Search papers, labs, and topics across Lattice.
The Hong Kong University of Science and Technology
3
0
7
SkillReranker redefines skill selection by leveraging semantic decomposition to improve task performance and efficiency in agent systems.
LLMs can achieve remarkable out-of-distribution generalization by learning to self-update their context through a novel reinforcement learning framework.
Fine-grained 3D object grounding gets a boost: SSR3D-LLM uses latent spatial reasoning steps to iteratively refine candidate rankings, outperforming single-pointer methods and setting a new standard for unified 3D-LLMs.
