PeopleofSuperintelligence

Researcher

Alonso Martinez

Alonso Martinez is an AI researcher whose work connects computer animation, character behavior, and video generation. They spent 16 years in industry with Pixar Animation Studios and Google Research, contributed to Up, Inside Out, and Coco, and led teams that explored interactive characters. They coauthored a reinforcement-learning character system in 2022 and VideoPoet, which received ICML's 2024 Best Paper Award; they also coauthored audiovisual diffusion research at NeurIPS in 2024. As of October 2026, they are a computer-vision master's student in Berkeley's EECS department and BAIR lab, advised by Alyosha Efros.

Links
Website

Timeline

  1. 2018

    Patch-based surface relaxation

    In 2018, Martinez coauthors Patch-based Surface Relaxation. The paper introduces a patch-aware relaxation method for general polygonal meshes.

  2. 2019

    Affine-invariant mesh wrapping

    In 2019, Martinez coauthors an affine-invariant mesh-wrap method with Fernando de Goes. The method transfers mesh connectivity between differently shaped 3D models and wraps 600 humanoid assets to reference mesh connectivity at Pixar.

  3. 2022

    Autonomous animated characters

    In 2022, Martinez coauthors a system that uses reinforcement learning and procedural animation to create an autonomous character with responsive, expressive behavior. The work wins Best Presentation at MIG '22.

  4. 2023

    VideoPoet for video generation

    Google Research introduces VideoPoet in 2023, with Martinez among its contributors. The autoregressive language model handles text-to-video, image-to-video, stylization, video inpainting, outpainting, and video-to-audio.

  5. 2024

    The ICML Best Paper Award

    Martinez coauthors VideoPoet, which wins ICML's 2024 Best Paper Award.

  6. 2024

    Audiovisual diffusion research

    In 2024, Martinez coauthors a transformer-based audiovisual latent diffusion model. It varies diffusion timesteps across time and input modalities to support task-agnostic cross-modal generation and multimodal interpolation.

  7. As of October 2026

    Graduate study at Berkeley

    After 16 years in industry with companies including Pixar Animation Studios and Google Research, Martinez returns to study AI at Berkeley. Their Pixar work includes Up, Inside Out, and Coco, across character modeling, rigging, art, animation, and research; their Google Research work includes leading teams that explored interactive characters with reinforcement learning and generative models. As of October 2026, they are an M.S. student in computer vision in Berkeley's EECS department and BAIR lab, advised by Alyosha Efros.

  1. 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.
  2. 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.
  3. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes Google. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.
  4. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Google. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.

Sources and credits

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

  1. Patch-based Surface Relaxation | Papers | Enrique Velasco enriquevelasco.com. Checked 20 October 2026.
  2. Mesh wrap based on affine-invariant coordinates — Lacuna lacuna.tiptreesystems.com. Checked 20 October 2026.
  3. Toward Believable Acting for Autonomous Animated Characters believable-acting.github.io. Checked 20 October 2026.
  4. VideoPoet: A large language model for zero-shot video generation research.google. Checked 20 October 2026.
  5. ICML 2024 Awards icml.cc. Checked 20 October 2026.
  6. A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation proceedings.neurips.cc. Checked 20 October 2026.
  7. About — Alonso Martinez alonsorobots.com. Checked 20 October 2026.
  8. Research — Alonso Martinez alonsorobots.com. Checked 20 October 2026.