Search papers, labs, and topics across Lattice.
City University of Hong Kong
3
0
6
Memory dilution in LLMs is tackled head-on with a novel framework that not only preserves information but also amplifies reasoning capabilities.
A lightweight architecture that distills long textual sequences using visual tokens as dynamic queries boosts LLM performance on 2D table understanding by 23.9%.
Forget independent feature extraction: a new architecture uses LVLMs to explicitly model the relationships between drone and satellite imagery, substantially boosting geolocalization accuracy.
