Pavlo Molchanov

Pavlo Molchanov received his PhD from Tampere University of Technology, Finland, in 2014 in the field of RADAR signal processing. During his studies, he was awarded the Nokia Foundation Scholarship, the GETA Graduate School grant, a Best Paper Award, and the EuRAD Young Researcher Award.

Since 2015, he has been with NVIDIA Research, where he is now a Research Director leading a deep learning efficiency team. His work focuses on LLMs and multimodal models, including research on model compression, NAS-like acceleration, novel architectures, and adaptive/conditional inference.

His earlier research has been widely deployed across NVIDIA platforms and technologies through advances in keypoint estimation, efficient vision backbones, and model optimization techniques. More recently, he has contributed to the design and compression of NVIDIA’s large-scale foundation models.