arXiv subjects

Haiquan Lu

Publications and source records attributed to Haiquan Lu.

At least 19 recordsLinked to original sources

arXiv2026

Universal CKM for Environment-Aware Wireless Networks: Enabling Cross-Device and Cross-Task Channel Knowledge Transfer

Channel knowledge map (CKM) is a promising technology for environment-aware sixth-generation (6G) wireless networks. However, most existing CKMs are tightly coupled with wireless devices and downstream tasks, which limit their scalability and reusability in wireless networks. To address these limitations, this article proposes the concept of universal CKM (uCKM) as a foundational wireless environment prior, which aims to enable cross-device and cross-task channel knowledge transfer for environment-aware wireless networks. We first revisit the representative CKMs and discuss their limitations. Then, the uCKM-enabled new paradigm for environment-aware wireless networks is introduced, and its benefits are highlighted from the perspectives of uCKM construction and utilization phases, for which we propose the visions of ``All for uCKM'' and ``uCKM for All'', i.e., the data acquired by all devices and tasks should contribute to the construction of uCKM, and vice versa. Subsequently, we discuss the main challenges of uCKM and propose potential solutions. Last, we provide simulation results to demonstrate the feasibility and performance gains brought by uCKM and outline future research directions.

cs.IT↗

arXiv2026

Mode Switching for RDARS-Aided ISAC Systems: From Optimization to Deep Unfolding

Reconfigurable distributed antennas and reflecting surface (RDARS) has recently emerged as a promising architecture for integrated sensing and communication (ISAC), owing to its flexible element-wise mode switching between connection and reflection modes. In this paper, to fully reap the benefits of mode configuration, muting elements that can absorb the incident energy are introduced into RDARS-aided ISAC systems to mitigate multi-user interference (MUI) and enhance sensing performance. To draw useful insights, we first investigate the special cases of single-UE communication, single-target sensing, and two-UE communication to reveal the importance of muting elements. Specifically, the maximum communication and sensing signal-to-noise ratio (SNR), and the signal-to-interference-plus-noise ratio (SINR) expressions are respectively derived for the three cases, together with the optimal number of muting elements for explicitly characterizing the tradeoff between reflection gain loss and MUI suppression. Next, we consider the joint waveform and tri-mode switching design for RDARS-aided ISAC systems, where an alternating optimization (AO)-based penalty dual decomposition (APDD) algorithm is proposed to solve the mixed-integer nonlinear programming (MINLP) problem. Furthermore, a model-driven APDD-Net is developed by deeply unfolding the APDD iterations into a layer-wise architecture, where key parameters are learned to reduce the computational complexity and accelerate convergence. Simulation results verify the theoretical findings on the muting gain and demonstrate that the proposed APDD-Net achieves a better tradeoff between communication and sensing performance compared with benchmark schemes.

eess.SP↗

arXiv2026

Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization

Neural networks trained under different hyperparameter settings can fall into distinct training "regimes," with consistent behavior within regimes and qualitative differences across regimes. In this paper, we study such multi-regime behavior in scientific machine learning (SciML) models through a regime-aware diagnostic framework that jointly analyzes performance, training dynamics, and loss-landscape geometry. We identify three key findings: (i) a consistent three-regime structure emerges across many standard SciML models, different constraint enforcements, and various optimizer designs; (ii) optimization effectiveness is regime-specific, with no single method performing well across all regimes; and (iii) SciML models can exhibit fine-grained failure modes that can challenge conventional interpretations of standard loss-landscape metrics. Our results provide an approach to establish a unified, task-oblivious perspective on failure modes in SciML and to inform regime-aware guidance for improving robustness. We validate these findings across widely-used SciML models, including physics-informed neural networks, neural operators, and neural ordinary differential equations, on benchmarks spanning representative ordinary and partial differential equations.

cs.LG↗

arXiv2026

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs

LLM agents have recently emerged as a powerful paradigm for solving complex tasks through planning, tool use, memory retrieval, and multi-step interaction. However, these agentic workflows often introduce substantial input-side overhead, making the compute-intensive prefilling stage a key bottleneck in long-context, multi-turn inference. In this work, we propose Mix-Quant, a simple and effective phase-aware quantization framework for fast agentic inference. We first investigate FP4 quantization in agentic LLM workflows and observe that quantizing the entire inference process can incur significant performance degradation. In contrast, the prefilling stage exhibits substantial quantization redundancy and can therefore be quantized with minimal accuracy loss, despite being the dominant source of computation. Based on this insight, we apply high-throughput NVFP4 quantization to the prefilling phase while preserving BF16 precision for decoding. By decoupling prefilling acceleration from decoding quality, Mix-Quant combines phase-aware algorithmic quantization with hardware-efficient NVFP4 execution to alleviate the inference bottleneck in LLM agents. Extensive experiments across long-context and agentic benchmarks demonstrate that Mix-Quant largely preserves task performance while delivering significant efficiency improvements, achieving up to a 3x speedup during prefilling.

cs.CL↗

arXiv2026

UAV Swarm Enabled Aerial Movable Antenna System for Low-Altitude Economy: From Far-Field to Near-Field Communication

Unmanned aerial vehicle (UAV) with the intrinsic three-dimensional (3D) mobility provides an ideal platform for implementing aerial movable antenna (AMA) system enabled by UAV swarm cooperation. Besides, AMA system is readily to achieve an extremely large-scale array aperture, rendering the conventional far-field uniform plane wave (UPW) model no longer valid for aerial-to-ground links. This paper studies the UAV swarm enabled near-field AMA communication, by taking into account the non-uniform spherical wave (NUSW) model, where UAV swarm trajectory simultaneously influences the channel amplitude and phase. We formulate a general optimization problem to maximize the minimum average communication rate over user equipments (UEs), by jointly optimizing the 3D UAV swarm trajectory and receive beamforming for all UEs. To draw useful insights, the special case of single UE is first studied, and successive convex approximation (SCA) technique is proposed to efficiently optimize the UAV swarm trajectory. For the special case of placement optimization, the optimal placement positions of UAVs for cases of single UAV and two UAVs are derived in closed-form. Then, for the special case of two UEs, we show that an inter-UE interference (IUI)-free communication can be achieved by symmetrically placing an even number of UAVs along a hyperbola, with its foci corresponding to the locations of the two UEs. Furthermore, for arbitrary number of UEs, an alternating optimization algorithm is proposed to efficiently tackle the non-convex optimization problem. Numerical results validate the significant performance gains over the benchmark schemes.

cs.IT↗

arXiv2026

Joint Sparsity and Beamforming Design for RDARS-Aided Systems

Reconfigurable distributed antennas and reflecting surface (RDARS) has emerged as a promising architecture for communication and sensing performance enhancement. In particular, the new selection gain can be achieved by leveraging the dynamic working mode selection between connection and reflection modes, whereas low-complexity element configuration remains an open issue. In this paper, we consider a RDARS-assisted communication system, where the connected elements are formed as a uniform sparse array for simplified mode configuration while achieving enlarged physical array aperture. The sum rate maximization problem is then formulated by jointly optimizing the active and passive beamforming matrices and sparsity of connected element array. For the special cases of a single user equipment (UE) and two UEs, the optimal sparsity designs are derived in closed-form. Then, for an arbitrary number of UEs, a weighted minimum mean-square error-based alternating optimization (AO) algorithm is proposed to tackle the non-convex optimization problem. Numerical results demonstrate the importance of optimizing the sparsity and the effectiveness of low-complexity sparsity optimization.

eess.SP↗

arXiv2025

Trajectory Optimization for Cellular-Connected UAV in Complex Environment with Partial CKM

Cellular-connected unmanned aerial vehicles (UAVs) are expected to play an increasingly important role in future wireless networks. To facilitate the reliable navigation for cellular-connected UAVs, channel knowledge map (CKM) is considered a promising approach capable of tackling the non-negligible co-channel interference resulting from the high line-of-sight (LoS) probability of air-ground (AG) channels. Nevertheless, due to measurement constraints and the aging of information, CKM is usually incomplete and needs to be regularly updated to capture the dynamic nature of complex environments. In this paper, we propose a novel trajectory design strategy in which UAV navigation and CKM completion are incorporated into a common framework, enabling mutual benefits for both tasks. Specifically, a cellular-connected UAV deployed in an urban environment measures the radio information during its flight and completes the CKM with Kriging interpolation. Based on the method of grid discretization and spherical approximation, a mixed-integer multi-objective optimization problem is formulated. The problem falls into the category of combinatorial mathematics and is essentially equivalent to determining an optimum sequence of grid points to traverse. Through proper mathematical manipulation, the problem is reformulated as variants of two classic models in graph theory, namely the shortest-path problem (SPP) and the traveling salesman problem (TSP). Two navigation strategies based on the two different models are proposed and thoroughly compared based on numerical results to provide implementable methods for engineering practice and reveal the trade-offs between UAV navigation and CKM completion. Simulation results reveal that the proposed navigation strategies can quickly expand the Pareto boundary of the problem and approach the performance of fully-known CKM.

cs.IT↗

arXiv2025

MixReasoning: Switching Modes to Think

Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of thought before producing an answer. However, applying extended reasoning to every step introduces substantial redundancy, as sub-problems vary widely in difficulty and complexity: a small number of pivotal steps are genuinely challenging and decisive for the final answer, while many others only involve straightforward revisions or simple computations. Therefore, a natural idea is to endow reasoning models with the ability to adaptively respond to this variation, rather than treating all steps with the same level of elaboration. To this end, we propose MixReasoning, a framework that dynamically adjusts the depth of reasoning within a single response. The resulting chain of thought then becomes a mixture of detailed reasoning on difficult steps and concise inference on simpler ones. Experiments on GSM8K, MATH-500, and AIME show that MixReasoning shortens reasoning length and substantially improves efficiency without compromising accuracy.

cs.AI↗

arXiv2025

Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs

Discrete Diffusion Large Language Models (dLLMs) have recently emerged as a competitive paradigm for non-autoregressive language modeling. Their distinctive decoding mechanism enables faster inference speed and strong performance in code generation and mathematical tasks. In this work, we show that the decoding mechanism of dLLMs not only enhances model utility but also can be used as a powerful tool for model attribution. A key challenge in this problem lies in the diversity of attribution scenarios, including distinguishing between different models as well as between different checkpoints or backups of the same model. To ensure broad applicability, we identify two fundamental problems: what information to extract from the decoding trajectory, and how to utilize it effectively. We first observe that relying directly on per-step model confidence yields poor performance. This is mainly due to the bidirectional decoding nature of dLLMs: each newly decoded token influences the confidence of other decoded tokens, making model confidence highly redundant and washing out structural signal regarding decoding order or dependencies. To overcome this, we propose a novel information extraction scheme called the Directed Decoding Map (DDM), which captures structural relationships between decoding steps and better reveals model-specific behaviors. Furthermore, to make full use of the extracted structural information during attribution, we propose Gaussian-Trajectory Attribution (GTA), where we fit a cell-wise Gaussian distribution at each decoding position for each target model, and define the likelihood of a trajectory as the attribution score: if a trajectory exhibits higher log-likelihood under the distribution of a specific model, it is more likely to have been generated by that model. Extensive experiments under different settings validate the utility of our methods.

cs.CL↗

arXiv2025

Flexible XL-MIMO via Array Configuration Codebook: Codebook Design and Array Configuration Training

XL-MIMO emerges as a promising technology to achieve unprecedented enhancements in spectral efficiency and spatial resolution, via orders-of-magnitude increase in the antenna array size. However, the practical issues of high hardware cost and power consumption pose great challenges towards the cost-effective implementation of XL-MIMO. To address such challenges, this paper proposes a novel concept called array configuration codebook (ACC), which enables flexible XL-MIMO cost-effectively and improves the system performance compared with conventional antenna selection (AS) schemes with limited number of RF chains. Specifically, ACC refers to a set of pre-designed array configuration codewords, where each codeword specifies the positions of activated antenna pixels. Then, flexible XL-MIMO architecture can be enabled via dynamical pixel activation based on the designed ACC, without having to exhaustively try all possible combinations of the antenna pixels activations. As an illustration, we give a specific codebook design, encompassing the classic compact array (CA), uniform sparse array (USA), modular array (MoA), nested array (NA), and co-prime array (CPA), and each codeword is specified by one array configuration parameter. With the designed ACC, array configuration training is considered for multi-UE communication to maximize the sum rate. To reduce the training overhead of exhaustive scanning, a two-stage scanning scheme is proposed, including the array- and pixel-level scanning. For comparison, the greedy AS scheme is proposed, where the resulting incremental SINR expression by activating antenna pixel sequentially is derived in closed-form. Subsequently, array configuration training is extended to the wireless localization scenario. Simulation results demonstrate the effectiveness of codeword optimization for scenarios of multi-UE communication and wireless localization.

cs.IT↗

arXiv2025

Model-Driven Deep Learning Enhanced Joint Beamforming and Mode Switching for RDARS-Aided MIMO Systems

Reconfigurable distributed antenna and reflecting surface (RDARS) is a promising architecture for future sixth-generation (6G) wireless networks. In particular, the dynamic working mode configuration for the RDARS-aided system brings an extra selection gain compared to the existing reconfigurable intelligent surface (RIS)-aided system and distributed antenna system (DAS). In this paper, we consider the RDARS-aided downlink multiple-input multiple-output (MIMO) system and aim to maximize the weighted sum rate (WSR) by jointly optimizing the beamforming matrices at the based station (BS) and RDARS, as well as mode switching matrix at RDARS. The optimization problem is challenging to be solved due to the non-convex objective function and mixed integer binary constraint. To this end, a penalty term-based weight minimum mean square error (PWM) algorithm is proposed by integrating the majorization-minimization (MM) and weight minimum mean square error (WMMSE) methods. To further escape the local optimum point in the PWM algorithm, a model-driven DL method is integrated into this algorithm, where the key variables related to the convergence of PWM algorithm are trained to accelerate the convergence speed and improve the system performance. Simulation results are provided to show that the PWM-based beamforming network (PWM-BFNet) can reduce the number of iterations by half and achieve performance improvements of 26.53% and 103.2% at the scenarios of high total transmit power and a large number of RDARS transmit elements (TEs), respectively.

eess.SP↗

arXiv2025

Wireless Communication for Low-Altitude Economy with UAV Swarm Enabled Two-Level Movable Antenna System

Unmanned aerial vehicle (UAV) is regarded as a key enabling platform for low-altitude economy, due to its advantages such as 3D maneuverability, flexible deployment, and LoS air-to-air/ground communication links. In particular, the intrinsic high mobility renders UAV especially suitable for operating as a movable antenna (MA) from the sky. In this paper, by exploiting the flexible mobility of UAV swarm and antenna position adjustment of MA, we propose a novel UAV swarm enabled two-level MA system, where UAVs not only individually deploy a local MA array, but also form a larger-scale MA system with their individual MA arrays via swarm coordination. We formulate a general optimization problem to maximize the minimum achievable rate over all ground user equipments (UEs), by jointly optimizing the 3D UAV swarm placement positions, their individual MAs' positions, and receive beamforming for different UEs. To gain useful insights, we first consider the special case where each UAV has only one antenna, under different scenarios of one single UE, two UEs, and arbitrary number of UEs. In particular, for the two-UE case, we derive the optimal UAV swarm placement positions in closed-form that achieves IUI-free communication when the uniform plane wave (UPW) model holds, where the UAV swarm forms a uniform sparse array (USA) satisfying minimum safe distance constraint. While for the general case with arbitrary number of UEs, we propose an efficient alternating optimization algorithm to solve the formulated non-convex optimization problem. Then, we extend the results to the case where each UAV is equipped with multiple antennas. Numerical results verify that the proposed low-altitude UAV swarm enabled MA system significantly outperforms various benchmark schemes, thanks to the exploitation of two-level mobility to create more favorable channel conditions for multi-UE communications.

cs.IT↗

arXiv2025

A Model Zoo on Phase Transitions in Neural Networks

Using the weights of trained Neural Network (NN) models as data modality has recently gained traction as a research field - dubbed Weight Space Learning (WSL). Multiple recent works propose WSL methods to analyze models, evaluate methods, or synthesize weights. Weight space learning methods require populations of trained models as datasets for development and evaluation. However, existing collections of models - called `model zoos' - are unstructured or follow a rudimentary definition of diversity. In parallel, work rooted in statistical physics has identified phases and phase transitions in NN models. Models are homogeneous within the same phase but qualitatively differ from one phase to another. We combine the idea of `model zoos' with phase information to create a controlled notion of diversity in populations. We introduce 12 large-scale zoos that systematically cover known phases and vary over model architecture, size, and datasets. These datasets cover different modalities, such as computer vision, natural language processing, and scientific ML. For every model, we compute loss landscape metrics and validate full coverage of the phases. With this dataset, we provide the community with a resource with a wide range of potential applications for WSL and beyond. Evidence suggests the loss landscape phase plays a role in applications such as model training, analysis, or sparsification. We demonstrate this in an exploratory study of the downstream methods like transfer learning or model weights averaging.

cs.LG↗

arXiv2025

Reconfigurable Codebook-Based Beamforming for RDARS-Aided mmWave MU-MIMO Systems

Reconfigurable distributed antenna and reflecting surface (RDARS) is a new architecture for the sixth-generation (6G) millimeter wave (mmWave) communications. In RDARS-aided mmWave systems, the active and passive beamforming design and working mode configuration for reconfigurable elements are crucial for system performance. In this paper, we aim to maximize the weighted sum rate (WSR) in the RDARS-aided mmWave system. To take advantage of RDARS, we first design a reconfigurable codebook (RCB) in which the number and dimension of the codeword can be flexibly adjusted. Then, a low overhead beam training scheme based on hierarchical search is proposed. Accordingly, the active and passive beamforming for data transmission is designed to achieve the maximum WSR for both space-division multiple access (SDMA) and time-division multiple access (TDMA) schemes. For the TDMA scheme, the optimal number of RDARS transmit elements and the allocated power budget for WSR maximization are derived in closed form. Besides, the superiority of the RDARS is verified and the conditions under which RDARS outperforms RIS and DAS are given. For the SDMA scheme, we characterize the relationship between the number of RDARS connected elements and the user distribution, followed by the derivation of the optimal placement positions of the RDARS transmit elements. High-quality beamforming design solutions are derived to minimize the inter-user interference (IUI) at the base station and RDARS side respectively, which nearly leads to the maximal WSR. Finally, simulation results confirm our theoretical findings and the superiority of the proposed schemes.

eess.SP↗

arXiv2025

Wireless Communication with Flexible Reflector: Joint Placement and Rotation Optimization for Coverage Enhancement

Passive metal reflectors for communication enhancement have appealing advantages such as ultra low cost, zero energy expenditure, maintenance-free operation, long life span, and full compatibility with legacy wireless systems. To unleash the full potential of passive reflectors for wireless communications, this paper proposes a new passive reflector architecture, termed flexible reflector (FR), for enabling the flexible adjustment of beamforming direction via the FR placement and rotation optimization. We consider the multi-FR aided area coverage enhancement and aim to maximize the minimum expected receive power over all locations within the target coverage area, by jointly optimizing the placement positions and rotation angles of multiple FRs. To gain useful insights, the special case of movable reflector (MR) with fixed rotation is first studied to maximize the expected receive power at a target location, where the optimal single-MR placement positions for electrically large and small reflectors are derived in closed-form, respectively. It is shown that the reflector should be placed at the specular reflection point for electrically large reflector. While for area coverage enhancement, the optimal placement is obtained for the single-MR case and a sequential placement algorithm is proposed for the multi-MR case. Moreover, for the general case of FR, joint placement and rotation design is considered for the single-/multi-FR aided coverage enhancement, respectively. Numerical results are presented which demonstrate significant performance gains of FRs over various benchmark schemes under different practical setups in terms of receive power enhancement.

cs.IT↗

arXiv2024

Double-Side Delay Alignment Modulation for Multi-User Millimeter Wave and TeraHertz Communications

Delay alignment modulation (DAM) is an innovative broadband modulation technique well suited for millimeter wave (mmWave) and terahertz (THz) massive multiple-input multiple-output (MIMO) communication systems. Leveraging the high spatial resolution and sparsity of multi-path channels, DAM mitigates inter-symbol interference (ISI) effectively, by aligning all multi-path components through a combination of delay pre/post-compensation and path-based beamforming. As such, ISI is eliminated while preserving multi-path power gains. In this paper, we explore multi-user double-side DAM with both delay pre-compensation at the transmitter and post-compensation at the receiver, contrasting with prior one-side DAM that primarily focuses on delay pre-compensation only. Firstly, we reveal the constraint for the introduced delays and the delay pre/post-compensation vectors tailored for multi-user double-side DAM, given a specific number of delay pre/post-compensations. Furthermore, we show that as long as the number of base station (BS)/user equipment (UE) antennas is sufficiently large, single-side DAM, where delay compensation is only performed at the BS/UE, is preferred than double-side DAM since the former results in less ISI to be spatially eliminated. Next, we propose two low-complexity path-based beamforming strategies based on the eigen-beamforming transmission and ISI-zero forcing (ZF) principles, respectively, based on which the achievable sum rates are studied. Simulation results verify that with sufficiently large BS/UE antennas, single-side DAM is sufficient. Furthermore, compared to the benchmark scheme of orthogonal frequency division multiplexing (OFDM), multi-user BS-side DAM achieves higher spectral efficiency and/or lower peak-to-average power ratio (PAPR).

eess.SP↗

arXiv2024

AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models

Recent work on pruning large language models (LLMs) has shown that one can eliminate a large number of parameters without compromising performance, making pruning a promising strategy to reduce LLM model size. Existing LLM pruning strategies typically assign uniform pruning ratios across layers, limiting overall pruning ability; and recent work on layerwise pruning of LLMs is often based on heuristics that can easily lead to suboptimal performance. In this paper, we leverage Heavy-Tailed Self-Regularization (HT-SR) Theory, in particular the shape of empirical spectral densities (ESDs) of weight matrices, to design improved layerwise pruning ratios for LLMs. Our analysis reveals a wide variability in how well-trained, and thus relatedly how prunable, different layers of an LLM are. Based on this, we propose AlphaPruning, which uses shape metrics to allocate layerwise sparsity ratios in a more theoretically principled manner. AlphaPruning can be used in conjunction with multiple existing LLM pruning methods. Our empirical results show that AlphaPruning prunes LLaMA-7B to 80% sparsity while maintaining reasonable perplexity, marking a first in the literature on LLMs. We have open-sourced our code at https://github.com/haiquanlu/AlphaPruning.

cs.LG↗

arXiv2024

Group Movable Antenna With Flexible Sparsity: Joint Array Position and Sparsity Optimization

Movable antenna (MA) is a promising technology to exploit the spatial variation of wireless channel for performance enhancement, by dynamically varying the antenna position within a certain region. However, for multi-antenna communication systems, moving each antenna independently not only requires prohibitive complexity to find the optimal antenna positions, but also incurs sophisticated movement control in practice. To address this issue, this letter proposes a new MA architecture termed group MA (GMA), enabling the group movement of all elements collectively in a continuous manner, and simultaneously achieving flexible array architecture by antenna selection (AS). In this letter, we focus on the uniform sparse array based GMA, where equally spaced antenna elements are selected to achieve desired array sparsity. The array position and sparsity level are jointly optimized to maximize the sum rate of the multi-user communication system. Numerical results verify the necessity to optimize the position and sparsity of GMA, and considerable performance gain is achieved as compared to the conventional fixed-position antenna (FPA).

cs.IT↗