Amazon ScienceResearch
Mitra-v2: Scaling synthetic pretraining for tabular foundation models

Much of the data that businesses run on lives in tables: the rows might represent customers, transactions, or interactions, and their “attributes” are listed in the columns.
Read at Amazon Science ↗Related

ResearchStrengthening AI safety evaluation through independent third-party review Amazon Science

ResearchCan we change an AI model’s architecture without retraining it from scratch? Amazon Science

ResearchWhen LLM judges agree, should we believe them? Amazon Science

ResearchSOP-Bench: A new benchmark for evaluating AI agents on real business procedures Amazon Science

ResearchA decade of mathematical certainty: Reflections on the Automated Reasoning Group Amazon Science
