Pavlo Molchanov

Pavlo Molchanov is a Distinguished Research Scientist and Team Manager at NVIDIA Research. Since 2023, he has been leading the Deep Learning Efficiency Team at NVIDIA Research. He obtained a PhD from Tampere University of Technology, Finland, in 2014 with Karen Eguiazarian. During his studies, he received the Nokia Foundation Scholarship, GETA Graduate School grant, Best Paper Award, and Young Researcher Award at EuRAD. Recently, he has focused on efficiency in LLMs and multi-modal models: 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.

We are always on the lookout for promising interns and full-time positions in the area of LLM and VLM efficiency. Feel free to reach out to me for more details. I am also interested in connecting with individuals who share similar research interests.

Publications

Full list with filter

X-VILA: Cross-Modality Alignment for Large Language Model. Hanrong Ye, De-An Huang, Yao Lu, Zhiding Yu, Wei Ping, Andrew Tao, Jan Kautz, Song Han, Dan Xu, Pavlo Molchanov, Hongxu Yin (2024). In Arxiv.

PDF Cite

DoRA: Weight-Decomposed Low-Rank Adaptation. Shih-Yang Liu, Chien-Yi Wang, Hongxu Yin, Pavlo Molchanov, Yu-Chiang Frank Wang, Kwang-Ting Cheng, Min-Hung Chen (2024). ICML 2024.

PDF Cite Code Project Video ICML2024(Oral)

AM-RADIO: Reduce All Domains Into One. Mike Ranzinger, Greg Heinrich, Jan Kautz, Pavlo Molchanov (2023). In Arxiv.

PDF Cite Code CVPR2024

VILA: On Pre-training for Visual Language Models. Ji Lin, Hongxu Yin, Wei Ping, Yao Lu, Pavlo Molchanov, Andrew Tao, Huizi Mao, Jan Kautz, Mohammad Shoeybi, Song Han (2023). In Arxiv.

PDF Cite CVPR2024

FasterViT: Fast Vision Transformers with Hierarchical Attention. A. Hatamizadeh, G. Heinrich, H. Yin, A. Tao, J. Alvarez, J. Kautz, P. Molchanov (2023). In Arxiv.

PDF Cite Code ICLR2024

Heterogeneous Continual Learning. D. Madaan, H. Yin, W. Byeon, J. Kautz, P. Molchanov (2023). In CVPR 2023.

PDF Cite Code Video CVPR2023 Highlight

Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Models. P. Micaelli, A. Vahdat, H. Yin, J. Kautz, P. Molchanov (2023). In CVPR 2023.

PDF Cite Code Video CVPR2023

Global context vision transformers. A. Hatamizadeh, H. Yin, J. Kautz, P. Molchanov (2023). In ICML 2023.

PDF Cite Code ICML2023

LANA: Latency Aware Network Acceleration. P. Molchanov, J. Hall, H. Yin, J. Kautz, N. Fusi, A. Vahdat (2022). In CVPR 2022.

PDF Cite Video ECCV2022

Structural pruning via latency-saliency knapsack. M. Shen, H. Yin, P. Molchanov, L. Mao, J. Liu, J. Alvarez (2022). In NeurIPS2022.

PDF Cite Code Video NeurIPS2022

See all publications