Search papers, labs, and topics across Lattice.
Peking University, Affiliation:
4
0
6
Explicit 3D skeletal representations unlock parameter-efficient robotic manipulation, achieving 85.9% success on LIBERO-Plus with half the parameters of prior methods.
Redefining cross-modal fusion at the prototype level, ProtoHGF-Net significantly enhances target detection by suppressing background noise.
Forget complex setups and limited data access: VulGD offers a dynamic, open-access vulnerability graph database with LLM-enhanced descriptions, ready for real-time exploration and analysis.
Achieve state-of-the-art semantic 3D reconstruction from sparse views by intelligently pruning redundant Gaussians and blending 2D and 3D semantic cues.
