Hello, I'm Wassim Swaileh
PhD in Computer Science with 8+ years post-PhD experience building production AI models and training pipelines for multimodal and autonomous systems. Expertise in VLMs, video understanding, video generation, and robotics.
8+
Years Experience
CVPR
Tier-1 Conference
15+
Publications
About Me
I am an AI Engineer with a PhD in Computer Science, specializing in building production AI models and training pipelines for multimodal and autonomous systems.
My extensive experience spans several cutting-edge domains, including:
- Video Understanding & Long Video Analysis (ReWind - CVPR 2025)
- Video Generation using VLMs and Diffusion Architectures
- Vision-Language Models (LLaVA, CLIP, QwenVL, LayoutVLM)
- Vision-Language-Action (VLA) Models
- 4D LiDAR Generation & Autonomous Systems
- Generative Diffusion Models
- 3D Scene Reconstruction
- Kinematic Time Series Analysis
I currently work at Huawei Suomi Finland Research Center as a Senior Researcher in Multimodal AI, where I build and ship production-scale video generation models and co-developed the ReWind model for long video understanding (CVPR 2025).
Current Position
Senior Researcher - Multimodal AI
Huawei Suomi Finland Research Center
2023 - PresentHelsinki, Finland
Research Areas
Video Understanding
Long video analysis with instructed learnable memory (ReWind - CVPR 2025)
Video Generation
Production-scale video generation using VLMs and diffusion architectures
Vision-Language Models
LLaVA, CLIP, QwenVL, LayoutVLM for multimodal perception
Autonomous Systems
4D LiDAR generation, sensor fusion, and 3D scene reconstruction
Generative Diffusion
Advanced generative AI for creating and manipulating visual content
Kinematic Analysis
Time series analysis for motion and trajectory reconstruction
Featured Publications
Research Impact
15+
Publications
CVPR
Tier-1 Conference
Patent
Submitted
8+
Years Experience
Let's Connect
Interested in collaboration or want to learn more about my research?