Contact
I can be reached via email at (remove spaces and brackets):[firstname] [15] [lastname] [] at [gmail] dot [com]
Research Interests
I currently work on customizing Frontier-class LLMs and VLMs exploring ideas such as compute efficiency, generalization and adaptation. In the past I spent time studying uncertainty quantification, knowledge-driven learning, and robust generalization across distribution shifts. In general, I enjoy developing methods to better understand model's limitations, and make them aware of these for more robust performance.
Outreach & Other Efforts
Previously at LLNL, I led the Open Data Initiative with the goal of releasing LLNL's high impact scientific datasets for machine learning. AI.gov cited this effort under "DATA RESOURCES FOR AI R&D"!
I also serve on the program committees for several ML and vision venues (NeurIPS, CVPR, ICLR, ICCV, ICML, AAAI).
Education & Background
I got my PhD from Arizona State University (ASU) working with Prof. Pavan Turaga. In grad school, I developed tools spanning computer vision, machine learning, and Riemannian Geometry to improve our understanding of human movement and activity, when observed through various visual and non-visual sensors.
My PhD thesis is available for download here — Statistical and dynamical modeling of Riemannian trajectories with application to human movement analysis
I also received my M.S. (2012) from ASU, and my B.Tech (2010) from National Institute of Technology Karnataka (NITK), consistently ranked among the top 10 engineering schools in India.
Prior to that I spent two years of high school in Chennai, India and grew up in my hometown — Secunderabad, India. In all I have lived in, and am associated with, 6 cities across India and the US.