Demos

These are some of the open-source demos we built to make our research more readily available for developers and researchers.

Screenshot of NeuralOS: Towards Simulating Operating Systems via Neural Generative Models
NeuralOS: Towards Simulating Operating Systems via Neural Generative Models
An operating system entirely powered by neural networks.
demo code
Screenshot of Predicting Multiplication without Intermediate Reasoning Steps
Predicting Multiplication without Intermediate Reasoning Steps
Directly predict the product of 20-digit multiplication without chain-of-thought reasoning, using a 12-layer GPT-2.
demo code
Screenshot of Solving Grade School Math Problems without Intermediate Reasoning Steps
Solving Grade School Math Problems without Intermediate Reasoning Steps
Directly predict the answer to grade school math problems without chain-of-thought reasoning at 52% accuracy.
demo code
Screenshot of Real-Time Visualization of WildChat Usage
Real-Time Visualization of WildChat Usage
A visualization of real-time user interactions with WildChat chatbots.
demo
Screenshot of WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild
WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild
An interactive tool for searching and visualizing million-scale chat datasets such as WildChat and LMSYS-Chat.
demo data
Screenshot of AK Hugging Face Paper Selection Predictor
AK Hugging Face Paper Selection Predictor
Predict if @_akhaliq will select a paper into Hugging Face papers based on its title, authors, and abstract.
demo code data models
Screenshot of OpenAI Watch
OpenAI Watch
Monitoring the consistency of GPT-4 under greedy decoding (T=0) with a web-based application that commands GPT-4 to draw a unicorn every hour.
demo data
Screenshot of Markup-to-Image Diffusion Models with Scheduled Sampling
Markup-to-Image Diffusion Models with Scheduled Sampling
A learning-based system to compile presentational markup, such as LaTeX, into corresponding images.
demo code paper models
Screenshot of Neural Linguistic Steganography
Neural Linguistic Steganography
Hide secret messages in fluent texts using arithmetic coding and strong neural models.
demo code paper
Screenshot of OpenNMT
OpenNMT
A full service open-source neural machine translation system. Originally developed in Lua with Systran, since ported to PyTorch and TensorFlow and maintained externally.
code paper
Screenshot of Image-to-Markup
Image-to-Markup
A learning-based system to decompile an image into presentational markup. For example, we can infer the LaTeX or HTML source from a rendered image.
demo code paper data models
Screenshot of Cascaded Text Generation with Markov Transformers
Cascaded Text Generation with Markov Transformers
A parallel, fast, autoregressive, and accurate text generation algorithm using high-order Conditional Random Fields (CRFs).
code paper