LiteRT continues the legacy of TensorFlow Lite as the trusted, high-performance runtime for on-device AI. Now with LiteRT Next, we're expanding our vision with a new generation of APIs designed for…

The best ChatGPT that $100 can buy.

A web-based collaborative LaTeX editor

The TypeScript AI agent framework. ⚡ Assistants, RAG, observability. Supports any LLM: GPT-4, Claude, Gemini, Llama.

Evolution Strategies in JAX 🦎

RL Environments in JAX 🌍

Code for BLT research paper

Roi extraction and manipulation in python

Links to works on deep learning algorithms for physics problems, TUM-I15 and beyond

Learning Deep Representations of Data Distributions

Practical marketing resources to get the first 10/100/1000 users for your SaaS/App/Startup

Prompt Orchestration Markup Language

A TypeScript chess library for chess move generation/validation, piece placement/movement, and check/checkmate/draw detection

Stockfish NNUE (Chess evaluation) trainer in Pytorch

Fast State-of-the-Art Static Embeddings

Frontier Open-Source Text-to-Speech

optimizer & lr scheduler & loss function collections in PyTorch

Felafax is building AI infra for non-NVIDIA GPUs

Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.

Bringing BERT into modernity via both architecture changes and scaling

Links to works on deep learning algorithms for physics problems, TUM-I15 and beyond

Differentiable, Hardware Accelerated, Molecular Dynamics

PDE-Transformer is a neural network architecture designed to efficiently process and predict the evolution of physical systems described by partial differential equations.

A PyTorch-based Speech Toolkit

Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation

Code for the paper Universal Physics Transformers

PDEBench: An Extensive Benchmark for Scientific Machine Learning