arXiv preprint, 2019
A survey of supervised, weakly-supervised, and unsupervised approaches to predicting dense depth from a single RGB image, comparing methods and outlining open directions.
About
My research addresses a central problem in modern AI: how to rigorously evaluate agentic systems once they move beyond single-turn answers into long-horizon, multi-step tool-use with error recovery. In this regime the conventional axes of quality - correctness, completeness, relevancy - are necessary but no longer sufficient. I develop compound measures of agent behavior, including user utility, user-perceived defects, and the evaluation of multi-tool planning, and pursue a complementary line on cost and latency-aware routing that reserves frontier-model capacity for the hardest tasks while holding generation quality invariant. Together these threads aim to make agentic systems measurably more trustworthy, efficient, and accountable at production scale.
I pursue this work as a Senior Machine Learning Researcher in Apple's Human-Centered AI organization, where I scale agentic evaluation for Apple Media Products. Earlier, as an Applied Scientist at Amazon, I built LLM-driven conversational systems, large-scale insight generation, and multi-modal fraud detection across the Returns & Recommerce and Seller Partner Services organizations. I hold an M.S. in Computer Science from the University of Illinois at Chicago, where I was advised by Xinhua Zhang and worked at the intersection of few-shot machine learning and computer vision.
Selected Contributions
(Coming Soon)
Preprints & Technical Reports
Citation counts via Google Scholar (266 total citations; h-index 4, as of June 2026).
arXiv preprint, 2019
A survey of action localization in video — determining what action is performed, and when and where — across algorithms, datasets, and the most promising directions.
arXiv preprint, 2018
An exploration of pre-processing, features, and memory-network methods for classifying sentiment toward a specific aspect within a sentence.
arXiv preprint, 2018
A comparison of neural and universal style-transfer approaches, focused on real-time transfer and generalization to unseen styles.
Honors & Awards
-
Outstanding Thesis Award,
University of Illinois at Chicago · 2019
Sole master's thesis selected from a cohort of five nominees. -
Intel AI Student Ambassador · 2018
Selective program; profiled on Intel's developer site for computer-vision work. - Best Microsoft Hack, HackHarvard · 2017
-
Best Technical Innovation, Amity University
· 2017
Selected out of 800 students.
Professional Service
Peer reviewer for workshops at flagship machine-learning venues (ICML, KDD).
Talks & Media
-
Featured by Intel · 2018
Profiled on Intel's developer site on solving computer-vision problems as an AI Student Ambassador. -
Poster, CVPR 2018 (Intel AI booth) · 2018
Presented Tiramisu DenseNet Architecture for Precise Segmentation at the CVPR 2018 Intel AI booth. -
UC Santa Cruz newsletter · 2018
Featured for a low-poly VR application built at CruzHacks.
Experience
-
Apple — Senior Machine Learning Researcher
Human-Centered AI · Seattle, WAScaling agentic evaluations for Apple Media Products.
-
Amazon — Applied Scientist
Returns & Recommerce → Seller Experience Innovation · Seattle, WALLMs for conversational returns, large-scale insight generation, and multi-modal fraud detection; evaluation of generative-AI listings and Seller Assistant.
-
CCC Intelligent Solutions — Senior R&D Engineer
Computer Vision Group · Chicago, ILImage classification and segmentation for automotive damage assessment.
Education
-
M.S., Computer Science — University of Illinois at Chicago
Machine learning & computer vision; advised by Xinhua Zhang. Thesis: Invariant Kernels for Few-shot Learning (Outstanding Thesis Award).