arXiv subjects

Zhilin Chen

Publications and source records attributed to Zhilin Chen.

13 recordsLinked to original sources

arXiv2026

DiDrive: A Risk-Aware Hierarchical Diffusion Framework for Safe Offline Reinforcement Learning in Autonomous Driving

While diffusion models effectively capture multimodal behavioral priors for autonomous driving, offline reinforcement learning (RL) policies remain susceptible to distribution shift, heavy-tailed risk signals, out-of-distribution (OOD) action generation, and high-dimensional state redundancy. To address these challenges, we propose DiDrive, a distribution-guided offline diffusion framework featuring two synergistic components: the Risk-Aware Hierarchical Diffusion (RHDif) architecture and the 3DICE policy optimization paradigm. In the state space, RHDif utilizes a low-level risk-gated encoder and a high-level contextual modulator to filter environmental redundancy and focus on safety-critical threats. In the action space, 3DICE mitigates OOD overestimation and gradient oscillation through in-sample calibrated guidance, spatiotemporal optimization, and ensemble-based candidate ranking. Evaluations on the CARLA benchmark demonstrate DiDrive's superiority over baselines like IQL, CQL, and Diffusion-QL, particularly in complex, high-density traffic scenarios with 60 vehicles, where it achieves an 85% success rate and a 4295.68 average reward, providing a robust pathway for safe autonomous driving decision-making.

cs.LG↗

arXiv2026

Learning Design-Score Manifold to Guide Diffusion Models for Offline Optimization

Optimizing complex systems, from discovering therapeutic drugs to designing high-performance materials, remains a fundamental challenge across science and engineering, as the underlying rules are often unknown and costly to evaluate. Offline optimization aims to optimize designs for target scores using pre-collected datasets without system interaction. However, conventional approaches may fail beyond training data, predicting inaccurate scores and generating inferior designs. This paper introduces ManGO, a diffusion-based framework that learns the design-score manifold, capturing the design-score interdependencies holistically. Unlike existing methods that treat design and score spaces in isolation, ManGO unifies forward prediction and backward generation, attaining generalization beyond training data. Key to this is its derivative-free guidance for conditional generation, coupled with adaptive inference-time scaling that dynamically optimizes denoising paths. Extensive evaluations demonstrate that ManGO outperforms 24 single- and 10 multi-objective optimization methods across diverse domains, including synthetic tasks, robot control, material design, DNA sequence, and real-world engineering optimization.

cs.LG↗

arXiv2025

seg2med: a bridge from artificial anatomy to multimodal medical images

We present seg2med, a modular framework for anatomy-driven multimodal medical image synthesis. The system integrates three components to enable high-fidelity, cross-modality generation of CT and MR images based on structured anatomical priors. First, anatomical maps are independently derived from three sources: real patient data, XCAT digital phantoms, and synthetic anatomies created by combining organs from multiple patients. Second, we introduce PhysioSynth, a modality-specific simulator that converts anatomical masks into prior volumes using tissue-dependent parameters (e.g., HU, T1, T2, proton density) and modality-specific signal models. It supports simulation of CT and multiple MR sequences including GRE, SPACE, and VIBE. Third, the synthesized anatomical priors are used to train 2-channel conditional denoising diffusion models, which take the anatomical prior as structural condition alongside the noisy image, enabling generation of high-quality, structurally aligned images. The framework achieves SSIM of 0.94 for CT and 0.89 for MR compared to real data, and FSIM of 0.78 for simulated CT. The generative quality is further supported by a Frechet Inception Distance (FID) of 3.62 for CT synthesis. In modality conversion, seg2med achieves SSIM of 0.91 for MR to CT and 0.77 for CT to MR. Anatomical fidelity evaluation shows synthetic CT achieves mean Dice scores above 0.90 for 11 key abdominal organs, and above 0.80 for 34 of 59 total organs. These results underscore seg2med's utility in cross-modality synthesis, data augmentation, and anatomy-aware medical AI.

eess.IV↗

arXiv2024

High-performance Power Allocation Strategies for Active IRS-aided Wireless Network

Due to its intrinsic ability to combat the double fading effect, the active intelligent reflective surface (IRS) becomes popular. The main feature of active IRS must be supplied by power, and the problem of how to allocate the total power between base station (BS) and IRS to fully explore the rate gain achieved by power allocation (PA) to remove the rate gap between existing PA strategies and optimal exhaustive search (ES) arises naturally. First, the signal-to-noise ratio (SNR) expression is derived to be a function of PA factor beta [0, 1]. Then, to improve the rate performance of the conventional gradient ascent (GA), an equal-spacing-multiple-point-initialization GA (ESMPI-GA) method is proposed. Due to its slow linear convergence from iterative GA, the proposed ESMPI-GA is high-complexity. Eventually, to reduce this high complexity, a low-complexity closed-form PA method with third-order Taylor expansion (TTE) centered at point beta0 = 0.5 is proposed. Simulation results show that the proposed ESMPI-GA and TTE obviously outperform existing methods like equal PA.

eess.SP↗

arXiv2023

Three High-rate Beamforming Methods for Active IRS-aided Wireless Network

Due to its ability of breaking the double-fading effect experienced by passive intelligent reflecting surface (IRS), active IRS is evolving a potential technique for future 6G wireless networks. To fully exploit the amplifying gain achieved by active IRS, two high-rate methods, maximum ratio reflecting (MRR) and selective ratio reflecting (SRR) are presented, which are motivated by maximum ratio combining and selective ratio combining. Moreover, both MRR and SRR are in closed-form expressions. To further improve the rate, a maximum approximate-signal-to-noise ratio (Max-ASNR) is first proposed with an alternately iterative infrastructure between adjusting the norm of beamforming vector and its normalized vector. This may make a substantial rate enhancement over existing equal-gain reflecting (EGR). Simulation results show that the proposed three methods perform much better than existing method EGR in terms of rate. They are in decreasing order of rate performance: Max-ASNR, MRR, SRR, and EGR.

eess.SP↗

arXiv2021

Heterogeneous Transformer: A Scale Adaptable Neural Network Architecture for Device Activity Detection

To support the modern machine-type communications, a crucial task during the random access phase is device activity detection, which is to detect the active devices from a large number of potential devices based on the received signal at the access point. By utilizing the statistical properties of the channel, state-of-the-art covariance based methods have been demonstrated to achieve better activity detection performance than compressed sensing based methods. However, covariance based methods require to solve a high dimensional nonconvex optimization problem by updating the estimate of the activity status of each device sequentially. Since the number of updates is proportional to the device number, the computational complexity and delay make the iterative updates difficult for real-time implementation especially when the device number scales up. Inspired by the success of deep learning for real-time inference, this paper proposes a learning based method with a customized heterogeneous transformer architecture for device activity detection. By adopting an attention mechanism in the architecture design, the proposed method is able to extract the relevance between device pilots and received signal, is permutation equivariant with respect to devices, and is scale adaptable to different numbers of devices. Simulation results demonstrate that the proposed method achieves better activity detection performance with much shorter computation time than state-of-the-art covariance approach, and generalizes well to different numbers of devices, BS-antennas, and different signal-to-noise ratios.

cs.IT↗

arXiv2021

Phase Transition Analysis for Covariance Based Massive Random Access with Massive MIMO

This paper considers a massive random access problem in which a large number of sporadically active devices wish to communicate with a base station (BS) equipped with massive multiple-input multiple-output (MIMO) antennas. Each device is preassigned a unique signature sequence, and the BS identifies the active devices by detecting which sequences are transmitted. This device activity detection problem can be formulated as a maximum likelihood estimation (MLE) problem for which the sample covariance matrix of the received signal is a sufficient statistic. The goal of this paper is to characterize the feasible set of problem parameters under which this covariance based approach is able to successfully recover the device activities in the massive MIMO regime. Through an analysis of the asymptotic behaviors of MLE via its associated Fisher information matrix, this paper derives a necessary and sufficient condition on the Fisher information matrix to ensure a vanishing probability of detection error as the number of antennas goes to infinity, based on which a numerical phase transition analysis is obtained. This condition is also examined from a perspective of covariance matching, which relates the phase transition analysis to a recently derived scaling law. Further, we provide a characterization of the distribution of the estimation error in MLE, based on which the error probabilities in device activity detection can be accurately predicted. Finally, this paper studies a random access scheme with joint device activity and data detection and analyzes its performance in a similar way.

cs.IT↗

arXiv2021

Sparse Activity Detection in Multi-Cell Massive MIMO Exploiting Channel Large-Scale Fading

This paper studies the device activity detection problem in a multi-cell massive multiple-input multiple-output (MIMO) system, in which the active devices transmit signature sequences to multiple base stations (BSs) that are connected to a central unit (CU), and the BSs cooperate across multiple cells to detect the active devices based on the sample covariance matrices at the BSs. This paper demonstrates the importance of exploiting the knowledge of channel large-scale fadings in this cooperative detection setting through a phase transition analysis, which characterizes the length of signature sequences needed for successful device activity detection in the massive MIMO regime. It is shown that when the large-scale fadings are known, the phase transition for the multi-cell scenario is approximately the same as that of a single-cell system. In this case, the length of the signature sequences required for reliable activity detection in the multi-cell system can be made to be independent of the number of cells through cooperation, in contrast to the case where the large-scale fadings are not known. Further, this paper considers the case in which the fronthaul links between the BSs and the CU have capacity constraints and proposes a novel cooperation scheme based on the quantization of preliminary detection results at the BSs and the reconstruction of the sample covariance matrices at the CU. Simulations show that the proposed method significantly outperforms the scheme of directly quantizing the sample covariance matrices.

cs.IT↗

arXiv2021

Accelerating Coordinate Descent via Active Set Selection for Device Activity Detection for Multi-Cell Massive Random Access

We propose a computationally efficient algorithm for the device activity detection problem in the multi-cell massive multi-input multi-output (MIMO) system, where the active devices transmit their signature sequences to multiple BSs in multiple cells and all the BSs cooperate to detect the active devices. The device activity detection problem has been formulated as a maximum likelihood maximization (MLE) problem in the literature. The state-of-the-art algorithm for solving the problem is the (random) coordinate descent (CD) algorithm. However, the CD algorithm fails to exploit the special sparsity structure of the solution of the device activity detection problem, i.e., most of devices are not active in each time slot. In this paper, we propose a novel active set selection strategy to accelerate the CD algorithm and propose an efficient active set CD algorithm for solving the considered problem. Specifically, at each iteration, the proposed active set CD algorithm first selects a small subset of all devices, namely the active set, which contains a few devices that contribute the most to the deviation from the first-order optimality condition of the MLE problem thus potentially can provide the most improvement to the objective function, then applies the CD algorithm to perform the detection for the devices in the active set. Simulation results show that the proposed active set CD algorithm significantly outperforms the state-of-the-art CD algorithm in terms of the computational efficiency.

eess.SP↗

arXiv2021

Deep Active Learning Approach to Adaptive Beamforming for mmWave Initial Alignment

This paper proposes a deep learning approach to the adaptive and sequential beamforming design problem for the initial access phase in a mmWave environment with a single-path channel. For a single-user scenario where the problem is equivalent to designing the sequence of sensing beamformers to learn the angle of arrival (AoA) of the dominant path, we propose a novel deep neural network (DNN) that designs the adaptive sensing vectors sequentially based on the available information so far at the base station (BS). By recognizing that the AoA posterior distribution is a sufficient statistic for solving the initial access problem, we use the posterior distribution as the input to the proposed DNN for designing the adaptive sensing strategy. However, computing the posterior distribution can be computationally challenging when the channel fading coefficient is unknown. To address this issue, this paper proposes to use an estimate of the fading coefficient to compute an approximation of the posterior distribution. Further, this paper shows that the proposed DNN can deal with practical beamforming constraints such as the constant modulus constraint. Numerical results demonstrate that compared to the existing adaptive and non-adaptive beamforming schemes, the proposed DNN-based adaptive sensing strategy achieves a significantly better AoA acquisition performance.

cs.IT↗

arXiv2021

An Efficient Active Set Algorithm for Covariance Based Joint Data and Activity Detection for Massive Random Access with Massive MIMO

This paper proposes a computationally efficient algorithm to solve the joint data and activity detection problem for massive random access with massive multiple-input multiple-output (MIMO). The BS acquires the active devices and their data by detecting the transmitted preassigned nonorthogonal signature sequences. This paper employs a covariance based approach that formulates the detection problem as a maximum likelihood estimation (MLE) problem. To efficiently solve the problem, this paper designs a novel iterative algorithm with low complexity in the regime where the device activity pattern is sparse $\unicode{x2013}$ a key feature that existing algorithmic designs have not previously exploited for reducing complexity. Specifically, at each iteration, the proposed algorithm focuses on only a small subset of all potential sequences, namely the active set, which contains a few most likely active sequences (i.e., transmitted sequences by all active devices), and performs the detection for the sequences in the active set. The active set is carefully selected at each iteration based on the current detection result and the first-order optimality condition of the MLE problem. Simulation results show that the proposed active set algorithm enjoys significantly better computational efficiency (in terms of the CPU time) than the state-of-the-art algorithms.

eess.SP↗

arXiv2019

Multi-Cell Sparse Activity Detection for Massive Random Access: Massive MIMO versus Cooperative MIMO

This paper considers sparse device activity detection for cellular machine-type communications with non-orthogonal signatures using the approximate message passing algorithm. This paper compares two network architectures, massive multiple-input multiple-output (MIMO) and cooperative MIMO, in terms of their effectiveness in overcoming inter-cell interference. In the massive MIMO architecture, each base station (BS) detects only the users from its own cell while treating inter-cell interference as noise. In the cooperative MIMO architecture, each BS detects the users from neighboring cells as well; the detection results are then forwarded in the form of log-likelihood ratio (LLR) to a central unit where final decisions are made. This paper analytically characterizes the probabilities of false alarm and missed detection for both architectures. Numerical results validate the analytic characterization and show that as the number of antennas increases, a massive MIMO system effectively drives the detection error to zero, while as the cooperation size increases, the cooperative MIMO architecture mainly improves the cell-edge user performance. Moreover, this paper studies the effect of LLR quantization to account for the finite-capacity fronthaul. Numerical simulations of a practical scenario suggest that in that specific case cooperating three BSs in a cooperative MIMO system achieves about the same cell-edge detection reliability as a non-cooperative massive MIMO system with four times the number of antennas per BS.

cs.IT↗

arXiv2018

Sparse Activity Detection for Massive Connectivity

This paper considers the massive connectivity application in which a large number of potential devices communicate with a base-station (BS) in a sporadic fashion. The detection of device activity pattern together with the estimation of the channel are central problems in such a scenario. Due to the large number of potential devices in the network, the devices need to be assigned non-orthogonal signature sequences. The main objective of this paper is to show that by using random signature sequences and by exploiting sparsity in the user activity pattern, the joint user detection and channel estimation problem can be formulated as a compressed sensing single measurement vector (SMV) problem or multiple measurement vector (MMV) problem, depending on whether the BS has a single antenna or multiple antennas, and be efficiently solved using an approximate message passing (AMP) algorithm. This paper proposes an AMP algorithm design that exploits the statistics of the wireless channel and provides an analytical characterization of the probabilities of false alarm and missed detection by using the state evolution. We consider two cases depending on whether the large-scale component of the channel fading is known at the BS and design the minimum mean squared error (MMSE) denoiser for AMP according to the channel statistics. Simulation results demonstrate the substantial advantage of exploiting the statistical channel information in AMP design; however, knowing the large-scale fading component does not offer tangible benefits. For the multiple-antenna case, we employ two different AMP algorithms, namely the AMP with vector denoiser and the parallel AMP-MMV, and quantify the benefit of deploying multiple antennas at the BS.

cs.IT↗