Blog(1)
Introducing high-precision depth prediction on low-end devices with low-precision calculations using depth representation as two 2D Hilbert curve components. This solution addresses problem of efficient scene perception for mobile vision applications.
Research Areas(0)
Publications(21)
Hierarchical planning for complex tasks with KG-RAG and symbolic verification
AuthorCristina Cornelio
PublishedInternational Conference on Machine Learning (ICML)
Date2025-07-13
Prodigy: Expeditiously Adaptive Parameter-Free Learner
AuthorKonstantin Mishchenko
Date2024-07-23
Towards Neural Architecture Search through Hierarchical Generative Modeling
AuthorAbhinav Mehrotra, Hongkai Wen
News(1)
Recently we proposed a new optimization algorithm called Adaptive Sharpness-Aware Minimization (ASAM), which pushes the limit of deep learning via PAC-Bayesian theory. ASAM has been improving generalization performance for various tasks leveraging geometry of loss landscape, which is highly correlated with generalization. In recognition of its theoretical contribution and practicality, our paper was published at the 38th International Conference on Machine Learning (ICML 2021).
Others(1)
About Us Papers Play Samsung AI Center – Moscow is the first institution in Russia focused directly on artificial intelligence (AI), where Russia’s strengths and capabilities in fundamental sciences, especially mathematics and physics, are brought together with Samsung global R&D strategy. Samsung AI Center - Moscow is led by Dr. Anton Konushin who is world-known AI Computer Vision expert and associate professor at Moscow State University and Higher School of Econo...