☕️About Me
I am a PhD researcher in Computer Vision at Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI). My research focuses on Multimodal Visual Language Models (VLMs) for image, video, 3D, and 4D generation and perception.
I am the first author of 3D-CoMPaT (ECCV Oral) and 3D-CoMPaT++ (TPAMI 2025, accepted). I also led the NeurIPS paper PointNeXt (1,000+ citations). My work Exploring Scaling Laws of PointNets received a Spotlight Talk at 3DV 2025.
I have served as a core organizer of a CVPR workshop and as a program chair and reviewer for leading AI conferences and journals such as TPAMI, IJCV, CVPR, ICCV, AAAI, TCSVT, and NeurIPS. I also contributed to Apache RocketMQ as an open-source developer.
I previously interned at Amazon Science (Prime Video, Seattle) and Sony AI (Tokyo).
- Multimodal Visual Language Models (VLMs)
- Image / Video / 3D / 4D Generation and Perception
- Diffusion Models
- 3D Vision
PhD in Computer Vision
Mohamed Bin Zayed University of Artificial Intelligence
MSc in Computer Science
King Abdullah University of Science and Technology
BSc in Computer Science and Technology
Southern University of Science and Technology
School of Computing (Exchange Student)
National University of Singapore
Visiting Student (Electronics and Computer Engineering)
University of British Columbia
Experience
Applied Scientist Research Intern
Amazon Science - Prime VideoDeveloped a large visual-language model with 2D and 3D perception reasoning, bridging low-level perception with high-level reasoning.
Research Intern
Sony AI ResearchResearch on music-driven diffusion-based generative AI models, focusing on using music as guidance to generate synchronized human dance movements.
Assistant Researcher
Mohamed bin Zayed University of Artificial IntelligenceExplored 3D and video content generation and perception using diffusion and LLM models.
Innovation Associate
Dubai Business Associates - Emirates Airlines- Selected as one of 30 associates from 10k applicants for the prestigious mini-MBA program
- Served as a consultant in Emirates Airlines’ Research Department
- Implemented a data-driven AI chatbot product
- Developed a 3-year cabin crew performance strategy presented to VPs
Research Assistant
KAUST - Vision CAIR Group- Researched semi-supervised few-shot learning, meta-learning, and 3D object recognition
- Developed and participated in the creation of 3DCoMPat dataset and PointNeXt project
Visiting Research Student
Tsinghua University - Digital Manufacturing LabLed a team to research Micro-Organic Prediction Modeling of Cladding Process using CNNs.
Student Developer (Summer of Code) @ Apache
Apache RocketMQDeveloped the Apache RocketMQ JDBC Connector (23 commits, 3.4k LoC) as an independent developer (Alibaba Summer of Code).
Education
PhD in Computer Vision
Mohamed Bin Zayed University of Artificial IntelligenceResearch focus on Multimodal Visual Language Models (VLMs) for image, video, 3D, and 4D generation and perception.MSc in Computer Science
King Abdullah University of Science and TechnologyGPA: 3.67/4.0 Thesis: Compositional and Low-shot Understanding of 3D Objects Visual Computing Center
BSc in Computer Science and Technology
Southern University of Science and TechnologyGPA: 3.6/4.0 Thesis: Few-Shot Learning on 3D Object Recognition
School of Computing (Exchange Student)
National University of SingaporeExchange student at NUS School of Computing.
Visiting Student (Electronics and Computer Engineering)
University of British ColumbiaVisiting student at UBC.