الباحثون

Chunyuan Li

المنشورات 1

نسخة أولية وصول مفتوح

VideoGen-Agent: Reinforcing Video Generation Agents

Binxu Li, Haoyi Duan, Yuhui Zhang وآخرون · 2026

Recent advances in video generative models have enabled high-fidelity, temporally coherent video generation. However, these models often struggle to satisfy prompts requiring specialized knowledge, specific identities, physical consistency, or ordered events. In this paper, we present VideoGen-Agent, a multimodal agent …

المؤلفون المشاركون