4 papers
Epistemic-Probabilistic Model for Guarded Multi-Agent LLM Coordination
Mehdi Nasiri, Mohammad Saeed Arvenaghi, Sadegh Vaezi +1
Multi-agent large language models (LLMs) have become ubiquitous in applied AI, yet their theoretical foundations remain surprisingly understudied. Viewed through the lens of multi-…
No Trust Issues Here: A Technical Report on the Winning Solutions for the Rayan AI Contest
Ali Nafisi, Sina Asghari, Mohammad Saeed Arvenaghi +1
This report presents solutions to three machine learning challenges developed as part of the Rayan AI Contest: compositional image retrieval, zero-shot anomaly detection, and backd…
Certified Lipschitz Bounds for Hybrid Quantum-Classical Decision Models
Sajjad Hashemian, Mohammad Saeed Arvenaghi
We study certified upper bounds on Lipschitz constants for hybrid quantum-classical decision models, which combine classical neural-network layers with parameterized quantum circui…
Optimal Bound for PCA with Outliers using Higher-Degree Voronoi Diagrams
Sajjad Hashemian, Mohammad Saeed Arvenaghi, Ebrahim Ardeshir-Larijani
In this paper, we introduce new algorithms for Principal Component Analysis (PCA) with outliers. Utilizing techniques from computational geometry, specifically higher-degree Vorono…