A foundational researcher pursuing a Computer Science BSc at the University of London, with a focus on AI, Machine Learning, Data Science, and Deep Learning. Passionate about research, reproducibility, and high‑quality open‑source implementations.
A context-conditioned Denoising Diffusion Probabilistic Model (DDPM) for generating and analyzing satellite cloud imagery. Trained on a NASA dataset containing high-resolution images with associated timestamps, wind-speed annotations, and learned embeddings. Supports conditional generation (e.g., given wind speed or timestamp), robustness experiments, and rapid prototyping on small 16×16 images with straightforward scaling to larger resolutions.
Gitlawb/openclaude — Security
Replaced plaintext OAuth token storage with native secure vault integrations for Linux and Windows, including a graceful file-based fallback and scanner-friendly code refactoring.
Gitlawb/openclaude — MCP / Tooling
Finalized the MCP entrypoint by implementing strict Ajv schema validation, tool re-exposure, and structured outputs, alongside robust test coverage and CLI bug fixes.