PeopleofSuperintelligence

Researcher

Chaitanya Ryali

Chaitanya Ryali is a computer vision researcher whose work connects human perception with vision and multimodal AI. At UC San Diego, he pursued doctoral study and coauthored research on facial preference and fruit-fly-inspired word learning. He coauthored Hiera and MAViL in 2023 and SAM 2 in 2024; SAM 2 received an ICLR 2025 Outstanding Paper honorable mention. In 2025, he coauthored SAM 3, and he also coauthored the SA-FARI dataset for multi-animal tracking. He is a researcher at Meta whose work includes visual foundation models and self-supervised learning.

Now at
Meta
Badges

Timeline

  1. 2018

    A Bayesian model of facial preference

    In 2018, he coauthors a Bayesian statistical account of facial attractiveness that explains how context changes judgments of blended faces.

  2. 2019

    PhD research at UC San Diego

    In 2019, he is a Ph.D. student in computer science and engineering at UC San Diego.

  3. 2021

    Fruit-fly word embeddings

    In 2021, he coauthors a study showing that a fruit-fly-inspired network learns semantic representations of words and generates static and context-dependent word embeddings.

  4. 2023

    Hiera and MAViL

    In 2023, he coauthors Hiera, a hierarchical vision transformer that is more accurate than previous models and faster in training and inference. He also coauthors MAViL, which learns audio-visual representations through three forms of self-supervision.

  5. 2024

    SAM 2 for video segmentation

    In 2024, he coauthors SAM 2, a model that segments images and videos and uses streaming memory for real-time video processing.

  6. 2025

    An ICLR honorable mention

    In 2025, SAM 2 receives an ICLR Outstanding Paper honorable mention, and he coauthors SAM 3, which detects, segments, and tracks objects in images and videos from concept prompts.

  7. 2025

    The SA-FARI dataset

    In 2025, he coauthors The SA-FARI Dataset, an open-source multi-animal tracking dataset for wild animals.

  8. Since 2022

    Researcher at Meta

    He is a researcher at Meta, a role he has held since 2022, focusing on visual foundation models, self-supervised representation learning, and the intersection of cognitive science with artificial intelligence.

Career

  1. Since 2022MetaResearcher

Education

  1. From 2019University of California, San DiegoPhD

From the biography.

  1. 16% of AI career moves in the 2020s went from a university to a companyIncludes Chaitanya Ryali. 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 company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Meta. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  3. Companies supply the most prior-work hires at 7 of the 9 frontier AI labsIncludes Meta. Our estimates of the organizations where 550 people worked directly before joining 9 frontier AI labs across 620 career transitions, comparing the main feeder organizations per lab.
  4. Of 943 people shaping AI who worked at Google, 446 work there nowIncludes Meta. Our estimates of where the 943 people shaping AI who worked at Google and Google DeepMind work now: 446 at Google and 452 across 278 other organizations.

Colleagues

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

Sources and credits

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

  1. Beauty-in-averageness and its contextual modulations: A Bayesian statistical account papers.nips.cc. Checked 20 October 2026.
  2. YKavli: October 2019 Lunch - Kavli Institute for Brain and Mind kibm.ucsd.edu. Checked 20 October 2026.
  3. ICLR 2021 confviews.com. Checked 20 October 2026.
  4. Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles proceedings.mlr.press. Checked 20 October 2026.
  5. MAViL: Masked Audio-Video Learners proceedings.neurips.cc. Checked 20 October 2026.
  6. SAM 2: Segment Anything in Images and Videos arxiv.org. Checked 20 October 2026.
  7. Announcing the Outstanding Paper Awards at ICLR 2025 – ICLR Blog blog.iclr.cc. Checked 20 October 2026.
  8. SAM 3: Segment Anything with Concepts arxiv.org. Checked 20 October 2026.
  9. The SA-FARI Dataset: Segment Anything in Footage of Animals for Recognition and Identification arxiv.org. Checked 20 October 2026.
  10. Chaitanya Ryali (Meta): visual foundation models — Lacuna lacuna.tiptreesystems.com. Checked 20 October 2026.