Yuchi Wang

Yuchi Wang 王宇驰

AI PhD Student
MMLab, The Chinese University of Hong Kong
 wangyuchi369@gmail.com
GitHub Scholar LinkedIn Twitter

About Me

Hi! I am a first-year PhD student at MMLab, The Chinese University of Hong Kong, supervised by Prof. Hongsheng Li and Prof. Xiaogang Wang. Prior to this, I received my Master's degree from the AAIS, Peking University in 2025, where I was a member of Lanco Lab, Institute of Computational Linguistics (ICL), supervised by Prof. Xu Sun. I obtained my Bachelor's degree from the School of Data Science, Fudan University in 2022.

My research interests lie in multimodal learning, spanning from visual understanding to visual agents, especially for MLLMs. I am also interested in diffusion models and their application to visual generation.

News

  • [2026.05] Excited to join Qwen as a research intern.
  • [2026.04] Check out our new paper on reasoning-enhanced embedding models MMEmb-R1.
  • [2025.10] Release Techinical report for SAIL-Embedding, tailored for Douyin Recommendation.
  • [2025.08] Joining MMLab@CUHK as a PhD student.
  • [2025.08] One paper accepted by EMNLP 2025 – RICO.
  • [2025.07] One paper accepted by ACM MM 2025.
  • [2025.06] One paper accepted by ACL 2025.
  • [2025.02] One paper accepted by CVPR 2025 – VidTwin.
  • [2024.12] One paper accepted by AAAI 2025.
  • [2024.12] Two papers accepted by FinNLP@COLING 2025.
  • [2024.06] We release the InstructAvatar project page!
  • [2024.05] One paper accepted by ACL 2024 (Findings).
  • [2024.03] One paper accepted by NAACL 2024 – LaDiC.
  • [2024.01] One paper accepted by ICLR 2024 – GAIA.
  • [2023.10] We release the GAIA demo!
  • [2023.10] One paper accepted by FMDM@NeurIPS 2023.
  • [2023.05] Starting internship at Microsoft Research Asia ML Group.
  • [2022.09] Joining Lanco Lab, Peking University.

Education

The Chinese University of Hong Kong
AI PhD, MMLab
2025 – Expected 2029
Multimedia Lab  ·  Advisor: Prof. Hongsheng Li and Prof. Xiaogang Wang
Peking University
Master of Data Science, AAIS
2022 – 2025
Lanco Lab, ICL  ·  Advisor: Prof. Xu Sun
Fudan University
Bachelor of Science, School of Data Science
2018 – 2022
GPA Rank: 3 / 85

Selected Publications Full List →

Visual Understanding
embr1
MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control
Yuchi Wang, Haiyang Yu, Weikang Bian, Jiefeng Long, Xiao Liang, Chao Feng, Hongsheng Li
Preprint
Paper
SAIL
SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Model
Yuchi Wang (Core Contributor), et al
Technical Report
Paper
RICO
RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction
Yuchi Wang, Yishuo Cai, Shuhuai Ren, Sihan Yang, Linli Yao, Yuanxin Liu, Yuanxing Zhang, Pengfei Wan, Xu Sun
EMNLP 2025
Paper Code
ladic
LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?
Yuchi Wang*, Shuhuai Ren*, Rundong Gao, Linli Yao, Qingyan Guo, Kaikai An, Jianhong Bai, Xu Sun
NAACL 2024
Paper Code
Visual Generation
VidTwin
VidTwin: Video VAE with Decoupled Structure and Dynamics
Yuchi Wang, Junliang Guo, Xinyi Xie, Tianyu He, Xu Sun, Jiang Bian
CVPR 2025
Paper Code Project
InstructAvatar
InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation
Yuchi Wang, Junliang Guo, Jianhong Bai, Runyi Yu, Tianyu He, Xu Tan, Xu Sun, Jiang Bian
AAAI 2025
Paper Project
GAIA
GAIA: Zero-shot Talking Avatar Generation
Tianyu He*, Junliang Guo*, Runyi Yu*, Yuchi Wang*, Jialiang Zhu, Kaikai An, Leyi Li, Xu Tan, Chunyu Wang, Han Hu, HsiangTao Wu, Sheng Zhao, Jiang Bian
ICLR 2024
Paper Project

Internship

Alibaba Qwen
June 2026 – Now  ·  Hangzhou, China
Tongyi Qwen, Base Large Model Team, closely worked with Rongyao Fang and Shuai Bai
Topic: VL Agentic, AI Coding
ByteDance Douyin
June 2025 – April 2026  ·  Beijing/Shenzhen, China
Douyin (抖音) Content Group, Base Multimodal Model Team, closely worked with Dingkang Yang, Haiyang Yu and Xiao Liang
Topic: Multimodal Representation, MLLM, Recommendation
Kuaishou Kling
November 2024 – May 2025  ·  Beijing, China
Kling (可灵) AI, Multimodal Understanding Group, closely worked with Yuanxing Zhang
Topic: Multimodal Understanding, Image Captioning
Microsoft Research Asia (MSRA)
May 2023 – August 2024  ·  Beijing, China
ML (Machine Learning) Group, closely worked with Junliang Guo, Tianyu He and Xu Tan
Topic: Multimodal Generative Learning, Talking Avatar, Video VAE

Academic Service

Conference/Journal Reviewer
NeurIPS 2026 PR CVPR 2026 ACL 2025, 2026 EMNLP 2025, 2026 ARR Oct 2025, Mar 2026 AAAI 2025
Teaching Assistant
  • PKU Class 2024 Spring: Introduction to Large Language Models Peking University · 2024
  • ELEG5760: Machine Learning for Multimedia Applications CUHK · 2025
  • AIMS5710: Deep Learning Fundamentals and Theories CUHK · 2026
×