Yin-Loon Khor is an AI Engineer currently pursuing Master of Artificial Intelligence at Universiti Malaya. He specialises in computer vision, multimodal large language models and agentic workflows. His work spans end-to-end development of agentic AI systems including design, deployment and integration, alongside AI model development and training across computer vision and multimodal tasks. Beyond his professional role, he actively undertakes AI projects, applies emerging AI frameworks in practical settings and participates in competitive challenges, resulting in global competition wins, peer-reviewed publications and a CVPR Workshop accepted paper.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Universiti MalayaFaculty of Computer Science & Information Technology
Master StudentOct. 2025 - present -
Universiti Tunku Abdul RahmanBachelor of Electrical and Electronic Engineering with Honours (First Class)Jun. 2020 - Jun. 2024
Experience
-
MIMOS BerhadFreelance AI EngineerJun. 2025 - Sep. 2025
-
Intel Microelectronics MalaysiaGraduate Talent (SOC DFT Design Engineering)Sep. 2024 - Sep. 2025
Honors & Awards
-
2nd Place, SIQA @ ICME 2026 — Scientific Image Quality Assessment Challenge (Scoring Track)2026
-
Top 4 in LoViF @ CVPR 2026, the Challenge on Efficient VLM for Multimodal Creative Quality Scoring2026
-
Global Champion, IEEE Big Data Cup 2024 — Generalised Building Extraction Challenge2024
-
Global Semi-Finalist (Top 10), EY Open Science Data Challenge2024
News
Selected Publications (view all )
EffiMiniVLM: A Compact Dual-Encoder Regression Framework
Yin-Loon Khor*, Yi-Jie Wong*, Yan Chai Hum† (* equal contribution)
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2026 Top 4, LoViF @ CVPR 2026
A compact dual-encoder vision–language regression framework combining EfficientNet-B0 and MiniLMv2 for product quality scoring, achieving CES 0.40 with only 27.7M parameters and 6.8 GFLOPs — the lowest resource cost on the CVPR 2026 LoViF leaderboard, 4× to 8× more efficient than comparable top-5 methods, and the only top submission trained without external datasets.
EffiMiniVLM: A Compact Dual-Encoder Regression Framework
Yin-Loon Khor*, Yi-Jie Wong*, Yan Chai Hum† (* equal contribution)
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2026 Top 4, LoViF @ CVPR 2026
A compact dual-encoder vision–language regression framework combining EfficientNet-B0 and MiniLMv2 for product quality scoring, achieving CES 0.40 with only 27.7M parameters and 6.8 GFLOPs — the lowest resource cost on the CVPR 2026 LoViF leaderboard, 4× to 8× more efficient than comparable top-5 methods, and the only top submission trained without external datasets.
Cross-City Building Instance Segmentation: From More Data to Diffusion-Augmentation
Yi-Jie Wong, Yin-Loon Khor, Mau-Luen Tham, Ban-Hoe Kwan, Anissa Mokraoui, Yoong Choon Chang
IEEE International Conference on Big Data (BigData) 2024 1st Place, BEGC 2024
A data-centric approach to cross-city building instance segmentation that improves generalization through open-source data from the Microsoft Building Footprint dataset and a novel segmentation-guided diffusion augmentation pipeline. The YOLOv8-based solution achieved a private F1-score of 0.897, ranking 1st globally in the IEEE BigData Cup 2024 Building Extraction Generalization Challenge.
Cross-City Building Instance Segmentation: From More Data to Diffusion-Augmentation
Yi-Jie Wong, Yin-Loon Khor, Mau-Luen Tham, Ban-Hoe Kwan, Anissa Mokraoui, Yoong Choon Chang
IEEE International Conference on Big Data (BigData) 2024 1st Place, BEGC 2024
A data-centric approach to cross-city building instance segmentation that improves generalization through open-source data from the Microsoft Building Footprint dataset and a novel segmentation-guided diffusion augmentation pipeline. The YOLOv8-based solution achieved a private F1-score of 0.897, ranking 1st globally in the IEEE BigData Cup 2024 Building Extraction Generalization Challenge.
Automating Coastal Vulnerability Assessment: AI-Driven Geospatial Analysis via Building Damage Detection
Yin-Loon Khor, Yi-Jie Wong, Ziwei Liu
2024 Top 10 Semi-Finalist, EY 2024
An AI-driven geospatial analysis pipeline that automates coastal disaster assessment by detecting damaged buildings from satellite imagery. The model is pretrained on Microsoft's Building Footprint dataset and fine-tuned with a mix of manually and self-annotated data, then used to generate damage-count and damage-ratio heatmaps for disaster response and resilience planning. The solution ranked Top 10 Global Semi-Finalist in the 2024 EY Open Science Data Challenge out of 11,000+ registrants.
Automating Coastal Vulnerability Assessment: AI-Driven Geospatial Analysis via Building Damage Detection
Yin-Loon Khor, Yi-Jie Wong, Ziwei Liu
2024 Top 10 Semi-Finalist, EY 2024
An AI-driven geospatial analysis pipeline that automates coastal disaster assessment by detecting damaged buildings from satellite imagery. The model is pretrained on Microsoft's Building Footprint dataset and fine-tuned with a mix of manually and self-annotated data, then used to generate damage-count and damage-ratio heatmaps for disaster response and resilience planning. The solution ranked Top 10 Global Semi-Finalist in the 2024 EY Open Science Data Challenge out of 11,000+ registrants.