Alexey Artemov
Papers
1
Total Citations
14
H-Index
1
About
Alexey Artemov is a researcher whose work lies at the intersection of computer vision, generative modeling, and efficient deep learning. He is best known for his contributions to video generation, particularly through his work on the "Latent Video Transformer," which tackles the critical challenge of reducing the massive computational resources—such as the 512 Tensor Processing Units—typically required for training video models. By formulating video generation as a prediction task and leveraging latent space representations, Artemov has helped pave the way for more accessible and scalable generative systems. His research has garnered attention in the field, with his most-cited paper accumulating 14 citations, reflecting its relevance to the ongoing push for efficiency in AI. Beyond this, Artemov’s work addresses the broader goal of making advanced video synthesis practical for real-world applications, marking him as a thoughtful contributor to the next generation of generative models. His efforts continue to inspire students and researchers seeking to balance performance with resource constraints in deep learning.
Research Focus
Key Achievements
Top Papers
- 1Latent Video Transformer14 citations · 2021