Publications
Selected publications. See my Google Scholar profile for the complete list.
* Equal contribution. † Corresponding author. Highlighted entries are selected works.
All
VLM
Visual Grounding
Benchmark
Data Selection
Visual Foundation Model
Beyond Single and Earthbound: Exploring Multi-Image Grounding in Remote Sensing with Large Vision-Language Models
Xiao An ,
Chen Zhong ,
Jiaxing Sun ,
Jun Liu ,
Wei He†
Code
/
Paper
ISPRS JPRS 2026
MIGRANT advances multi-image grounding for remote sensing with a dedicated instruction dataset and benchmark.
Is One-Shot In-Context Learning Helpful for Data Selection in Task-Specific Fine-Tuning of Multimodal LLMs?
Xiao An ,
Jiaxing Sun ,
Ting Hu ,
Wei He†
Paper
ICME 2026 (Oral)
CLIPPER uses one-shot in-context learning for efficient, training-free data selection in task-specific multimodal LLM fine-tuning.
CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models
Xiao An* ,
Jiaxing Sun* ,
Zihan Gui ,
Wei He†
Code
/
Paper
NeurIPS 2025
CHOICE provides a hierarchical benchmark for evaluating the perception and reasoning capabilities of remote sensing VLMs.
Pretrain a Remote Sensing Foundation Model by Promoting Intra-Instance Similarity
Xiao An ,
Wei He† ,
Jiaqi Zou ,
Guangyi Yang ,
Hongyan Zhang
Code
/
Paper
IEEE TGRS 2024
PIS pretrains remote sensing foundation models by promoting similarity among augmented views of each image instance.