Lei Liang

4

Papers

21

Total Citations

Papers (4)

When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning

SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing

Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesis

TrustUQA: A Trustful Framework for Unified Structured Data Question Answering