Kirill Bobin's starred repositories
LightAutoML
Fast and customizable framework for automatic ML model creation (AutoML)
InvokeAI
InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products.
awesome-implicit-representations
A curated list of resources on implicit neural representations.
faq-slack-bot
LLM-powered RAG Question Answering Slack bot for DataTalksClub Zoomcamps
invest-bot
Trading bot based on Tinkoff Invest gRPC API
CNN-SINDy-MLROM
Sample codes of CNN-SINDy based reduced-order modeling for fluid flows by Fukami et al., JFM 2021.
MEDIUM_NoteBook
Repository containing notebooks of my posts on Medium
cvessentials
Tutorial Series (60 hour course): Essentials of computer vision
DL-ROM-Meth
Source code for deep learning-based reduced order models for nonlinear time-dependent parametrized PDEs. Available on doi.org/10.1007/s10915-021-01462-7.
vecsim-demo
Explore vector similarity in Redis
LSTM_ROM_Arxiv
A Deep Learning based Approach to Reduced Order Modeling for Turbulent Flow Control using LSTM Neural Networks. arXiv:1804.09269
recommenders
Best Practices on Recommendation Systems
sentence-transformers
Multilingual Sentence & Image Embeddings with BERT
IK-3LinkManipulator-NN
Solving the inverse kinematics problem of a 3 Link Planar Manipulator using neural networks.
Summer2025-Internships
Collection of Summer 2025 tech internships!
Building-a-Content-Based-Movie-Recommender-System
Applying Content-Based filtering and Matrix-Algebra to build a Movie-Recommender-System in Pandas
end-to-end-cv-mlops-project
The end-to-end computer vision (object detection) project with MLOps, including a model training pipeline/workflow, an API, and an application for detecting and counting house sparrows in a photo.
Physics-Informed-Deep-Learning-Solid-and-Fluid-Mechanics
Using Physics-Informed Deep Learning (PIDL) techniques (W-PINNs-DE & W-PINNs) to solve forward and inverse hydrodynamic shock-tube problems and plane stress linear elasticity boundary value problems
PINNpapers
Must-read Papers on Physics-Informed Neural Networks.
cs-video-courses
List of Computer Science courses with video lectures.