Multimodal

Important because several of the modern foundation-model playbooks trace back to work he helped drive, especially around generative pretraining and multimodal transfer.

Important both as a researcher and as an institution builder whose long-running agenda tied deep RL, multimodal systems, and scientific AI into one coherent lab strategy.

A foundational figure in modern sequence modeling whose work on the Transformer changed the technical direction of language and multimodal systems.

Foundational less for any single public paper than for shaping the infrastructure, engineering culture, and systems thinking that make frontier-model research possible.

One of the most important architecture-level thinkers in modern AI, with influence spanning Transformers, efficient scaling, and mixture-of-experts systems.

A strong person to follow for the point where machine learning research starts shaping the compute stack itself, especially in chip placement and systems-aware optimization.

A good researcher to follow for the infrastructure side of frontier language models, especially mixture-of-experts scaling, instruction tuning, and the data systems that make very large models usable.

A high-signal researcher for grounded language and retrieval-heavy systems, especially if you want to understand how language models stay useful as the world changes around them.

A central figure in modern reinforcement learning whose work turned deep RL from an exciting idea into a line of systems that repeatedly reset expectations.