Reproduce “ProactGen: Learning Proactive Clarification for Video Generation” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Zhixiao Wang, Yang Chen, Yifan Xu, Chenbin Li, Yue Chang, Kai Long, Fengming Dong, Limin Wang

ProactGen asks users to refine text-to-video prompts through questions grounded in a low-cost draft. A trained vision-language policy observes sampled draft frames, and a simulated user answers before a frozen model incorporates details into the final video. On 500 InstanceCap samples, one round scores 0.678, versus 0.658 for direct generation; this measures simulated reference alignment, not real-user outcomes.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.