Esha Singh

Reformulates multi-objective combinatorial optimization as online learning over decomposed decision spaces, achieving 80–98% of specialized solvers with two to three orders of magnitude improvement in sample and computational efficiency.

Temporally aligned multi-modality video generation using latent diffusion models for ambient sounds. Work done as an Applied Scientist II Intern at Amazon Alexa+ AI, Bellevue, WA.

Adaptive optimizers that expedite exploration with faster convergence while ensuring avoidance of over-exploitation, leading to convergence to good solutions.

A scoping review of SBDH factors, the relationship between SBDH and diseases, NLP techniques to extract SBDH from clinical notes, and predictive models using SBDH factors.

Develops the first Conversational Agent system for Dietary Supplement use using the MindMeld framework and iDISK knowledge base.

A proof-of-concept framework for enhancing health and wellbeing via tailored wearable and Conversational Agent solutions for non-invasive monitoring and personalized interventions.

A prototype conversational agent system catered to resolve user queries regarding dietary supplements.