Di Hu is one tenured faculty at Gaoling School of Artificial Intelligence, Renmin University of China. Before that, he was previously a research scientist at Baidu Research. Di Hu obtained the Ph.D degree from Northwestern Polytechnical University in 2019, supervised by Xuelong Li. Currently, Di Hu is leading the GeWu Lab and exploring how to understand and interact with the world via the natural multimodal messages. He is an aficionado of cognitive neuroscience and has wrote one study note during his undergraduate. Inspired by what he learned from cognitive neuroscience, and what he observed and deliberated from the daily-life, he strongly convinced that the pervasive, free, natural multimodal messages can provide sufficient information for perceiving, learning and understanding environment, even the agent itself, which promisingly makes multimodal learning become one of the key to achieve machine intelligence.

Wenke is a Ph.D student since 2022 Fall at Gaoling School of Artificial Intelligence, Renmin University of China, advised by Prof. Di Hu. His research interests include reinforcement learning and embodied AI. Now, he focus on building a generalizable manipulation policy with computer vision.

Zequn is a Ph.D. student at GeWu-Lab, Gaoling School of Artificial Intelligence, Renmin University of China. He currently focuses on the mechanism of multi-modal learning, including theoretical comprehension and algorithm design. He also has a keen interest in developing efficient and effective multi-view clustering techniques utilizing machine learning methods.

Ruoxuan is a first-year Ph.D. student in GeWu-Lab at Gaoling School of Artificial Intelligence, Renmin University of China, advised by Prof. Di Hu. He received his bachelor’s degree from the College of Computer Science and Electronic Engineering, Hunan University in 2023, and his master’s degree from the Gaoling School of Artificial Intelligence, Renmin University of China. His research interests focus on multi-modal embodied AI, enabling robots to perceive and interact with the physical world through vision, audition, touch, and force sensing.

Mingxin is a first-year Ph.D. student at the GeWu-Lab, Gaoling School of Artificial Intelligence, Renmin University of China, advised by Prof. Di Hu. She obtained her master’s degree from University of Electronic Science and Technology of China in 2025. She is also jointly trained by the Beijing Academy of Artificial Intelligence (BAAI). Her research interests focus on multimodal interaction and embodied intelligence.

Dongnuan is a Ph.D student since 2025 Fall at Gaoling School of Artificial Intelligence, Renmin University of China, advised by Prof. Di Hu. He received his bachelor’s degree in South China University of Technology. He is interested in multimodal understanding and multimodal large language models.

Youquan is a PhD student at Gaoling School of Artificial Intelligence, Renmin University of China. He received his bachelor’s degree in School of Artificial Intelligence, Xidian University in 2025. Now his research interests focus on the audio and visual.

Yu Miao is a Ph.D. student at Gaoling School of Artificial Intelligence, Renmin University of China, advised by Prof. Di Hu. She received her bachelor’s degree in Beijing University of Posts and Telecommunications in 2025. Now she has a keen interest in multimodal large language models.

Jifan Li is a first-year Ph.D. student at GeWu-Lab, jointly trained with the Beijing Academy of Artificial Intelligence (BAAI). He received his B.E. from the School of Automation Science and Electrical Engineering (SASEE), Beihang University. His research focuses on embodied AI.

Yizhuo is a Ph.D. student since Fall 2026 at Gaoling School of Artificial Intelligence, Renmin University of China, advised by Prof. Di Hu. He received his bachelor’s degree from the School of Computer Science and Technology, Jilin University. His research interests lie in embodied intelligence, with a particular focus on the generalization of embodied AI systems.

Ziheng is a first-year Ph.D. student at the Gaoling School of Artificial Intelligence, Renmin University of China, advised by Prof. Di Hu. He received his bachelor’s degree from the School of Computer Science and Technology, Jilin University. His research interests lie in multimodal learning.

Bowen is a fourth-year student at the School of Information and Communication Engineering (SICE), University of Electronic Science and Technology of China (UESTC). He will be a doctoral candidate in joint training with Zhongguancun Academy (ZGCA) in 2027 fall. His research focuses on embodied intelligence.

Jiaxuan is a fourth-year undergraduate student majoring in Computer Science at Beihang University (BUAA). His research interests include audio-visual large language models and multimodal understanding.

Yaoxuan is a fourth-year student at the School of Mathematics and Statistics, Beijing Institute of Technology (BIT). She is interested in multimodal large language models.

Zijian Zhou is a fourth-year student at the School of Computer Science and Engineering (CSE), Sun Yat-Sen University (SYSU). He will be a doctoral candidate in joint training with Beijing Academy of Artificial Intelligence (BAAI) in 2027 fall. His research focuses on embodied AI.

Yuchen is a master student in GeWu-Lab at Renmin University of China, advised by Prof. Di Hu. He has got his bachelor’s degree in Zhejiang University in 2024.

Chengxiang is a fourth-year undergraduate student of Beijing University of Posts and Telecommunications. He is interested in multimodal learning and currently focuses on the multimodal imbalance problem.

HaoTian Ni is a third-year undergraduate student at the School of Computer Science and Engineering (SCSE), Beihang University (BUAA). He joined GeWu-Lab as a research assistant in July 2024, with research interests in multimodal learning and generative models.

Bitao is a second-year undergraduate student at Gaoling School of Artificial Intelligence, Renmin University of China. He is interested in embodied intelligence and multimodal perception and interaction.

Kailin is a third-year undergraduate student at the School of Computer Science, Wuhan University. He is currently interested in multimodal learning, particularly the multimodal imbalance problem.

Weitao Zhang is a second-year undergraduate student at Gaoling School of Artificial Intelligence, Renmin University of China. He is interested in embodied intelligence and computer vision.

Wenbo Yu is an undergraduate student at Beijing Forestry University. His research interests lie in foundational challenges within embodied intelligence, including Sim2Real transfer.

Yubo is a third-year undergraduate student at the School of Computer Science and Engineering, Beihang University (BUAA). He is interested in multimodal large language models, with a particular focus on audio-visual understanding and reasoning.

Yutong is a senior undergraduate student at the School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University (BJTU). Since joining GeWu-Lab as a research assistant in October 2025, his research has primarily focused on multimodal perception and interactive manipulation. He will pursue his graduate studies at CASIA.

Luan Zhang is a third-year undergraduate student at the School of Statistics, Renmin University of China. She is interested in multi-modal representation learning and multi-modal large language models, focusing on cross-modal interaction.

Zhiyi is a second-year undergraduate student at Gaoling School of Artificial Intelligence, Renmin University of China. She is interested in embodied intelligence and multi-modal collaborative perception and interaction.

Chengpeng is a second-year undergraduate student at Gaoling School of Artificial Intelligence, Renmin University of China. He is interested in multimodal learning and computer vision.

Keying is a second-year undergraduate student at School of Statistics, Renmin University of China. She is interested in embodied intelligence.

Yu Pan is a third-year undergraduate student at the School of Statistics, Renmin University of China. His research focuses on audio-visual multimodal learning and generative models, with a long-term aspiration of advancing multisensory world models toward immersive physical simulation.

Hao is a second-year undergraduate student at Gaoling School of Artificial Intelligence, Renmin University of China. She is interested in embodied intelligence, agentic systems, and multimodal perception and interaction.

Zhirong is a second-year undergraduate student at the School of Information, Renmin University of China. He is interested in embodied intelligence and multimodal understanding.