Xiaodong Wang's Projects
a modify version of 3d-photo-inpainting
Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ
A collection of AWESOME things about domian adaptation
Paper-Reading about the Pre-training
clean code for BLIP
Domian Adaptation via Diffusion Models
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
This is a simple yet effective framework for Domain Adaptation.
Emu: An Open Multimodal Generalist
[ICCV 2023 Oral] "FateZero: Fusing Attentions for Zero-shot Text-based Video Editing"
a Baike Chat robot using GPT2
Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch
A Generalizable World Model for Autonomous Driving
Face Analysis Project on MXNet
使用Java开发的图书管理系统,读者可以注册登录,登录时会判断账号类型再分别跳到各自对应的页面,读者可以查找,借阅,还书,查看历史借阅记录,修改个人资料,密码等,管理员可以修改添加图书,修改添加读者,修改添加分类,管理借阅信息等等
High-Resolution Image Synthesis with Latent Diffusion Models
Released code of "Revisiting Unsupervised Domain Adaptation Models: a Smoothness Perspective"
Open Academic Research on Improving LLaMA to SOTA LLM
[NeurIPS 2023 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.
This is a logistics robot competition project. It will be updated anytime.
This is an Android based on Java language. It implements the function of word book.
This project aim to reproducing Sora (Open AI T2V model), but we only have limited resource. We deeply wish the all open source community can contribute to this project.