機械学習 · GitHub

OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.

SPLATNet: Sparse Lattice Networks for Point Cloud Processing (CVPR2018)

ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.

Our first fully AI generated deep learning system

Abstract visualization of biological neural network

Implementation of Everybody Dance Now by pytorch

Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening

AutoKernel 是一个简单易用，低门槛的自动算子优化工具，提高深度学习算法部署效率。

Bayesian Deep Learning Benchmarks

Real-time people Multitracker using YOLO v2 and deep_sort with tensorflow

This repository provides the code examples for the corresponding blog posts. In case you have questions, feel free to contact me directly.

Two-timescale threshold flips (TTF): training and converting ternary {-1,0,1} LLMs without full-precision master weights. ~1 byte of optimizer state per weight; 23B trains on a 16 GB GPU, Qwen3.8-27B converted and recovered on one 24 GB card.

A TensorFlow based wake word detection training framework using synthetic sample generation suitable for certain microcontrollers.

PyTorch Implementation of "Resource Efficient 3D Convolutional Neural Networks", codes and pretrained models.

FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion

Faceswap with Pytorch or DeepFake with Pytorch

A model that predicts the punctuation of English, Italian, French and German texts.

🐋 Simple implementations of various popular Deep Reinforcement Learning algorithms using TensorFlow2

MLOps simplified. One-stop AI delivery platform, all the features you need.