3 papers
cs.CY2025
The Violation State: Safety State Persistence in a Multimodal Language Model Interface
Bentley DeVilling
Multimodal AI systems integrate text generation, image generation, and other capabilities within a single conversational interface. These systems employ safety mechanisms to preven…
cs.CY2025
The Polite Liar: Epistemic Pathology in Language Models
Bentley DeVilling
Large language models exhibit a peculiar epistemic pathology: they speak as if they know, even when they do not. This paper argues that such confident fabrication, what I call the…
cs.CC2024
Tightening I/O Lower Bounds through the Hourglass Dependency Pattern
Lionel Eyraud-Dubois, Guillaume Iooss, Julien Langou +1
When designing an algorithm, one cares about arithmetic/computational complexity, but data movement (I/O) complexity plays an increasingly important role that highly impacts perfor…