Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2026

Abstract

Recent advances in video generation models enable visually compelling single clips. However, real-world video creation is inherently continuous and iterative: creators refine content over multiple rounds while maintaining narrative, style, and entity consistency. Existing standalone generators are largely stateless and lack memory of previously generated segments, making it difficult to produce a coherent and consistent video project. To address this gap, we present VideoCreator, a unified video agent that integrates generation and understanding with a project-level memory system. VideoCreator leverages understanding capabilities to perform fine-grained analysis of newly produced content and uses persistent memory to retain and reuse prior context across turns, enabling continuous multi-round creation with consistency throughout the project. The code is in https://github.com/chrisx599/VideoCreator.

Keywords

Video Creation, Video Generation, Video Generation Agent, Multiturn Video Generation

Discipline

Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

ICMR '26: Proceedings of the 2026 International Conference on Multimedia Retrieval, Amsterdam, The Netherlands, June 16-19

First Page

2852

Last Page

2856

ISBN

9798400726170

Identifier

10.1145/3805622.3810431

Publisher

ACM

City or Country

New York

Additional URL

https://doi.org/10.1145/3805622.3810431

Download

Share

COinS