4 papers
Hybrid Distillation with CoT Guidance for Edge-Drone Control Code Generation
Yizhan Feng, Hichem Snoussi, Yuhang Wang +3
With large language models demonstrating significant potential in code generation tasks, their application to onboard control of resource-constrained Unmanned Aerial Vehicles has e…
Edge-Optimized Multimodal Learning for UAV Video Understanding via BLIP-2
Yizhan Feng, Hichem Snoussi, Jing Teng +4
The demand for real-time visual understanding and interaction in complex scenarios is increasingly critical for unmanned aerial vehicles. However, a significant challenge arises fr…
Large Language Models to Enhance Multi-task Drone Operations in Simulated Environments
Yizhan Feng, Hichem Snoussi, Jing Teng +2
Benefiting from the rapid advancements in large language models (LLMs), human-drone interaction has reached unprecedented opportunities. In this paper, we propose a method that int…
Pinco: Position-induced Consistent Adapter for Diffusion Transformer in Foreground-conditioned Inpainting
Guangben Lu, Yuzhen Du, Zhimin Sun +6
Foreground-conditioned inpainting aims to seamlessly fill the background region of an image by utilizing the provided foreground subject and a text description. While existing T2I-…