Jacob Junyi Chen

📧 chenjunyi.work@gmail.com

😍 Research Interest

My research centers on multi-modal learning, with a particular focus on developing foundational models. I specialize in creating systems that can concurrently process, understand and generate diverse data modalities — including text, images, videos, and 3D representations — to build a universal comprehension of our physical world.

📢 Publications

* denotes equal contribution, † denotes corresponding author
π³: Scalable Permutation-Equivariant Visual Geometry Learning
Yifan Wang*, Jianjun Zhou*, Haoyi Zhu, Wenzheng Chang, Yang Zhou, Zizun Li, Junyi Chen, Jiangmiao Pang, Chunhua Shen, Tong He†
[project page] [paper] [code]
DeepVerse: 4D Autoregressive Video Generation as a World Model
Junyi Chen, Haoyi Zhu, Xianglong He, Yifan Wang*, Jianjun Zhou*, Wenzheng Chang*, Yang Zhou*, Zizun Li*, Zhoujie Fu, Jiangmiao Pang, Tong He†
[project page] [paper] [code]
ICCV 2025
Aether: Geometric-Aware Unified World Modeling
Aether Team (Haoyi Zhu*, Yifan Wang*, Jianjun Zhou*, Wenzheng Chang*, Yang Zhou*, Zizun Li*, Junyi Chen*, Chunhua Shen, Jiangmiao Pang, Tong He†)
[project page] [paper] [code]
MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTs
Xianglong He, Junyi Chen, Di Huang, Zexiang Liu, Xiaoshui Huang, Wanli Ouyang, Chun Yuan†, Yangguang Li†
[paper] [code]
CoSurfGS: Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction
Yuanyuan Gao, Yalun Dai, Hao Li, Weicai Ye†, Junyi Chen, Danpeng Chen, Dingwen Zhang†, Tong He, Guofeng Zhang, Junwei Han
[project page] [paper] [code]
ICLR 2025
Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction
Junyi Chen, Di Huang†, Weicai Ye, Wanli Ouyang, Tong He†
[project page] [paper] [code]
AAAI 2025
GigaGS: Scaling up Planar-Based 3D Gaussians for Large Scene Surface Reconstruction
Junyi Chen, Weicai Ye†, Yifan Wang, Danpeng Chen, Di Huang, Wanli Ouyang, Guofeng Zhang, Yu Qiao, Tong He†
[project page] [paper] [code]
ECCV 2024
GVGEN: Text-to-3D Generation with Volumetric Representation
Xianglong He*, Junyi Chen*, Sida Peng, Di Huang, Yangguang Li, Xiaoshui Huang, Chun Yuan†, Wanli Ouyang, Tong He†
[project page] [paper] [code]

📖 Education & Experience

Shanghai Artificial Intelligence Laboratory 2023 to present

Research Intern

3D Generation | 3D Reconstruction | World Models | Generative Models

Supervisor: Tong He & Wanli Ouyang

Shanghai Jiao Tong University 2023.9 to 2028.6

PhD in Computer Science and Technology

Supervisor: Tong He & Wanli Ouyang & Xiaogang Wang

Huazhong University of Science and Technology 2019.9 to 2023.6

BS in Electronic Information Engineering

GPA: 3.97 / 4

Rank: 4% (8 / 180)

🏆 Awards

📌 Service