xf-zhao
Follow
Stars
VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
The official PyTorch implementation of the paper "Human Motion Diffusion Model"
Self-Supervised Alignment with Mutual Information
Official webpage for "Agentic Skill Discovery"
This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.
Official implementation of Zero-Hero paper
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Linux virtual machines, with a focus on running containers
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
Minimal scripts to launch a flask server for llama 3
A habit tracker app which treats your goals like a Role Playing Game.
Train transformer language models with reinforcement learning.
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
Official inference library for Mistral models
Reference implementation for DPO (Direct Preference Optimization)
A V2Ray client for Android, support Xray core and v2fly core
An official implementation of paper: Causal State Distillation for Explainable Reinforcement Learning
A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/
Fast and simple implementation of RL algorithms, designed to run fully on GPU.
🔮 SuperDuper: Bring AI to your database! Build, deploy and manage any AI application directly with your existing data infrastructure, without moving your data. Including streaming inference, scalab…
Xufeng Zhao, University of Hamburg, Ph.D student, interested in Robotics, Reinforcement Learning, Large Language Models.
Unified framework for robot learning built on NVIDIA Isaac Sim
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.