StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

[NeurIPS 2022] Denoising Diffusion Restoration Models -- Official Code Repository

EUSIPCO2024: Ultrasound Imaging based on the Variance of a Diffusion Restoration Model

Learn about designing and training LLM Agents from Colab Notebooks

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

EB1A Full Application - I-140 and I-485

EB1A DIY Collection

Codes for paper: Evaluating the Utilities of Large Language Models in Single-cell Data Analysis.

A unifying representation of single cell expression profiles that quantifies similarity between expression states and generalizes to represent new studies without additional training.

A React Dashboard Admin Template built on top of Amplify UI.

Solidity, the Smart Contract Programming Language

A simple pip-installable Python tool to generate your own HTML citation world map from your Google Scholar ID.

润学全球官方指定GITHUB，整理润学宗旨、纲领、理论和各类润之实例；解决为什么润，润去哪里，怎么润三大问题； 并成为新中国人的核心宗教，核心信念。

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Paper list for Personal LLM Agents

Lab Materials for MIT 6.S191: Introduction to Deep Learning

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Instant voice cloning by MIT and MyShell. Audio foundation model.

Subset selection / data pruning for weak supervision

[TMLR 2024] Efficient Large Language Models: A Survey

Alzheimer's dementia classification and MMSE score regression