5 papers
SA-GEM: Scale-Adaptive and Geospatial Evidence-Modulated Token Pruning for Efficient Remote Sensing Large Vision-Language Models
Kexin Ma, Jing Xiao, Bowen Xing +2
RS-LVLMs have advanced multimodal understanding of Earth observation imagery, yet their performance is fundamentally constrained by high-resolution processing, as visual token coun…
Observe Less, Understand More: Cost-aware Cross-scale Observation for Remote Sensing Understanding
Zhenghao Xie, Jing Xiao, Zhenqi Wang +4
Remote sensing understanding inherently requires multi-resolution observation, since different targets and application tasks demand different levels of spatial detail. While low-re…
Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models
Kexin Ma, Jing Xiao, Chaofeng Chen +4
Token pruning has emerged as an effective approach to reduce the substantial computational overhead of Large Vision-Language Models (LVLMs) by discarding less informative visual to…
CAST: Character-and-Scene Episodic Memory for Agents
Kexin Ma, Bojun Li, Yuhua Tang +2
Episodic memory is a central component of human memory, which refers to the ability to recall coherent events grounded in who, when, and where. However, most agent memory systems o…
Context-Driven Index Trimming: A Data Quality Perspective to Enhancing Precision of RALMs
Kexin Ma, Ruochun Jin, Xi Wang +3
Retrieval-Augmented Large Language Models (RALMs) have made significant strides in enhancing the accuracy of generated responses.However, existing research often overlooks the data…