Search papers, labs, and topics across Lattice.
The Hong Kong University of Science and Technology
3
0
5
UDG transforms how we approach interval-predicate queries, achieving superior performance while simplifying the indexing process across multiple predicates.
Predicting fine-grained traffic from coarse data could revolutionize traffic management systems by drastically improving prediction accuracy without the burden of extensive data collection.
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.
