PeopleofSuperintelligence

Researcher

Fred Yang

Also known as Fu-En Yang

Fred Yang is an AI researcher whose work connects visual learning, generative video, and embodied AI. He earned an electrical engineering bachelor's degree at National Taiwan University in 2018, pursued visual-transfer research at ASUS AICS from 2020 to 2022, and completed a PhD at NTU under Yu-Chiang Frank Wang in 2023. He coauthored Dual-MTGAN for image-to-video motion transfer in 2021 and pFedPG for federated personalization in 2023; TAAI gave his PhD thesis an Honorable Mention in 2023. In 2024, he coauthored Receler for text-to-image concept erasure; in 2025, he coauthored VideoMage for controllable video generation and ThinkAct for embodied reasoning. Since February 2024, he is a Research Scientist at NVIDIA Research Taiwan, focused on physical AI, vision-language-action models, and world modeling.

Timeline

  1. 2018

    Electrical engineering at NTU

    He earns a bachelor's degree in electrical engineering at National Taiwan University in 2018.

  2. 2020–2022

    Doctoral research at ASUS AICS

    From September 2020 to October 2022, he works as a PhD program researcher at ASUS AICS, specializing in visual transfer learning.

  3. 2021

    Dual-MTGAN motion transfer

    He coauthors Dual-MTGAN in 2021, a model that separates content and motion for image-to-video synthesis and supports deterministic transfer and stochastic motion generation.

  4. 2023

    PhD, pFedPG and TAAI honors

    He completes a PhD at National Taiwan University in July 2023 under Yu-Chiang Frank Wang. In 2023, he coauthors pFedPG, a federated-learning framework that generates client-specific visual prompts for local data distributions. TAAI gives his thesis an Honorable Mention in its 2023 PhD Thesis Award.

  5. 2024–2025

    Receler, VideoMage and ThinkAct

    In 2024, he coauthors Receler, which uses a lightweight eraser to remove target concepts from text-to-image diffusion models. In 2025, he coauthors VideoMage for customization of multiple subjects and interactive motion in video, and ThinkAct, which connects high-level reasoning with action through reinforced visual latent planning.

  6. Since February 2024

    Research Scientist at NVIDIA

    He joins NVIDIA Research as a Research Scientist in February 2024 and is a Research Scientist at NVIDIA Research Taiwan. His research focuses on physical AI, vision-language-action models, world modeling, and embodied reasoning. In 2026, he coauthors PhaseLock, a training-free framework that preserves valid motion priors from few-step inference through denoising.

  1. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI from 1961 to 2025, with a year-by-year chart.
  2. The United States employs an estimated 53% of people in our data with a known employment countryOur estimates of where AI careers are concentrated now and how countries’ shares of dated positions changed over time.
  3. 46% of living people in our data with known birth and employment countries work outside their birth countryOur estimate of cross-border careers in AI, from country of birth and the country of each current organization.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionOur estimates of where the people shaping AI studied and where their careers led, from education records in cited biographies.

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 Fred Yang yet. Send us a free-licensed photo.

  1. Fu-En Yang fuenyang1127.github.io. Checked 19 October 2026.
  2. [2102.13329] Dual-MTGAN: Stochastic and Deterministic Motion Transfer for Image-to-Video Synthesis arxiv.org. Checked 19 October 2026.
  3. Fred Yang | Research research.nvidia.com. Checked 19 October 2026.
  4. [2308.15367] Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generation arxiv.org. Checked 19 October 2026.
  5. [2311.17717] Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers arxiv.org. Checked 19 October 2026.
  6. VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models openaccess.thecvf.com. Checked 19 October 2026.
  7. ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning research.nvidia.com. Checked 19 October 2026.
  8. Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them research.nvidia.com. Checked 19 October 2026.