Scholar
Alexander Vilesov
Google Scholar ID: LtHRlX4AAAAJ
PhD ECE at UCLA
Citations & Impact
Citations
92
H-index
3
i10-index
2
Publications
9
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Publications:
- - VLM4D: Towards Spatiotemporal Awareness in Vision Language Models (ICCV, 2025)
- - Chimera: Creating Digitally Signed Fake Photos by Fooling Image Recapture and Deepfake Detectors (Usenix Security, 2025)
- - Implicit Neural Models to Extract Heart Rate from Video (ECCV, 2024)
- - Solutions to Deepfakes: Can Camera Hardware, Cryptography, and Deep Learning Verify Real Images? (White Paper, 2024)
- - CG3D: Compositional Generation for Text-to-3D via Gaussian Splatting (Arxiv, 2023)
Research Experience
- PhD research in the Visual Machines Group at UCLA, focusing on spatial intelligence in vision-language models; collaborated with Prof. Antonio Ortega in the GSP Lab and with Prof. Rahul Jain in the S2L2 Lab on inverse reinforcement learning at USC; worked on the TriG GPS receiver project at NASA JPL; developed computer vision models during an internship at Terrawise AI.
Education
- Received a Bachelor's degree in Electrical and Computer Engineering from the University of Southern California (USC) in 2021; worked at NASA JPL on TriG GPS receivers (mounted on Cosmic-2) to support tracking of GALILEO satellites in 2020-2021; interned at Terrawise AI in 2025, developing computer vision models for robot navigation and solar asset monitoring as well as agentic LLM applications for robotic fleet management.
Background
- Research Interests: Computer vision, spatial intelligence in vision-language models, large language models, diffusion models, digital health, camera security. Bio: PhD student in the Visual Machines Group at UCLA, advised by Prof. Achuta Kadambi.
Miscellany
- Contact: vilesov@ucla.edu / (626)-390-7241
Co-authors