I am Aditya, a machine learning research scientist at the Adobe Media and Data Science Research (MDSR) Laboratory. I received my PhD from IIIT Hyderabad under the supervision of Prof. C.V. Jawahar and Prof. M. Pawan Kumar (University of Oxford). My broad interests lie in computer vision and machine learning. During my PhD, I focused on weakly supervised learning for diverse visual tasks, developing probabilistic methods that enable models to learn from limited or imprecise annotations while remaining robust and generalizable. My work spans structured prediction, uncertainty modeling, and label-efficient training strategies, with applications in object detection, human pose estimation, and semantic segmentation. Following my PhD, my research has expanded to include visual reasoning models and compositional generation using diffusion models. If you’re interested in discussing any of these topics or exchanging ideas, please feel free to reach out via email. You can find more details about my work here: adityaarun1.github.io