DrJiankang Deng

Jiankang Deng is currently an Assistant Professor at Imperial College London and the MVP Lab director. His research focuses on three main areas: (1) multi-modal foundation models, with an emphasis on perceiving, understanding, and modelling complex multi-sensory signals such as visual, acoustic, and tactile data; (2) generative modeling of the physical world, with the goal of synthesizing scalable and reliable digital assets that reproduce real-world entities; and (3) embodied AI and world models, aiming to build agents capable of closed-loop spatial perception, physically grounded reasoning, and dexterous manipulation in open-world scenarios. His research is at the intersection of computer vision and real-world applications, striving to pioneer transformative technologies for social benefit. He actively serves as an Area Chair for leading conferences in computer vision and machine learning, including CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, and AAAI. He is also an Associate Editor for Transactions on Machine Learning Research, IEEE Transactions on Image Processing, and Neural Networks.

Previously, he obtained his Ph.D. (2020) from the IBUG group under the supervision of Prof. Stefanos Zafeiriou. His doctoral research focused on deep face analysis and modeling, encompassing efficient geometry estimation, robust feature embedding, and photorealistic texture modeling. He developed algorithms and systems (InsightFace) to capture, represent, and synthesize diverse human faces with high efficiency, robustness, and fidelity. Additionally, he worked in the field of visual representation learning and won many visual perception challenges (e.g., ImageNet and ActivityNet) in the past years.