detection, segmentation, multi-modal learning, and evaluation on real-world datasets.
Interpretability
Attributions, saliency maps, concept probes, and human-centered evaluation for explanations.
Responsible AI
Robustness, fairness, data quality, and transparent reporting for trustworthy systems.
What we do
We publish open research, release datasets and tools, and collaborate with academia and industry. Explore our projects and publications to see how we make AI more understandable.
