Xu Gu




About

My name is Xu Gu. I am a PhD Candidate at AIMind, Gaoling School of Artificial Intelligence, Renmin University of China, advised by Prof. Ruihua Song.
I was a Visiting Scholar at National University of Singapore (NUS), supervised by Prof. Roger ZIMMERMANN (funded by the China Scholarship Council). Prior to that, I spent time as a Research Intern at Shanghai AI Lab. My research journey has been deeply shaped by these collaborative experiences in diverse academic and industrial environments.
Research Interests: My research lives at the intersection of Multimodal Large Language Models, Multimodal Video Understanding, and Cinematic Intelligence, with a focus on Storyboard Generation and advancing AI-driven Video Creation. Get in Touch: I am always open to new ideas and collaborations broadly related to Multimodal AI and beyond. Please feel free to reach out at: guxu97[at]gmail.com



News



    • [04/2026] One paper accepted by ACL 2026 (Findings)!
    • [08/2025] One paper accepted by PRCV 2025!
    • [08/2025] One paper accepted by ACM MM Workshop MUCG 2025!
    • [10/2024] One paper accepted by ACM MM Asia 2024!
    • [07/2023] One paper accepted by ACM Multimedia 2023!
    • [12/2022] Created my personal homepage!

Publications


Detecting AI-Generated Video: A Vision-Language Dual-View Survey
Dylan Xinming Hou, Juntian Zhang, Xu Gu, Yichen Wu, Nils Lukas, Gus Xia, Xiuying Chen, Yuhan Liu

ACL, 2026 (Findings). [Project]  [Paper] 

All-in-One: Boosting Basic Capabilities in one Omni-MLLM to Enhance Movie Understanding
Shaojun Shi*, Yuchen Ren*, Xu Gu*, Wenhui Tan, Yuchong Sun, Jianghan Chao, Ruihua Song

A Mixture-of-Experts Framework based on Depth Images for Text to Video Storyboard Task
Xu Gu, Feiyue Ni, Ruihua Song

PRCV, 2025. [Paper] 

Towards Incremental Learning in Cross-Modal Text-Audio Retrieval
Xu Gu*, Yingfei Sun*, Wei Ji, Hanbin Zhao, Roger Zimmermann

Under Review.

ScaMo: Towards Text to Video Storyboard Generation Using Scale and Movement of Shots
Xu Gu, Xihua Wang, Chuhao Jin, Ruihua Song

ACM Multimedia Asia, 2024. [Paper] 

TeViS: Translating Text Synopses to Video Storyboards
Xu Gu*, Yuchong Sun*, Feiyue Ni, Shizhe Chen, Xihua Wang, Ruihua Song, Boyuan Li, Xiang Cao

ACM Multimedia, 2023. [Project]  [Paper]  [Code] 

(* represents the equal contribution)


Awards&Honors



    • 2024 SIGMM Student Travel Grant.
    • 2023 Third Prize of Outstanding Scholarship for Postgraduate Studies of Renmin University of China.
    • 2019 Merit Student of University of Chinese Academy of Sciences.
    • 2017 Merit Student of Henan Province.

Services



      NeurIPS 2026, ACM MM2026, TOMM, PRCV2025, ACL2025, CVPR 2025, ACM MM 2025, ACM MM 2024.