Publications

Developed a cascaded MRI reconstruction model using Frequency Mining with SOTA transformer-based U-Net models for k-space data, efficiently handling MRI multi-contrast.

Developed a generative framework coupled with multi-objective Bayesian optimization to creatively explore industrial design spaces under expensive native forward processes.

Integrated FinBERT, a financial sentiment analysis LLM, to extract sentiment from news and combined it with stock prices in a PPO-LSTM model for stock trading. Achieved 134.39% cumulative return (2.34× initial budget) and a 1.46 Sharpe ratio, significantly outperforming DJIA, Ensemble, and PPO models.

Applied SincNet layers to classify Parkinson’s Disease from gait data, achieving 98.7% accuracy. Pruned filters after initial training using K-means clustering and silhouette scores to identify key frequency bands that explain the model's decisions.

Role-optimized agents (goalkeeping, defense, teamwork) in the 2D Simulation League; team placed 2nd at IranOpen 2023.