4 papers
From Training to Escalation: Forensic Analysis and Local Recreation of RL/RLHF-Induced Privilege Escalation in AI Agents (CVE-2026-65616)
Alicia Colmenero-Fernández
Mid-2026 reporting on autonomous AI evaluation incidents claimed that frontier large language model (LLM) agents escaped server containment through emergent coordination and cloud…
A prism hierarchy of learning regimes in large linear autoencoders
Eugene Golikov, Yaroslav Gusev, Dmitry Yarotsky
Theoretical studies of machine learning models commonly consider different limiting regimes in which the learning dynamics of gradient descent becomes theoretically tractable. It i…
Gradient Flow Through Diagram Expansions: Learning Regimes and Explicit Solutions
Dmitry Yarotsky, Eugene Golikov, Yaroslav Gusev
We develop a general mathematical framework to analyze scaling regimes and derive explicit analytic solutions for gradient flow (GF) in large learning problems. Our key innovation…
A Generalization Bound for Nearly-Linear Networks
Eugene Golikov
We consider nonlinear networks as perturbations of linear ones. Based on this approach, we present novel generalization bounds that become non-vacuous for networks that are close t…