← Search

Gashon Hussein

2 accepted papers

2026

π∗0.6π0.6∗\pi^{*}_{0.6}: a VLA That Learns From Experience

RSS 2026poster

Vision–language–action (VLA) models offer a promising path toward general-purpose robots, but achieving the reliability and speed required for practical deployment remains challenging. We present a general-purpose method, RL with Experience and Corrections via Advantage-conditioned Policies (RECAP) …

Cited by 0SourceScholar
2025

Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

ICLR 2025oral

Language Model (LM) agents for cybersecurity that are capable of autonomously identifying vulnerabilities and executing exploits have potential to cause real-world impact. Policymakers, model providers, and researchers in the AI and cybersecurity communities are interested in quantifying the capabil…

Cited by 33SourcePDFScholar