16 papers
KV Cache Compression Through the Lens of Transform Coding
Hannah Laus, Claudio Mayrink Verdun, Hao Wang +2
The key-value (KV) cache stores information from past tokens and is a major memory bottleneck in long-context inference. Existing quantization methods address this bottleneck by re…
An Instrument to Evaluate Governance Proposals: AI Policy Analysis at Scale
Paulo Carvao, Claudio Mayrink Verdun, Isabel Adler +1
This paper introduces a policy analysis framework for systematic, transparent assessment of AI governance proposals in an evolving and contested regulatory landscape. AI policy deb…
Evaluating AI Models' Capability to Automate Voice Phishing Attacks
Fred Heiding, Claudio Mayrink Verdun, Simon Lermen +5
Voice phishing (vishing) attacks have traditionally been limited by the need for human operators. The rapid emergence of high-quality AI voice synthesis and large language models (…
Reading Between the Dots: Decoding Hidden Computation across Filler Tokens
Kaley Brauer, Claudio Mayrink Verdun, Samuel Marks
Frontier LLMs can perform multi-step reasoning over content-free filler tokens like dots or counting sequences, producing correct answers with no visible chain-of-thought (CoT). Th…
Prioritization of Risks from Artificial Intelligence: A Delphi Study of 272 International Experts
Alexander K. Saeri, Jess Graham, Michael Noetel +185
Artificial intelligence poses many risks, ranging from familiar present-day harms to unprecedented and potentially catastrophic ones. Effective risk management requires prioritizat…
GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection
Mariia Seleznova, Hung-Hsu Chou, Claudio Mayrink Verdun +1
We introduce GradPCA, an Out-of-Distribution (OOD) detection method that exploits the low-rank structure of neural network gradients induced by Neural Tangent Kernel (NTK) alignmen…