Tutorial on the technical background behind OpenAI o1. Talk written with Daniel Ritter.
Slides: https://github.com/srush/awesome-o1
Talk: The “large” in LLM is more foundational than descriptive: models improve predictably as they grow. Increases in parameters and data lead to reliable increases in accuracy. Recent results from OpenAI demonstrate that a third axis, test-time compute, also exhibits similar properties in specific domains. While the details of this method are not yet known, the result is critical for future LLM design. This survey talk will introduce the literature related to test-time compute and model self-improvement, and will discuss the expected implications of test-time scaling. This talk will also briefly connect these research directions to current open-source efforts to build effective reasoning models