4 accepted papers
Safe deployment of increasingly capable AI agents may require visibility into how they make decisions. Chain-of-thought (CoT) monitoring can detect misbehavior in today’s reasoning models, but this “monitorability” may be fragile under different training procedures, data sources, or continued system…
Intense recent discussions have focused on how to provide individuals with control over when their data can and cannot be used --- the EU’s Right To Be Forgotten regulation is an example of this effort. In this paper we initiate a framework studying what to do when it is no longer permissible to dep…
We propose Efficient Neural Architecture Search (ENAS), a fast and inexpensive approach for automatic model design. ENAS constructs a large computational graph, where each subgraph represents a neural network architecture, hence forcing all architectures to share their parameters. A controller is tr…
Knowing when a classifier's prediction can be trusted is useful in many applications and critical for safely using AI. While the bulk of the effort in machine learning research has been towards improving classifier performance, understanding when a classifier's predictions should and should not be t…