LLM-powered multiagent persona simulation for imagination enhancement and business insights.

JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.

MIMIC Code Repository: Code shared by the research community for the MIMIC family of databases

A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/

Library for clinical NLP with spaCy.

AI model evaluation with a focus on healthcare

Test-time preferenece optimization (ICML 2025).

Work on using Retrieval-Augmented Generation (RAG) to combine Fast Healthcare Interoperable Resources (FHIR) with Generative AI.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

A Python Natural Language Processing Toolkit for Medical Text Generation

Self-verification for LLMs.

A version of MIMIC-IV in FHIR

An OCR project to extract information about patient and prescription details.

[NeurIPS 2022] Code for "Retrieve, Reason, and Refine: Generating Accurate and Faithful Discharge/Patient Instructions"

Clinical charting tool for physicians. Automatically generates structured SOAP notes from telehealth appointment recordings or clinical audio memos.

Parameter-efficient Fine Tuning for Clinical LLMs

Notebooks etc. Analysis of SNOMED-CT for the Clinical Coding Pilot and related work

Basic entity linker for the SNOMED EL Challenge

A Python Natural Language Processing Toolkit for Electronic Health Record Texts

Creates a concept graph from a SNOMED CT release

[JAMIA 2024] A dataset and benchmark for hospital course summarization with adapted large language models

Medical coding using Vertex AI

A quick tutorial for using spaCy Layout.

Contribution to the LabLabAI AI Challenge Hackathon October 2023

A collection of applications that can be used with Large Language Models (LLMs).

AI Researcher for Students and Research Professionals

Contains my experiments for ZS's hiring hackathon (II).

We have to identify specific clinical concepts in `patient notes` and develop and automated method to map clinical concepts from an excam rubic.