Yu Lu

Postdoctoral Researcher

Zhejiang University
Email: aniki.yulu [AT] gmail dot com
[Google Scholar] [Github] [Twitter] [LinkedIn]

Yu Lu (路雨) is a Postdoctoral Researcher at Zhejiang University. Before that, he obtained his Ph.D. degree at University of Technology Sydney (UTS). His academic advisor is Prof. Yi Yang. In past years, he has extensive research experience at leading tech institutions including WeXin Group (Tencent), Kwai Tech, Tencent AI Lab, and Baidu Research. His research focuses on long-context multi-modal video understanding and generation, particularly the development of multi-modal large language models and video diffusion models. He is currently leading a research team focuses on image editing at Zhejiang University.

We are seeking multiple research interns at video generation and understanding. Please feel free to drop me an email if you are interested in working with us.

News

  • July 2025: We have released the paper FreeLong++ for long video generation with 8x longer extension!
  • June 2025: We have released the paper FlexSelect for long video understanding with 9x faster than baseline!
  • May 2025: We have released the paper In-context edit for image editing!
  • Feb 2025: HarmonySet accepted by CVPR 2025!
  • Dec 2024: Paper on Video-Text Retrieval with unlabeled videos accepted by TIP 2024
  • Sep 2024: Two papers (FreeLong and AMP) accepted by NeurIPS 2024!
  • Sep 2024: Successfully defended Ph.D. thesis "Zero-shot Natural Language-Driven Video Analysis and Synthesis"
  • Jan 2024: Paper on Zero-shot Video Grounding accepted by TIP 2024

Selected Publications

FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusion
Yu Lu, Yi Yang
Arxiv
[Paper] [Project]

FlexSelect: Flexible Token Selection for Efficient Long Video Understanding
Yunzhu Zhang*, Yu Lu*, Tianyi Wang, Fengyun Rao, Yi Yang, Linchao Zhu
Arxiv
[Paper] [Project]

In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer
Zechuan Zhang, Ji Xie, Yu Lu, Zongxin Yang, Yi Yang
Arxiv
[Paper] [Project]

HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization
Zitang Zhou, Ke Mei, Yu Lu ✉ , Tianyi Wang, Fengyun Rao (✉ means corresponding author)
CVPR 2025
[Paper] [Project]

FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention
Yu Lu, Yuanzhi Liang, Linchao Zhu, Yi Yang
NeurIPS 2024
[Paper] [Project] [Code]

FlowZero: Zero-Shot Text-to-Video Synthesis with LLM-Driven Dynamic Scene Syntax
Yu Lu, Linchao Zhu, Hehe Fan, Yi Yang
Arxiv
[Paper] [Project] [Code]

Zero-shot Video Grounding with Pseudo Query Lookup and Verification
Yu Lu, Ruijie Quan, Linchao Zhu, Yi Yang
IEEE Transactions on Image Processing (TIP) , 2024
[Paper] [code]

Show Me a Video: A Large-Scale Narrated Video Dataset for Coherent Story Illustration
Yu Lu, Feiyue Ni, Haofan Wang, Xiaofeng Guo, Linchao Zhu, Zongxin Yang, Ruihua Song, Lele Cheng, Yi Yang
IEEE Transactions on MultiMedia (TMM) , 2023
[Paper] [Project]

CRIS: CLIP-Driven Referring Image Segmentation
Zhaoqing Wang*, Yu Lu*, Qiang Li, Xunqiang Tao, Yandong Guo, MingMing Gong, Tongliang Liu (* means equal contribution)
CVPR 2022
[Paper] [Code]

Professional Activities

Journal Review:
TPAMI, TIP, TMM, KBS

Conference Review:
CVPR, ICCV, ECCV, ACL, NeurIPS, ICLR, ICML