Kien T. Pham (TK)
PhD @ HKUST
- tkpham [at] connect.ust.hk
- Google Scholar
- GitHub
Hi👋, I am currently a PhD student at HKUST, co-advised by Prof. Long Chen in the LONG Group and Prof. Qifeng Chen in the Visual Intelligence Lab. Previously, I completed my MPhil at HKUST under the guidance of Prof. Qifeng Chen, a journey filled with joy and success. Before that, I earned my BSc Degree with First Class Honors, double majoring in Data Science and Computer Science. I am also an alum of the S.S. Chern Class, an elite class for students with demonstrated mathematical excellence.
Currently, my research focuses on Diffusion-based Multimodal Generation. Previously, I have worked on some creative application areas in AIGC such as Image Composition. Additionally, I have also been engaged in projects regarding Visual Perception Understanding for Autonomous Driving and Humanoid Robotics.
Feel free to contact me by email if you are interested in discussing or collaborating with me!
One paper accepted to ACM MM 2024.
I am serving as a Reviewer for NeurIPS 2024.
One paper accepted to RO-MAN 2024.
I am very excited to attend ICRA 2024 to present our paper!
We launch project page for a training-free diffusion-based cross-domain image composition approach: TALE.
One paper accepted to ICRA 2024.
A Dialogue System Architecture for Humanoid Robots Targeting Patient Interview Tasks
IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), 2024
✨ 3rd Place for the Best Industry Application Award
Cross-Cluster Shifting for Efficient and Effective 3D Object Detection in Autonomous Driving
IEEE International Conference on Robotics and Automation (ICRA), 2024
A Dialogue System Architecture for Humanoid Robots Targeting Patient Interview Tasks
Develop a visual cue extraction framework to enhance the ability of a nurse robot (Grace) to interact and engage with patients during interviews. Various visual perception understanding tasks are explored including Object Detection, Tracking, and Reidentification, 2D-3D Body/Head Pose Estimation, Facial Expression Recognition and Analysis, Abnormal Action Recognition...
An approach for medical cancer image generation leveraging pretrained Stable Diffusion
Propose a method for generating highly realistic medical cancer images given any pairs of non-tumorous background and tumour object images, directly utilizing the pretrained Stable Diffusion.
Project Report, 2024
FMLU: Weighted Federated Mutual Learning with Uncertainty-aware Balancing Scheme
Attempt to improve FML by quantifying the uncertainty levels of the meme and local models for each client and leverage it as the weighting scheme for both global model aggregation and client update stages.
Project Report, 2023
2022 SPRING: COMP1021 - Introduction to Computer Science
2023 FALL: COMP4471/ELEC4240 - Deep Learning in Computer Vision
Conference Reviewer: NeurIPS 2024
Postgraduate Studentship
Chern Class Achievement Scholarship
Chern Class Talent Scholarship
Chern Class Scholarship
Heart Free Lodge Scholarship
University Scholarship
Dean's List