World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning
World2VLM: 将世界模型的想象能力蒸馏到VLM中以实现动态空间推理
机构 * Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所) ; School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院) ; Tsinghua University(清华大学) ; Harbin Institute of Technology(哈尔滨工业大学) ; Wuhan AI Research(武汉人工智能研究院)
AI总结 本文提出World2VLM框架,通过蒸馏生成式世界模型的空间想象能力到VLM中,提升动态空间推理性能,优于基线模型和测试时世界模型耦合方法。
Comments The code is available at https://github.com/WanyueZhang-ai/World2VLM. The dataset is available at https://huggingface.co/datasets/WanyueZhang/World2VLM