1
ViewMind3D: Modular View-Aware Inference for Training-Free 3D-QA
无需3D训练数据，模块化视图感知让大模型直接推理3D问答，机器人感知新思路。
arXiv:2607.28442v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled new pos…