Pavlo Molchanov
I'm a Research Director at NVIDIA leading DLER team (webpage) at NVIDIA Research. My research focuses on efficiency in LLMs and multi-modal models: compression, NAS-like acceleration, novel architectures, and adaptive/conditional inference.
News
Projects and publications (full list)
Foundation Models
Post-training Optimization
Multi-Modal Models
Vision Encoders
Professional Service
I am happy to give keynotes and invited talks, contact me.
Awards & Recognition
- 2014: Best Paper Award, EuRAD Conference
- 2014: Young Researcher Award, EuRAD Conference
- 2012-2014: Nokia Foundation Scholarship
- 2011-2014: GETA Graduate School Grant
Bio
Pavlo Molchanov obtained a PhD from Tampere University of Technology, Finland, in 2014, in the field of RADAR signal processing. During his studies, he received the Nokia Foundation Scholarship, GETA Graduate School grant, Best Paper Award, and Young Researcher Award at EuRAD.
Since 2015, he has been working in NVIDIA Research where he is now a Research Director leading a deep learning efficiency team. With the focus on LLMs and multi-modal models, he has been working on compression, NAS-like acceleration, novel architectures, and adaptive/conditional inference.
His past research has led to several NVIDIA product integrations: hand, body, and facial keypoint estimation and recognition in DriveIX, Broadcast, Omniverse, Maxine; efficient vision backbones in TAO, developed compression techniques in TAO, NVIDIA AV, TRT Model Optimization; and small in-game LLMs called Minitron. More recently, he has been working on design and compression of NVIDIA Nemotron models.