Tech Blog | Featured Capital One Technology

An uncertainty measure defined as the cross-entropy between predictive distribution and unknown true distribution. (ICLR)

An evaluation architecture that incorporates reasoning and iterative refinement. (EACL)

A new training-free framework based on a simple yet powerful forward-looking strategy. (AACL)

A collection of public datasets and prediction tasks that incorporate personal and relational events. (LoG)

A novel framework that constructs an intent-centric knowledge graph where both users and items are explicitly linked. (LoG)

Utilizing an alignment-first strategy to transfer advanced reasoning skills to a non-reasoning model (NeurIPS).