一作ACL 2026Findings· Findings of ACL
SCMAPR : Self-Correcting Multi-Agent Prompt Refinement for Complex-Scenario Text-to-Video Generation
Chengyi Yang · Pengzhen Li · Jiayin Qi · Aimin Zhou · Ji Wu · Ji Liu
摘要
Text-to-Video (T2V) generation has benefited from recent advances in diffusion models, yet current systems still struggle under complex scenarios, which are generally exacerbated by the ambiguity and underspecification of text prompts. In this work, we formulate complex-scenario prompt refinement...