▶ Watch ↗AI Engineer World's Fair 202620:14
Conference affiliation: RL Lead · MiniMax · 2026
Olive Song leads reinforcement-learning research at MiniMax, overseeing the final training and release of open-weight models for coding and autonomous digital work. She focuses on making agents dependable when tools fail, environments change, tasks run for hours, and imperfect rewards invite shortcuts.
An alumna of New York University’s Courant Institute, Song lived in New York for six years before moving from academic research into industrial model development. In 2025, she helped introduce MiniMax-M2, an open-weight coding model with 10 billion active parameters. By 2026, she was leading reinforcement-learning research for MiniMax’s increasingly multimodal models, including MiniMax-M3.
Song approaches alignment as an implementation problem as much as a theoretical one: one training investigation traced stalled reinforcement-learning progress to numerical precision in the language-model head. Her interests extend into GPU data layouts and shared-memory bank conflicts.
▶ Watch ↗AI Engineer World's Fair 202620:14
▶ Watch ↗15:03
▶ Watch ↗20:48
Loading more talks and highlights…