PeopleofSuperintelligence

Researcher

Rinon Gal

Rinon Gal is a generative-AI researcher known for personalizing text-to-image models. A computer science PhD student at Tel Aviv University under Daniel Cohen-Or and Amit Bermano, he joined NVIDIA Research as an intern in June 2021. There he coauthored StyleGAN-NADA in 2021, Textual Inversion in 2022 and Perfusion in 2023, and he won a Blavatnik Prize for Outstanding PhD Students in Computer Science in 2023. In 2024 he coauthored ConsiStory, a training-free method for consistent text-to-image generation. Since 2025, he is a researcher at Black Forest Labs.

Works
41
Citations
2,388
h-index
17
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2018–2020

    Reading receipts and documents

    He coauthors a 2018 ACCV paper, Visual-linguistic methods for receipt field recognition, and a 2020 DocEng paper, Cardinal Graph Convolution Framework for Document Information Extraction, both with Roy Shilkrot.

  2. June 2021

    Intern at NVIDIA Research

    He is a computer science PhD student at Tel Aviv University, supervised by Daniel Cohen-Or and Amit Bermano. He joins NVIDIA Research as an intern in June 2021.

  3. 2021

    StyleGAN-NADA domain adaptation

    In 2021, he introduces StyleGAN-NADA with Or Patashnik, Haggai Maron, Gal Chechik and Daniel Cohen-Or. The method uses CLIP to shift an image generator to new domains from a text prompt, without collecting a single image.

  4. 2022–2023

    The Textual Inversion paper

    In 2022, he introduces Textual Inversion with Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit Bermano, Gal Chechik and Daniel Cohen-Or. Three to five images of a concept become a new word in the embedding space of a frozen text-to-image model, and the paper appears at ICLR in 2023 as a spotlight.

  5. 2023

    Perfusion and Key-Locking

    In 2023, he coauthors Perfusion with Yoad Tewel, Gal Chechik and Yuval Atzmon at SIGGRAPH. The text-to-image personalization method uses dynamic rank-1 updates and a mechanism called Key-Locking to avoid overfitting.

  6. June 2023

    A Blavatnik Prize

    He receives the Blavatnik Prize for Outstanding PhD Students in Computer Science in June 2023.

  7. 2024

    Consistent images and animated sketches

    In February 2024, he coauthors an NVIDIA Technical Blog post with Gal Chechik and Yuval Atzmon on personalizing text-to-image models, including the encoder-for-tuning (E4T) method. His 2024 papers include Breathing Life Into Sketches Using Text-to-Video Priors, a CVPR spotlight, and ConsiStory, a training-free method for consistent text-to-image generation at SIGGRAPH.

  8. Since 2025

    Researcher at Black Forest Labs

    He joins Black Forest Labs as a researcher in 2025, after working at NVIDIA from 2021. In February 2026, he posts Spanning the Visual Analogy Space with a Weight Basis of LoRAs with Hila Manor, Haggai Maron, Tomer Michaeli and Gal Chechik, a paper accepted to ECCV 2026.

Career

  1. Since 2025Black Forest LabsResearcher
  2. 2021–2024NVIDIAIntern

Education

  1. Tel Aviv UniversityPhD

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion2022 · 611 citationsWith Gal Chechik
  2. StyleGAN-NADA2022 · ACM Transactions on Graphics · 500 citationsWith Gal Chechik
  3. HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing2022 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 269 citations
  4. Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models2023 · ACM Transactions on Graphics · 165 citationsWith Gal Chechik
  5. Key-Locked Rank One Editing for Text-to-Image Personalization2023 · 126 citationsWith Gal Chechik

From OpenAlex, as of 21 October 2026.

  1. 16% of AI career moves in the 2020s went from a university to a companyIncludes Rinon Gal. 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. 11% of AI doctorate holders from 2010 to 2016 founded or led a company or lab by 10 years after graduationIncludes Black Forest Labs. We estimate how often AI doctorate holders founded or led a company or lab by 10 years after graduation, how waiting times compare between founders and top jobs, and which universities trained the most.
  3. Universities (31%) and startups and other companies (25%) employ the largest shares of 2020–2026 entrantsIncludes Black Forest Labs. 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. Google has the highest combined h-index among AI organizationsIncludes NVIDIA. 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 Rinon Gal yet. Send us a free-licensed photo.

  1. Rinon Gal rinongal.github.io. Checked 20 October 2026.
  2. Author: Rinon Gal | NVIDIA Technical Blog developer.nvidia.com. Checked 20 October 2026.
  3. StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators arxiv.org. Checked 20 October 2026.
  4. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion | NVIDIA Research Tel-Aviv Lab research.nvidia.com. Checked 20 October 2026.
  5. Key-Locked Rank One Editing for Text-to-Image Personalization | NVIDIA Research Tel-Aviv Lab research.nvidia.com. Checked 20 October 2026.
  6. Generative AI Research Spotlight: Personalizing Text-to-Image Models | NVIDIA Technical Blog developer.nvidia.com. Checked 20 October 2026.
  7. Rinon Gal (Black Forest Labs): generative models — Lacuna lacuna.tiptreesystems.com. Checked 20 October 2026.
  8. Spanning the Visual Analogy Space with a Weight Basis of LoRAs arxiv.org. Checked 20 October 2026.