PeopleofSuperintelligence

Researcher

Chi-Pin Huang

As of October 2026, Chi-Pin Huang is a Research Scientist at NVIDIA Research Taiwan, where he studies vision-language generative and vision-language-action models. He earned a bachelor's degree in computer science and information engineering at National Taiwan University in 2022 and completed a PhD there under Yu-Chiang Frank Wang in January 2026. His research includes Receler, which learns lightweight erasers to remove target concepts from text-to-image diffusion models, and VideoMage, which customizes text-to-video generation for multiple subjects. He coauthored ThinkAct for visual planning in robot tasks and Fast-ThinkAct for more efficient vision-language-action reasoning.

Now at
NVIDIA
Works
14
Citations
55
h-index
3
Badges

Publication numbers from OpenAlex, as of 19 October 2026.

Timeline

  1. 2022

    A computer science degree

    He earns a bachelor's degree in computer science and information engineering at National Taiwan University in 2022.

  2. 2024

    Receler at ECCV

    At ECCV 2024, he coauthors Receler, which learns a lightweight eraser to remove target concepts from text-to-image diffusion models.

  3. February 2025

    Research internship at NVIDIA

    He joins NVIDIA Research as a Research Intern in February 2025.

  4. June 2025

    Customizing videos with VideoMage

    At CVPR 2025, he coauthors VideoMage, a framework for customizing text-to-video generation with multiple subjects and interactive motions.

  5. September 2025

    ThinkAct for robot planning

    In September 2025, NeurIPS accepts his coauthored ThinkAct paper. The framework connects embodied reasoning to robot actions through reinforced visual latent planning.

  6. January 2026

    A PhD at National Taiwan University

    He completes a PhD at National Taiwan University in January 2026 under Professor Yu-Chiang Frank Wang.

  7. June 2026

    Fast-ThinkAct for robot planning

    At CVPR 2026, he coauthors Fast-ThinkAct, which uses verbalizable latent reasoning to reduce inference time for vision-language-action models.

  8. As of October 2026

    Research scientist at NVIDIA

    As of October 2026, he is a Research Scientist at NVIDIA Research Taiwan, where his research focuses on vision-language generative and vision-language-action models. Before joining NVIDIA as a Research Scientist, he works as an Applied Scientist Intern at Microsoft and develops deep learning models for Bing Maps.

Career

  1. Since 2025NVIDIAResearch Intern
  2. MicrosoftApplied Scientist Intern

Education

  1. 2026National Taiwan UniversityPhD
  2. 2022National Taiwan UniversityBachelor's degree in computer science and information engineering

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

Most-cited works

  1. Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers2024 · Lecture notes in computer science · 30 citationsWith Yu-Chiang Frank Wang
  2. Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models2024 · Lecture notes in computer science · 10 citationsWith Yu-Chiang Frank Wang
  3. ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning2025 · neural information processing systems · 8 citationsWith Yu-Chiang Frank Wang
  4. VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models2025 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 3 citationsWith Yu-Chiang Frank Wang
  5. Continual Personalization for Diffusion Models2025 · IEEE/CVF International Conference on Computer Vision (ICCV) · 2 citationsWith Yu-Chiang Frank Wang

From OpenAlex, as of 19 October 2026.

  1. 14% of AI career moves in the 2020s went from a university to a companyIncludes Chi-Pin Huang. Our estimates of how university-to-company career transitions changed by decade, including roles added alongside an earlier job.
  2. Google alumni founded or led 87 other organizations, the most among the labs we compareIncludes NVIDIA. We trace 212 organizations founded or led by AI lab alumni, and 223 career moves between the labs.
  3. 44% of AI career moves go from one university to anotherIncludes NVIDIA. We estimate how 14,272 AI career moves link universities, companies, labs and government research centers, with net flows and the most common paths.
  4. Google has the highest combined h-index among AI organizationsIncludes NVIDIA. Our estimates of combined and median h-index at AI organizations, using current affiliations and OpenAlex records.

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 Chi-Pin Huang yet. Send us a free-licensed photo.

  1. Chi-Pin Huang jasper0314-huang.github.io. Checked 19 October 2026.
  2. Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers ecva.net. Checked 19 October 2026.
  3. VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models openaccess.thecvf.com. Checked 19 October 2026.
  4. ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning proceedings.neurips.cc. Checked 19 October 2026.
  5. Chi-Pin Huang | Research research.nvidia.com. Checked 19 October 2026.
  6. Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning openaccess.thecvf.com. Checked 19 October 2026.