collaborators

6 papers

cs.LG2026

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…

cs.AI2026

TRACER: Trajectory Risk Aggregation for Critical Episodes in Agentic Reasoning

Sina Tayebati, Divake Kumar, Nastaran Darabi +3

Estimating uncertainty for AI agents in real-world multi-turn tool-using interaction with humans is difficult because failures are often triggered by sparse critical episodes (e.g.…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2025

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…