提出样本高效后训练方法，突破乐高空间物理推理任务的数据瓶颈
arXiv:2606.07602v1 Announce Type: new Abstract: LLM-based LEGO assembly generation requires both semantic grounding and physical feasibility. We ident…
多模态大模型在物理图示推理上的首个专门基准，揭示模型读图理解物理学关键短板。
arXiv:2604.03893v2 Announce Type: replace Abstract: Current multimodal benchmarks for scientific reasoning primarily evaluate local information extrac…
首个针对多模态大模型物理推理的台球基准，测试从静态图预测动态的能力
arXiv:2605.30900v1 Announce Type: new Abstract: Current multimodal models handle static image recognition well, but intuitive physical reasoning remai…
重新定义物理推理评估：代码驱动视频重建让MLLMs必须真正理解物理规律，而非表面识别。
arXiv:2602.13294v3 Announce Type: replace Abstract: Evaluating whether Multimodal Large Language Models (MLLMs) genuinely reason about physical dynami…
看AI如何像人类一样通过观察和交互学习物理与因果，1000+异构游戏基准测试揭秘突破！
arXiv:2511.15407v3 Announce Type: replace Abstract: Humans learn by observing, interacting with environments, and internalizing physics and causality.…