Ruochen Xu

Ruochen Xu

xu_ruochen@hzlh.com

About

I am an AI researcher specializing in large language models, multimodal AI, and natural language processing. With extensive experience at Microsoft AI and now at Om AI, I focus on developing cutting-edge AI technologies that bridge language technologies and practical applications. My research interests span multilingual systems, multimodal language model, and agent frameworks. I received my Ph.D. from Language Technologies Institute, Carnegie Mellon University, where I was advised by Professor Yiming Yang.

Work Experience

Principal Scientist - Om AI

May 2024 - Present

  • Multimodal Large Language Model
  • Language Agent Framework
  • Agent as A Service

Senior Researcher - Microsoft AI

Sep 2019 - Apr 2024

  • Large Language Model (LLM) Pretrain
  • LLM Evaluation
  • Language Understanding and Reasoning
  • Multilingual and Multimodal

Education

Carnegie Mellon University

August 2016 - August 2019

Ph.D. candidate in Language Technologies, School of Computer Science

Research advisor: Professor Yiming Yang

Carnegie Mellon University

August 2014 - August 2016

M.S. in Language Technologies, School of Computer Science

Research advisor: Professor Yiming Yang

Tsinghua University

August 2010 - July 2014

B.S. in Electronic Engineering (with honors)

Publications

Selected Publications

  • G-Eval: NLG Evaluation Using GPT-4 with Better Human Alignment (875 citations)

    Y Liu, D Iter, Y Xu, S Wang, R Xu, C Zhu

    arXiv 2023

  • Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners (126 citations)

    Z Wang, M Li, R Xu, L Zhou, J Lei, X Lin, S Wang, et al.

    NeurIPS 2022

  • A Hierarchical Network for Abstractive Meeting Summarization with Cross-Domain Pretraining (171 citations)

    C Zhu, R Xu, M Zeng, X Huang

    EMNLP Findings 2020

  • Enhancing Factual Consistency of Abstractive Summarization (211 citations)

    C Zhu, W Hinthorn, R Xu, et al.

    NAACL 2021

  • CLIP-Event: Connecting Text and Images with Event Structures (139 citations)

    M Li, R Xu, S Wang, L Zhou, et al.

    CVPR 2022

View full publication list →