7 papers
Talk Less, Fly Lighter: Autonomous Semantic Compression for UAV Swarm Communication via LLMs
Fei Lin, Tengchao Zhang, Qinghua Ni +5
The rapid adoption of Large Language Models (LLMs) in unmanned systems has significantly enhanced the semantic understanding and autonomous task execution capabilities of Unmanned…
Context-Aware Probabilistic Modeling with LLM for Multimodal Time Series Forecasting
Yueyang Yao, Jiajun Li, Xingyuan Dai +4
Time series forecasting is important for applications spanning energy markets, climate analysis, and traffic management. However, existing methods struggle to effectively integrate…
Hierarchical Self-Prompting SAM: A Prompt-Free Medical Image Segmentation Framework
Mengmeng Zhang, Xingyuan Dai, Yicheng Sun +6
Although the Segment Anything Model (SAM) is highly effective in natural image segmentation, it requires dependencies on prompts, which limits its applicability to medical imaging…
MiniDrive: More Efficient Vision-Language Models with Multi-Level 2D Features as Text Tokens for Autonomous Driving
Enming Zhang, Xingyuan Dai, Min Huang +2
Vision-language models (VLMs) serve as general-purpose end-to-end models in autonomous driving, performing subtasks such as prediction, planning, and perception through question-an…
Offline Reinforcement Learning with Discrete Diffusion Skills
RuiXi Qiao, Jie Cheng, Xingyuan Dai +2
Skills have been introduced to offline reinforcement learning (RL) as temporal abstractions to tackle complex, long-horizon tasks, promoting consistent behavior and enabling meanin…
UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility
Yonglin Tian, Fei Lin, Yiduo Li +11
Low-altitude mobility, exemplified by unmanned aerial vehicles (UAVs), has introduced transformative advancements across various domains, like transportation, logistics, and agricu…