Hello!
Iโm Nikita Durasov, a Research Scientist at NVIDIA (
), working on semantic video search and vision-language models (VLMs) post-training.
Previously, I worked at Apple, Amazon, and Samsung AI on deep learning and computer vision. I completed my PhD at EPFL (๐จ๐ญ) with Pascal Fua at CVLAB, focusing on uncertainty and robustness.
Research
Iโm interested in advancing vision-language models (VLMs) and video understanding, building scalable retrieval and reasoning pipelines that turn complex video data into searchable, interpretable knowledge.
My work explores robustness, generalization, and semantic search to make multimodal AI systems more powerful and reliable. For a non-exhaustive list of my research interests, refer to my Google Scholar.
I have also contributed as a reviewer for various academic conferences and journals, such as: CVPR NeurIPS ICLR ICML ICCV ECCV ICRA IROS ACCV RA-L IJCV AISTATS TPAMI TMLR WACV, and other (full list).
Publications
Hover or select a paper to see details.
Handbook of Bayesian Deep Learning
View details +
Diffusion Models are Secretly Zero-Shot 3DGS Harmonizers
View details +
Uncertainty-Guided Data Curation for 3D Object Detection
View details +
Scalable Parallel Prompting for Complex AV Video Captioning
View details +
April Yang*, Roberto Amoroso*, Nikita Durasov, Devansh Bisla, Sandipan Kundu, Elmar Haussmann, Ruchi Bhargava, Maying Shen, Nadine Chang, Jose M. Alvarez
CVPRW 2026
