论文题目：Hyper-RAG: combating LLM hallucinations using hypergraph-driven retrieval-augmented generation中文题目：Hyper-RAG：利用超图驱动的检索增强生成抑制大...[详细]

规划与问题求解是人类智能最核心的能力之一。面对一个目标，人并不总是依赖“走一步、看一步”的试错，而能够在真正行动之前，在内部先预演若干种可能的路径，再据此选...[详细]

论文题目：Embedding high-resolution touch across robotic hands enables adaptive human-like grasping作者：Zihang Zhao, Wanlin Li, Yuyang Li, Tengyu Liu, Boren...[详细]

导语近年来，大语言模型进入机器人领域已经不算新鲜。从用自然语言生成任务规划，到根据图像选择动作，再到直接生成机器人控制代码，越来越多的工作试图让机器人“听懂...[详细]

论文题目：Visual-tactile pretraining and online multitask learning for humanlike manipulation dexterity作者：Qi Ye, Qingtao Liu, Siyun Wang, Jiaying Chen, Yu...[详细]

论文题目：Accelerating scientific discovery with Co-Scientist作者：Gottweis, J., Weng, W.-H., Daryin, A., Tu, T., Sirkovic, P., Myaskovsky, A., et al.发表期...[详细]

Chignoli, Matthew, et al. "A propagation perspective on recursive forward dynamics for systems with kinematic loops." IEEE Transactions on Robotics (2025). D...[详细]

J.Hu, Z.Chen, Y. Lin, Z. Chen, B. Yao, and X. Ma, “On the Fully Decoupled Rigid-Body Dynamics Identification of Serial Industrial Robots,”IEEE Transactions...[详细]

论文题目：Bridging the interpretability gap for medical artificial intelligence models using class‑association manifold learning发表期刊：Nature Biomedical ...[详细]

有些机器人失败，看上去像是没有听懂人话，细看往往是没有看懂空间。人说把碗放到盘子上，机器人需要知道碗的底面在哪里，盘子的上表面在哪里，两个面的中心和法向该怎...[详细]