ayush zenith

whoami

I'm a researcher at Tera AI, where I work on spatial foundation models that let robots figure out where they are and where they're going using just a camera. No GPS, no clean maps, no per-platform tuning. Lately that means real-time visual navigation running onboard drones, from low passes over featureless desert to thermal cameras in the dark.

Before Tera I was at Northeastern studying CS (AI concentration). I taught a Boston Dynamics Spot to navigate buildings, open doors, and pick things up at GRAIL with Prof. Lawson Wong, built a quality metric for synthetic data at the Air Force Research Laboratory with Dr. Jing Lin, and did deep learning for drug development at Genentech.

ls ./research

google scholar ↗ semantic scholar ↗

1. 2026
   SDQM: Synthetic Data Quality Metric for Object Detection Dataset Evaluation

   A. Zenith, A. Zumbrun, N. Raut, J. Lin

   Journal of Electronic Imaging 35(3), 2026

   [journal] [arxiv] [code]

2. 2025
   TARDIS STRIDE: A Spatio-Temporal Road Image Dataset and World Model for Autonomy

   H. Carrión, Y. Bai, V. A. Hernández Castro, K. Panaganti, A. Zenith, M. Trang, T. Zhang, P. Perona, J. Malik

   arXiv preprint, 2025

   [arxiv] [blog] [code] [dataset]

3. pat.
   Spatially Consistent Geolocation Model

   H. Carrión, H. Zhang, M. Trang, V. Hernandez, E. Ramirez, A. Zenith, et al.

   US Patent Application 19/339,112

tail -f tera.log

recent transmissions from the Tera blog:

• Your GPS-denied nav "demo" is likely still using GPS
• Navigating in the dark: GPS-denied visual navigation on LWIR
• Delivering autonomy in days instead of months via software
• Pushing the limits of visual navigation in ultra-sparse environments
• Universal navigation for every moving robot
• TARDIS STRIDE: towards rich real-world understanding

cat ./off-hours.txt

When I'm not staring at trajectories, I'm shooting on my Fujifilm (@yush.jpg), sparring after 10+ years of taekwondo and karate, occasionally rolling jiu-jitsu, keeping strongly held food opinions on Beli, losing at chess, and watching too much anime.

ping ayush

Working on robots, navigation, or anything spatial? Say hi.

email

ayushp.zenith@gmail.com

scholar

google scholar / semantic scholar

github

@ayushzenith

linkedin

in/ayushzenith

x

@AyushZenith

instagram

@ayushzenith