Looped language model training cannot control hidden-state norm growth because RMSNorm normalizes scale away before the loss ...

AI text detector accuracy is worse than most institutions realize. New research from Pindrop and the Authors Guild confirms that skilled human writers are systematically flagged as AI-generated — and ...

As artificial intelligence (AI) models are increasingly capable of producing more life-like content, there has been an understandable hesitancy regarding “deepfakes” and their potential negative ...

While there have been some notable successes with program verification systems, a the use of such systems is still perceived as a niche activity for the most critical and specialized projects. 1, 23, ...

1 On our inability to do much. 4 On the reliability of mechanisms. 8 On our mental aids. 15 An example of a correctness proof. 19 On the validity of proofs versus the validity of implementations. 21 ...

In this work, we introduce signal-to-noise ratio (SNR) based fault detection and identification mechanisms for a networked control system feedback loop, where the network component is represented by ...

This article provides a theory for provably safe and computationally efficient distributed constrained control, and describes an application to a swarm of nano-quadrotors with limited on-board ...

Ultrasound is a flexible and powerful medical imaging tool. However, variations in organ tissue structure cause propagating waves to undergo unexpected phase shifts, resulting in aberration (blurring) ...

Syntex-guided synthesis formalizes the computational problem of searching for a program expression that meets both syntactic and logical constraints. A wide variety of problems, such as programming by ...

Algorithms that decompose a manifold into simple pieces reveal the geometric and topological structure of the manifold, showing how complicated structures are constructed from simple building blocks.