2 papers
cs.CR2026
HoF-Bench: Rediscovering Real AI-Discovered CVEs Without Frontier Models
Petr Simecek, Elnaz Babayeva, Jiri Balhar +23
LLM-based analyzers have begun finding real vulnerabilities in mature open-source projects: AISLE's analyzer is credited with more than 280 CVEs across 78 projects, including OpenS…
cs.CL2024
A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
David Chanin, James Wilken-Smith, Tomáš Dulka +3
Sparse Autoencoders (SAEs) aim to decompose the activation space of large language models (LLMs) into human-interpretable latent directions or features. As we increase the number o…