Haoyu Chen

About

Haoyu Chen · [Researcher @ Tongyi Lab, Alibaba · Ph.D. @ HKUST (GZ)]

I am currently with Tongyi Lab at Alibaba, where I work on the WAN video team, focusing on video generation.

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.

News[2]

August 2026

WAN 3.0 is released!

I was one of the core contributors to the model’s post-training.

Invited TalkRepresented the Wan team at the Wan 3.0 Global Launch Live Session.

April 2026

WAN 2.7 is released!

I was one of the core contributors to the model’s post-training.

Experience[4]

Tongyi Lab

[Researcher]

2026
Adobe

[Research Intern]

2025
Xiaobing.AI

[Research Intern]

2021
AWS

[Research Intern]

2020

Publications[10]

First-author publications

How Long Can Unified Multimodal Models Generate Images Reliably? Taming Long-Horizon Interleaved Image Generation via Context Curation [Generative Models] PDF SIGGRAPH Asia 2026
POSTA: A Go-to Framework for Customized Artistic Poster Generation [Generative Models] Homepage PDF CVPR 2025
JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration [Multi-Modal Agent] Homepage PDF CVPR 2025
PhotoArtAgent: Intelligent Photo Retouching with Artist Agents [Multi-Modal Agent] PDF CVPR 2026 Findings
RestoreAgent: Autonomous Image Restoration Agent via Multimodal LLMs [Multi-Modal Agent] Homepage PDF NeurIPS 2024
Low-Res Leads the Way: Improving Generalization for Super-Resolution [Low-level Vision] Homepage PDF CVPR 2024
Masked Image Training for Generalizable Deep Image Denoising [Low-level Vision] Code PDF CVPR 2023
Snow Removal in Video: A New Dataset and A Novel Method [Adverse Weather] Homepage PDF ICCV 2023
Density-Aware Video Desnowing with Robust Alignment on a Large-Scale Dataset [Adverse Weather] TMM 2026
Attention in Attention Network for Image Super-Resolution [Low-level Vision] Code PDF arXiv 2021