About

Hello! I am a Senior Machine Learning Research Scientist at Netflix in the US. My research spans image and video generation and editing, digital humans, and 3D vision and graphics, with a focus on VFX applications.

My work includes large-scale DiT-based image and video generation model development, mid-training and post-training, real-time image editing models built from scratch, and distillation for faster inference. I also work on digital face animation, editing, and identity swapping. I work end-to-end across data collection, annotation, filtering, agent-driven dataset generation, and model training, evaluation, and deployment.

Prior to joining Netflix, I completed my PhD under the supervision of Prof. Dr. Christian Theobalt and co-supervision of Dr. Vladislav Golyanik at Max Planck Institute for Informatics in Germany, graduating summa cum laude. My doctoral research focused on physics-based monocular 3D human motion capture and animation synthesis with environment interactions, as well as non-rigid deformation capture for hand–face interactions.

Contact:



Publications

Click here for the publication list!

Experiences

netflix
Jun 2024 - Current:
Research Scientist at Netflix, U.S.
google
Jun 2022 - Dec 2022:
Research intern at Google, Switzerland
mpii
Oct 2019 - 2024 March:
Ph.D. Candidate in Visual Computing and Artificial Intelligence department at Max-Planck-Institut für Informatik , Germany
DFKI
Oct 2017 - Sep 2019:
Research assistant at German Research Center for Artificial Intelligence (DFKI), Germany

Talks

Awards & Honors

  • Best paper finalist at CVPR 2022

  • Best student paper at 3DV 2022

  • Scholarship grant from German Academic Exchange Service (DAAD), 2017

  • Scholarship grant from Waseda University (Azusa Ono Memorial Scholarship), 2011

Reviewer Experience

ACM TOG, SIGGRAPH, SIGGRAPH Asia, CVPR, ECCV, TPAMI, CG Forum, 3DV, TVCG, IROS