معرفی
Dr. Haotong Qin is a Researcher at the Department of Information Technology and Electrical Engineering (D-ITET) at ETH Zurich, affiliated with the Center for Project-Based Learning. His work focuses on model compression techniques such as quantization and binarization, with applications in deepfake detection, diffusion models, and autonomous systems. Key research interests include improving the efficiency and robustness of neural networks, particularly for real-world deployment.
Research highlights involve developing methods like SAGNet for robust deepfake detection under limited data, and Q-SAM2 for efficient segmentation models. His contributions span domains from computer vision to robotics, addressing challenges in safety-critical systems and large language model optimization.
Recent publications emphasize low-bit quantization for diffusion models, vision-language integration, and traffic demand prediction using graph-based approaches. Collaborative projects include work on autonomous racing trajectory planning and cybersecurity for online social networks.
No specific grants or advisees are listed, though his involvement with ETH's project-based learning initiatives suggests pedagogical engagement. The Center for Project-Based Learning serves as his primary research hub.
