Name: Can Xu
Type: User
Company: Microsoft
Bio: Senior Researcher at Microsoft. Creator of Evol-Instruct and WizardLM Family: WizardLM, WizardCoder and WizardMath.
Project: https://twitter.com/WizardLM_AI
Twitter: CanXu20
Location: Seattle, U.S.A.
Can Xu's Projects
A paper list of Conversational Recommendation System, Information-Seeking Dialog System, Recommender Dialog System and related areas.
Dance Revolution: Long Sequence Dance Generation with Music via Curriculum Learning
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"
Tensorflow implementation for IOI model
Open Academic Research on Improving LLaMA to SOTA LLM
PyTorch implementation for ACL 2021 paper "Maria: A Visual Experience Powered Conversational Agent".
Tensorflow implementation for MRFN in Retrieval-based Chatbots
the Pytorch implementation for our EMNLP 2021 paper "Learning Neural Templates for Recommender Dialogue System"
使用recursive auto encoder做复述检测
Source code for ACL 2022 Paper "Prompt-based Data Augmentation for Low-Resource NLU Tasks"
ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training https://arxiv.org/pdf/2001.04063.pdf
Code for EMNLP2019 paper "Low-Resource Response Generation with Template Prior"
Code and documentation to train Stanford's Alpaca models, and generate the data.
The code for ``STYLEDGPT: Stylized Response Generation with Pre-trained LanguageModels'' (Findings of EMNLP2020))
UniLM - Unified Language Model Pre-training / Pre-training for NLP and Beyond
LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath
Yahoo! news dataset of DeepCom (EMNLP2019)