PeopleofSuperintelligence

Researcher

Meera Hahn

Meera Hahn is an AI researcher whose work links embodied navigation with generative video and text-to-image systems. She earned a BS in computer science and mathematics at Emory and completed a PhD in computer science at Georgia Tech, then joined Google in 2022. She coauthored Where Are You?, No RL, No Simulation, VideoPoet, W.A.L.T., MALT Diffusion and proactive text-to-image agents. As of October 2026, she is a research scientist at Google DeepMind and has contributed to creative AI projects including Wizard of Oz at Sphere and Dear Upstairs Neighbors.

Badges

Timeline

  1. 2016–2022

    Degrees at Emory and Georgia Tech

    She earns a BS in computer science and mathematics at Emory in 2016 and completes a PhD in computer science at Georgia Tech in July 2022, advised by James M. Rehg.

  2. 2020–2021

    Dialog localization and navigation

    At EMNLP in 2020, she coauthors Where Are You?, a dataset of about 6,000 cooperative-localization dialogs. In 2021, she coauthors No RL, No Simulation, a self-supervised method for image-goal navigation that learns from passive videos.

  3. 2022

    Joining Google Research

    She joins Google in 2022 after completing her PhD at Georgia Tech. At Google Research, she works at the intersection of computer vision and natural language processing.

  4. 2024

    VideoPoet and WALT

    In 2024, she coauthors VideoPoet, a language model for multimodal video generation that wins ICML's Best Paper Award. At ECCV in 2024, she coauthors W.A.L.T., a diffusion transformer for photorealistic video generation.

  5. 2025

    Long video and text-to-image agents

    In 2025, she coauthors MALT Diffusion, a diffusion model specialized for long video generation. She also coauthors proactive text-to-image agents that ask clarifying questions and present an editable belief graph of user intent.

  6. By 2026

    Technical art for creative AI

    By 2026, she works as a technical artist on creative projects including Wizard of Oz at Sphere and Dear Upstairs Neighbors.

  7. As of October 2026

    Google DeepMind research scientist

    As of October 2026, she is a research scientist at Google DeepMind, working to connect complex AI models with entertainment.

Career

  1. NowGoogle DeepMindResearch Scientist
  2. From 2022Google Research

Education

  1. 2022Georgia Institute of TechnologyPhD in Computer Science
  2. 2016Emory UniversityBS in Computer Science and Mathematics

From the biography.

  1. 16% of AI career moves in the 2020s went from a university to a companyIncludes Meera Hahn. We estimate that 16% of AI career moves in the 2020s went from a university to a company; 29% of moves starting at a university went to a company, and 76% ended the university role.
  2. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Meera Hahn. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  3. Google had the most people shaping AI every year from 2014 to 2025Includes Google. Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  4. Google has the highest combined h-index among AI organizationsIncludes Google. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Meera Hahn yet. Send us a free-licensed photo.

  1. Meera Hahn meerahahn.github.io. Checked 21 October 2026.
  2. Where Are You? Localization from Embodied Dialog aclanthology.org. Checked 21 October 2026.
  3. No RL, No Simulation: Learning to Navigate without Navigating proceedings.neurips.cc. Checked 21 October 2026.
  4. Meera Hahn research.google. Checked 21 October 2026.
  5. ICML 2024 Awards icml.cc. Checked 21 October 2026.
  6. Photorealistic Video Generation with Diffusion Models research.google. Checked 21 October 2026.
  7. MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation arxiv.org. Checked 21 October 2026.
  8. Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty deepmind.google. Checked 21 October 2026.
  9. SIGGRAPH Spotlight: Episode 103 - Artists, Engineers, and Generative AI in Animation Production blog.siggraph.org. Checked 21 October 2026.