I am currently an associate professor at the School of Computer Science and Engineering, Beihang University, and a member of the State Key Laboratory of Virtual Reality Technology and Systems. I received my B.E. from Harbin Institute of Technology in 2016 and my Ph.D. from Beihang University in 2021. From November 2021 to January 2024, I was a Boya Postdoctoral Fellow at the National Engineering Research Center of Visual Technology, Peking University, working with Prof. Yonghong Tian. My Ph.D. advisor was Prof. Jia Li.

My research focuses on generative artificial intelligence, fine-grained visual object recognition & parsing, and AR/VR content generation. I have published over 40 CCF-A papers in top-tier journals and conferences such as TPAMI, IJCV, CVPR, ICCV, and NeurIPS. Among these, 23 are first/co-first/corresponding author CCF-A papers, including 16 first-authored works with 4 first-authored TPAMI papers.

I have served as an Area Chair for prestigious conferences, including NeurIPS 2025 and ICLR 2026, and have been recognized as an Outstanding Reviewer at ICCV 2021 and NeurIPS 2023. I also led the team that won the Championship in the FGVC8-iMET Challenge at CVPR 2021.

My research has been supported by grants from the National Natural Science Foundation of China (Youth Program) and the China Postdoctoral Science Foundation. I have also participated in two Key Programs of the National Natural Science Foundation of China. In addition, I have applied for 22 Chinese/U.S. invention patents, with 19 already granted.

I have been honored with several awards for my doctoral work, including the Outstanding Doctoral Dissertation Award from Beihang University and the Excellent Doctoral Dissertation Nomination Award from the China Society of Image and Graphics.

He is a member of CVTEAM. Lab Page: Github Page:

Email: zhaoyf@buaa.edu.cn

📝 Publications

• Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCIL, Ruitao Wu, Yifan Zhao^*, Guangyao Chen, Jia Li^*, Advances in Neural Information Processing Systems (NeurIPS) 2025
• Re-coding for Uncertainties: Edge-awareness Semantic Concordance for Resilient Event-RGB Segmentation, Nan Bao, Yifan Zhao^*, Lin Zhu, Jia Li^*, Advances in Neural Information Processing Systems (NeurIPS) 2025-
• TGA: True-to-Geometry Avatar Dynamic Reconstruction, Bo Guo, Sijia Wen, Ziwei Wang, Yifan Zhao, Advances in Neural Information Processing Systems (NeurIPS) 2025, Spotlight
• FICGen: Frequency-Inspired Contextual Disentanglement for Layout-driven Degraded Image Generation , Wenzhuang Wang, Yifan Zhao^*, Mingcan Ma, Ming Liu, Zhonglin Jiang, Yong Chen, Jia Li IEEE International Conference on Computer Vision (ICCV) 2025
• Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped Disentanglement, Ruitao Wu, Yifan Zhao^*, Jia Li IEEE International Conference on Computer Vision (ICCV) 2025
• When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network, Dong Xiao, Guangyao Chen, Peixi Peng, Yangru Huang, Yifan Zhao, Yongxing Dai, Yonghong Tian Forty-second International Conference on Machine Learning (ICML) 2025, Spotlight

• Free Lunch to Meet the Gap: Intermediate Domain Reconstruction for Cross-Domain Few-Shot Learning, Tong Zhang, Yifan Zhao^*, Liangyu Wang, Jia Li International Journal of Computer Vision (IJCV) 2025

• Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning, Cheng Chen, Yunpeng Zhai, Yifan Zhao^*, Jinyang Gao, Bolin Ding, Jia Li IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2025
• Language-Inspired Relation Transfer for Few-Shot Class-Incremental Learning, Yifan Zhao, Jia Li, Zeyin Song, Yonghong Tian IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI) 2025

• How to Use Diffusion Priors under Sparse Views?, Qisen Wang, Yifan Zhao^*, Jiawei Ma, Jia Li Advances in Neural Information Processing Systems (NeurIPS) 2024

• Seek Commonality but Preserve Differences: Dissected Dynamics Modeling for Multi-modal Visual RL, Yangru Huang, Peixi Peng,Yifan Zhao, Guangyao Chen, Yonghong Tian Advances in Neural Information Processing Systems (NeurIPS) 2024
• Deblurring neural radiance fields with event-driven bundle adjustment, Yunshan Qi, Lin Zhu, Yifan Zhao, Nan Bao, Jia Li ACM International Conference on Multimedia (MM) 2024

• Parsing Objects at a Finer Granularity: A Survey, Yifan Zhao Jia Li^*, Yonghong Tian^* Machine Intelligence Research (MIR) 2024 [Survey Paper]

• Sensitivity Decouple Learning for Image Compression Artifacts Reduction, Li Ma^#, Yifan Zhao^#, Peixi Peng, Yonghong Tian, IEEE Transactions on Image Processing (TIP) 2024

• SpikeNeRF: Learning Neural Radiance Fields from Continuous Spike Stream, Lin Zhu, Kangmin Jia, Yifan Zhao, Yunshan Qi, Lizhi Wang, Hua Huang, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2024

• DR2: Disentangled Recurrent Representation Learning for Data-Efficient Speech Video Synthesis, Chenxu Zhang, Chao Wang, Yifan Zhao, Shuo Cheng, Linjie Luo, Xiaohu Guo, Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024

• Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning, Yifan Zhao^#, Zhang Tong^#, Li Jia^*, Tian Yonghong^*, IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI) 2023

• Semantic Contrastive Bootstrapping for Single-positive Multi-label Recognition, Cheng Chen^#, Yifan Zhao^#, Li Jia^*, International Journal of Computer Vision (IJCV) 2023

• Hierarchical Adaptive Value Estimation for Multi-modal Visual Reinforcement Learning, Yangru Huang, Peixi Peng, Yifan Zhao, Haoran Xu, Mengyue Geng, Yonghong Tian, Advances in Neural Information Processing Systems (NeurIPS) 2023

• Simoun: Synergizing Interactive Motion-appearance Understanding for Vision-based Reinforcement Learning, Yangru Huang, Peixi Peng, Yifan Zhao, Yunpeng Zhai, Haoran Xu, Yonghong Tian, IEEE International Conference on Computer Vision (ICCV) 2023

• Stabilizing Visual Reinforcement Learning via Asymmetric Interactive Cooperation, Yunpeng Zhai, Peixi Peng, Yifan Zhao, Yangru Huang, Yonghong Tian, IEEE International Conference on Computer Vision (ICCV) 2023

• Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning, Zeyin Song^#, Yifan Zhao^#, Yujun Shi, Peixi Peng^*, Li Yuan, Yonghong Tian^*, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023

• Invariant and consistent: Unsupervised representation learning for few-shot visual recognition, Heng Wu,Yifan Zhao, Jia Li^*, Neurocomputing 2023

• 局部关系泛化表征的小样本增量学习, 赵一凡， 李甲^*， 田永鸿^*, 中国科学：信息科学 2023 (CCF-A中文期刊)

• From Pose to Part: Weakly-Supervised Pose Evolution for Human Part Segmentation, Yifan Zhao, Yu Zhang, Li Jia^*, Tian Yonghong, IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI) 2022

• Joint self-supervised and reference-guided learning for depth inpainting , Heng Wu, Kui Fu, Yifan Zhao, Haokun Song, Jia Li, Computational Visual Media (CVMJ) 2022

• Picking Up Quantization Steps for Compressed Image Classification , Li Ma, Peixi Peng, Guangyao Chen, Yifan Zhao, Siwei Dong, Yonghong Tian, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) 2022

• Revisiting stochastic learning for generalizable person re-identification , Jiajian Zhao^#, Yifan Zhao^#,Xiaowu Chen, Jia Li, ACM International Conference on Multimedia (MM) 2022

• Spectrum Random Masking for Generalization in Image-based Reinforcement Learning, Yangru Huang, Peixi Peng, Yifan Zhao, Guangyao Chen, Yonghong Tian, Advances in Neural Information Processing Systems (NeurIPS) 2022

• Part-guided relational transformers for fine-grained visual recognition, Yifan Zhao, Jia Li, Xiaowu Chen, Yonghong Tian, IEEE Transactions on Image Processing (TIP) 2021

• M3tr: Multi-modal multi-label recognition with transformer, Jiawei Zhao, Yifan Zhao, Jia Li, ACM International Conference on Multimedia (MM) 2021

• Pose-guided inter-and intra-part relational transformer for occluded person re-identification, Zhongxing Ma, Yifan Zhao, Jia Li, ACM International Conference on Multimedia (MM) 2021

• RGB-D salient object detection with ubiquitous target awareness, Yifan Zhao, Jiawei Zhao, Jia Li, Xiaowu Chen, IEEE Transactions on Image Processing (TIP) 2021

• Selective, structural, subtle: Trilinear spatial-awareness for few-shot fine-grained visual recognition, Heng Wu, Yifan Zhao, Jia Li, IEEE International Conference on Multimedia and Expo (ICME) 2021

• DanceIt: music-inspired dancing video synthesis, Xin Guo, Yifan Zhao, Jia Li, IEEE Transactions on Image Processing (TIP) 2021

• Ordinal Multi-task Part Segmentation with Recurrent Prior Generation, Yifan Zhao, Yu Zhang, Yafei Song, Li Jia^*, Tian Yonghong, IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI) 2021

• Transformer-based dual relation graph for multi-label image recognition, Jiawei Zhao, Ke Yan, Yifan Zhao, Xiaowei Guo, Feiyue Huang, Jia Li, IEEE International Conference on Computer Vision (ICCV) 2021

• Heterogeneous relational complement for vehicle re-identification, Jiajian Zhao^#, Yifan Zhao^#, Jia Li, Ke Yan, Yonghong Tian, IEEE International Conference on Computer Vision (ICCV) 2021

• Facial: Synthesizing dynamic talking face with implicit attribute learning, Chenxu Zhang, Yifan Zhao, Yifei Huang, Ming Zeng, Saifeng Ni, Madhukar Budagavi, Xiaohu Guo, IEEE International Conference on Computer Vision (ICCV) 2021

• Graph-based high-order relation discovery for fine-grained recognition, Yifan Zhao, Ke Yan, Feiyue Huang, Jia Li, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021

• Cooperative bi-path metric for few-shot learning, Zeyuan Wang, Yifan Zhao, Jia Li, Tian Yonghong, ACM International Conference on Multimedia (MM) 2020

• Cartoon Face Recognition: A Benchmark Dataset, Yi Zheng, Yifan Zhao, Mengyuan Ren, He Yan, Xiangju Lu, Junhui Liu, Jia Li, ACM International Conference on Multimedia (MM) 2020

• Is Depth Really Necessary for Salient Object Detection?, Jiawei Zhao^#, Yifan Zhao^#, Jia Li, Xiaowu Chen, ACM International Conference on Multimedia (MM) 2020

• Reconstructing part-level 3D models from a single image, Dingfeng Shi, Yifan Zhao, Jia Li, Xiaowu Chen, IEEE International Conference on Multimedia and Expo (ICME) 2020

• Cross-reference stitching quality assessment for 360 omnidirectional images, Jia Li, Kaiwen Yu, Yifan Zhao, Yu Zhang, Long Xu, ACM International Conference on Multimedia (MM) 2019

• Multi-class part parsing with joint boundary-semantic awareness, Yifan Zhao, Jia Li, Yu Zhang, Tian Yonghong, IEEE International Conference on Computer Vision (ICCV) 2019, Oral

• Part-regularized near-duplicate vehicle re-identification, Bing He, Jia Li, Yifan Zhao, Tian Yonghong, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019

💻 Research Projects

MIR 2024

Paper

Yifan Zhao, Jia Li, Tian Yonghong, Parsing Objects at a Finer Granularity: A Survey, Machine Intelligence Research (MIR) 2024.

Project

• Fine-grained Recognition and Segmentation: A Survey.

ICCV 2019

Paper

Yifan Zhao, Jia Li, Yu Zhang, Tian Yonghong, Multi-class part parsing with joint boundary-semantic awareness, IEEE International Conference on Computer Vision (ICCV) 2019.

Project

• First Multi-class Part Segmentation Dataset, Oral (Top 4.3%).

📖 Education and Experiences

• 2024.02 - Now, Associate Professor, Beihang University.
• 2021.11 - 2024.01, Boya Postdoctoral Researcher, Peking University.
• 2016.09 - 2021.10, Ph.D., Beihang University.
• 2012.09 - 2016.06, B.Eng, Harbin Institute of Technology.

🎖 Honors and Awards

• 2023.10 CSIG Excellent Doctoral Dissertation Award Nomination.
• 2022.06 Excellent Doctoral Dissertation Award of Beihang University.
• 2021.06 Champion of FGVC8-iMET CVPR2021 Challenge.
• ICCV 2021 Outstanding Reviewer, NeurIPS 2023 Outstanding Reviewer.