About
Research
I work on multimodal learning (vision + IMU + Wi‑Fi FTM + text), efficient machine learning (few‑class evaluation, pruning, model selection), and robot visual navigation (hierarchical RL, metric learning, 3D Gaussian Splatting).
Current focus
- Vision–wireless identity association & cross‑modal trajectory reconstruction
- Embodied navigation: representation learning and mapping
- Efficient AI/ML: Few‑class regime (benchmark tooling + dataset difficulty measurement), model pruning/merging
Affiliations
- Ph.D. Candidate, Stony Brook University
- Research Intern/Co‑op, Nokia Bell Labs (Jun 2021 – Fall 2025)
Education
- Stony Brook University — Ph.D. in Computer Science (2026 expected)
- University of Colorado Boulder — M.S. in Computer Science (2018)
Interests
- Multimodal learning (vision + IMU + Wi‑Fi + text)
- Few‑class evaluation and efficient inference
- Robot learning and visual navigation