Bo Zhao

ABOUT ME

​Bo Zhao is a researcher (Principal Investigator) at Beijing Academy of Artificial Intelligence (BAAI). Before, he received Ph.D. from The University of Edinburgh under Prof. Hakan Bilen, and M.Eng. from Peking University under Prof. Yizhou Wang. He was a research intern in Snap Inc. and SenseTime. His research interests include Machine Learning, Data-centric AI, Data-efficient Learning and Meta-learning. He was invited to give talks at Peking University, UBC, Fudan University, RIKEN, A*STAR, et al. He received ICML 2022 Outstanding Paper Award. 

News: We are recruiting self-motivated researchers, engineers and interns working on Data-centric AI. Collaborations are also welcome. If you are interested, feel free to contact me. 

Research topics include training data optimization/selection, training data synthesis, data-efficient deep learning, continual learning, data denoising, data privacy, adversarial examples, federated learning, meta-learning, et al. We study these topics in context of large-scale model and dataset.

• One highlight paper (top 2.5%) has been accepted by CVPR 2023!

PUBLICATIONS 

Full list in Google Scholar

• Dataset Condensation with Distribution Matching. Bo Zhao; Hakan Bilen. WACV 2023. PDF. Code.

• Synthesizing Informative Training Samples with GAN. Bo Zhao; Hakan Bilen. NeurIPS Workshops 2022. PDF. Code.

• Privacy for Free: How does Dataset Condensation Help Privacy? Tian Dong; Bo Zhao; Lingjuan Lyu. ICML 2022 Outstanding Paper Award (Top 1.7‰). PDF.

• CAFE: Learning to Condense Dataset by Aligning Features. Kai Wang*; Bo Zhao*; Xiangyu Peng; Zheng Zhu; Shuo Yang; Shuo Wang; Guan Huang; Hakan Bilen; Xinchao Wang; and Yang You. CVPR 2022. PDF.

• Dataset Condensation with Differentiable Siamese Augmentation. Bo Zhao; Hakan Bilen. ICML 2021. PDF. Code.

• Dataset Condensation with Gradient Matching. Bo Zhao; Konda Reddy Mopuri; Hakan Bilen. ICLR 2021 Oral (Top 1.8%). PDF. Code.

The second-highest rated paper in ICLR 2021. Ranking.

• Continual Representation Learning for Biometric Identification. Bo Zhao*; Shixiang Tang*; Dapeng Chen; Hakan Bilen; Rui Zhao. WACV 2021. PDF. Code.

• iDLG: Improved Deep Leakage from Gradients. Bo Zhao; Konda Reddy Mopuri; Hakan Bilen. 2020. arXiv. Code.

• Zero-shot Learning via Recurrent Knowledge Transfer. Bo Zhao; Xinwei Sun; Xiaopeng Hong; Yuan Yao; Yizhou Wang. WACV 2019. PDF. Code.

• MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning. Bo Zhao*; Xinwei Sun*; Yanwei Fu; Yuan Yao; Yizhou Wang. ICML 2018. PDF. Code.

• EasyFont: A Style Learning based System to Easily Build Your Large-scale Handwriting Fonts. Zhouhui Lian; Bo Zhao; Xudong Chen; Jianguo Xiao. ACM Transactions on Graphics, 2018, (presented at SIGGRAPH 2019) PDF. 

• Automatic Generation of Large-scale Handwriting Fonts via Style Learning. Zhouhui Lian; Bo Zhao; Jianguo Xiao. SIGGRAPH ASIA 2016. PDF.