A survey investigating the concept space prior in Vision and Language models

🪶 Neural premise selection for Agda.

For the now-deprecated e75 and e150 cards

🎓 My PhD thesis.

Standalone Aevov System (experimental and mostly for learning)

The project aims to design and evaluate machine learning models that incorporate domain-specific knowledge for improved analysis of hyperspectral data.

Experiment code for dissertation report "Improving Classification using Neuro-Symbolic Algorithms"

A Python/Prolog project for generating and validating sandwich recipes using LLMs, semantic embeddings, and logic programming. Demonstrates a simple neurosymbolic pipeline.

Aevov's NeuroSymbolic architecture for Web3

Extensible Cognitive Hybrid Intelligence for Deductive Neural Assistance. A neurosymbolic theorem proving platform that transforms Quill (Agda-only neural solver) into a universal multi-prover system with aspect tagging, OpenCyc integration, and DeepProbLog probabilistic logic.

⌛ [WIP] Differentiable temporal logics in PyTorch.

Web 3 Aevov ML System in Go which is an extension of https://github.com/aevov/Aevov-Web3/tree/main

The Web's NeuroSymbolic Network (pending archival - visit GitHub.com/aevov/Aevov-web3 to view our latest progress)

The infrastructure behind the Scallop website.

This repo presents codes that allows user to run localized Ollama based Reasoning LLM to integrate with neuro-symbolic abductive reasoning for fault diagnosis

TinyNS: Platform-Aware Neurosymbolic Auto Tiny Machine Learning

PyTorch implementation for the Neuro-Symbolic Concept Learner (NS-CL).

Mythral Neurosymbolic AI

A comprehensive implementation of a Neurosymbolic framework for Visual Question Answering (VQA) on the CLEVR dataset. This project translates natural language questions into symbolic programs using three different learning strategies: Supervised (LSTM & Transformer), Reinforcement Learning (REINFORCE), and In-Context Learning (LLM).

Sparse Circuits on the GPU (ICLR2025)