Search papers, labs, and topics across Lattice.
University of Chinese Academy of Sciences, Beijing, China, Peng Cheng Laboratory, Shenzhen, Guangdong, China
3
0
4
Hierarchical tokenization transforms bounding-box representation, leading to substantial improvements in localization accuracy and model performance across various benchmarks.
QueryGaussian achieves a 180x speedup in 3D instance retrieval while slashing GPU memory usage by over 70%, making it feasible on consumer-grade hardware.
Medical VQA models can now reason more reliably thanks to a new framework that disentangles true causal effects from spurious correlations by jointly tackling observable and unobservable confounders.
