Guangzhi Wang 王广智

Email: gzwang98@gmail.com
Location: Shenzhen, China

     


Short Bio

I am a researcher at ARC Lab, PCG Tencent, working on controllable visual content generation and editing. I obtained my PhD degree from National University of Singapore advised by Prof. Mohan Kankanhalli in 2024. Before that, I obtained my B.Eng. degree of Computer Science from Zhejiang University in June, 2019. I was fortunate to have conducted research at Microsoft Research (Redmond), Tencent ARC Lab.

We are looking for self-motivated research interns on related topic. I am also open to colablrations in any forms. Feel free to reach out if you are interested.

Publications

* indicates equal contribution, # stands for correspondence or project lead.
ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing
Lingen Li, Guangzhi Wang#, Zhaoyang Zhang#, Yaowei Li, Xiaoyu Li, Qi Dou, Jinwei Gu, Tianfan Xue#, Ying Shan
arXiv preprint arXiv:2508.10881
Blobctrl: A unified and flexible framework for element-level image generation and editing
Yaowei Li, Lingen Li, Zhaoyang Zhang, Xiaoyu Li, Guangzhi Wang, Hongxiang Li, Xiaodong Cun, Ying Shan, Yuexian Zou
arXiv preprint arXiv:2503.13434
PELA: Learning Parameter-Efficient Models with Low-Rank Approximation
Yangyang Guo, Guangzhi Wang, Ziwei Xu, Mohan Kankanhalli
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2024
Bilateral Adaptation for Human-Object Interaction Detection with Occlusion-Robustness
Guangzhi Wang, Yangyang Guo, Ziwei Xu, Mohan Kankanhalli
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2024
SEED-Bench-2: Benchmarking Multimodal Large Language Models
Bohao Li*, Yuying Ge*, Yixiao Ge, Guangzhi Wang, Rui Wang, Ruimao Zhang, Ying Shan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2024
S3Editor: A Sparse Semantic-Disentangled Self-Training Framework for Face Video Editing
Guangzhi Wang, Tianyi Chen, Kamran Ghasedi, HsiangTao Wu, Tianyu Ding, Chris Nuesmeyer, Ilya Zharkov, Mohan Kankanhalli, Luming Liang
Arxiv Preprint
SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension
Bohao Li*, Rui Wang*, Guangzhi Wang*, Yuying Ge, Yixiao Ge, Ying Shan
Arxiv Preprint
What Makes for Good Visual Tokenizers for Large Language Models?
Guangzhi Wang, Yixiao Ge, Xiaohan Ding, Mohan Kankanhalli, Ying Shan
Arxiv Preprint
Text to Point Cloud Localization with Relation Enhanced Transformer
Guangzhi Wang, Hehe Fan, Mohan Kankanhalli
AAAI Conference on Artificial Intelligence (AAAI) 2023
Distance Matters in Human-Object Interaction Detection
Guangzhi Wang, Yangyang Guo, Yongkang Wong, Mohan Kankanhalli
ACM International Conference on Multimedia (ACM MM) 2022
Chairs Can be Stood on: Overcomming Object Bias in Human-Object Interaction Detection
Guangzhi Wang, Yangyang Guo, Yongkang Wong, Mohan Kankanhalli
European Conference on Computer Vision (ECCV) 2022
Semantic-aware Triplet Loss for Image Classification
Guangzhi Wang, Yangyang Guo, Yongkang Wong, Mohan Kankanhalli
IEEE Transactions on Multimedia (TMM) 2022
Dynamic knowledge distillation with cross-modality knowledge transfer
Guangzhi Wang
ACM Conference on Multimedia(ACM MM), Doctoral Symposium 2021
Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition
Ziwei Xu, Guangzhi Wang, Yongkang Wong, Mohan Kankanhalli
IEEE Transactions on Multimedia (TMM) 2021
Multi-source Distilling Domain Adaptation
Sicheng Zhao*, Guangzhi Wang*, Shanghang Zhang*, Yang Gu, Yaxian Li, Zhichao Song, Pengfei Xu, Runbo Hu, Hua Chai, Kurt Keutzer
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) 2020

Education

Internship Experience

Teaching

Services


© Guangzhi Wang | Last updated: Apr. 2024