{"ID":2836951,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.20280","arxiv_id":"2511.20280","title":"Bootstrapping Physics-Grounded Video Generation through VLM-Guided Iterative Self-Refinement","abstract":"Recent progress in video generation has led to impressive visual quality, yet current models still struggle to produce results that align with real-world physical principles. To this end, we propose an iterative self-refinement framework that leverages large language models and vision-language models to provide physics-aware guidance for video generation. Specifically, we introduce a multimodal chain-of-thought (MM-CoT) process that refines prompts based on feedback from physical inconsistencies, progressively enhancing generation quality. This method is training-free and plug-and-play, making it readily applicable to a wide range of video generation models. Experiments on the PhyIQ benchmark show that our method improves the Physics-IQ score from 56.31 to 62.38. We hope this work serves as a preliminary exploration of physics-consistent video generation and may offer insights for future research.","short_abstract":"Recent progress in video generation has led to impressive visual quality, yet current models still struggle to produce results that align with real-world physical principles. To this end, we propose an iterative self-refinement framework that leverages large language models and vision-language models to provide physics...","url_abs":"https://arxiv.org/abs/2511.20280","url_pdf":"https://arxiv.org/pdf/2511.20280v1","authors":"[\"Yang Liu\",\"Xilin Zhao\",\"Peisong Wen\",\"Siran Dai\",\"Qingming Huang\"]","published":"2025-11-25T13:09:03Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\",\"LoRA\"]","has_code":false}