Bo Zhao

ABOUT ME

​Bo Zhao is an Associate Professor (Tenure Track) at School of Artificial Intelligence, Shanghai Jiao Tong University. Before, he was with BAAI as Principal Investigator, leading DCAI group. He received Ph.D. from The University of Edinburgh and M.Eng. from Peking University. He was a research intern in Snap Inc. and SenseTime. His research interests include Data-centric AI, Multimodal LLM, Embodied AI and Machine Learning. He received ICML 2022 Outstanding Paper Award. He was the only nominee of The University of Edinburgh for Informatics-Europe Best Dissertation Award 2023. He received NSFC funding on Dataset Condensation. He served as an Area Chair for NeurIPS'24 and BMVC'24.

I am working on DCAI, MLLM, and their applications, e.g., Agents & Embodied AI. Collaborations are welcome. Feel free to contact me. 

News: 

• I am recruiting Ph.D./Master Students and Research Assistants/Interns. If you are interested, please read this page.

• Try our lightweight MLLM - Bunny-3B/4B/8B: Demo Code.

• I will co-organize Dataset Distillation Workshops and Challenges on at CVPR'24 and at ECCV'24. Call for Papers.

PUBLICATIONS 

Full list in Google Scholar

• [NeurIPS 2024 Spotlight] SegVol: Universal and Interactive Volumetric Medical Image Segmentation. Yuxin Du, Fan Bai, Tiejun Huang, Bo Zhao. PDF. Code. 

• [NeurIPS 2024] Fetch and Forge: Efficient Dataset Condensation for Object Detection. Coming soon.

• [NeurIPS 2024 D&B Track] Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation? Coming soon.

• [ECCV 2024] Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking. Jiyao Zhang*, Weiyao Huang*, Bo Peng*, Mingdong Wu, Fei Hu, Zijian Chen, Bo Zhao, Hao Dong. Project Page. PDF. 

• [ACL 2024] VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval. Junjie Zhou, Shitao Xiao, Zheng Liu, Bo Zhao, Yongping Xiong. PDF. Code.

• [RSS 2024] RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Multi-Modal Large Language Model Learning. Jianhao Yuan, Shuyang Sun, Daniel Omeiza, Bo Zhao, Paul Newman, Lars Kunze, Matthew Gadd. Project Page. PDF. Code. 

• [ICLR 2024] Real-Fake: Effective Training Data Synthesis Through Distribution Matching. Jianhao Yuan, Jie Zhang, Shuyang Sun, Philip Torr, Bo Zhao#. PDF. Code.

• [CVPR 2023 Highlight (Top 2.5%)] Accelerating Dataset Distillation via Model Augmentation. Lei Zhang*, Jie Zhang*, Bowen Lei, Subhabrata Mukherjee, Xiang Pan, Bo Zhao, Caiwen Ding, Yao Li, Dongkuan Xu. PDF.

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

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

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

• [CVPR 2022] 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. PDF.

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

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

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

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

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

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

• [ICML 2018] 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. PDF. Code.

• [ACM TOG 2018 & SIGGRAPH 2019] EasyFont: A Style Learning based System to Easily Build Your Large-scale Handwriting Fonts. Zhouhui Lian; Bo Zhao; Xudong Chen; Jianguo Xiao. PDF. 

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

PROJECTS

• Emu3: Next-Token Prediction is All You Need. Project Page. Technical Report.

• Bunny: A family of lightweight multimodal models. Project Page. Technical Report.

• SegVol: Universal and Interactive Volumetric Medical Image Segmentation. Project Page. PDF.

• M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models. Project Page. PDF.

COMPETITIONS

• [CVPR 2024] The 2nd place in MeViS: Motion expressions guided Video Segmentation. Bin Cao, Yisi Zhang, Xuanxu Lin, Xingjian He, Bo Zhao, Jing Liu. Certificate.