Ian Maquignaz enhanced the Lightning-AI/torchmetrics repository by refining documentation for the VisualInformationFidelity (VIF) metric, focusing on clarifying input shape requirements. He updated the Python docstrings to specify that both predicted and ground truth images must have a minimum shape of (41, 41), and detailed the ValueError raised for non-conforming inputs. This documentation-focused contribution addressed common misconfigurations, providing clearer guidance for developers and reducing onboarding friction. Ian’s work demonstrated attention to detail in technical writing and a strong understanding of API usability, though the scope was limited to a single feature update without direct code or bug fixes.