Tech Blog | Featured Capital One Technology

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).

An efficient solution to enforce the well-typedness of LLM functions. (EurIPS)

Visual reasoning models that achieve SoTA performance using an order of magnitude fewer training samples. (NeurIPS)

A study across models and benchmarks and an alternative test-time scaling approach. (NeurIPS)

An RL proxy task that trains VLMs to localize synthetic hallucinations injected into human-written captions. (NeurIPS)