Zhaoqing Wang

Zhaoqing Wang (王兆卿)

Founding Research Scientist at PixVerse | Ph.D., The University of Sydney

I received my Ph.D. from the Sydney AI Centre (SAIC), The University of Sydney, where I was advised by two brilliant supervisors, Prof. Tongliang Liu and Prof. Mingming Gong.

I am currently a Founding Research Scientist at PixVerse, where I focus on large-scale pretraining and supervised finetuning of video generative models.

Before that, I was a research intern at Microsoft Research Asia (supervised by Wenlei Shi), OPPO Research Institute (supervised by Yandong Guo), Kuaishou Y-Tech (supervised by Qiang Li) and IDL of Baidu Research (supervised by Guodong Guo).

My research currently focuses on Multi-modal Understanding and Generation. Previously, I worked on Visual Representation Learning and Visual Perception.

News

  • 2026.03 One paper (When Safety Collides) accepted to CVPR 2026.
  • 2026.03 I completed my Ph.D. at the University of Sydney.
  • 2025.08 One paper (Aligning What Matters) accepted to NeurIPS 2025.
  • 2025.02 One paper (LaVin-DiT) accepted to CVPR 2025.
  • 2024.03 I joined PixVerse as a Founding Research Scientist.
  • 2024.01 One paper (IDEAL) accepted to ICLR 2024.
  • 2023.05 I started internship at Microsoft Research Asia.
  • 2023.03 One paper (BEV-SAN) accepted to CVPR 2023.
  • 2023.02 One paper (MosRep) accepted to ICLR 2023 (Spotlight).
  • 2022.08 One paper (RSA) accepted to NeurIPS 2022.
  • 2022.04 One paper (PointShift) accepted to IGARSS 2022 (Oral).
  • 2022.02 Two papers (CRIS, SetSim) accepted to CVPR 2022.
  • 2021.09 I started internship at OPPO Research Institute.
  • 2021.06 One paper (CaFM) accepted to ICCV 2021.
  • 2021.03 One paper (VecNet) accepted to IGARSS 2021.
  • 2021.02 I started internship at Kuaishou Y-Tech.
  • 2020.01 I started internship at IDL of Baidu Research.

Selected Publications

When Safety Collides

When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety Guidance

Yongli Xiang, Ziming Hong, Zhaoqing Wang, Xiangyu Zhao, Bo Han, Tongliang Liu

CVPR 2026

PDF
Aligning What Matters

Aligning What Matters: Masked Latent Adaptation for Text-to-Audio-Video Generation

Jiyang Zheng, Siqi Pan, Yu Yao, Zhaoqing Wang, Dadong Wang, Tongliang Liu

NeurIPS 2025

PDF
Lavin-DiT

Lavin-DiT: Large Vision Diffusion Transformer

Zhaoqing Wang, Xiaobo Xia, Runnan Chen, Dongdong Yu, Changhu Wang, Mingming Gong, Tongliang Liu

CVPR 2025

PDF
IDEAL

IDEAL: Influence-driven Selective Annotations Empower In-context Learners in Large Language Models

Shaokun Zhang, Xiaobo Xia, Zhaoqing Wang, Ling-Hao Chen, Jiale Liu, Qingyun Wu, Tongliang Liu

ICLR 2024

PDF
MosRep

Mosaic Representation Learning for Self-supervised Visual Pre-training

Zhaoqing Wang, Ziyu Chen, Yaqian Li, Yandong Guo, Jun Yu, Mingming Gong, Tongliang Liu

ICLR 2023 Spotlight

PDF
BEV-SAN

BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks

Xiaowei Chi, Jiaming Liu, Ming Lu, Rongyu Zhang, Zhaoqing Wang, Yandong Guo, Shanghang Zhang

CVPR 2023

PDF
RSA

RSA: Reducing Semantic Shift from Aggressive Augmentations for Self-supervised Learning

Yingbin Bai, Erkun Yang, Zhaoqing Wang, Yuxuan Du, Bo Han, Cheng Deng, Dadong Wang, Tongliang Liu

NeurIPS 2022

PDF
CRIS

CRIS: CLIP-Driven Referring Image Segmentation

Zhaoqing Wang, Yu Lu, Qiang Li, Xunqiang Tao, Yandong Guo, Mingming Gong, Tongliang Liu

CVPR 2022

PDF
SetSim

Exploring Set Similarity for Dense Self-supervised Representation Learning

Zhaoqing Wang, Qiang Li, Guoxin Zhang, Pengfei Wan, Wen Zheng, Nannan Wang, Mingming Gong, Tongliang Liu

CVPR 2022

PDF
CaFM

Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation

Jiaming Liu, Ming Lu, Kaixin Chen, Xiaoqi Li, Shizun Wang, Zhaoqing Wang, Enhua Wu, Yurong Chen, Chuang Zhang, Ming Wu

ICCV 2021

PDF
PointShift

PointShift: Point-wise Shift MLP for Pixel-level Cloud Type Classification

Yixiang Huang, Zhaoqing Wang, Xin Jiang, Ming Wu, Ming Wu, Chuang Zhang, Chuang Zhang, Jun Guo

IGARSS 2022 Oral

PDF
VecNet

Vecnet: A Spectral and Multi-Scale Spatial Fusion Deep Network for Pixel-Level Cloud Type Classification

Zhaoqing Wang, Xiangyu Kong, Zhanbei Cui, Ming Wu, Chuang Zhang, MingMing Gong, Tongliang Liu

IGARSS 2021

PDF
View Full List on Google Scholar

Mentoring & Professional Activities

Reviewer Service

CVPR, ICCV, ECCV, ICLR, NeurIPS, ICML, AAAI, IGARSS, ICPR, ACM Computing Surveys, T-PAMI, PR

My professional activities mainly center on multimodal generation, diffusion models, and visual understanding.