Minimal, lightweight JAX implementations of popular models.

Open-Source Frontier Voice AI

Real Time 3-D Pose Estimation for Mice with Only 2-D Annotation Via Data Synthesis

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds (CVPR 2023)

Automatically update function definitions in a running Julia session

记录对nerf各种算法、应用、软件等等的学习过程

A multi-platform proxy client based on ClashMeta,simple and easy to use, open-source and ad-free.

Official implementation for the paper: "Real-Time Inverse Kinematics for Generating Multi-Constrained Movements of Virtual Human Characters"

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Awesome papers for markerless animal motion capture and 3D reconstruction.

SimpleClick: Interactive Image Segmentation with Simple Vision Transformers (ICCV 2023)

Hierarchical Reasoning Model Official Release

Code for the paper, Temporal Action Localization with Enhanced Instant Discriminability

A lifting transformer used to generate 3D DeepLabCut estimates for an adult mouse forelimb

Digital Mind Extension

srun 深澜认证登录，超轻量、多平台，支持多拨、自动探测IP、指定网卡

TradingAgents: Multi-Agents LLM Financial Trading Framework

The AI to keep you focused 😈

Train your AI self, amplify you, bridge the world

fit smpl parameters model using 3D joints

一分钟自建zerotier-planet

Solving SMPL/MANO parameters from keypoint coordinates.

Demo code for CAPTURE and DANNCE

An AI Hedge Fund Team

Continuous Thought Machines, because thought takes time and reasoning is a process.

I made my AI think harder by making it argue with itself repeatedly. It works stupidly well.

A label tool for video segment