Curriculum Vitae

Chen Zhiyuan

AI Researcher Computer Vision & Multimodal Learning

Ant Group (Alipay)

Profile

I am an AI researcher at Ant Group working on computer vision and multimodal learning. My research spans human-centric generative modeling, digital humans, 2D/3D visual understanding, and multimodal foundation models. I received both my B.E. and M.S. from Beihang University, where I conducted research at the IRIP Laboratory.

Current
Ant Group
Education
Beihang University
Focus
Vision & Multimodal AI

Research Interests

  • Human-Centric Generative Modeling Digital humans, portrait animation, and controllable visual synthesis.
  • Multimodal Foundation Models Visual understanding, generation, editing, and instruction alignment.
  • 2D/3D Computer Vision Face modeling, person analysis, biometrics, and geometric representations.
  • Embodied Intelligence Perception and interaction for agents operating in the physical world.

Professional Experience

May 2019 — Present

AI Researcher

Ant Group (Alipay)

Research and development in computer vision, multimodal generation, and visual editing, spanning model design, instruction alignment, data curation, benchmark design, and production quality.

Education

B.E. · Jun 2017

Computer Science and Engineering

Beihang University

Selected Publications

EchoMimic: Lifelike Audio-Driven Portrait Animations Through Editable Landmark Conditions

Chen Zhiyuan*, Cao Jiajiong*, Chen Zhiquan, Li Yuming, Ma Chenguang.

AAAI 2025CCF-A

Project Paper Code

FaceVerse: A Fine-Grained and Detail-Controllable 3D Face Morphable Model From a Hybrid Dataset

Wang Lizhen, Chen Zhiyuan, Yu Tao, Ma Chenguang, Li Liang, Liu Yebin.

CVPR 2022CCF-A

Paper Code

Video Person Re-Identification Using Attribute-Enhanced Features

Chai Tianrui, Chen Zhiyuan, Li Annan, Chen Jiaxin, Mei Xinyu, Wang Yunhong.

IEEE TCSVT 2022CCF-B

Paper Code

A Temporal Attentive Approach for Video-Based Pedestrian Attribute Recognition

Chen Zhiyuan, Li Annan, Wang Yunhong.

PRCV 2019Best Student Paper

Paper Code

BUAA-PRO: A Tracking Dataset With Pixel-Level Annotation

Li Annan, Chen Zhiyuan, Wang Yunhong.

BMVC 2018CCF-C

Paper

* Equal contribution.

Beyond Research

  • 3D printing
  • Quantitative trading
  • Literature and history

tag:

    缺失模块。
    1、请确保node版本大于6.2
    2、在博客根目录（注意不是yilia根目录）执行以下命令：
    npm i hexo-generator-json-content --save

    3、在根目录_config.yml里添加配置： 

      jsonContent:
    meta: false
    pages: false
    posts:
      title: true
      date: true
      path: true
      text: false
      raw: false
      content: false
      slug: false
      updated: false
      comments: false
      link: false
      permalink: false
      excerpt: false
      categories: false
      tags: true