Scholar
Skanda Koppula
Google Scholar ID: hlC76YUAAAAJ
Google DeepMind
Citations & Impact
Citations
2,454
H-index
16
i10-index
19
Publications
20
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- Published several papers including but not limited to: TAPNext: Tracking Any Point (TAP) as Next Token Prediction, SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications, TAPVid-3D: A Benchmark for Tracking Any Point in 3D, Scaling 4D Representations, etc.
Research Experience
- Worked on new versions of PilotNet with NVIDIA's Autonomous Driving Team; in 2017, worked with the Google Acoustic Modeling research team under Prof. Khe Chai Sim; previously interned at Yahoo and Square.
Education
- Was a Fulbright researcher at ETH Zürich in 2019 working with Prof. Onur Mutlu; completed MEng at MIT in 2018, advised by Professor Anantha Chandrakasan and Dr. Jim Glass; received B.S. in Computer Science from MIT in 2016.
Background
- Currently a research engineer at Google DeepMind and part of the PRISM vision research group at University College London. Works on dynamic 3D vision, visual representation learning, and video understanding. Research background includes computer vision, natural language understanding, computer security, and computer architecture.
Miscellany
- Loves painting and building racecars.
Co-authors