Ziyuan Huang
Ziyuan Huang

Research scientist

About Me

Hi there! I am Ziyuan Huang (黄子渊), currently a research scientist at Ant Group, building large multi-modal models. I received my Ph.D. from National University of Singapore in 2023, where I was advised by Prof. Marcelo Ang. My main research interests are on representation learning and multi-modal learning.

Prior to Ant, I have spent wonderful times conducting research in the MARS Lab under Professor Zhao Hang, TONGYI under Dr. Zhang Shiwei, and Vision4Robotics Group at Tongji University under Professor Fu Changhong. I am also fortunate to have worked closely with Dr. Pan Liang and Professor Liu Ziwei in S-Lab@NTU.

We are actively hiring self-motivated full-time engineers and interns to work on cutting-edge research projects on large multi-modal models. Feel free to drop me an email if you are interested!

Recent Publications
(2024). Accelerating Pre-training of Multimodal LLMs via Chain-of-Sight. Tech report.
(2024). Towards Better Vision-Inspired Vision-Language Models. In CVPR.
(2024). Res-tuning: A flexible and efficient tuning paradigm via unbinding tuner from backbone. In NeurIPS.
(2023). Towards Real-World Visual Tracking with Temporal Contexts. In TPAMI.
(2023). Temporally-Adaptive Models for Efficient Video Understanding. Tech report.