This paper proposes an adaptive channel contention mechanism to optimize the queuing performance of a distributed millimeter wave (mmWave) uplink system with the capability of environment and mobility sensing. The mobile agents determine their back-off timer parameters according to their local knowledge of the uplink queue lengths, channel quality, and future channel statistics, where the channel prediction relies on the environment and mobility sensing. The optimization of queuing performance with this adaptive channel contention mechanism is formulated as a decentralized multi-agent Markov decision process (MDP). Although the channel contention actions are determined locally at the mobile agents, the optimization of local channel contention policies of all mobile agents is conducted in a centralized manner according to the system statistics before the scheduling. In the solution, the local policies are approximated by analytical models, and the optimization of their parameters becomes a stochastic optimization problem along an adaptive Markov chain. An unbiased gradient estimation is proposed so that the local policies can be optimized efficiently via the stochastic gradient descent method. It is demonstrated by simulation that the proposed gradient estimation is significantly more efficient in optimization than the existing methods, e.g., simultaneous perturbation stochastic approximation (SPSA).
In this paper, a reinforcement-learning-based scheduling framework is proposed and implemented to optimize the application-layer quality-of-service (QoS) of a practical wireless local area network (WLAN) suffering from unknown interference. Particularly, application-layer tasks of file delivery and delay-sensitive communication, e.g., screen projection, in a WLAN with enhanced distributed channel access (EDCA) mechanism, are jointly scheduled by adjusting the contention window sizes and application-layer throughput limitation, such that their QoS, including the throughput of file delivery and the round trip time of the delay-sensitive communication, can be optimized. Due to the unknown interference and vendor-dependent implementation of the network interface card, the relation between the scheduling policy and the system QoS is unknown. Hence, a reinforcement learning method is proposed, in which a novel Q-network is trained to map from the historical scheduling parameters and QoS observations to the current scheduling action. It is demonstrated on a testbed that the proposed framework can achieve a significantly better QoS than the conventional EDCA mechanism.
Dynamic Graph Neural Networks (GNNs) combine temporal information with GNNs to capture structural, temporal, and contextual relationships in dynamic graphs simultaneously, leading to enhanced performance in various applications. As the demand for dynamic GNNs continues to grow, numerous models and frameworks have emerged to cater to different application needs. There is a pressing need for a comprehensive survey that evaluates the performance, strengths, and limitations of various approaches in this domain. This paper aims to fill this gap by offering a thorough comparative analysis and experimental evaluation of dynamic GNNs. It covers 81 dynamic GNN models with a novel taxonomy, 12 dynamic GNN training frameworks, and commonly used benchmarks. We also conduct experimental results from testing representative nine dynamic GNN models and three frameworks on six standard graph datasets. Evaluation metrics focus on convergence accuracy, training efficiency, and GPU memory usage, enabling a thorough comparison of performance across various models and frameworks. From the analysis and evaluation results, we identify key challenges and offer principles for future research to enhance the design of models and frameworks in the dynamic GNNs field.
Adversarial patch attacks present a significant threat to real-world object detectors due to their practical feasibility. Existing defense methods, which rely on attack data or prior knowledge, struggle to effectively address a wide range of adversarial patches. In this paper, we show two inherent characteristics of adversarial patches, semantic independence and spatial heterogeneity, independent of their appearance, shape, size, quantity, and location. Semantic independence indicates that adversarial patches operate autonomously within their semantic context, while spatial heterogeneity manifests as distinct image quality of the patch area that differs from original clean image due to the independent generation process. Based on these observations, we propose PAD, a novel adversarial patch localization and removal method that does not require prior knowledge or additional training. PAD offers patch-agnostic defense against various adversarial patches, compatible with any pre-trained object detectors. Our comprehensive digital and physical experiments involving diverse patch types, such as localized noise, printable, and naturalistic patches, exhibit notable improvements over state-of-the-art works. Our code is available at https://github.com/Lihua-Jing/PAD.
This report details the development and key achievements of our latest language model designed for custom large language models. The advancements introduced include a novel Online Data Scheduler that supports flexible training data adjustments and curriculum learning. The model's architecture is fortified with state-of-the-art techniques such as Rotary Positional Embeddings, QK-LayerNorm, and a specially crafted multilingual tokenizer to enhance stability and performance. Moreover, our robust training framework incorporates advanced monitoring and rapid recovery features to ensure optimal efficiency. Our Wonton 7B model has demonstrated competitive performance on a range of multilingual and English benchmarks. Future developments will prioritize narrowing the performance gap with more extensively trained models, thereby enhancing the model's real-world efficacy and adaptability.GitHub: \url{https://github.com/nyonicai/nyonic-public}
Chain-of-Thought (CoT) has been a widely adopted prompting method, eliciting impressive reasoning abilities of Large Language Models (LLMs). Inspired by the sequential thought structure of CoT, a number of Chain-of-X (CoX) methods have been developed to address various challenges across diverse domains and tasks involving LLMs. In this paper, we provide a comprehensive survey of Chain-of-X methods for LLMs in different contexts. Specifically, we categorize them by taxonomies of nodes, i.e., the X in CoX, and application tasks. We also discuss the findings and implications of existing CoX methods, as well as potential future directions. Our survey aims to serve as a detailed and up-to-date resource for researchers seeking to apply the idea of CoT to broader scenarios.
This letter introduces a novel unmanned aerial vehicle (UAV)-intelligent reflecting surface (IRS) structure into near-field localization systems to enhance the design flexibility of IRS, thereby obtaining additional performance gains. Specifically, a UAV-IRS is utilized to improve the harsh wireless environment and provide localization possibilities. To improve the localization accuracy, a joint optimization problem considering UAV position and UAV-IRS passive beamforming is formulated to maximize the receiving signal-to-noise ratio (SNR). An alternative optimization algorithm is proposed to solve the complex non-convex problem leveraging the projected gradient ascent (PGA) algorithm and the principle of minimizing the phase difference of the receiving signals. Closed-form expressions for UAV-IRS phase shift are derived to reduce the algorithm complexity. In the simulations, the proposed algorithm is compared with three different schemes and outperforms the others in both receiving SNR and localization accuracy.
Continuous real-time data collection in wireless sensor networks is crucial for facilitating timely decision-making and environmental monitoring. Unmanned aerial vehicles (UAVs) have received plenty of attention for collecting data efficiently due to their high flexibility and enhanced communication ability, nonetheless, the limited onboard energy restricts UAVs' application on persistent missions, such as disaster search and rescue. In this paper, we propose a rechargeable UAV-assisted periodic data collection scheme, where the UAV replenishes energy through the wireless charging platform during the mission to provide persistent information services for the sensor nodes (SNs). Specifically, the total completion time is minimized by optimizing the trajectory of the UAV to reach the balance among the collecting time, flight time, and recharging time. However, optimally solving this problem is highly non-trivial due to the non-convex constraints and the involved integer variables. To address this issue, the formulated problem is decomposed into two subproblems, namely, UAV data collection trajectory optimization and SN clustering and UAV visiting order optimization. By exploiting the convex optimization techniques and proving the total time is non-decreasing with the cluster number, a periodic trajectory optimization algorithm based on successive convex approximation (SCA) and bisection search is proposed to solve the main problem. The simulation results show the efficiency of the proposed scheme in practical scenarios and the completion time of the proposed algorithm is on average 39% and 33% lower than the two benchmarks, respectively.
A common prerequisite for evaluating a visual(-inertial) odometry (VO/VIO) algorithm is to align the timestamps and the reference frame of its estimated trajectory with a reference ground-truth derived from a system of superior precision, such as a motion capture system. The trajectory-based alignment, typically modeled as a classic hand-eye calibration, significantly influences the accuracy of evaluation metrics. However, traditional calibration methods are susceptible to the quality of the input poses. Few studies have taken this into account when evaluating VO/VIO trajectories that usually suffer from noise and drift. To fill this gap, we propose a novel spatiotemporal hand-eye calibration algorithm that fully leverages multiple constraints from screw theory for enhanced accuracy and robustness. Experimental results show that our algorithm has better performance and is less noise-prone than state-of-the-art methods.
Adversarial example detection, which can be conveniently applied in many scenarios, is important in the area of adversarial defense. Unfortunately, existing detection methods suffer from poor generalization performance, because their training process usually relies on the examples generated from a single known adversarial attack and there exists a large discrepancy between the training and unseen testing adversarial examples. To address this issue, we propose a novel method, named Adversarial Example Detection via Principal Adversarial Domain Adaptation (AED-PADA). Specifically, our approach identifies the Principal Adversarial Domains (PADs), i.e., a combination of features of the adversarial examples from different attacks, which possesses large coverage of the entire adversarial feature space. Then, we pioneer to exploit multi-source domain adaptation in adversarial example detection with PADs as source domains. Experiments demonstrate the superior generalization ability of our proposed AED-PADA. Note that this superiority is particularly achieved in challenging scenarios characterized by employing the minimal magnitude constraint for the perturbations.