5 papers · 1 filter
Structure and Redundancy in Large Language Models: A Spectral Study via Random Matrix Theory
Davide Ettori
This thesis addresses two persistent and closely related challenges in modern deep learning, reliability and efficiency, through a unified framework grounded in Spectral Geometry a…
Spectral Geometry for Deep Learning: Compression and Hallucination Detection via Random Matrix Theory
Davide Ettori
Large language models and deep neural networks achieve strong performance but suffer from reliability issues and high computational cost. This thesis proposes a unified framework b…
EigenTrack: Spectral Activation Feature Tracking for Hallucination and Out-of-Distribution Detection in LLMs and VLMs
Davide Ettori, Nastaran Darabi, Sina Tayebati +4
Large language models (LLMs) offer broad utility but remain prone to hallucination and out-of-distribution (OOD) errors. We propose EigenTrack, an interpretable real-time detector…
RMT-KD: Random Matrix Theoretic Causal Knowledge Distillation
Davide Ettori, Nastaran Darabi, Sureshkumar Senthilkumar +1
Large deep learning models such as BERT and ResNet achieve state-of-the-art performance but are costly to deploy at the edge due to their size and compute demands. We present RMT-K…
SPARC: Subspace-Aware Prompt Adaptation for Robust Continual Learning in LLMs
Dinithi Jayasuriya, Sina Tayebati, Davide Ettori +2
We propose SPARC, a lightweight continual learning framework for large language models (LLMs) that enables efficient task adaptation through prompt tuning in a lower-dimensional sp…