5 papers
Synergistic Learning in Domain Adaptation with a Known Link: A Minimax Understanding
Pengcheng Xiang, Ling Zhou, Yuhong Yang
When can combining source and target data yield much better performance than using either alone? From a minimax viewpoint, writing for the minimax risk from source a…
Do System Prompts Leave Behavioral Fingerprints? A Large-Scale Empirical Study of Clone Detection via Output Similarity
Linghan Chen, Yudong Gao, Jiyao Wang +2
System prompts can be extracted from commercial LLMs with over 80\% success and redeployed at zero cost, yet a prompt owner has no way to verify whether a suspected deployment is a…
Lingjing: A Simulation Testbed for Multi-Agent Embodied Tasks in Open-Ended Cities
Xiaohe Li, Yiru Wang, Junhao Fan +6
Urban embodied intelligence requires coordination among heterogeneous agents (e.g., UAVs, ground robots, and autonomous vehicles) in dynamic cities. Simulators therefore provide a…
Decoding the Delta: Unifying Remote Sensing Change Detection and Understanding with Multimodal Large Language Models
Xiaohe Li, Jiahao Li, Kaixin Zhang +5
While Multimodal Large Language Models (MLLMs) excel in general vision-language tasks, their application to remote sensing change understanding is hindered by a fundamental "tempor…
CINet: Realizing Incremental Trajectory Prediction with Prior-Aware Continual Causal Intervention
Xiaohe Li, Feilong Huang, Zide Fan +4
Trajectory prediction for multi-agents in complex scenarios is crucial for applications like autonomous driving. However, existing methods often overlook environmental biases, whic…