🎓 Master’s Researcher in Computer Science (Université de Montréal & Mila)
🔬 Focus: Uncertainty Estimation | Robotics | Probabilistic Modeling | Time Series Prediction | Generative Modelling | Spatial Awareness in VLMs
🌍 Currently seeking: Internship opportunities in AI/ML applied research, solving real-world problems with tools from deep learning and statistics.
📖 Thesis: Differentiable Harmonic Exponential Filters for SE(2) State Estimation
- Developing flexible non-parametric filters for modeling non-Gaussian uncertainty in robotics.
- Leveraging Lie group representations and Fourier transforms for efficient computation.
- Passionate about applied AI research with impact in real-world problems.
- Strong foundation in deep geometric methods, Bayesian methods, time series modelling, generative modelling, and computer vision.
- 3+ years of industry experience (Tesco, Bosch) in search systems & computer vision.
📄 Harmonic Exponential Filter for State Estimation on Lie Groups – Accepted at RAL 2025
📄 Differentiable Filters for Uncertainty Estimation – Thesis in progress
📄 Workshop: Uncertainty in Robotics (IROS 2025)
- Diff-HEF – Differentiable Bayes filter for uncertainty estimation
- SE(2) FFT – Custom Fourier transform implementation on SE(2) with PyTorch
- LLM_Finance_Predictor – Implemented RAG, LoRA fine-tuning, and explored system-level design for LLM-based applications
- AI Systems Project – Research & implementation on Vision-Language Models (VLMs), Vision-Language-Action Models (VLAs), and Model Predictive Control (MPC)
- MoodBoard AI – Hackathon project: visual diary + vibe tracker
Python PyTorch Hydra W&B
Computer Vision Fourier Analysis Time Series Forecasting
Robotics Generative Models Bayesian Methods Deep Geometric Learning
LLMs VLMs LoRA RAG
⭐️ “Building more robust AI systems means embracing uncertainty.”