Machine Learning Engineer & PhD Candidate building the next generation of safe, scalable, and resource-efficient AI. My research focuses on the continual adaptation and compression of Large Language Models. My published work optimizes deep learning models, resulting in significantly improved efficiency and state-of-the-art performance across vision and language tasks.
tkatraouras [at] uth [dot] gr
Resource-Constrained Continual Learning and Alignment for Large Language Models
Information Retrieval
Real-Time Perception and Localization for Autonomous Racing
Proposed MBC, a memory-augmented continual learning model that reduces the memory bank footprint by 99.7% by compressing stored representations through codebook optimization and online resetting mechanisms. Improved QA accuracy by 11.84% (EM) and 12.99% (F1) over state-of-the-art baselines, enabling efficient knowledge updates in LLMs without catastrophic forgetting.
Proposed MIR-L, a compressed multi-task image restoration model that achieves 90% reduction in trainable parameters through lottery tickets while maintaining or exceeding state-of-the-art performance on deraining, dehazing, and denoising tasks.
Developed a LSTM model for Bitcoin price forecasting that integrates X (Twitter) sentiment analysis, achieving 15.88% reduction in RMSE, 15.49% reduction in MAE, and 11.71% reduction in MAPE compared to price-only baseline.
Developed a text classification system for news articles using CNNs with custom word embeddings and fine-tuned Transformer models (DistilBERT) to improve accuracy to 78.9%.
Built a recommender system for Steam games using content-based and collaborative filtering (Cosine Similarity, SVD), featuring a custom review-weighted algorithm, an experimental Neural Network with embeddings, and an interactive GUI.