Long Jiao

Mahmuda Keya, Sneh Pillai, Jiawei Yuan et al.

There is growing interest in enabling wireless sensing systems to interpret human motion from unsegmented wireless signals; however, existing CSI-based applications rely heavily on accurate signal segmentation and predefined action labels, limiting their applicability in zero-shot scenarios. We present WirelessSenseLLM, a language-driven framework that leverages large language models (LLMs) to enable zero-shot human motion understanding from unsegmented Wi-Fi Channel State Information (CSI). To bridge the modality gap between time-series CSI and discrete language representations, we introduce a CSI-to-Language Adapter and a cross-modal projection mechanism that maps CSI features into a language-aligned semantic space. This design enables the generation of fine-grained natural language descriptions of sequential and overlapping human motions, supporting downstream reasoning without segmented training data. We address two core technical challenges: modality mismatch between CSI features and language embeddings, and overlapping actions in unsegmented CSI streams. Extensive experiments demonstrate strong performance in zero-shot action understanding (92% accuracy and 91% F1-score), language-based reasoning quality (30% factual and 15% reasoning improvements), and multi-person motion explanation with an average 12.33% improvement over prior methods. These results highlight WirelessSenseLLM's effectiveness for robust and interpretable human motion understanding from CSI signals.

Wenhao Wang, Yanyan Li, Long Jiao et al.

Recent advances in large language models (LLMs) provide robots with contextual reasoning abilities to comprehend human instructions. Yet, current LLM-enabled robots typically depend on cloud-based models or high-performance computing infrastructure, which limit their deployment on robots under unreliable internet environments or with constrained computational resources, such as UAVs and small ground vehicles. Thus, deploying fine-tuned small language models (SLMs) that support onboard deployment offers a promising alternative. This paper introduces Ro-SLM, a framework that enables reliable SLM-driven robot operation by distilling LLMs' knowledge and reasoning. Ro-SLM starts from dataset synthesis by leveraging LLMs to generate diverse task instructions, produce corresponding ground truth code with minimal human assistance, and augment instructions into real-world application scenarios. Ro-SLM is then fine-tuned with the dataset, in which LLM serves as a reward function to guide the training. Extensive experiments on UAV operation tasks demonstrate that Ro-SLM improves the performance of SLM from being incapable of supporting robotic task planning and code generation to achieving performance that approaches LLM.

Wenhao Wang, Yanyan Li, Long Jiao et al.

The integration of Large Language Models (LLMs) into robotic control, including drones, has the potential to revolutionize autonomous systems. Research studies have demonstrated that LLMs can be leveraged to support robotic operations. However, when facing tasks with complex reasoning, concerns and challenges are raised about the reliability of solutions produced by LLMs. In this paper, we propose a prompt framework with enhanced reasoning to enable reliable LLM-driven control for drones. Our framework consists of novel technical components designed using Guidelines, Skill APIs, Constraints, and Examples, namely GSCE. GSCE is featured by its reliable and constraint-compliant code generation. We performed thorough experiments using GSCE for the control of drones with a wide level of task complexities. Our experiment results demonstrate that GSCE can significantly improve task success rates and completeness compared to baseline approaches, highlighting its potential for reliable LLM-driven autonomous drone systems.

Hanyu Zhu, Lance Fiondella, Jiawei Yuan et al.

Retrieval-Augmented Generation (RAG) empowers Large Language Models (LLMs) to dynamically integrate external knowledge during inference, improving their factual accuracy and adaptability. However, adversaries can inject poisoned external knowledge to override the model's internal memory. While existing attacks iteratively manipulate retrieval content or prompt structure of RAG, they largely ignore the model's internal representation dynamics and neuron-level sensitivities. The underlying mechanism of RAG poisoning has not been fully studied and the effect of knowledge conflict with strong parametric knowledge in RAG is not considered. In this work, we propose NeuroGenPoisoning, a novel attack framework that generates adversarial external knowledge in RAG guided by LLM internal neuron attribution and genetic optimization. Our method first identifies a set of Poison-Responsive Neurons whose activation strongly correlates with contextual poisoning knowledge. We then employ a genetic algorithm to evolve adversarial passages that maximally activate these neurons. Crucially, our framework enables massive-scale generation of effective poisoned RAG knowledge by identifying and reusing promising but initially unsuccessful external knowledge variants via observed attribution signals. At the same time, Poison-Responsive Neurons guided poisoning can effectively resolves knowledge conflict. Experimental results across models and datasets demonstrate consistently achieving high Population Overwrite Success Rate (POSR) of over 90% while preserving fluency. Empirical evidence shows that our method effectively resolves knowledge conflict.

Long Jiao, Ning Wang, Pu Wang et al.

The bloom of the fifth generation (5G) communication and beyond serves as a catalyst for physical layer key generation techniques. In 5G communications systems, many challenges in traditional physical layer key generation schemes, such as co-located eavesdroppers, the high bit disagreement ratio, and high temporal correlation, could be overcome. This paper lists the key-enabler techniques in 5G wireless networks, which offer opportunities to address existing issues in physical layer key generation. We survey the existing key generation methods and introduce possible solutions for the existing issues. The new solutions include applying the high signal directionality in beamforming to resist co-located eavesdroppers, utilizing the sparsity of millimeter wave (mmWave) channel to achieve a low bit disagreement ratio under low signal-to-noise-ratio (SNR), and exploiting hybrid precoding to reduce the temporal correlation among measured samples. Finally, the future trends of physical layer key generation in 5G and beyond communications are discussed.