About Me
I am a final-year PhD student in Computer Science at
University of Cambridge, advised by Prof. Cengiz Öztireli and Prof. Rafal Mantiuk.
Before starting my Ph.D., I obtained my Master's degree in Robotics, Systems and Control from ETH Zurich under supervision of Prof. Luc Van Gool. I worked as research scientist intern at Nvidia, Qualcomm, Google Research and Microsoft Research. I was the finalist of Qualcomm Innovation Fellowship 2024.
My research focuses on developing AI systems with spatial intelligence that can perceive, understand, and interact with the physical world. I approach this by building generative world models and efficient 3D/4D reconstruction methods that capture real-world objects, scene and motion, while designing edge-optimized sparse ML systems for practical deployment in AR/VR, robotics, and immersive experiences. My expertise spans three core areas:
- 3D/4D Reconstruction and Generative Modeling from Images/Monocular Video with Perceptual Foundation:
Bullet-Timer, GNT-MOVE, ERM, Perceptual-NeRF, αSurf, Diffusion4D, L4GM, NeRF-NQA - On-device Mixture of Experts for Multi-task/modal Agents:
M3ViT, GNT-MOVE, Edge-MoE - Self-supervised Learning for Point Cloud Understanding:
MLSP, GCC-3D, ONCE-Dataset
Recent News
- Our work BulletTimer is accepted by NeurIPS'25. Congratulations to our collaborators.
- Our work αSurf is accepted by 3DV'25 as oral presentation.
- Our work Diffusion4D, L4GM, SCube are accepted by NeurIPS'24. Congratulations to our collaborators.
- I was one of the finalists of the Qualcomm Innovation Fellowship 2024 (QIF 2024). Innovation title: "Real-time On-device 3D Modeling via Neural Implicit Scene Representations".
- Our work NeRF-NQA is accepted by Transactions on Visualization and Computer Graphics (TVCG) 24.
- Our work Perceptual-NeRF is accepted by EUROGRAPHICS'24.
- Our work GNT-MOVE is accepted by ICCV'23.
- We won 3rd place in the University Demo Best Demonstration at the 59th Design Automation Conference (DAC 2022). We demo for a multi-task vision transformer on FPGA.
- Our work M3ViT is accepted by NeurIPS'22.
- Our work MLSP is accepted by ECCV'22.
Research Overview
Selected Publications
Full publication list at Google
Scholar
3D/4D Reconstruction and Generation from Images/Monocular Video
On-device Mixture of Experts for Multi-task/modality Learning Agent
Self-supervised Learning for Point Cloud Understanding
Services
-
Conference Reviewers:NeurIPS 23/24, ICLR 24/25, CVPR 24/25, ECCV 24 .
Teaching and Supervision (Uni of Cam)
-
Further Graphics 2023-2024
-
Machine Vision Perception 2024-2025
-
Further Graphics 2024-2025