Samuel Teodoro

About Me#

I am a Ph.D. student at the Video and Image Computing Lab (VICLab) at KAIST, advised by Prof. Munchurl Kim. I received my B.S. in Electrical Engineering from the University of the Philippines Los Baños in 2018. Currently, my research focuses on controllable image and video editing using generative models. Outside of research, I enjoy street and portrait photography.

News#

• Sep 2026
  🎉 MotionGrounder is accepted at NeurIPS 2026! See you in Sydney! 🇦🇺
• Aug 2026
  🎉 PRIMEdit is accepted at IEEE TPAMI (IF: 20.4)!
• Apr 2026
  🗣️ Presented OmniText at ICLR 2026 in Rio!
• Jan 2026
  🎉 OmniText is accepted at ICLR 2026! See you in Rio! 🇧🇷

Education#

• Aug 2021 – Present
  Integrated M.S.-Ph.D. in Electrical Engineering Korea Advanced Institute of Science and Technology, Daejeon, South Korea
• Jun 2013 – Jun 2018
  B.S. in Electrical Engineering, cum laude University of the Philippines Los Baños, Los Baños, Laguna, Philippines

Publications#

Conference NeurIPS 2026

MotionGrounder: Grounded Multi-Object Motion Transfer via Diffusion Transformer

Samuel Teodoro, Yun Chen, Agus Gunawan, Soo Ye Kim, Jihyong Oh^†, Munchurl Kim^†

Paper Project Page

Conference ICLR 2026

OmniText: A Training-Free Generalists for Controllable Text-Image Manipulation

Agus Gunawan*, Samuel Teodoro*, Yun Chen, Soo Ye Kim, Jihyong Oh^†, Munchurl Kim^†

Paper Project Page Code Dataset

Journal IEEE TPAMI

PRIMEdit: Probability Redistribution for Instance-aware Multi-object Video Editing with a New Benchmark Dataset

Samuel Teodoro*, Agus Gunawan*, Soo Ye Kim, Jihyong Oh^†, Munchurl Kim^†

Paper Project Page Code Dataset

* Equal Contribution  ·  ^† Co-Corresponding Authors