☕️
Yanning Zhou
Researcher
XPENG Robotics.
About Me
I am a Researcher Scientist of multimodal intelligence department at XPENG Robotics. We focus on cutting-edge technologies of embodied AI, including but not limited to embodied multimodal models, world models, spatial intelligence. Previously, I was a Researcher at Tencent AIPD. I hold a PhD from The Chinese University of Hong Kong, where I was fortunate to be advised by Professor Pheng Ann Heng. My research interests span multimodal understanding and generation, embodied AI, world models.
We're hiring! We are looking for motivated full-time researchers (all levels) and interns to join us. If you are interested in our work on embodied AI, feel free to reach out.
Recent Publications
(2025).
CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modeling.
Accepted by SIGGRAPH ASIA 2025🎉.
(2025).
DreamCube: 3D Panorama Generation via Multi-plane Synchronization.
Accepted by ICCV 2025🎉.
(2025).
PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformer.
SIGGRAPH 2025.
(2025).
StdGEN: Semantic-Decomposed 3D
Character Generation from Single Images.
CVPR 2025.
(2024).
GAInS: Gradient Anomaly-aware
Biomedical Instance Segmentation.
2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).
(2023).
Deep learning for computational
cytology: A survey.
Medical Image Analysis.
(2023).
Donet: Deep de-overlapping network
for cytology instance segmentation.
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.
(2022).
Rethinking annotation granularity
for overcoming shortcuts in deep learning--based radiograph diagnosis: A multicenter
study.
Radiology: Artificial Intelligence.