A full-featured open-source Wi-Fi fuzzer

Pivotal Token Search

A Deep Learning framework that analyses Windows PE files to detect malicious Softwares.

Python Implementation of Zero Shot Learning Algorithms (ALE, DeViSE, ESZSL, SAE, SJE) under ZSLGBU protocol

Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)

Sparse Embedding Compression for Scalable Retrieval in Recommender Systems

Multi-Layer Sparse Autoencoders (ICLR 2025)

Official Triton kernels for TopK and HierarchicalTopK Sparse Autoencoder decoders.

Sparse Autoencoders (SAE) vs CLIP fine-tuning fun.

Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the paper "Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small"

A flexible computer-vision pipeline that connects to video source, detects, tracks and geo-maps objects.

🚢 Simple implementations of various popular Deep Reinforcement Learning algorithms using TensorFlow2

autonomous drone flight and payload drop on target

FastSAE: Adopt seamlessly, train fast

A structured guide to learning ADAS systems, sensors, AI applications, and modern vehicle safety features with hands-on Python exercises.

SAE component that tracks objects via multiple video frames.

Data model for Starwit's Awareness Engine

We use stacked Autoencoders to build a powerfull recommender system for movies.

Reproducible case study of pitfalls in contrastive SAE discovery and steering for "consciousness" features (GemmaScope SAEs, Gemma 3 4B/12B): reconstruction confound, delta-steering fix, matched controls, and false-positive scaling law vs dataset size.