Research Experience

My research spans reinforcement learning, LLM alignment, Bayesian inference, and applied mathematics.

Jan 2025 – Mar 2025

Dynamic Self-Rewarding for Medical LLMs

Research Collaborator · University of Edinburgh

  • Developed a dynamic self-rewarding framework for aligning medical LLMs without human-annotated supervision
  • Integrated a two-tier judge system where ChatGPT-4o dynamically refines evaluation prompts to mitigate reward misspecification and scoring bias
  • Executed multi-round Direct Preference Optimization (DPO) to align model behavior through self-generated preference pairs and adaptive reward modeling
  • Fine-tuned and evaluated LLMs (Mistral-7B) on domain-specific datasets (HealthCareMagic, PubMedQA, MedMCQA), targeting empathy, factuality, and coherence
  • Conducted task-specific benchmarking and error analysis to uncover performance bottlenecks due to hallucination and distributional drift across iteration stages
LLM Alignment DPO Medical AI Self-Rewarding
Aug 2024 – Apr 2025

A Comparative Study of Simulation-Based Inference Algorithms

Honours Dissertation · Supervisor: Dr. Amanda Lenzi · University of Edinburgh

  • Benchmarked three cutting-edge SBI algorithms — BayesFlow, Sequential Neural Likelihood (SNL), and Affine Flow Matching (AFM) — on synthetic and real-world inference tasks
  • Demonstrated that AFM outperforms amortized and sequential methods in capturing spatial structure in high-dimensional Poisson–CAR disease mapping models
  • Designed a robust evaluation framework using recovery line metrics and ECDF-based posterior calibration
  • Identified key trade-offs in joint parameter inference: increasing dimensionality improves model expressiveness but amplifies uncertainty
  • Implemented a full end-to-end SBI workflow and published open-source code
Bayesian Inference Normalizing Flows SBI
Jun 2024 – Sep 2024

Optimizing Texera: AI-Driven Data Analysis Workflows

Summer Research Assistant · Supervisor: Prof. Chen Li (IEEE Fellow) · UC Irvine

  • Integrated AI-driven automation for workflow optimization, enabling seamless machine learning pipeline execution
  • Developed an automated report generation system that converts data analysis workflows into structured insights
  • Enhanced Texera's data cleaning and visualization capabilities to improve model interpretability
ML Systems Data Analysis Automation
Feb 2024 – May 2024

Uncertainty in Economic Forecasting during COVID-19

Research Assistant · University of Edinburgh

  • Analyzed the economic impact of uncertainty during the COVID-19 pandemic using stochastic models
  • Implemented Monte Carlo simulations and Bayesian inference techniques for probabilistic estimation
  • Developed computational tools for visualizing uncertainty in economic forecasting
Bayesian Inference Monte Carlo Economics
Sep 2023 – Dec 2023

ODE Modeling for Bacterial Infection & Antibiotic Treatment

Project Leader · University of Edinburgh

  • Developed a system of ODEs to model bacterial infections and antibiotic treatments
  • Used Fourier series analysis and Laplace transforms to predict bacterial resistance patterns
  • Optimized drug treatment schedules using numerical simulations
ODEs Mathematical Modeling Biomedical
Dec 2022

Population Dynamics Modeling with Fertility Rate Adjustments

Research Project · Dalian University of Technology

  • Developed a population dynamics model incorporating fertility rate adjustments
  • Improved predictive accuracy by incorporating age-stratified birth rate variations
  • Performed parameter sensitivity analysis to optimize demographic forecasting
Mathematical Modeling Demographics Sensitivity Analysis