I am a third-year Ph.D. student at USTC and a Research Intern at Qwen, Alibaba Group. I am co-supervised by Feng Zhao, Bo Dai, and Dahua Lin. Previously, I conducted research at Shanghai AI Laboratory and received my B.Eng. from Wuhan University in 2023.
Some topics that I currently focus on include:
- Controllable image generation and editing: Qwen-Image-3.0, Qwen-Image-2.0
- 3D reconstruction and scalable neural rendering: AnySplat, Horizon-GS, Octree-GS, MatrixCity
🔥 News
- 2026.08 Two papers were accepted to the main track of EMNLP 2026.
- 2026.08 We’re excited to celebrate the release of Qwen-Image-3.0! Congratulations to the whole team, and I’m delighted to work with so many talented people. Many thanks to Arena.ai for featuring Qwen-Image-3.0-Pro at #5 with 1,263 points on the Text-to-Image Arena, up from #15 and 1,191 points for Qwen-Image-2.0-Pro. [Leaderboard]
- 2026.05 We released the Qwen-Image-2.0 Technical Report.
- 2026.02 One paper was accepted to CVPR 2026.
- 2025.09 One paper was accepted to NeurIPS 2025.
- 2025.08 One paper was accepted to SIGGRAPH Asia 2025 (ACM TOG).
Earlier news
- 2025.06 One paper was accepted to ICCV 2025.
- 2025.05 One paper was accepted to SIGGRAPH 2025.
- 2025.05 One paper was accepted to TPAMI 2025.
- 2025.02 Two papers were accepted to CVPR 2025.
- 2024.09 One paper was accepted to NeurIPS 2024.
- 2023.09 One paper was accepted to NeurIPS 2023 D&B Track.
- 2023.07 Our LandMark System was released.
- 2023.07 One paper was accepted to ICCV 2023.
- 2023.06 Graduated from Wuhan University.
🔖 Technical Reports
Qwen-Image-3.0: Rich Content, Authentic Details, Deep Knowledge
Qwen Team · Core Contributor
Built for useful visual work with prompts up to 4.5K tokens, legible text down to 10 px, native rendering in 12 languages, knowledge-rich generation, and realistic interfaces.
Qwen-Image-2.0-RL Technical Report
Qwen Team
A post-training pipeline combining task-specific reward models, GRPO-based reinforcement learning, and on-policy distillation to improve visual quality, instruction following, editing accuracy, and face identity preservation.
Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation
Qwen Team
A context-centric image generation agent that plans for missing information and grounds requests through reasoning, search, memory, and feedback, turning underspecified user intent into reliable generation context.
Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation
Qwen Team
A language-conditioned video world model that predicts physically grounded future trajectories across robotic manipulation, autonomous driving, indoor navigation, and human-to-robot transfer.
Qwen-Image-Flash: Beyond Objective Design
Qwen Team
A unified 4-NFE model for fast text-to-image generation and instruction-guided editing, developed through a systematic study of data composition, multi-teacher guidance, and generation-editing task mixtures.
Qwen-Image-VAE-2.0 Technical Report
Qwen Team
A high-compression VAE suite designed for strong reconstruction fidelity and diffusion-friendly latent representations, with particular gains on text-rich imagery and efficient encoding.
Qwen-Image-2.0 Technical Report
Qwen Team · Core Contributor
Qwen-Image-2.0 is an omni-capable image generation foundation model that integrates high-fidelity image creation and precise image editing into a single unified framework.
📝 Research Papers
(† corresponding author; * equal contribution)
G²VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
Wenbo Hu*, Jingli Lin*, Yilin Long*, Yunlong Ran, Lihan Jiang, Yifan Wang, Chenming Zhu, Runsen Xu, Tai Wang†, Jiangmiao Pang†
AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
Lihan Jiang*, Yucheng Mao*, Linning Xu, Tao Lu, Kerui Ren, Yichen Jin, Xudong Xu, Mulin Yu, Jiangmiao Pang, Feng Zhao, Dahua Lin, Bo Dai†
MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation
Kerui Ren, Jiayang Bai, Linning Xu, Lihan Jiang, Jiangmiao Pang, Mulin Yu†, Bo Dai†
ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting
Ruijie Zhu, Mulin Yu, Linning Xu, Lihan Jiang, Yixuan Li, Tianzhu Zhang, Jiangmiao Pang, Bo Dai†,
Virtualized 3D Gaussians: Flexible Cluster-based Level-of-Detail System for Real-Time Rendering of Composed Scenes
Xijie Yang, Linning Xu, Lihan Jiang, Dahua Lin, Bo Dai†,
Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration
Zilong Huang, Jun He, Junyan Ye, Lihan Jiang, Weijia Li, Yiping Chen, Ting Han
Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes
Lihan Jiang*, Kerui Ren*, Mulin Yu, Linning Xu, Junting Dong, Tao Lu, Feng Zhao, Dahua Lin, Bo Dai†
Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians
Kerui Ren*, Lihan Jiang*, Tao Lu, Mulin Yu, Linning Xu, Zhangkai Ni, Bo Dai†
GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction
Mulin Yu*, Tao Lu*, Linning Xu, Lihan Jiang, Yuanbo Xiangli†, Bo Dai
PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection
Qiang Zhou*, Weize Li*, Lihan Jiang, Guoliang Wang, Guyue Zhou, Shanghang Zhang, Hao Zhao†
MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond
Yixuan Li*, Lihan Jiang*, Linning Xu, Yuanbo Xiangli, Zhengzhi Wang, Dahua Lin, Bo Dai†
🎖 Honors and Awards
- Outstanding Graduate Student, WHU, 2023
- China National Scholarships, 2021
- China National Scholarships, 2020
- The First Prize Scholarship, WHU, 2021
- The First Prize Scholarship, WHU, 2020
📖 Education
- Ph.D. in Control Science and Engineering, University of Science and Technology of China, Sep 2023 - Jun 2028 (expected)
- B.Eng. in Geodesy and Geomatics Engineering, Wuhan University, Sep 2019 - Jun 2023
- GPA: 3.95/4.00, Rank: 1/225
🧐 Academic Service
Reviewer
- NeurIPS: 2024, 2025
- ICLR: 2025, 2026
- ICML: 2025, 2026
- CVPR: 2025, 2026
- EuroGraphics: 2025
- SIGGRAPH: 2025, 2026
💻 Research Experience
Qwen, Alibaba Group
Research Intern
Shanghai AI Laboratory
Research Intern