Search papers, labs, and topics across Lattice.
Rimbot
3
0
5
UniDexTok slashes reconstruction errors by over 98% for dexterous hands, enabling unprecedented accuracy in fine manipulation tasks.
Endowing VLMs with intrinsic 3D geometric awareness and physical interaction cues via XEmbodied substantially boosts performance on spatial reasoning and embodied tasks, surpassing existing 2D image-text pretrained models.
Current multimodal LLMs struggle with guideline-constrained clinical reasoning, but a simple multi-agent framework can significantly boost their performance on real-world lung cancer diagnosis and treatment.
