Knowledge-Intensive Video Generation 事件

Knowledge-Intensive Video Generation arXiv:2606.01285v1 Announce Type: new Abstract: Text-to-video generation has advanced rapidly in visual quality, but remains under-evaluated for factuality and practical usefulness. We introduce knowledge-intensive video generation (KIVI), where models generate videos from short information-seeking prompts that ask for explanations, procedures, or demonstrations. To evaluate this setting, we construct KIVI-Bench, a benchmark of 1,080 prompts, and propose aut