Selected work
Research and engineering across recommendation systems, ML infrastructure, multimodal learning, graph intelligence, computer vision, and language.
An end-to-end recommendation system combining inductive temporal graph retrieval, reproducible model releases, in-memory decision serving, and statistically controlled experiments.
Take a look
An AWS-native ML platform that separates infrastructure, application artifacts, and deployment state across recommendation, computer-vision, edge, and translation workloads.
Take a look
Inverse-LLaVA projects text embeddings into continuous visual space and fuses the modalities within intermediate transformer layers, enabling multimodal reasoning without explicit alignment pre-training.
Take a look
A fusion architecture that injects graph representations into a language model with PEFT to generate text associated with social-network edges.
Take a look
LLM systems that code negotiation transcripts and simulate realistic negotiation scenarios for research.
Take a look
A Vision Transformer pipeline for classifying ancient mortar particles and comparing material composition across archaeological samples.
Take a look
