5 papers
Complex-Valued Unitary Representations as Classification Heads for Improved Uncertainty Quantification in Deep Neural Networks
Akbar Anbar Jafari, Cagri Ozcinar, Gholamreza Anbarjafari
Modern deep neural networks achieve high predictive accuracy but remain poorly calibrated: their confidence scores do not reliably reflect the true probability of correctness. We p…
A Multi-physics Simulation Framework for High-power Microwave Counter-unmanned Aerial System Design and Performance Evaluation
Akbar Anbar Jafari, Gholamreza Anbarjafari
The proliferation of small unmanned aerial systems (sUAS) operating under autonomous guidance has created an urgent need for non-kinetic neutralization methods that are immune to c…
A Lightweight Modular Framework for Constructing Autonomous Agents Driven by Large Language Models: Design, Implementation, and Applications in AgentForge
Akbar Anbar Jafari, Cagri Ozcinar, Gholamreza Anbarjafari
The emergence of LLMs has catalyzed a paradigm shift in autonomous agent development, enabling systems capable of reasoning, planning, and executing complex multi-step tasks. Howev…
Closed-Loop Transformers: Autoregressive Modeling as Iterative Latent Equilibrium
Akbar Anbar Jafari, Gholamreza Anbarjafari
Contemporary autoregressive transformers operate in open loop: each hidden state is computed in a single forward pass and never revised, causing errors to propagate uncorrected thr…
A Mathematical Framework for AI Singularity: Conditions, Bounds, and Control of Recursive Improvement
Akbar Anbar Jafari, Cagri Ozcinar, Gholamreza Anbarjafari
AI systems improve by drawing on more compute, data, energy, and better training methods. This paper asks a precise, testable version of the "runaway growth" question: under what m…