I am Waikit Xiu, an M.Sc. student in Artificial Intelligence at The University of Hong Kong. I received my B.Eng. in Traffic Engineering from Sun Yat-sen University. My research interests lie in multimodal visual understanding and embodied world models, with an emphasis on large-scale video understanding in complex dynamic environments and efficient world-model inference.

My work centers on video understanding in complex dynamic environments. I study how models can capture spatio-temporal relationships and environmental change from continuous visual streams, while supporting longer temporal horizons and more complex reasoning under practical compute constraints. My current interests include multimodal spatio-temporal understanding, fine-grained vision-language modeling, and efficient world models.

I am seeking Ph.D. opportunities for Fall 2027 and welcome conversations with faculty and groups working on these problems.

Spatio-temporal Reasoning Vision-Language Models Visual Generation Autonomous Driving Embodied AI
2026.09

🎉 Our explainable semantic sensing paper was accepted to IEEE Sensors Journal — an exciting milestone.

2026.08

🚀 New chapter unlocked — joining HKUST (Guangzhou) as RA in the Transportation Thrust. No cap, I'm hyped. LFG!

2026.06

🎉 NanoVerse-TSR accepted to IEEE Sensors Journal! All that grind finally paid off — let's keep going!

2026.05

✨ Sony internship done. Learned a great deal, met great people — genuinely one of the best summers I've had.

2026.02

🎉🎉 LASAR was accepted to CVPR 2026! Looking forward to Nashville! 🔥

The University of Hong Kong

Master of Science in Artificial Intelligence

Core coursework: Deep Learning, Natural Language Processing, Computer Vision, and AI Ethics.

Sun Yat-sen University

Bachelor of Traffic Engineering

GPA: 3.6/4.0. Relevant coursework: Computer Vision, Image Processing, Deep Learning, Data Structures and Algorithms, and Machine Learning.

CVPR 2026 Preview of LASAR paper

LASAR: Towards Spatio-temporal Reasoning with Latent Cognitive Map.

Jinzhou Tang*, Sidi Liu*, Waikit Xiu*, Weixing Chen, Keze Wang.

CVPR 2026.

IEEE Sensors Preview of traffic sign perception paper

NanoVerse-TSR: Contrastive Learning-Driven Traffic Sign Recognition.

Qiang Lu*, Waikit Xiu*, Xiying Li, Shenyu Hu, Shengbo Sun.

IEEE Sensors Journal, 2026.

IEEE Sensors Preview of explainable semantic sensing paper

Explainable Semantic Sensing for Traffic Safety Risk Detection: A Vision-Language Approach.

Qiang Lu, Waikit Xiu, Xiying Li, Yuqing Zou, Qianyin Jiang.

Accepted to IEEE Sensors Journal, 2026.

Patent Preview of surrounding-vehicle trajectory prediction patent

自动驾驶场景中周围车辆的轨迹预测方法、设备及介质

Invention Patent

ZL 2025 1 0113641.6, granted in 2025.

* Equal contribution.

In prep Preview of PredErase

PredErase: Training-Free Object-and-Effect Removal with Predictive Latent Guidance.

Waikit Xiu, Qiang Lu, Junbiao Chen, Xiying Li.

Manuscript in preparation, 2026.

In prep Preview of Traffic-MLLM paper

Traffic-MLLM: Curiosity-Regularized Supervised Learning for Traffic Scenario Case-Based Reasoning.

Waikit Xiu, Qiang Lu, Bingchen Liu, Chen Sun, Xiying Li.

Manuscript in preparation, 2026.

The Hong Kong University of Science and Technology (Guangzhou)

Research Assistant, Transportation Thrust

  • Conducting research on intelligent transportation systems, with a focus on reasoning for autonomous driving and multimodal scene understanding.
  • Exploring vision-language models and spatio-temporal reasoning for safety-critical traffic scenarios.

Sony Research

Research Intern, MLLM & Generative AI Team

  • Conducted research on fine-grained matching for anime characters using multimodal large language models to improve cross-modal alignment.
  • Built a RAG-based knowledge base for anime IP to mitigate hallucination in multimodal retrieval and reasoning.
  • Designed an AI-agent workflow for intelligent IP retrieval, supporting the pipeline from natural language queries to precise character localization.

GAC R&D Center

Embodied AI Intern, Vision & Perception Group

  • Developed an open-vocabulary detection system for robotic platforms leveraging vision-language models.
  • Performed hand-eye calibration and robotic-arm joint debugging to improve spatial coordinate transformation.
  • Collaborated on real-vehicle sensor fusion to reduce visual perception drift under complex lighting conditions.

Reviewer, Frontiers in Plant Science (JCR Q1).

Reviewer, IEEE ICASSP 2025.

Reviewer, IJCNN 2026.

LiDAR-Vision Fusion BEV State Prediction System

Principal Researcher

Developed a multi-modal state prediction system integrating LiDAR point clouds and camera images to generate bird's-eye view representations for real-time scene understanding and dynamic agent behavior prediction. The project was recognized as a national-level innovation project with excellent final results and produced an invention patent.

ROS-based Autonomous Smart Vehicle Development

Lead Developer

Led the development of an autonomous smart vehicle system using ROS, covering visual perception, SLAM-based navigation, and tracking and control. The project received university-level recognition and won first prize in the South China regional competition and second prize in the national final of the 18th National College Student Smart Car Competition.

Core programming, AI development, robotics, and system operations skills.

Python

Research & automation

C++

Systems development

PyTorch

Deep learning

Vibe Coding

AI-assisted building

ROS / ROS 2

Robotics middleware

Linux

Shell & environments

Docker

Container workflows

DevOps

Operations & automation

Git & GitHub

Version control

Selected Awards

  • First Prize, Guangdong Provincial Computer Design Competition for College Students (2024)
  • Third Prize, National Computer Design Competition for College Students (2024)
  • First Place, National Statistical Modeling Competition for College Students, university level (2024)
  • Second Prize, National Final of the 18th National College Student Smart Car Competition (2023)
  • First Prize, South China Regional Competition of the 18th National College Student Smart Car Competition (2023)
  • Second Prize, Guangdong Provincial Mathematical Modeling Competition (2023)

Honors

  • Special Award, Ministry of Education Scholarship for Hong Kong, Macau, and Taiwan Students (2024)
  • Special Award, Ministry of Education Scholarship for Hong Kong, Macau, and Taiwan Students (2023)
  • Second Prize, Sun Yat-sen University Excellent Student Scholarship (2024)
  • Second Prize, Sun Yat-sen University Excellent Student Scholarship (2023)
  • Sun Yat-sen University Special Scholarship (2023)