Qun Wang

Jiajun Xu, Zhiyuan Li, Wei Chen et al.

The advent of large language models (LLMs) revolutionized natural language processing applications, and running LLMs on edge devices has become increasingly attractive for reasons including reduced latency, data localization, and personalized user experiences. This comprehensive review examines the challenges of deploying computationally expensive LLMs on resource-constrained devices and explores innovative solutions across multiple domains. The paper investigates the development of on-device language models, their efficient architectures, including parameter sharing and modular designs, as well as state-of-the-art compression techniques like quantization, pruning, and knowledge distillation. Hardware acceleration strategies and collaborative edge-cloud deployment approaches are analyzed, highlighting the intricate balance between performance and resource utilization. Case studies of on-device language models from major mobile manufacturers demonstrate real-world applications and potential benefits. The review also addresses critical aspects such as adaptive learning, multi-modal capabilities, and personalization. By identifying key research directions and open challenges, this paper provides a roadmap for future advancements in on-device language models, emphasizing the need for interdisciplinary efforts to realize the full potential of ubiquitous, intelligent computing while ensuring responsible and ethical deployment. For a comprehensive review of research work and educational resources on on-device large language models (LLMs), please visit https://github.com/NexaAI/Awesome-LLMs-on-device. To download and run on-device LLMs, visit https://www.nexaai.com/models.

Jiajun Xu, Qun Wang, Yuhang Cao et al.

This paper investigates integrating large language models (LLMs) with advanced hardware, focusing on developing a general-purpose device designed for enhanced interaction with LLMs. Initially, we analyze the current landscape, where virtual assistants and LLMs are reshaping human-technology interactions, highlighting pivotal advancements and setting the stage for a new era of intelligent hardware. Despite substantial progress in LLM technology, a significant gap exists in hardware development, particularly concerning scalability, efficiency, affordability, and multimodal capabilities. This disparity presents both challenges and opportunities, underscoring the need for hardware that is not only powerful but also versatile and capable of managing the sophisticated demands of modern computation. Our proposed device addresses these needs by emphasizing scalability, multimodal data processing, enhanced user interaction, and privacy considerations, offering a comprehensive platform for LLM integration in various applications.

Xiuxin Xia, Qun Wang, He Wang et al.

The taste electroencephalogram (EEG) evoked by the taste stimulation can reflect different brain patterns and be used in applications such as sensory evaluation of food. However, considering the computational cost and efficiency, EEG data with many channels has to face the critical issue of channel selection. This paper proposed a channel selection method called class activation mapping with attention (CAM-Attention). The CAM-Attention method combined a convolutional neural network with channel and spatial attention (CNN-CSA) model with a gradient-weighted class activation mapping (Grad-CAM) model. The CNN-CSA model exploited key features in EEG data by attention mechanism, and the Grad-CAM model effectively realized the visualization of feature regions. Then, channel selection was effectively implemented based on feature regions. Finally, the CAM-Attention method reduced the computational burden of taste EEG recognition and effectively distinguished the four tastes. In short, it has excellent recognition performance and provides effective technical support for taste sensory evaluation.

Luoying Hao, Yan Hu, Wenjun Lin et al.

Recognition and localization of surgical detailed actions is an essential component of developing a context-aware decision support system. However, most existing detection algorithms fail to provide high-accuracy action classes even having their locations, as they do not consider the surgery procedure's regularity in the whole video. This limitation hinders their application. Moreover, implementing the predictions in clinical applications seriously needs to convey model confidence to earn entrustment, which is unexplored in surgical action prediction. In this paper, to accurately detect fine-grained actions that happen at every moment, we propose an anchor-context action detection network (ACTNet), including an anchor-context detection (ACD) module and a class conditional diffusion (CCD) module, to answer the following questions: 1) where the actions happen; 2) what actions are; 3) how confidence predictions are. Specifically, the proposed ACD module spatially and temporally highlights the regions interacting with the extracted anchor in surgery video, which outputs action location and its class distribution based on anchor-context interactions. Considering the full distribution of action classes in videos, the CCD module adopts a denoising diffusion-based generative model conditioned on our ACD estimator to further reconstruct accurately the action predictions. Moreover, we utilize the stochastic nature of the diffusion model outputs to access model confidence for each prediction. Our method reports the state-of-the-art performance, with improvements of 4.0% mAP against baseline on the surgical video dataset.

Yichuan Wang, Yang Liu, Yu Yan et al.

We introduce Xmodel-LM, a compact and efficient 1.1B language model pre-trained on around 2 trillion tokens. Trained on our self-built dataset (Xdata), which balances Chinese and English corpora based on downstream task optimization, Xmodel-LM exhibits remarkable performance despite its smaller size. It notably surpasses existing open-source language models of similar scale. Our model checkpoints and code are publicly accessible on GitHub at https://github.com/XiaoduoAILab/XmodelLM.

Xiaodong Qu, Andrews Damoah, Joshua Sherwood et al.

Artificial Intelligence (AI) agents have rapidly evolved from specialized, rule-based programs to versatile, learning-driven autonomous systems capable of perception, reasoning, and action in complex environments. The explosion of data, advances in deep learning, reinforcement learning, and multi-agent coordination have accelerated this transformation. Yet, designing and deploying unified AI agents that seamlessly integrate cognition, planning, and interaction remains a grand challenge. In this review, we systematically examine the architectural principles, foundational components, and emergent paradigms that define the landscape of contemporary AI agents. We synthesize insights from cognitive science-inspired models, hierarchical reinforcement learning frameworks, and large language model-based reasoning. Moreover, we discuss the pressing ethical, safety, and interpretability concerns associated with deploying these agents in real-world scenarios. By highlighting major breakthroughs, persistent challenges, and promising research directions, this review aims to guide the next generation of AI agent systems toward more robust, adaptable, and trustworthy autonomous intelligence.

Satvik Verma, Qun Wang, E. Wes Bethel

The widespread adoption of Internet of Things (IoT) devices has introduced significant cybersecurity challenges, particularly with the increasing frequency and sophistication of Distributed Denial of Service (DDoS) attacks. Traditional machine learning (ML) techniques often fall short in detecting such attacks due to the complexity of blended and evolving patterns. To address this, we propose a novel framework leveraging On-Device Large Language Models (ODLLMs) augmented with fine-tuning and knowledge base (KB) integration for intelligent IoT network attack detection. By implementing feature ranking techniques and constructing both long and short KBs tailored to model capacities, the proposed framework ensures efficient and accurate detection of DDoS attacks while overcoming computational and privacy limitations. Simulation results demonstrate that the optimized framework achieves superior accuracy across diverse attack types, especially when using compact models in edge computing environments. This work provides a scalable and secure solution for real-time IoT security, advancing the applicability of edge intelligence in cybersecurity.

Qun Wang, Yingzhou Lu, Guiran Liu et al.

Unlicensed 6GHz is becoming a primary workhorse for high-capacity access, with Wi-Fi and 5G NR-U competing for the same channels under listen-before-talk (LBT) rules. Operating in this regime requires decisions that jointly trade throughput, energy, and service-level objectives while remaining safe and auditable. We present an agentic controller that separates {policy} from {execution}. At the start of each scheduling epoch the agent summarizes telemetry (per-channel busy and baseline LBT failure; per-user CQI, backlog, latency, battery, priority, and power mode) and invokes a large language model (LLM) to propose a small set of interpretable knobs: a fairness index α, per-channel duty-cycle caps for Wi-Fi/NR-U, and class weights. A deterministic optimizer then enforces feasibility and computes an α-fair allocation that internalizes LBT losses and energy cost; malformed or unsafe policies are clamped and fall back to a rule baseline. In a 6GHz simulator with two 160MHz channels and mixed Wi-Fi/NR-U users, LLM-assisted policies consistently improve energy efficiency while keeping throughput competitive with a strong rule baseline. One LLM lowers total energy by 35.3% at modest throughput loss, and another attains the best overall trade-off, finishing with higher total bits (+3.5%) and higher bits/J (+12.2%) than the baseline. We release code, per-epoch logs, and plotting utilities to reproduce all figures and numbers, illustrating how transparent, policy-level LLM guidance can safely improve wireless coexistence.

Qun Wang, Haijian Sun, Rose Qingyang Hu et al.

The exponential growth of internet connected systems has generated numerous challenges, such as spectrum shortage issues, which require efficient spectrum sharing (SS) solutions. Complicated and dynamic SS systems can be exposed to different potential security and privacy issues, requiring protection mechanisms to be adaptive, reliable, and scalable. Machine learning (ML) based methods have frequently been proposed to address those issues. In this article, we provide a comprehensive survey of the recent development of ML based SS methods, the most critical security issues, and corresponding defense mechanisms. In particular, we elaborate the state-of-the-art methodologies for improving the performance of SS communication systems for various vital aspects, including ML based cognitive radio networks (CRNs), ML based database assisted SS networks, ML based LTE-U networks, ML based ambient backscatter networks, and other ML based SS solutions. We also present security issues from the physical layer and corresponding defending strategies based on ML algorithms, including Primary User Emulation (PUE) attacks, Spectrum Sensing Data Falsification (SSDF) attacks, jamming attacks, eavesdropping attacks, and privacy issues. Finally, extensive discussions on open challenges for ML based SS are also given. This comprehensive review is intended to provide the foundation for and facilitate future studies on exploring the potential of emerging ML for coping with increasingly complex SS and their security problems.

Xiang Ma, Haijian Sun, Qun Wang et al.

A new machine learning (ML) technique termed as federated learning (FL) aims to preserve data at the edge devices and to only exchange ML model parameters in the learning process. FL not only reduces the communication needs but also helps to protect the local privacy. Although FL has these advantages, it can still experience large communication latency when there are massive edge devices connected to the central parameter server (PS) and/or millions of model parameters involved in the learning process. Over-the-air computation (AirComp) is capable of computing while transmitting data by allowing multiple devices to send data simultaneously by using analog modulation. To achieve good performance in FL through AirComp, user scheduling plays a critical role. In this paper, we investigate and compare different user scheduling policies, which are based on various criteria such as wireless channel conditions and the significance of model updates. Receiver beamforming is applied to minimize the mean-square-error (MSE) of the distortion of function aggregation result via AirComp. Simulation results show that scheduling based on the significance of model updates has smaller fluctuations in the training process while scheduling based on channel condition has the advantage on energy efficiency.