Publication GeoChrono: Benchmarking and Rethinking Long-Term Temporal Understanding in Remote Sensing We introduce ChronoBench, a multidimensional benchmark that decomposes long-term remote sensing understanding into four progressive cognitive levels, and GeoChrono, an MLLM that traces, memorizes, and reasons about long-term geographic evolution. Research
Four research directions: multi-modal LLMs, agents, intelligence for LEO communication and network, and Earth observation applications.
01
Multi-Modal LLMs
Vision-language models that align imagery with text: multimodal pre-training and instruction tuning, in-context learning, model compression and pruning, and benchmarks that measure what these models actually understand.
Latest Publications
View all publications Publication GeoChrono: Benchmarking and Rethinking Long-Term Temporal Understanding in Remote Sensing We introduce ChronoBench, a multidimensional benchmark that decomposes long-term remote sensing understanding into four progressive cognitive levels, and GeoChrono, an MLLM that traces, memorizes, and reasons about long-term geographic evolution. 
Publication Self-in-Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence We introduce SIS-Bench, a large-scale benchmark for evaluating self-awareness and spatial cognition in UAV vision-language models through real-world aerial video understanding. 
Publication Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency A comprehensive study of compressing LVLMs by structurally pruning the language backbone and recovering with lightweight finetuning and distillation, characterizing pruning dynamics and data efficiency. Latest News
View all news
News ACM MM 2026 | GeoChrono: Benchmarking and Rethinking Long-Term Temporal Understanding in Remote Sensing ChronoBench breaks long-term remote sensing understanding into four cognitive levels and 12 sub-tasks, pinpointing long-term memory as the key bottleneck for MLLMs. GeoChrono reaches 78.34% overall accuracy, more than 20 points above the best commercial model. 
News ACM MM 2026 | Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence SIS-Bench evaluates spatial cognition and self-awareness of multimodal LLMs for UAV embodied intelligence across 1,646 real UAV videos and 4,856 QA pairs, while SIS-Motion probes whether explicit optical-flow motion cues help. 
02
Agent
Autonomous systems that plan, call tools and verify their own work — hierarchical multi-agent architectures for long-horizon tasks, tool-augmented reasoning, and agents that operate real analysis pipelines end to end.
Latest Publications
View all publications
Publication HiRS-Agent: A Hierarchical Multi-Agent System for Reliable Long-Horizon Remote Sensing Task Solving We propose HiRS-Agent, a hierarchical multi-agent system with RS-specialized execution and verification-guided control for reliable long-horizon remote sensing task solving. 
Publication RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent A domain-adapted agent that connects user intent to professional remote sensing workflows through a central controller, a dynamic toolkit, a solution space of expert guidance, and a domain knowledge space. Publication Self-in-Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence We introduce SIS-Bench, a large-scale benchmark for evaluating self-awareness and spatial cognition in UAV vision-language models through real-world aerial video understanding. Latest News
View all news News ACM MM 2026 | Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence SIS-Bench evaluates spatial cognition and self-awareness of multimodal LLMs for UAV embodied intelligence across 1,646 real UAV videos and 4,856 QA pairs, while SIS-Motion probes whether explicit optical-flow motion cues help. 
News SCIS | RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent RS-Agent turns a large language model from a passive image-understanding tool into an agent that plans and executes remote sensing tasks, reaching over 95% planning accuracy across 9 datasets and 18 task types. Accepted by Science China Information Sciences. 
03
Intelligence for LEO Communication and Network
Learning-based signal and network intelligence for low-Earth-orbit systems: specific emitter identification, intelligent signal processing, and the integration of communication with remote sensing on a single platform.
Latest Publications
View all publications
Latest News
View all newsNews for this direction will appear here.
04
Earth Observation Applications
Turning satellite and UAV observations into usable measurements: scene classification, change detection, height and depth estimation, multi-view stereo, and UAV visual localization.
Latest Publications
View all publications Publication HiRS-Agent: A Hierarchical Multi-Agent System for Reliable Long-Horizon Remote Sensing Task Solving We propose HiRS-Agent, a hierarchical multi-agent system with RS-specialized execution and verification-guided control for reliable long-horizon remote sensing task solving. Publication RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent A domain-adapted agent that connects user intent to professional remote sensing workflows through a central controller, a dynamic toolkit, a solution space of expert guidance, and a domain knowledge space. Publication GeoChrono: Benchmarking and Rethinking Long-Term Temporal Understanding in Remote Sensing We introduce ChronoBench, a multidimensional benchmark that decomposes long-term remote sensing understanding into four progressive cognitive levels, and GeoChrono, an MLLM that traces, memorizes, and reasons about long-term geographic evolution. Latest News
View all news News ACM MM 2026 | GeoChrono: Benchmarking and Rethinking Long-Term Temporal Understanding in Remote Sensing ChronoBench breaks long-term remote sensing understanding into four cognitive levels and 12 sub-tasks, pinpointing long-term memory as the key bottleneck for MLLMs. GeoChrono reaches 78.34% overall accuracy, more than 20 points above the best commercial model. News SCIS | RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent RS-Agent turns a large language model from a passive image-understanding tool into an agent that plans and executes remote sensing tasks, reaching over 95% planning accuracy across 9 datasets and 18 task types. Accepted by Science China Information Sciences.