Hi, Im Pinon. I am a Second year Ph.D. student at Mila & Concordia University. My research focuses on Image World Models and Generative AI for Video/3D, particularly 3D human reconstruction, novel view synthesis, and pose-driven human video generation.
Aside from research I love cooking, learning languages, following valorant matches and hiking.
Recent Roles
![]() | Student Researcher, PhD | Oct. 2025 - Present Mila - Quebec AI Institute |
![]() | Associate Researcher, Intern | June. 2025 - December. 2025 Noah's Ark Lab Huawei Toronto |
Education
![]() | Doctor of Philosophy, Computer Science | Sep. 2024 - Present Department of Computer Science and Software Engineering (CSSE) Concordia University |
![]() | Bachelor of Science in Computing | Sep. 2020 - Jun. 2024 Department of Computing The Hong Kong Polytechnic University |
Research
![]() | No Adaptation Without Observation: Observability-Constrained Test-Time Prompt Tuning for LiDAR Semantic Segmentation Linlian Jiang, Wentao Ju, Sadman Rakib Pinon, Jianwei Xian, Zhixiang Chi, Xinxin Zuo, Yang Wang IROS 2026 arXiv |
![]() | One Image Is Enough: Self-Generated Supervision for Personalizing Human Video Diffusion at Test Time Sadman Rakib Pinon, Adamo Orsini, Yanis Falaki, Linlian Jiang, Jacob Kingi, Yang Wang, Xinxin Zuo (Under Review) |
![]() | TRACE-GS: On-Policy Trajectory Distillation with Privileged Geometric Conditioning for Sparse-View 3DGS Restoration Linlian Jiang, Yuchen Xi, Sadman Rakib Pinon, Ruigang Yang, Yang Wang, Xinxin Zuo (Under Review) arXiv |
![]() | LUPI-GCD: Generalized Category Discovery with Privileged Multimodal Information Jacob Kingi, Hareesh Vardhan Shanmugam, Zhixiang Chi, Sadman Rakib Pinon, Adamo Orsini, Yuqing Wu, Yang Wang, Xinxin Zuo (Under Review) |
![]() | Not All Graphs Are Maps: A Task-Agnostic Exploration Framework for Mobile GUI Navigation Adamo Orsini, Seyed Mohammad Ayyoubzadeh, Sadman Rakib Pinon, Hang Zhang, Khashayar G. Baradari, Yue Yu, Xinxin Zuo, Yang Wang (Under Review) |
![]() | Count to Five! Efficient Test-Time Personalization for Pose-Guided Human Video Synthesis Sadman Rakib Pinon, et al. (In Preparation) |
![]() | Detecting Non-Recurrent Congestion in Urban Networks: A Comparative Analysis of Advanced Computational Models and Traffic Pattern Visualization Sadman Rakib Pinon, XieXin Zou, Edward Chung The 24th COTA International Conference of Transportation Professionals (CICTP 2024) Paper |
Awards & Scholarship
- Split Concordia University Doctoral Fellowship, Concordia University, 2024
- EDPS Innovative Scholarship, EDPS Systems Limited, 2024
- Syndicate Lab and Alliances Scholarship, 2024
- Commercial Radio 50th Anniversary Scholarship, Hong Kong Polytechnic University, 2023
- HKSAR Reaching Out Award, Hong Kong Special Adminstrative Region Government, 2022
- Wong Tit-Shing Exchange Scholarship, Hong Kong Polytechnic University, 2021
- HKSAR Belt & Road Scholarship, Hong Kong Special Adminstrative Region Government, 2020
Contact
For like-minded peers, I’m always keen to collaborate on research ideas. Feel free to reach out to me on any of the channels below:
Je parle un peu français. Si vous parlez français et souhaitez apprendre l’anglais, n’hésitez pas à me contacter !










