Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

"RAG-Anything: All-in-One RAG Framework"

Fast and Accurate ML in 3 Lines of Code

PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

Solve Visual Understanding with Reinforced VLMs

⚡ TabPFN: Foundation Model for Tabular Data ⚡

Scalable and user friendly neural 🧠 forecasting algorithms.

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2509.03505

[AAAI-23 Oral] Official implementation of the paper "Are Transformers Effective for Time Series Forecasting?"

mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation

Framework for Easily Invertible Architectures

Edit Banana: A framework for converting statistical formats into editable.

An unified model that seamlessly integrates multimodal understanding, text-to-image generation, and image editing within a single powerful framework.

Towards Generalized and Efficient Blackbox Optimization System/Package (KDD 2021 & JMLR 2024)

VisioFirm: Cross-Platform AI-assisted Annotation Tool for Computer Vision

Python module for creating GDSII stream files, usually CAD layouts.

ikan: many kan variants for every body

Robust Molecular Structure Recognition with Image-to-Graph Generation

Deep Reinforcement Learning of Analog Circuit Designs

Python (3.5) tool to convert .asc files into circuiTikz graphics

A versatile generative model capable of designing topologies for wide range of analog circuits.

Code release for Representation Subspace Distance for Domain Adaptation Regression (ICML 2021)