PeopleofSuperintelligence

Researcher

Noam Aigerman

Noam Aigerman is a researcher in 3D geometry processing who builds neural networks that map, deform and generate shapes. He completed a PhD at the Weizmann Institute of Science in 2017 under Yaron Lipman, then worked as a research scientist at Adobe Research, where he coauthored Neural Jacobian Fields at SIGGRAPH in 2022. In 2023 and 2024 he turned to text-guided geometry with TextDeformer and Generative Escher Meshes, and MeshUp was a best paper runner-up at 3DV 2025. He is a professor at Université de Montréal and an associate academic member of Mila, where his research combines geometry processing, deep learning and optimization.

Timeline

  1. 2015–2017

    Doctorate at the Weizmann Institute

    Working with Yaron Lipman, he publishes Orbifold Tutte Embeddings at SIGGRAPH Asia in 2015. He earns his PhD at the Weizmann Institute of Science in 2017 under Lipman, with the thesis "On bijective and low-distortion mapping of meshes".

  2. 2017

    Convolutional networks on surfaces

    In 2017, he coauthors Convolutional Neural Networks on Surfaces via Seamless Toric Covers at SIGGRAPH with Haggai Maron, Yaron Lipman, Vladimir Kim and others.

  3. By 2022

    Neural Jacobian Fields at Adobe

    After his PhD, he joins Adobe Research as a research scientist, focusing on geometry processing, numerical optimization and machine learning. In 2022, he coauthors Neural Jacobian Fields at SIGGRAPH with Kunal Gupta, Vladimir Kim, Siddhartha Chaudhuri, Jun Saito and Thibault Groueix. The framework predicts mappings of arbitrary meshes with a neural network, including meshes with different triangulations.

  4. 2023–2024

    Text-guided meshes and tilings

    In 2023, he coauthors TextDeformer with William Gao, Thibault Groueix, Vladimir Kim and Rana Hanocka, which deforms a triangle mesh from a text prompt using CLIP and DINO features. In 2024, he and Groueix present Generative Escher Meshes at SIGGRAPH, a text-guided method that produces repeating, tile-able 2D imagery by optimizing the geometry and texture of a 2D mesh against an image diffusion model.

  5. 2024

    Neural Geometry Processing course

    In winter 2024, he teaches the graduate course Neural Geometry Processing (IFT6095) at Université de Montréal, having moved from Adobe Research. Graduate students begin working with him in 2024, including the PhD student Tianshu Kuai.

  6. 2025

    A 3DV runner-up and PoissonNet

    MeshUp, which he coauthors with Hyunwoo Kim, Itai Lang, Thibault Groueix, Vladimir Kim and Rana Hanocka, is a best paper runner-up at 3DV 2025; it deforms a 3D mesh towards several target concepts defined as text or images. In 2025, he also coauthors PoissonNet at SIGGRAPH Asia, a neural architecture for learning on meshes that propagates features across a surface by solving Poisson's equation.

  7. As of October 2026

    Professor at Université de Montréal

    He is a professor at Université de Montréal and an associate academic member of Mila, where his research lies at the intersection of geometry processing, deep learning and optimization. In 2026, he coauthors Matérn Noise for Triangulation-Agnostic Flow Matching on Meshes, a SIGGRAPH 2026 paper with Tianshu Kuai, Arman Maesumi and Daniel Ritchie that adapts flow matching to triangle meshes of different triangulations.

Career

  1. NowUniversité de MontréalProfessor
  2. NowMilaAssociate Academic Member
  3. AdobeResearch Scientist

Education

  1. 2017Weizmann Institute of SciencePhD

From the biography.

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Université de Montréal. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  2. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes Université de Montréal. 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.
  3. Universities (31%) and startups and other companies (25%) employ the largest shares of 2020–2026 entrantsIncludes Mila. Among 819 people whose first recorded role started in 2020–2026 and who have a known current organization, 60% work in commercial sectors (25% at startups and other companies, 23% at frontier labs and 13% at big tech, with 9 in two), and 31% work at universities, compared with 66% for earlier entrants.
  4. Companies supply the most prior-work hires at 7 of the 9 frontier AI labsIncludes Mila. 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.

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 Noam Aigerman yet. Send us a free-licensed photo.

  1. Noam Aigerman's Homepage noamaig.github.io. Checked 22 October 2026.
  2. Moross Lab – Alumni wisdom.weizmann.ac.il. Checked 22 October 2026.
  3. [Colloquium] REMINDER: [TTIC Talks] 1/4 Talks at TTIC: Noam Aigerman, Adobe Research mailman.cs.uchicago.edu. Checked 22 October 2026.
  4. Seminar • Computer Graphics • Neural Shape Mapping: Modifying, Manipulating, and Matching Geometry Through Deep Learning uwaterloo.ca. Checked 22 October 2026.
  5. Adobe Research » Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes research.adobe.com. Checked 22 October 2026.
  6. [2304.13348] TextDeformer: Geometry Manipulation using Text Guidance arxiv.org. Checked 22 October 2026.
  7. [2309.14564] Generative Escher Meshes arxiv.org. Checked 22 October 2026.
  8. Noam Aigerman | Mila mila.quebec. Checked 22 October 2026.
  9. [2408.14899] MeshUp: Multi-Target Mesh Deformation via Blended Score Distillation arxiv.org. Checked 22 October 2026.
  10. [2510.14146] PoissonNet: A Local-Global Approach for Learning on Surfaces arxiv.org. Checked 22 October 2026.
  11. [2605.19305] Matérn Noise for Triangulation-Agnostic Flow Matching on Meshes arxiv.org. Checked 22 October 2026.