3 papers
cs.CR2026
Large-scale online deanonymization with LLMs
Simon Lermen, Daniel Paleka, Joshua Swanson +3
We show that large language models can be used to perform at-scale deanonymization. With full Internet access, our agent can re-identify Hacker News users and Anthropic Interviewer…
cs.CV2025
Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?
Michael Aerni, Joshua Swanson, Kristina Nikolić +1
We present modal aphasia, a systematic dissociation in which current unified multimodal models accurately memorize concepts visually but fail to articulate them in writing, despite…
math.CO2024
Super major index and Thrall's problem
Sam Armon, Joshua P. Swanson
Thrall's problem asks for the Schur decomposition of the higher Lie modules , which are defined using the free Lie algebra and decompose the tensor algebra as a gene…