👋 Welcome!

I am currently a Ph.D. candidate (2023 Fall) at the Hong Kong University of Science and Technology, Guangzhou, advised by Prof. Ying-Cong Chen. Prior to this, I began my research journey as a Master’s student in 2020 at the MAC Lab of Xiamen University, advised by Prof. Rongrong Ji.

My research interests focus on visual generative models, particularly in exploring their versatility (Lotus, Lotus-2), controllability (DisEnvisioner), and efficiency (PixelFolder). I am currently working on video generation and world models, focusing on both realism and efficiency.

I am currently seeking Research Scientist / Research Engineer roles in industry for a 2027 start, particularly in visual generation, geometric perception, and world models. I would be delighted to connect and discuss any potential opportunities. Please feel free to reach out!

💻 Internships

• 2026.01 - Present, Kuaishou, Kling Team, Shenzhen, China.
• 2021.08 - 2022.01, Tencent Youtu Lab, Shanghai, China.

📝 Publications

Arxiv 2025

Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model

Jing He, Haodong Li, Mingzhi Sheng, Ying-Cong Chen^†
arXiv 2025
Paper / Project Page / Github / Demo (D) / Demo (N)

ICLR 2025

LOTUS: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

Jing He* , Haodong Li*, Wei Yin, Yixun Liang, Kaiqiang Zhou, Hongbo Zhang, Bingbing Liu, Ying-Cong Chen^†
ICLR 2025
Paper / Project Page / Github / Demo (Depth) / Demo (Normal) / ComfyUI

ICLR 2025

DisEnvisioner: Disentangled and Enriched Visual Prompt for Image Customization

Jing He* , Haodong Li*,Yongzhe Hu, Guibao Shen, Yingjie Cai, Weichao Qiu, Ying-Cong Chen^†
ICLR 2025
Paper / Project Page / Github / Demo (Soon)

ECCV 2022

PixelFolder: An efficient progressive pixel synthesis network for image generation

Jing He, Yiyi Zhou^†, Qi Zhang, Jun Peng, Yunhang Shen, Xiaoshuai Sun, Chao Chen, Rongrong Ji
ECCV 2022
Paper / Github

ICLR 2026

DA$^2$: Depth Anything in Any Direction

Haodong Li, Wangguangdong Zheng, Jing He, Yuhao Liu, Xin Lin, Xin Yang, Ying-Cong Chen, Chunchao Guo
ICLR 2026
Paper / Project Page / GitHub / Demo / Data

Arxiv 2025

StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors

Guibao Shen, Yihua Du, Wenhang Ge, Jing He, Chirui Chang, Donghao Zhou, Zhen Yang, Luozhou Wang, Xin Tao, Ying-Cong Chen^†
arXiv 2025
Paper / Project Page / Github / Model

Arxiv 2024

OmniBooth: Learning Latent Control for Image Synthesis with Multi-modal Instruction

Leheng Li, Weichao Qiu, Xu Yan, Jing He, Kaiqiang Zhou, Yingjie Cai, Qing Lian, Bingbing Liu, Ying-Cong Chen^†
arXiv 2024
arXiv / Project Page / Github / Model

AAAI 2024

Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks

Siyu Zou, Jiji Tang, Yiyi Zhou, Jing He, Chaoyi Zhao, Rongsheng Zhang, Zhipeng Hu, Xiaoshuai Sun^†
AAAI 2024
Paper / Github

ACM MM 2022

Learning dynamic prior knowledge for text-to-face pixel synthesis

Jun Peng, Xiaoxiong Du, Yiyi Zhou, Jing He, Yunhang Shen, Xiaoshuai Sun, Rongrong Ji ^†
ACM MM 2022
Paper / Github

ACM MM 2022

Towards open-ended text-to-face generation, combination and manipulation

Jun Peng, Han Pan, Yiyi Zhou, Jing He, Xiaoshuai Sun, Yan Wang, Yongjian Wu, Rongrong Ji ^†
ACM MM 2022
Paper / Github

📚 Services

Reviewer:

• ICML: 2026
• ICCV/ECCV: 2025, 2026
• NeurIPS: 2025, 2026
• AAAI: 2024, 2027
• ICLR: 2025, 2026
• CVPR: 2026
• Pattern Recognition (PR): 2026

📖 Educations

• 2023.09 - present, Ph.D. Student, The Hong Kong University of Science and Technology, GuangZhou. Advisor: Ying-Cong Chen.
• 2020.09 - 2023.06, Master of Engineering, Xiamen University. Advisor: Rongrong Ji.
• 2016.09 - 2020.06, Bachelor of Engineering, Wuhan Institute of Technology.

🎖 Honors and Awards

• 2023-2025 Postgraduate Scholarship, HKUST-GZ.
• 2020 Outstanding graduate student by WIT.
• 2016-2020 First-Class Scholarship by WIT.