arXiv subjects

Robert C. Qiu

Publications and source records attributed to Robert C. Qiu.

At least 19 recordsLinked to original sources

arXiv2026

Diving into Kronecker Adapters: Component Design Matters

Kronecker adapters have emerged as a promising approach for fine-tuning large-scale models, enabling high-rank updates through tunable component structures. However, existing work largely treats the component structure as a fixed or heuristic design choice, leaving the dimensions and number of Kronecker components underexplored. In this paper, we identify component structure as a key factor governing the capacity of Kronecker adapters. We perform a fine-grained analysis of both the dimensions and number of Kronecker components. In particular, we show that the alignment between Kronecker adapters and full fine-tuning depends on component configurations. Guided by these insights, we propose Component Designed Kronecker Adapters (CDKA). We further provide parameter-budget-aware configuration guidelines and a tailored training stabilization strategy for practical deployment. Experiments across various architectures and modalities demonstrate the effectiveness of CDKA. Code is available at https://github.com/rainstonee/CDKA.

cs.LG↗

arXiv2026

Consistency Deep Equilibrium Models

Deep Equilibrium Models (DEQs) have emerged as a powerful paradigm in deep learning, offering the ability to model infinite-depth networks with constant memory usage. However, DEQs incur significant inference latency due to the iterative nature of fixed-point solvers. In this work, we introduce the Consistency Deep Equilibrium Model (C-DEQ), a novel framework that leverages consistency distillation to accelerate DEQ inference. We cast the DEQ iterative inference process as evolution along a fixed ODE trajectory toward the equilibrium. Along this trajectory, we train C-DEQs to consistently map intermediate states directly to the fixed point, enabling few-step inference while preserving the performance of the teacher DEQ. At the same time, it facilitates multi-step evaluation to flexibly trade computation for performance gains. Extensive experiments across various domain tasks demonstrate that C-DEQs achieve consistent 2-20$\times$ accuracy improvements over implicit DEQs under the same few-step inference budget. Our code is available at https://github.com/landrarwolf/CDEQ.

cs.LG↗

arXiv2026

A Large-Dimensional Analysis of ESPRIT DoA Estimation: Inconsistency and a Correction via RMT

In this paper, we perform asymptotic analyses of the widely used ESPRIT direction-of-arrival (DoA) estimator for large arrays, where the array size $N$ and the number of snapshots $T$ grow to infinity at the same pace. In this large-dimensional regime, the sample covariance matrix (SCM) is known to be a poor eigenspectral estimator of the population covariance. We show that the classical ESPRIT algorithm, that relies on the SCM, and as a consequence of the large-dimensional inconsistency of the SCM, produces inconsistent DoA estimates as $N,T \to \infty$ with $N/T \to c \in (0,\infty)$, for both widely-~and~closely-spaced DoAs. Leveraging tools from random matrix theory (RMT), we propose an improved G-ESPRIT method and prove its consistency in the same large-dimensional setting. From a technical perspective, we derive a novel bound on the eigenvalue differences between two potentially non-Hermitian matrices, which may be of independent interest. Numerical simulations are provided to corroborate our theoretical findings.

eess.SP↗

arXiv2026

Metasurface-Enabled Extremely Large-Scale Antenna Systems: Transceiver Architecture, Physical Modeling, and Channel Estimation

Extremely large-scale antenna arrays (ELAAs) have emerged as a pivotal technology for addressing the unprecedented performance demands of next-generation wireless communication systems. To enhance their practicality, we propose metasurface-enabled extremely large-scale antenna (MELA) systems -- novel transceiver architectures that employ reconfigurable transmissive metasurfaces to facilitate efficient over-the-air RF-to-antenna coupling and phase control. This architecture eliminates the need for bulky switch matrices and costly phase-shifter networks typically required in conventional solutions. Physically grounded models are developed to characterize electromagnetic field propagation through individual transmissive unit cells, capturing the fundamental physics of wave transformation and transmission. Additionally, distance-dependent approximate models are introduced, exhibiting structural properties conducive to efficient parameter estimation and signal processing. Based on the channel model, a two stage channel estimation framework is proposed for the scenarios comprising users in the hybrid near- and far-fields. In the first stage, a dictionary-driven beamspace filtering technique enables rapid angular-domain scanning. In the refinement stage, the rotational symmetry of subarrays is exploited to design super-resolution estimators that jointly recover angular and range parameters. An analytical expression for the half-power beamwidth of MELA is derived, revealing its near-optimal spatial resolution relative to conventional ELAA architectures. Numerical experiments further validate the high-resolution of the proposed channel estimation algorithm and the fidelity of the electromagnetic model, positioning the MELA architecture as a highly competitive and forward-looking solution for practical ELAA deployment.

eess.SP↗

arXiv2025

Bayesian Optimization for Non-Cooperative Game-Based Radio Resource Management

Radio resource management in modern cellular networks often calls for the optimization of complex utility functions that are potentially conflicting between different base stations (BSs). Coordinating the resource allocation strategies efficiently across BSs to ensure stable network service poses significant challenges, especially when each utility is accessible only via costly, black-box evaluations. This paper considers formulating the resource allocation among spectrum sharing BSs as a non-cooperative game, with the goal of aligning their allocation incentives toward a stable outcome. To address this challenge, we propose PPR-UCB, a novel Bayesian optimization (BO) strategy that learns from sequential decision-evaluation pairs to approximate pure Nash equilibrium (PNE) solutions. PPR-UCB applies martingale techniques to Gaussian process (GP) surrogates and constructs high probability confidence bounds for utilities uncertainty quantification. Experiments on downlink transmission power allocation in a multi-cell multi-antenna system demonstrate the efficiency of PPR-UCB in identifying effective equilibrium solutions within a few data samples.

eess.SP↗

arXiv2025

Adaptive Discretization for Consistency Models

Consistency Models (CMs) have shown promise for efficient one-step generation. However, most existing CMs rely on manually designed discretization schemes, which can cause repeated adjustments for different noise schedules and datasets. To address this, we propose a unified framework for the automatic and adaptive discretization of CMs, formulating it as an optimization problem with respect to the discretization step. Concretely, during the consistency training process, we propose using local consistency as the optimization objective to ensure trainability by avoiding excessive discretization, and taking global consistency as a constraint to ensure stability by controlling the denoising error in the training target. We establish the trade-off between local and global consistency with a Lagrange multiplier. Building on this framework, we achieve adaptive discretization for CMs using the Gauss-Newton method. We refer to our approach as ADCMs. Experiments demonstrate that ADCMs significantly improve the training efficiency of CMs, achieving superior generative performance with minimal training overhead on both CIFAR-10 and ImageNet. Moreover, ADCMs exhibit strong adaptability to more advanced DM variants. Code is available at https://github.com/rainstonee/ADCM.

cs.LG↗

arXiv2025

DGAR: A Unified Domain Generalization Framework for RF-Based Human Activity Recognition

Radio-frequency (RF)-based human activity recognition (HAR) provides a contactless and privacy-preserving solution for monitoring human behavior in applications such as astronaut extravehicular activity monitoring, human-autonomy collaborative cockpit, and unmanned aerial vehicle surveillance. However, real-world deployments usually face the challenge of domain knowledge shifts arising from inter-subject variability, heterogeneous physical environments, and unseen activity patterns, resulting in significant performance degradation. To address this issue, we propose DGAR, a domain-generalized activity recognition framework that learns transferable representations without collecting data from the target domain. DGAR integrates instance-adaptive feature modulation with cross-domain distribution alignment to enhance both personalization and generalization. Specifically, it incorporates a squeeze-and-excitation (SE) block to extract salient spatiotemporal features and employs correlation alignment to mitigate inter-domain discrepancies. Extensive experiments on public RF-based datasets -- HUST-HAR, Lab-LFM, and Office-LFM -- demonstrate that DGAR consistently outperforms state-of-the-art baselines, achieving up to a 5.81% improvement in weighted F1-score. The empirical results substantiate the generalization capability of DGAR in real-time RF sensing across dynamic scenarios.

eess.SP↗

arXiv2025

IGNN-Solver: A Graph Neural Solver for Implicit Graph Neural Networks

Implicit graph neural networks (IGNNs), which exhibit strong expressive power with a single layer, have recently demonstrated remarkable performance in capturing long-range dependencies (LRD) in underlying graphs while effectively mitigating the over-smoothing problem. However, IGNNs rely on computationally expensive fixed-point iterations, which lead to significant speed and scalability limitations, hindering their application to large-scale graphs. To achieve fast fixed-point solving for IGNNs, we propose a novel graph neural solver, IGNN-Solver, which leverages the generalized Anderson Acceleration method, parameterized by a tiny GNN, and learns iterative updates as a graph-dependent temporal process. To improve effectiveness on large-scale graph tasks, we further integrate sparsification and storage compression methods, specifically tailored for the IGNN-Solver, into its design. Extensive experiments demonstrate that the IGNN-Solver significantly accelerates inference on both small- and large-scale tasks, achieving a $1.5\times$ to $8\times$ speedup without sacrificing accuracy. This advantage becomes more pronounced as the graph scale grows, facilitating its large-scale deployment in real-world applications. The code to reproduce our results is available at https://github.com/landrarwolf/IGNN-Solver.

cs.LG↗

arXiv2025

Textual and Visual Prompt Fusion for Image Editing via Step-Wise Alignment

The use of denoising diffusion models is becoming increasingly popular in the field of image editing. However, current approaches often rely on either image-guided methods, which provide a visual reference but lack control over semantic consistency, or text-guided methods, which ensure alignment with the text guidance but compromise visual quality. To resolve this issue, we propose a framework that integrates a fusion of generated visual references and text guidance into the semantic latent space of a \textit{frozen} pre-trained diffusion model. Using only a tiny neural network, our framework provides control over diverse content and attributes, driven intuitively by the text prompt. Compared to state-of-the-art methods, the framework generates images of higher quality while providing realistic editing effects across various benchmark datasets.

cs.CV↗

arXiv2024

TRIS-HAR: Transmissive Reconfigurable Intelligent Surfaces-assisted Cognitive Wireless Human Activity Recognition Using State Space Models

Human activity recognition (HAR) using radio frequency (RF) signals has garnered considerable attention for its applications in smart environments. However, traditional systems often struggle with limited independent channels between transmitters and receivers, multipath fading, and environmental noise, which particularly degrades performance in through-the-wall scenarios. In this paper, we present a transmissive reconfigurable intelligent surface (TRIS)-assisted through-the-wall human activity recognition (TRIS-HAR) system. The system employs TRIS technology to actively reshape wireless signal propagation, creating multiple independent paths to enhance signal clarity and improve recognition accuracy in complex indoor settings. Additionally, we propose the Human intelligence Mamba (HiMamba), an advanced state space model that captures temporal and frequency-based information for precise activity recognition. HiMamba achieves state-of-the-art performance on two public datasets, demonstrating superior accuracy. Extensive experiments indicate that the TRIS-HAR system improves recognition performance from 85.00% to 98.06% in laboratory conditions and maintains high performance across various environments. This approach offers a robust solution for enhancing RF-based HAR, with promising applications in smart home and elderly care systems.

eess.SP↗

arXiv2024

Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures

Deep equilibrium models (DEQs), as a typical implicit neural network, have demonstrated remarkable success on various tasks. There is, however, a lack of theoretical understanding of the connections and differences between implicit DEQs and explicit neural network models. In this paper, leveraging recent advances in random matrix theory (RMT), we perform an in-depth analysis on the eigenspectra of the conjugate kernel (CK) and neural tangent kernel (NTK) matrices for implicit DEQs, when the input data are drawn from a high-dimensional Gaussian mixture. We prove, in this setting, that the spectral behavior of these Implicit-CKs and NTKs depend on the DEQ activation function and initial weight variances, but only via a system of four nonlinear equations. As a direct consequence of this theoretical result, we demonstrate that a shallow explicit network can be carefully designed to produce the same CK or NTK as a given DEQ. Despite derived here for Gaussian mixture data, empirical results show the proposed theory and design principle also apply to popular real-world datasets.

cs.LG↗

arXiv2024

RISAR: RIS-assisted Human Activity Recognition with Commercial Wi-Fi Devices

Human activity recognition (HAR) holds significant importance in smart homes, security, and healthcare. Existing systems face limitations because of the insufficient spatial diversity provided by a limited number of antennas. Furthermore, inefficiencies in noise reduction and feature extraction from sensing data pose challenges to recognition performance. This study presents a reconfigurable intelligent surface (RIS)-assisted passive human activity recognition (RISAR) method, compatible with commercial Wi-Fi devices. RISAR leverages a RIS to enhance the spatial diversity of Wi-Fi signals, effectively capturing a wider range of information distributed across the spatial domain. A novel high-dimensional factor model based on random matrix theory is proposed to address noise reduction and feature extraction in the temporal domain. A dual-stream spatial-temporal attention network model is developed to assign variable weights to different characteristics and sequences, mimicking human cognitive processes in prioritizing essential information. Experimental analysis shows that RISAR significantly outperforms existing HAR methods in accuracy and efficiency, achieving an average accuracy of 97.26%. These findings underscore RISAR's adaptability and potential as a robust activity recognition solution in real environments.

eess.SY↗

arXiv2024

"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach

Modern deep neural networks (DNNs) are extremely powerful; however, this comes at the price of increased depth and having more parameters per layer, making their training and inference more computationally challenging. In an attempt to address this key limitation, efforts have been devoted to the compression (e.g., sparsification and/or quantization) of these large-scale machine learning models, so that they can be deployed on low-power IoT devices. In this paper, building upon recent advances in neural tangent kernel (NTK) and random matrix theory (RMT), we provide a novel compression approach to wide and fully-connected \emph{deep} neural nets. Specifically, we demonstrate that in the high-dimensional regime where the number of data points $n$ and their dimension $p$ are both large, and under a Gaussian mixture model for the data, there exists \emph{asymptotic spectral equivalence} between the NTK matrices for a large family of DNN models. This theoretical result enables "lossless" compression of a given DNN to be performed, in the sense that the compressed network yields asymptotically the same NTK as the original (dense and unquantized) network, with its weights and activations taking values \emph{only} in $\{ 0, \pm 1 \}$ up to a scaling. Experiments on both synthetic and real-world data are conducted to support the advantages of the proposed compression scheme, with code available at \url{https://github.com/Model-Compression/Lossless_Compression}.

stat.ML↗

arXiv2023

DeLR: Active Learning for Detection with Decoupled Localization and Recognition Query

Active learning has been demonstrated effective to reduce labeling cost, while most progress has been designed for image recognition, there still lacks instance-level active learning for object detection. In this paper, we rethink two key components, i.e., localization and recognition, for object detection, and find that the correctness of them are highly related, therefore, it is not necessary to annotate both boxes and classes if we are given pseudo annotations provided with the trained model. Motivated by this, we propose an efficient query strategy, termed as DeLR, that Decoupling the Localization and Recognition for active query. In this way, we are probably free of class annotations when the localization is correct, and able to assign the labeling budget for more informative samples. There are two main differences in DeLR: 1) Unlike previous methods mostly focus on image-level annotations, where the queried samples are selected and exhausted annotated. In DeLR, the query is based on region-level, and we only annotate the object region that is queried; 2) Instead of directly providing both localization and recognition annotations, we separately query the two components, and thus reduce the recognition budget with the pseudo class labels provided by the model. Experiments on several benchmarks demonstrate its superiority. We hope our proposed query strategy would shed light on researches in active learning in object detection.

cs.CV↗

arXiv2023

Invisible Units Detection and Estimation Based on Random Matrix Theory

Invisible units mainly refer to small-scale units that are not monitored by, and thus are not visible to utilities. Integration of these invisible units into power systems does significantly affect the way in which a distribution grid is planned and operated. This paper, based on random matrix theory (RMT), proposes a statistical, data-driven framework to handle the massive grid data, in contrast to its deterministic, model-based counterpart. Combining the RMT-based data-mining framework with conventional techniques, some heuristics are derived as the solution to the invisible units detection and estimation task: linear eigenvalue statistic indicators (LESs) are suggested as the main ingredients of the solution; according to the statistical properties of LESs, the hypothesis testing is formulated to conduct change point detection in the high-dimensional space. The proposed method is promising for anomaly detection and pertinent to current distribution networks-it is capable of detecting invisible power usage and fraudulent behavior while even being able to locate the suspect's location. Case studies, using both simulated data and actual data, validate the proposed method.

stat.AP↗

arXiv2023

RIS-aided Real-time Beam Tracking for a Mobile User via Bayesian Optimization

The conventional beam management procedure mandates that the user equipment (UE) periodically measure the received signal reference power (RSRP) and transmit these measurements to the base station (BS). The challenge lies in balancing the number of beams used: it should be large enough to identify high-RSRP beams but small enough to minimize reporting overhead. This paper investigates this essential performance-versus-overhead trade-off using Bayesian optimization. The proposed approach represents the first application of real-time beam tracking via Bayesian optimization in RIS-assisted communication systems. Simulation results validate the effectiveness of this scheme.

eess.SY↗

arXiv2023

Timestamp-supervised Wearable-based Activity Segmentation and Recognition with Contrastive Learning and Order-Preserving Optimal Transport

Human activity recognition (HAR) with wearables is one of the serviceable technologies in ubiquitous and mobile computing applications. The sliding-window scheme is widely adopted while suffering from the multi-class windows problem. As a result, there is a growing focus on joint segmentation and recognition with deep-learning methods, aiming at simultaneously dealing with HAR and time-series segmentation issues. However, obtaining the full activity annotations of wearable data sequences is resource-intensive or time-consuming, while unsupervised methods yield poor performance. To address these challenges, we propose a novel method for joint activity segmentation and recognition with timestamp supervision, in which only a single annotated sample is needed in each activity segment. However, the limited information of sparse annotations exacerbates the gap between recognition and segmentation tasks, leading to sub-optimal model performance. Therefore, the prototypes are estimated by class-activation maps to form a sample-to-prototype contrast module for well-structured embeddings. Moreover, with the optimal transport theory, our approach generates the sample-level pseudo-labels that take advantage of unlabeled data between timestamp annotations for further performance improvement. Comprehensive experiments on four public HAR datasets demonstrate that our model trained with timestamp supervision is superior to the state-of-the-art weakly-supervised methods and achieves comparable performance to the fully-supervised approaches.

cs.CV↗

arXiv2023

On the Equivalence between Implicit and Explicit Neural Networks: A High-dimensional Viewpoint

Implicit neural networks have demonstrated remarkable success in various tasks. However, there is a lack of theoretical analysis of the connections and differences between implicit and explicit networks. In this paper, we study high-dimensional implicit neural networks and provide the high dimensional equivalents for the corresponding conjugate kernels and neural tangent kernels. Built upon this, we establish the equivalence between implicit and explicit networks in high dimensions.

cs.LG↗