Progyan

gp-zoo. A repository with implementations of major papers on Gaussian Process regression models, implemented from scratch in Python, notably including Stochastic Variational Gaussian Processes.

pineapple-emulator. A C++ based emulator for the CPU of the Nintendo Entertainment System that ran on the Ricoh 2A03, with limited PPU capabilities.

SDFNet. Work on the research paper under Prof. Shanmuganathan Raman on visual synthesis and representation through Signed Distance Functions (SDFs).

nanodiff. Clean, fast, and parallel discrete text diffusion.

coinframe. Library for analysing, backtesting, and presenting cryptocurrency portfolios reliably, and with very little code.

gossip. Gossip is a beautiful tree-walk interpreter (that now also supports bytecode!) that allows for beautiful visualizations for abstract syntax trees, and is built to support beginners starting a course on Compiler Design.

interfere. Can you interfere with a model's understanding of the world?

cerebruh. A Windows-based python application aimed at putting Wikipedia at the tip of your finger. One finger.

macOS-OpenGL. Template repository for working on openGL with macOS.

climate-gnn. A temporal GNN based model for climate data.

N-body-simulation. The scripts in vPython for visualization n-body simulations through iterative, numerical analysis, especially Euler-Crömer techniques.

no-imagegen. Recursive Denoising Neural Operators for superfast image-generation.

NanoGPT-MoE. A compact Transformer model for character-level generation with Mixture-of-Experts, Rotary Attention, and F-gram contextual augmentation.

torch-tangent. Composable, differentiable, and simple finite-width and infinite-width NTKs for Gaussian Processes, with cross-functionality with GPyTorch.

TemporalGCN. Spatio-Temporal Inferencing frameworks.

codeMixedTextToolkit. Constructing an open-source library like NLTK and spaCy for efficient processing of code-mixed text, models, and datasets under Prof. Mayank Singh.

velocity. Position and momentum.

wimpyML. Python library with wimpy implementations of common ML algorithms that I wrote in the process of learning them.