Portrait of Zhuo Li

Zhuo Li

Tech Lead at ByteDance

I am a Tech Lead at ByteDance, working on intelligent creation and video generation. Previously, I was a Research Engineer at Tencent (WeChat). I received my Master's degree from the Institute of Computing Technology, Chinese Academy of Sciences, and my Bachelor's degree in Computer Science from Northwestern Polytechnical University.

My research interests include video generation, multimodal learning, and physically plausible human motion, with an interest in embodied AI.

Publications & Research

ICLR · SubmittedVideo generation · RGBA

UniRGBA: Unifying RGB and Alpha in Pretrained Video Diffusion Models

Lei Xu, Zhuo Li†, Yongyi Jin, Aoyu Wang

† corresponding author

UniRGBA framework unifying RGB and alpha in pretrained video diffusion models

A unified framework that extends a causal video VAE to four-channel RGBA via zero-initialized channel expansion and selective layer unfreezing. Standard DoRA adapts a pretrained DiT to the unified latent space without alpha-specific architectural changes.

NeurIPS 2026PosterMotion generation

AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling

Yiheng Li*, Zhuo Li*‡, Ruibing Hou†, Yingjie Chen, Hong Chang, Hao Liu, Shiguang Shan

* equal contribution · † corresponding author · ‡ project leader

AnyMo framework for motion generation conditioned on multiple modalities

OmniHuMo, a large-scale multimodal motion dataset, and a unified framework combining a Residual FSQ motion tokenizer with masked modeling for any-modality conditional motion generation. Deployed in WeChat multimodal generation business.

2023

2022

2021

2020

Honors & Awards

  • 1st · Argoverse Stereo Competition

    CVPR 2021 Workshop

  • Outstanding Undergraduate Student

    Northwestern Polytechnical University, China

  • National Scholarship

    Top 1% in Northwestern Polytechnical University

Academic Services

Reviewer for NeurIPS, AAAI, CVPR, ICCV, ECCV, and other journals and conferences.