Stars
Because `model.fit()` isn't an explanation
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
This project captures webcam input, detects a hand using MediaPipe, and draws a white, mechanical-style kinematic HUD over the hand (palm-centered radial UI, finger bones, rotation readout, small 3…
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
POSNoise: An Effective Countermeasure Against Topic Biases in Authorship Analysis
Examples of playing with Circle Loss from the paper "Circle Loss: A Unified Perspective of Pair Similarity Optimization", CVPR 2020.
A graphical editor for directed graphs used for Abstract Meaning Representation (AMR)
Compendium of free ML reading resources
Python Implementation of Weighted Generalized Canonical Correlation Analysis
Repo for the paper "Detecting Logical Fallacies: From Quiz to Climate Change News" (2021)
This is my repository for my Masterthesis about Hatespeech Detection in a Politial Discourse in Germany.
Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.
Universal and Transferable Attacks on Aligned Language Models
Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models
Teaching Models to Express Their Uncertainty in Words
SacreROUGE is a library dedicated to the use and development of text generation evaluation metrics with an emphasis on summarization.
Carefully curated resource links for data science in one place
A package for handy processing of semantic graphs such as AMR, with a special focus on standardized evaluation
Interpretability for sequence generation models 🐛 🔍
Exercises for the Deep Learning textbook at www.deeplearningbook.org
Tips and tricks for working with Large Language Models like OpenAI's GPT-4.
A curated list of Best Artificial Intelligence Resources
Interact with your documents using the power of GPT, 100% privately, no data leaks
PyTorch Tutorial for Deep Learning Researchers