PeopleofSuperintelligence

Researcher

Aditi Mavalankar

Aditi Mavalankar is a reinforcement-learning researcher whose published work spans policy adaptation, interactive world models and language-model code repair. She completed an honours undergraduate degree at IIIT Hyderabad in 2016, coauthored a 2020 ICML paper on model-based policy adaptation, and earned a PhD in Reinforcement Learning at UC San Diego under Lawrence Saul in 2022. During her PhD, she completed Research Scientist internships at DeepMind Montreal in 2021 and 2022; she also completed two Amazon Lab126 internships in Sunnyvale. She coauthored Genie, an 11-billion-parameter foundation world model trained on unlabelled Internet videos, and the paper won ICML's 2024 Best Paper award. Her 2025 AuPair paper used ordered in-context examples to help language models repair code, and as of October 2026 she is a Research Scientist at Google DeepMind in London.

Badges
Links
Website, Google Scholar, X, LinkedIn and GitHub

Timeline

  1. 2016

    Honours at IIIT Hyderabad

    She completes undergraduate studies with Honours at IIIT Hyderabad in 2016.

  2. 2020

    Policy adaptation at ICML

    In 2020, she coauthors Provably Efficient Model-based Policy Adaptation, which introduces model-based online adaptation for unseen target environments.

  3. 2021–2022

    DeepMind Montreal internships

    She completes two Research Scientist internships at DeepMind Montreal, hosted by Prof. Doina Precup in 2021 and 2022.

  4. By 2022

    Amazon Lab126 internships

    By 2022, she completes two internships at Amazon Lab126 in Sunnyvale, California, during her PhD.

  5. 2022

    A reinforcement-learning PhD

    She completes a PhD in Reinforcement Learning at UC San Diego in 2022, advised by Prof. Lawrence Saul.

  6. 2024

    Genie wins Best Paper

    In 2024, she coauthors Genie, an 11-billion-parameter foundation world model trained on unlabelled Internet videos. ICML awards it Best Paper for 2024.

  7. 2025

    AuPair for code repair

    In 2025, she coauthors AuPair, an inference-time code-repair method that selects ordered example pairs as in-context demonstrations for language models.

  8. As of October 2026

    Research Scientist in London

    As of October 2026, she is a Research Scientist at Google DeepMind in London.

Career

  1. NowGoogle DeepMindResearch Scientist Intern
  2. AmazonIntern

Education

  1. 2022University of California, San DiegoPhD
  2. 2016International Institute of Information Technology, HyderabadUndergraduate studies with Honours

From the biography.

  1. 16% of AI career moves in the 2020s went from a university to a companyIncludes Aditi Mavalankar. 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 Aditi Mavalankar. 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 named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

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

  1. Aditi Mavalankar aditimavalankar.github.io. Checked 21 October 2026.
  2. Provably Efficient Model-based Policy Adaptation proceedings.mlr.press. Checked 21 October 2026.
  3. ICML 2024 Awards icml.cc. Checked 21 October 2026.
  4. Genie: Generative Interactive Environments proceedings.mlr.press. Checked 21 October 2026.
  5. Genie: Generative Interactive Environments — Google DeepMind deepmind.google. Checked 21 October 2026.
  6. AuPair: Golden Example Pairs for Code Repair arxiv.org. Checked 21 October 2026.
  7. AuPair: Golden Example Pairs for Code Repair proceedings.mlr.press. Checked 21 October 2026.
  8. AuPair: Golden Example Pairs for Code Repair — Google DeepMind deepmind.google. Checked 21 October 2026.