April 2026
WAN 2.7 is released!
WAN 2.7, our latest video generation model, is out.
Haoyu Chen
About
I am a Ph.D. candidate at the Hong Kong University of Science and Technology (Guangzhou), advised by Prof. Lei Zhu and Prof. Ping Tan, and will be graduating in July 2026.
I am currently with Tongyi Lab at Alibaba, where I work on the WAN video team, focusing on video generation.
News[1]
Experience[4]
-
Tongyi Lab
[Research Scientist]
2026
-
Adobe
[Research Intern]
2025
-
Xiaobing.AI
[Research Intern]
2021
-
AWS
[Research Intern]
2020
Publications[10]
Selected first-author work. Full list available on Google Scholar.
- How Long Can Unified Multimodal Models Generate Images Reliably? Taming Long-Horizon Interleaved Image Generation via Context Curation arXiv 2026
- POSTA: A Go-to Framework for Customized Artistic Poster Generation CVPR 2025
- JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration CVPR 2025
- PhotoArtAgent: Intelligent Photo Retouching with Artist Agents CVPR 2026 Findings
- RestoreAgent: Autonomous Image Restoration Agent via Multimodal LLMs NeurIPS 2024
- Low-Res Leads the Way: Improving Generalization for Super-Resolution CVPR 2024
- Masked Image Training for Generalizable Deep Image Denoising CVPR 2023
- Snow Removal in Video: A New Dataset and A Novel Method ICCV 2023
- Density-Aware Video Desnowing with Robust Alignment on a Large-Scale Dataset TMM 2026
- Attention in Attention Network for Image Super-Resolution arXiv 2021
Interests
Feel free to reach out if you share any of these.
Tennis
Diving
Photography
