LlamaIndex is the leading document agent and OCR platform

Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!

Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS ev…

A secure authentication module to manage user access in a Streamlit application.

Normalizing flows in PyTorch

OCTIS: Comparing Topic Models is Simple! A python package to optimize and evaluate topic models (accepted at EACL2021 demo track)

A library for prompt engineering and optimization (SAMMO = Structure-aware Multi-Objective Metaprompt Optimization)

Enhance your application with the ability to see and interact with humans using any RGB camera.

TopicGPT: A Prompt-Based Framework for Topic Modeling (NAACL'24)

🧱 Modula software package

[ECCV 2024] ShapeLLM: Universal 3D Object Understanding for Embodied Interaction

Python 3.7 version of David Barber's MATLAB BRMLtoolbox

The Official Repository of the Cryptonite Dataset

Natural Langugae Processing toolbox

Pytorch implementation of Localised Generative Flows

Repository for paper Decrypting Cryptic Crosswords

An efficient, massively parallel probabilistic programming language

ELT pipeline to move CAD data from Fusion360 to Neo4j graph database. This is a rewrite of the version used for my PhD.

Code to reproduce the experiments of my Approximate Manifold Sampling paper.

Code implementing Integrator Snippets, joint work with Christophe Andrieu and Chang Zhang

A game for the visually impaired, 2nd place MLH Hack the South 2019

Feature-rich codebase for pretrained language models research in PyTorch and 🤗

Normalizing flows in PyTorch

Code for Neural Spline Flows paper

UNDER DEVELOPMENT This project, Refactoring CAD POC, is designed to showcase a proof of concept (POC) for refactoring CAD models using CadQuery. It includes a library for CAD model refactoring, exa…