Hi, I am Rui 👋, a Master of Computing in Artificial Intelligence student at the National University of Singapore. I am interested in how machines can see, connect information across modalities, and reason more reliably. My current interests include computer vision, robust machine learning, multimodal learning, vision-language models, and audio processing. I enjoy turning open-ended ideas into careful experiments, and I am naturally curious, collaborative, and always happy to learn from a good technical puzzle. 🔍
Education
National University of Singapore
Xi'an Jiaotong-Liverpool University
Work Experience
Bosch China Software Center (BCSC)
- Developed a vision-language-model-based workflow for industrial video inspection and video understanding.
- Worked on structured temporal evidence, verification, and multimodal reasoning to support more reliable interpretation of video content.
Core Projects
Reserved for detailed technical project pages.
Vision-Language Model Project
Selected Publications
SceneGuard: Training-Time Voice Protection with Scene-Consistent Audible Background Noise
Rui Sang, Yuxuan Liu
AAAI 2026 Workshop Accepted · First author
Training-time voice protection using audible background noise selected to match the recording context.
SceneGuard: Training-Time Voice Protection with Scene-Consistent Audible Background Noise
Rui Sang, Yuxuan Liu
AAAI 2026 Workshop Accepted · First author
Training-time voice protection using audible background noise selected to match the recording context.
Training a Perceptual Model for Evaluating Auditory Similarity in Music Adversarial Attack
Yuxuan Liu, Rui Sang, Peihong Zhang, Zhixin Li, Shengchen Li
17th International Symposium on Computer Music Multidisciplinary Research (CMMR) 2025
A perceptually aligned music representation framework that combines psychoacoustic conditioning with contrastive learning for more robust auditory similarity modelling.
Training a Perceptual Model for Evaluating Auditory Similarity in Music Adversarial Attack
Yuxuan Liu, Rui Sang, Peihong Zhang, Zhixin Li, Shengchen Li
17th International Symposium on Computer Music Multidisciplinary Research (CMMR) 2025
A perceptually aligned music representation framework that combines psychoacoustic conditioning with contrastive learning for more robust auditory similarity modelling.
Maia: An inpainting-based approach for music adversarial attacks
Yuxuan Liu*, Peihong Zhang*, Rui Sang, Zhixin Li, Shengchen Li (* equal contribution)
The 26th International Society for Music Information Retrieval Conference (ISMIR) 2025
A generative inpainting framework for white-box and black-box music adversarial attacks, designed to preserve perceptual audio quality.
Maia: An inpainting-based approach for music adversarial attacks
Yuxuan Liu*, Peihong Zhang*, Rui Sang, Zhixin Li, Shengchen Li (* equal contribution)
The 26th International Society for Music Information Retrieval Conference (ISMIR) 2025
A generative inpainting framework for white-box and black-box music adversarial attacks, designed to preserve perceptual audio quality.
All publications
Projects & Technical Portfolio
Research, engineering work, and an archive of selected coursework projects.