Skip to content
View YakovM93's full-sized avatar
2 followers · 6 following
  • Israel - Tel Aviv

Block or report YakovM93

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
YakovM93/README.md

👋 Hi, I'm Yakov Mishayev

🎓 About Me

  • 🔬 Master's Student in Applied Mathematics at Technion – Israel Institute of Technology
  • 📚 Research Focus: Graph Neural Networks and solving real-world oversquashing problems in Message Passing Neural Networks
  • 🎯 Career Goal: Transitioning from academia to industry as an Algorithm engineer

👀 Professional Interests

Applied AI, Graph Neural Networks, Computer Vision & 3D Vision, Computer Graphics, Numerical Algorithms, Digital Signal Processing, Deep Learning Engineering

💻 Technical Skills

  • Languages: Python, SQL, Git, MATLAB
  • ML/DL Frameworks: PyTorch, PyTorch Geometric, PyTorch Lightning, scikit-learn, OpenCV
  • 3D/Graphics: Point cloud processing, 3D reconstruction, geometric deep learning
  • Numerical Computing: NumPy, SciPy, numerical optimization, linear algebra
  • Engineering: Docker, CUDA, distributed training (DDP), model optimization
  • Tools: Weights & Biases, Jupyter, VS Code, Linux
  • Specialization: GNN architectures, Transformer models, computer vision, 3D vision, DSP

🏆 Key Achievements

  • 🎤 Oral Presentation at The Fourth Learning on Graphs Conference (LoG 2025) - Paper
  • 📝 Paper accepted: "Short-Range Oversquashing in Message Passing Neural Networks"

📫 Let's Connect!

"Bridging cutting-edge research with practical AI solutions"

Pinned Loading

  1. deep-learning-on-accelerator-mini-project deep-learning-on-accelerator-mini-project Public

    Mini project of the course and filnal assigmnent- Deep learning on accelerator

    Python

  2. Short-Range-Oversquashing Short-Range-Oversquashing Public

    In this work, we demonstrate that oversquashing is not limited to long-range tasks, but can also arise in short-range problems.

    Jupyter Notebook 2

  3. Bridging-the-Gap-Between-the-Scattering-Transform-and-Convolutional-Neural-Network Bridging-the-Gap-Between-the-Scattering-Transform-and-Convolutional-Neural-Network Public

    This project is an experiment designed to "bridge the gap" between the Wavelet Scattering Transform (WST) and a standard Convolutional Neural Network (CNN). It uses the Kymatio library to test how …

    Jupyter Notebook

  4. Gaussian_Avatar_Caricaturization Gaussian_Avatar_Caricaturization Public

    This is a geometry-based facial caricaturization pipeline that creates caricatures of human faces purely through mesh deformation, without any appearance/texture modeling.

    Python