Search papers, labs, and topics across Lattice.
5
0
8
6
A task-oriented framework that bypasses image reconstruction and directly transmits semantic features extracted by a multitask-pretrained backbone is investigated, with the largest improvements in the low-SNR regime.
STR-Agent is proposed, an LLM-driven framework for QoS-aware routing in LEO satellite networks that significantly outperforms conventional baselines, and results demonstrate the potential of LLM-driven agent architectures to enable serviceaware and adaptive QoS routing in future LEO satellite networks.
HiRS-Agent achieves remarkable improvements in long-horizon remote sensing tasks by leveraging a hierarchical multi-agent architecture that enhances coordination and tool-use policies.
Maps still enhance machine spatial reasoning, with a combined data and map approach yielding the best performance across diverse cognitive tasks.
Current UAV models struggle with self-awareness, but incorporating motion dynamics can bridge the gap and enhance performance across cognitive tasks.
