Mingxing TanResearch Director · WaymoResearcher↗
Researcher
WaymoResearch Director
Narang contributed to T5, which framed many language tasks in one text-to-text format,[1] and to influential studies of how model design, data and computing power affect performance at scale. He later became a research leader at Waymo, applying large-scale learning to autonomous driving.
Waymo2026-presentWork and education history is primarily focused on AI-relevant roles and may not be comprehensive.
T5 treats language tasks as text input and text output within one framework.
Presented Llama 2 and its chat models, including training methods and capability evaluations.
Presented PaLM, a large language model demonstrating gains in reasoning, translation and coding.
Narang and colleagues describe T5 and show how tasks such as translation and summarization can use the same text-in, text-out setup.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 8, 2026 · Checked for accuracy and new information.