What does a reward model really learn?
Testing the gap between reward-score accuracy, policy agreement, and action correctness in language-conditioned navigation.
Explore project ↗RESEARCH / PROJECTS
Nine research threads spanning all 17 papers in my CV. Explore the questions, methods, findings, and publications behind each project.
9 projects
Testing the gap between reward-score accuracy, policy agreement, and action correctness in language-conditioned navigation.
Explore project ↗A matched comparison of LLM-generated captions and human references on MS COCO.
Explore project ↗Examining readability, safety, and human–AI agreement in audience-targeted explanations of brain MRI images.
Explore project ↗Understanding the trade-offs between translation quality, inference latency, and estimated emissions.
Explore project ↗A research thread from word-terminal syllables and learned representations to phrase-aware neural text-to-speech.
Explore project ↗Two complementary studies of linguistic context and spectral representations for statistical parametric speech synthesis.
Explore project ↗Blizzard Challenge work spanning Indian-language evaluation tasks, unit-selection systems, and neural acoustic modeling.
Explore project ↗Comparing word-to-phone and phone-to-phone mapping for English words in a Telugu text-to-speech system.
Explore project ↗Comparing machine learning approaches to 30-day readmission prediction for diabetic patients.
Explore project ↗No projects match this filter.