arXiv subjects

Hei Victor Cheng

Publications and source records attributed to Hei Victor Cheng.

At least 19 recordsLinked to original sources

arXiv2026

TIMA: Text-Image Mutual Awareness for Balancing Zero-Shot Adversarial Robustness and Generalization Ability

Achieving zero-shot adversarial robustness without sacrificing generalization remains challenging for foundation models such as CLIP, especially under large adversarial perturbations. Through empirical analyses, we identify three critical yet overlooked issues: (1) Logit margins exhibit a stable offset between small and large adversarial perturbations, suggesting that explicitly adjusting margins could improve robustness against unseen large perturbations. (2) A significant negative correlation exists between logit margin and inter-class semantic similarity, indicating that semantic structures are insufficiently leveraged by existing methods. (3) Existing methods for adjusting text embeddings disrupt the intrinsic semantic consistency established by pre-trained models, undermining generalization capability. Motivated by these findings, we propose a novel Text-Image Mutual Awareness (TIMA) framework, including a Text-Aware Image (TAI) tuning module with an Adaptive Semantic-Aware Margin (ASAM) to explicitly calibrate logit margins, and an Image-Aware Text (IAT) tuning module with Semantic Consistent Minimum Hyperspherical Energy (SC-MHE) to preserve semantic consistency. Comprehensive experiments validate that TIMA significantly outperforms existing approaches by effectively addressing the identified limitations.

cs.CV↗

arXiv2026

RA-LWLM: Retrieval-Augmented In-Context Localization with Wireless Foundation Models

Wireless localization is a fundamental capability of sixth-generation (6G) networks. Conventional model-based methods require accurate modeling of the propagation environment and degrade in complex multipath and non-line-of-sight scenarios, while learning-based methods couple model parameters tightly to the training scene, requiring costly retraining whenever the base station (BS) configuration or propagation environment changes. In this paper, we propose RA-LWLM, a retrieval-augmented in-context localization framework that achieves training-free cross-scene adaptation by externalizing scene-specific information into a per-scene fingerprint database rather than encoding it in model weights. The framework consists of three components: a frozen wireless foundation model (FM) encoder that maps raw channel state information into a scene-agnostic representation; a retrieval module that selects the most informative references from the per-scene database via similarity search in the representation space; and a transformer-based in-context learning (ICL) module that fuses the query with the retrieved references to predict the user equipment (UE) position. To accommodate varying retrieval quality and propagation complexity across queries, the ICL module adopts a mixture-of-experts design in which experts specialize in different context sizes and are softly combined by a learnable selector. Extensive ray-tracing-based experiments across heterogeneous scenes with diverse BS configurations show that RA-LWLM achieves nearly identical accuracy on seen and unseen scenes without any per-scene retraining, substantially outperforming end-to-end and FM-based baselines. These results validate the proposed retrieval-augmented in-context paradigm as a scalable solution for cross-scene localization in 6G networks.

eess.SP↗

arXiv2026

Beam Scheduling for Cross-Layer ISAC: A Deep Reinforcement Learning Approach

Resource allocation in integrated sensing and communication (ISAC) systems needs to be optimized to balance the requirements of the communication and sensing modules considering complicated cross-layer data traffic and queue status in dynamic multi-user environments. This paper studies the beam allocation for cross-layer ISAC that achieves low-latency communication and minimizes sensing parameters estimation error. To handle the complex coupling between practical data buffer dynamics and varying wireless channels, we propose a deep reinforcement learning (DRL)-assisted approach. Rather than relying on explicit channel state information, the DRL-assisted beam allocation reduces feedback overhead by leveraging sensing observations. Simulation results verify that the DRL framework effectively takes buffer status into account and adapts to the wireless environment while allocating resources. The proposed multi-beam scheme improves overall throughput with only modest delay increases. Finally, the DRL-assisted beam management achieves both communication and sensing performance close to that of the genie-aided benchmark with perfect angle-of-departure (AoD) knowledge. These contributions advance the state-of-the-art intelligent resource management for ISAC systems.

eess.SP↗

arXiv2026

Information-Theoretic Limits on Exact Subgraph Alignment Problem

The graph alignment problem aims to identify the vertex correspondence between two correlated graphs. Most existing studies focus on the scenario in which the two graphs share the same vertex set. However, in many real-world applications, such as computer vision, social network analysis, and bioinformatics, the task often involves locating a small graph pattern within a larger graph. Existing graph alignment algorithms and analysis cannot directly address these scenarios because they are not designed to identify the specific subset of vertices where the small graph pattern resides within the larger graph. Motivated by this limitation, we introduce the subgraph alignment problem, which seeks to recover both the vertex set and/or the vertex correspondence of a small graph pattern embedded in a larger graph. In the special case where the small graph pattern is an induced subgraph of the larger graph and both the vertex set and correspondence are to be recovered, the problem reduces to the subgraph isomorphism problem, which is NP-complete in the worst case. In this paper, we formally formulate the subgraph alignment problem by proposing the Erdos-Renyi subgraph pair model together with some appropriate recovery criterion. We then establish almost-tight information-theoretic results for the subgraph alignment problem and present some novel approaches for the analysis.

cs.IT↗

arXiv2025

Link-Aware Energy-Frugal Continual Learning for Fault Detection in IoT Networks

The use of lightweight machine learning (ML) models in internet of things (IoT) networks enables resource constrained IoT devices to perform on-device inference for several critical applications. However, the inference accuracy deteriorates due to the non-stationarity in the IoT environment and limited initial training data. To counteract this, the deployed models can be updated occasionally with new observed data samples. However, this approach consumes additional energy, which is undesirable for energy constrained IoT devices. This letter introduces an event-driven communication framework that strategically integrates continual learning (CL) in IoT networks for energy-efficient fault detection. Our framework enables the IoT device and the edge server (ES) to collaboratively update the lightweight ML model by adapting to the wireless link conditions for communication and the available energy budget. Evaluation on real-world datasets show that the proposed approach can outperform both periodic sampling and non-adaptive CL in terms of inference recall; our proposed approach achieves up to a 42.8% improvement, even under tight energy and bandwidth constraint.

cs.LG↗

arXiv2025

Beampattern Synthesis for Discrete Phase RIS in Communication and Sensing Systems

Extensive research on Reconfigurable Intelligent Surfaces (RIS) has primarily focused on optimizing reflective coefficients for passive beamforming in specific target directions. This optimization typically assumes prior knowledge of the target direction, which is unavailable before the target is detected. To enhance direction estimation, it is critical to develop array pattern synthesis techniques that yield a wider beam by maximizing the received power over the entire target area. Although this challenge has been addressed with active antennas, RIS systems pose a unique challenge due to their inherent phase constraints, which can be continuous or discrete. This work addresses this challenge through a novel array pattern synthesis method tailored for discrete phase constraints in RIS. We introduce a penalty method that pushes these constraints to the boundary of the convex hull. Then, the Minorization-Maximization (MM) method is utilized to reformulate the problem into a convex one. Our numerical results show that our algorithm can generate a wide beam pattern comparable to that achievable with per-power constraints, with both the amplitudes and phases being adjustable. We compare our method with a traditional beam sweeping technique, showing a) several orders of magnitude reduction of the MSE of Angle of Arrival (AOA) at low to medium Signal-to-Noise Ratio (SNR)s; and b) $8$~dB SNR reduction to achieve a high probability of detection.

eess.SP↗

arXiv2025

See the Speaker: Crafting High-Resolution Talking Faces from Speech with Prior Guidance and Region Refinement

Unlike existing methods that rely on source images as appearance references and use source speech to generate motion, this work proposes a novel approach that directly extracts information from the speech, addressing key challenges in speech-to-talking face. Specifically, we first employ a speech-to-face portrait generation stage, utilizing a speech-conditioned diffusion model combined with statistical facial prior and a sample-adaptive weighting module to achieve high-quality portrait generation. In the subsequent speech-driven talking face generation stage, we embed expressive dynamics such as lip movement, facial expressions, and eye movements into the latent space of the diffusion model and further optimize lip synchronization using a region-enhancement module. To generate high-resolution outputs, we integrate a pre-trained Transformer-based discrete codebook with an image rendering network, enhancing video frame details in an end-to-end manner. Experimental results demonstrate that our method outperforms existing approaches on the HDTF, VoxCeleb, and AVSpeech datasets. Notably, this is the first method capable of generating high-resolution, high-quality talking face videos exclusively from a single speech input.

eess.AS↗

arXiv2025

Shuffling for Semantic Secrecy

Deep learning draws heavily on the latest progress in semantic communications. The present paper aims to examine the security aspect of this cutting-edge technique from a novel shuffling perspective. Our goal is to improve upon the conventional secure coding scheme to strike a desirable tradeoff between transmission rate and leakage rate. To be more specific, for a wiretap channel, we seek to maximize the transmission rate while minimizing the semantic error probability under the given leakage rate constraint. Toward this end, we devise a novel semantic security communication system wherein the random shuffling pattern plays the role of the shared secret key. Intuitively, the permutation of feature sequences via shuffling would distort the semantic essence of the target data to a sufficient extent so that eavesdroppers cannot access it anymore. The proposed random shuffling method also exhibits its flexibility in working for the existing semantic communication system as a plugin. Simulations demonstrate the significant advantage of the proposed method over the benchmark in boosting secure transmission, especially when channels are prone to strong noise and unpredictable fading.

cs.CR↗

arXiv2025

Multi-User Beamforming with Deep Reinforcement Learning in Sensing-Aided Communication

Mobile users are prone to experience beam failure due to beam drifting in millimeter wave (mmWave) communications. Sensing can help alleviate beam drifting with timely beam changes and low overhead since it does not need user feedback. This work studies the problem of optimizing sensing-aided communication by dynamically managing beams allocated to mobile users. A multi-beam scheme is introduced, which allocates multiple beams to the users that need an update on the angle of departure (AoD) estimates and a single beam to the users that have satisfied AoD estimation precision. A deep reinforcement learning (DRL) assisted method is developed to optimize the beam allocation policy, relying only upon the sensing echoes. For comparison, a heuristic AoD-based method using approximated Cramér-Rao lower bound (CRLB) for allocation is also presented. Both methods require neither user feedback nor prior state evolution information. Results show that the DRL-assisted method achieves a considerable gain in throughput than the conventional beam sweeping method and the AoD-based method, and it is robust to different user speeds.

eess.SP↗

arXiv2025

One-Bit Sigma-Delta DFRC Waveform Design: Using Quantization Noise for Radar Probing

Dual-functional radar-communication (DFRC) signal design has received much attention lately. We consider the scenario of one-bit massive multi-input multi-output (MIMO) wherein one-bit DACs are employed for the sake of saving hardware costs. Specifically, a spatial Sigma-Delta $(ΣΔ)$ modulation scheme is proposed for one-bit MIMO-DFRC waveform design. Unlike the existing approaches which require large-scale binary optimization, the proposed scheme performs $ΣΔ$ modulation on a continuous-valued DFRC signal. The subsequent waveform design is formulated as a constrained least square problem, which can be efficiently solved. Moreover, we leverage quantization noise for radar probing purposes, rather than treating it as unwanted noise. Numerical results demonstrate that the proposed scheme performs well in both radar probing and downlink precoding.

eess.SP↗

arXiv2024

Degree-of-Freedom of Modulating Information in the Phases of Reconfigurable Intelligent Surface

This paper investigates the information theoretic limit of a reconfigurable intelligent surface (RIS) aided communication scenario in which the RIS and the transmitter either jointly or independently send information to the receiver. The RIS is an emerging technology that uses a large number of passive reflective elements with adjustable phases to intelligently reflect the transmit signal to the intended receiver. While most previous studies of the RIS focus on its ability to beamform and to boost the received signal-to-noise ratio (SNR), this paper shows that if the information data stream is also available at the RIS and can be modulated through the adjustable phases at the RIS, significant improvement in the {degree-of-freedom} (DoF) of the overall channel is possible. For example, for an RIS system in which the signals are reflected from a transmitter with $M$ antennas to a receiver with $K$ antennas through an RIS with $N$ reflective elements, assuming no direct path between the transmitter and the receiver, joint transmission of the transmitter and the RIS can achieve a DoF of $\min\left(M+\frac{N}{2}-\frac{1}{2},N,K\right)$ as compared to the DoF of $\min(M,K)$ for the conventional multiple-input multiple-output (MIMO) channel. This result is obtained by establishing a connection between the RIS system and the MIMO channel with phase noise and by using results for characterizing the information dimension under projection. The result is further extended to the case with a direct path between the transmitter and the receiver, and also to the multiple access scenario, in which the transmitter and the RIS send independent information. Finally, this paper proposes a symbol-level precoding approach for modulating data through the phases of the RIS, and provides numerical simulation results to verify the theoretical DoF results.

cs.IT↗

arXiv2024

Accelerating Quadratic Transform and WMMSE

Fractional programming (FP) arises in various communications and signal processing problems because several key quantities in the field are fractionally structured, e.g., the Cramér-Rao bound, the Fisher information, and the signal-to-interference-plus-noise ratio (SINR). A recently proposed method called the quadratic transform has been applied to the FP problems extensively. The main contributions of the present paper are two-fold. First, we investigate how fast the quadratic transform converges. To the best of our knowledge, this is the first work that analyzes the convergence rate for the quadratic transform as well as its special case the weighted minimum mean square error (WMMSE) algorithm. Second, we accelerate the existing quadratic transform via a novel use of Nesterov's extrapolation scheme [1]. Specifically, by generalizing the minorization-maximization (MM) approach in [2], we establish a nontrivial connection between the quadratic transform and the gradient projection, thereby further incorporating the gradient extrapolation into the quadratic transform to make it converge more rapidly. Moreover, the paper showcases the practical use of the accelerated quadratic transform with two frontier wireless applications: integrated sensing and communications (ISAC) and massive multiple-input multiple-output (MIMO).

cs.IT↗

arXiv2024

SWAP: Sparse Entropic Wasserstein Regression for Robust Network Pruning

This study addresses the challenge of inaccurate gradients in computing the empirical Fisher Information Matrix during neural network pruning. We introduce SWAP, a formulation of Entropic Wasserstein regression (EWR) for pruning, capitalizing on the geometric properties of the optimal transport problem. The ``swap'' of the commonly used linear regression with the EWR in optimization is analytically demonstrated to offer noise mitigation effects by incorporating neighborhood interpolation across data points with only marginal additional computational cost. The unique strength of SWAP is its intrinsic ability to balance noise reduction and covariance information preservation effectively. Extensive experiments performed on various networks and datasets show comparable performance of SWAP with state-of-the-art (SoTA) network pruning algorithms. Our proposed method outperforms the SoTA when the network size or the target sparsity is large, the gain is even larger with the existence of noisy gradients, possibly from noisy data, analog memory, or adversarial attacks. Notably, our proposed method achieves a gain of 6% improvement in accuracy and 8% improvement in testing loss for MobileNetV1 with less than one-fourth of the network parameters remaining.

cs.AI↗

arXiv2023

Transmitting Data Through Reconfigurable Intelligent Surface: A Spatial Sigma-Delta Modulation Approach

Transmitting data using the phases on reconfigurable intelligent surfaces (RIS) is a promising solution for future energy-efficient communication systems. Recent work showed that a virtual phased massive multiuser multiple-input-multiple-out (MIMO) transmitter can be formed using only one active antenna and a large passive RIS. In this paper, we are interested in using such a system to perform MIMO downlink precoding. In this context, we may not be able to apply conventional MIMO precoding schemes, such as the simple zero-forcing (ZF) scheme, and we typically need to design the phase signals by solving optimization problems with constant modulus constraints or with discrete phase constraints, which pose challenges with high computational complexities. In this work, we propose an alternative approach based on Sigma-Delta ($ΣΔ$) modulation, which is classically famous for its noise-shaping ability. Specifically, first-order $ΣΔ$ modulation is applied in the spatial domain to handle phase quantization in generating constant envelope signals. Under some mild assumptions, the proposed phased $ΣΔ$ modulator allows us to use the ZF scheme to synthesize the RIS reflection phases with negligible complexity. The proposed approach is empirically shown to achieve comparable bit error rate performance to the unquantized ZF scheme.

eess.SP↗

arXiv2023

Realistic Speech-to-Face Generation with Speech-Conditioned Latent Diffusion Model with Face Prior

Speech-to-face generation is an intriguing area of research that focuses on generating realistic facial images based on a speaker's audio speech. However, state-of-the-art methods employing GAN-based architectures lack stability and cannot generate realistic face images. To fill this gap, we propose a novel speech-to-face generation framework, which leverages a Speech-Conditioned Latent Diffusion Model, called SCLDM. To the best of our knowledge, this is the first work to harness the exceptional modeling capabilities of diffusion models for speech-to-face generation. Preserving the shared identity information between speech and face is crucial in generating realistic results. Therefore, we employ contrastive pre-training for both the speech encoder and the face encoder. This pre-training strategy facilitates effective alignment between the attributes of speech, such as age and gender, and the corresponding facial characteristics in the face images. Furthermore, we tackle the challenge posed by excessive diversity in the synthesis process caused by the diffusion model. To overcome this challenge, we introduce the concept of residuals by integrating a statistical face prior to the diffusion process. This addition helps to eliminate the shared component across the faces and enhances the subtle variations captured by the speech condition. Extensive quantitative, qualitative, and user study experiments demonstrate that our method can produce more realistic face images while preserving the identity of the speaker better than state-of-the-art methods. Highlighting the notable enhancements, our method demonstrates significant gains in all metrics on the AVSpeech dataset and Voxceleb dataset, particularly noteworthy are the improvements of 32.17 and 32.72 on the cosine distance metric for the two datasets, respectively.

cs.CV↗

arXiv2023

Channel Estimation for Reconfigurable Intelligent Surface Aided Multi-User mmWave MIMO Systems

Channel acquisition is one of the main challenges for the deployment of reconfigurable intelligent surface (RIS) aided communication systems. This is because an RIS has a large number of reflective elements, which are passive devices with no active transmitting/receiving abilities. In this paper, we study the channel estimation problem for the RIS aided multi-user millimeter-wave (mmWave) multi-input multi-output (MIMO) system. Specifically, we propose a novel channel estimation protocol for the above system to estimate the cascaded channels, which are the products of the channels from the base station (BS) to the RIS and from the RIS to the users. Further, since the cascaded channels are typically sparse, this allows us to formulate the channel estimation problem as a sparse recovery problem using compressive sensing (CS) techniques, thereby allowing the channels to be estimated with less training overhead. Moreover, the sparse channel matrices of the cascaded channels of all users have a common block sparsity structure due to the common channel between the BS and the RIS. To take advantage of the common sparsity pattern, we propose a two-step multi-user joint channel estimation procedure. In the first step, we make use of the common column-block sparsity and project the received signals onto the common column subspace. In the second step, we make use of the row-block sparsity of the projected signals and propose a multi-user joint sparse matrix recovery algorithm that takes into account the common channel between the BS and the RIS.

eess.SP↗

arXiv2021

NOMA Versus Massive MIMO in Rayleigh Fading

This paper compares the sum rates and rate regions achieved by power-domain NOMA (non-orthogonal multiple access) and standard massive MIMO (multiple-input multiple-output) techniques. We prove analytically that massive MIMO always outperforms NOMA in i.i.d.~Rayleigh fading channels, if a sufficient number of antennas are used at the base stations. The simulation results show that the crossing point occurs already when having 20-30 antennas, which is far less than what is considered for the next generation cellular networks.

cs.IT↗

arXiv2021

Learning to Reflect and to Beamform for Intelligent Reflecting Surface with Implicit Channel Estimation

Intelligent reflecting surface (IRS), which consists of a large number of tunable reflective elements, is capable of enhancing the wireless propagation environment in a cellular network by intelligently reflecting the electromagnetic waves from the base-station (BS) toward the users. The optimal tuning of the phase shifters at the IRS is, however, a challenging problem, because due to the passive nature of reflective elements, it is difficult to directly measure the channels between the IRS, the BS, and the users. Instead of following the traditional paradigm of first estimating the channels then optimizing the system parameters, this paper advocates a machine learning approach capable of directly optimizing both the beamformers at the BS and the reflective coefficients at the IRS based on a system objective. This is achieved by using a deep neural network to parameterize the mapping from the received pilots (plus any additional information, such as the user locations) to an optimized system configuration, and by adopting a permutation invariant/equivariant graph neural network (GNN) architecture to capture the interactions among the different users in the cellular network. Simulation results show that the proposed implicit channel estimation based approach is generalizable, can be interpreted, and can efficiently learn to maximize a sum-rate or minimum-rate objective from a much fewer number of pilots than the traditional explicit channel estimation based approaches.

eess.SP↗