About Me
I am a Ph.D. student in Computer Science and Engineering at the University of Melbourne, advised by Prof. Naveed Akhtar. My thesis focuses on benchmarking video understanding. My broader research interests include the generalization and robustness of neural networks, responsible data augmentation with diffusion models, vision-language models, and consistent character generation.
Alongside my PhD, I work as a Senior Scientist – Autonomy AI at Neubility. Previously, I was Chief Technology Officer (CTO) – Gen AI at Upendi.app, a Research Scientist – CV/ML at CoreMax Technology, and a Research Associate at Sejong University, all in Seoul, South Korea.
I received my M.S. in Computer Science and Engineering from Sejong University, Seoul, where I worked on image understanding and reconstruction, including an image compression method presented at CVPRw. I have attended several summer schools and served as a technical volunteer at top AI/ML conferences.
News
- 07/2026 Two papers (S²-FracMix, HSFM) accepted at ECCV 2026!
- 06/2026 US Patent 12,657,783 B1 granted.
- 04/2026 GenMix accepted in Expert Systems with Applications (Elsevier).
- 03/2025 One paper on responsible data augmentation accepted at the ICLR 2025 workshop track.
- 09/2024 Starting my Ph.D. at the University of Melbourne, Australia.
See older news
- 02/2024 DiffuseMix accepted at CVPR 2024!
- 10/2022 Face Pyramid Vision Transformer accepted at BMVC 2022.
Current Service Appointments
- Reviewer – TPAMI IJCV CVIU
- Reviewer – CVPR ICCV ECCV NeurIPS ICML ICLR AAAI WACV
- Volunteer – NeurIPS ICML ICLR IJCAI AAAI CVPR
Publications
- S²-FracMix: Label-Preserving Self-Saliency Mixup Augmentation
- HSFM: Hard-Set-Guided Feature-Space Meta-Learning for Robust Classification under Spurious Correlations
- GenMix: Effective Data Augmentation with Generative Diffusion Model Image Editing
- Context-Guided Responsible Data Augmentation with Diffusion Models
- DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models
See more publications
- Face Pyramid Vision Transformer
- Image Compression with Recurrent Neural Network and Generalized Divisive Normalization
- Face Recognition Using Shallow Age-Invariant Data
- Person Search: New Paradigm of Person Re-Identification: A Survey and Outlook of Recent Works
Patents
- System and Method for Label-Preserving Data Augmentation with Diffusion Models
Awards & Honors
- NeurIPS Support, Sponsored by Naver Labs Europe, DeepMind, and Google AI, 2021
- Full Tuition Fee Waiver, School of Computer Engineering, Sejong University, 2020
- Prof. Stipend, CVPR Lab, Sejong University, 2020
- Conference Travel Grant, Ministry of Planning Commission, Pakistan, 2020
- Merit Scholarship for Bachelor Degree, Quaid-e-Azam Aligarh Society, Karachi, 2018
- Most Valuable Professional Award, C-SharpCorner, India, 2016 & 2017
- Laptop Award, Prime Minister Pakistan Program, Karachi, Pakistan, 2016
Academic Activities
Academic Services
- Technical Volunteer – NeurIPS 2021, IJCAI 2021, ICML 2021, ICLR 2021, AAAI 2021
- Student Volunteer – CVPR 2021
Reviewer – International Journals
- IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
- International Journal of Computer Vision (IJCV)
- Computer Vision and Image Understanding (CVIU)
Reviewer – International Conferences
- CVPR 2019–2023, ICCV 2019–2023, ECCV 2020–2022
- NeurIPS 2020–2022, ICML 2020–2023, ICLR 2021–2023
- AAAI 2020–2023, WACV 2020
Moderator
- AI Deep Group on Facebook, 23.1K members
- Artificial Intelligence, Machine and Deep Learning Group, 754.4K members
- Deep Learning and Machine Learning, 109.5K members
- Thailand Deep Learning, 19.8K members
- Computer Vision, 129.6K members
- Computer Vision and Machine Learning, 17.5K members
Projects
- High-Quality Video Generation from Diffusion Models (Text-2-Video), 2024–Present
Designed identity-specific prompts and fine-tuned models for video generation. - Image Restoration and Enhancement with GANs and Diffusion Models, 2024–Present
Worked on image super-resolution, deblurring, in-painting, and dehazing. - Image Editing Instructions with Diffusion Models (Image-to-Image), 2023
Integrated Imagic, SINE, and LEDITS for high-resolution image editing. - Foundation Multimodal Vision Language Models, 2023
Generated captions and evaluated models on various metrics. - Vision Language Models for Unseen Domains & Domain Shift, 2023
Fine-tuned models to improve robustness and performed experiments on multiple datasets. - Reliable Lightweight Real-Time Open-Vocabulary Object Detection, 2023
Investigated and fine-tuned models for state-of-the-art performance. - Online Continual Learning with Blurry Data and Incorrect Labels, 2022
Developed a framework for diversity and purity in memory updates. - Vision Transformer for General and Age-Invariant Face Recognition, 2021
Proposed a new ViT architecture and conducted experiments on face aging datasets.
Technical Skills
- IP Algorithms: Segmentation, Filter Design, Noise Removal, Compression, Super Resolution
- Object Detection: SSD, YOLO-NAS, YOLOX, Faster R-CNN, DETR, GroundingDINO, YOLOv8
- DL Techniques: Tracking, Optical Flow, Particle Filtering, Pose Estimation
- CV Algorithms: Image Classification and Detection, Tracking, Siamese Networks
- Software Control: JIRA, Agile, Scrum, GIT, Subversion
- Languages: Python, Keras, JAVA, Unix Shell Scripting
- Deployment: Docker, Kubernetes
- Editors: Cursor AI, Windsurf, Visual Studio Code, PyCharm, Jupyter Notebook
- Operating Systems: Windows 10, Ubuntu 18.04 / 20.04, macOS
- APIs: PyTorch, TensorFlow, Caffe, OpenCV, Flask, Django
Summer and Winter Schools
- OxML School, Oxford Machine Learning Summer School, 2022
- NYU AI School, New York Artificial Intelligence School, USA, 2022
- MLSS, Machine Learning Summer School, Taipei, Taiwan, 2021
- EEML, Eastern European Machine Learning Summer School, 2021
Q/A Mentorship Sessions
- Yingzhen Li, Mentor at ICML, Imperial College London
- Evan Shelhamer, Mentor at ICML, DeepMind, Google
- Wei-Lun (Harry) Chao, Mentor at ICLR, Ohio State University
- Shakir Mohamed, Mentor at ICLR, DeepMind, Google
- Emmanuel Kahembwe, Mentor at ICLR, VDE (UK & Ireland)