arXiv subjects

Lu Gan

Publications and source records attributed to Lu Gan.

At least 37 records · Page 2Linked to original sources

arXiv2026

Interlayer Error Calibration for Stacked Intelligent Metasurfaces:Modeling, Algorithms, and Future Perspectives

Stacked intelligent metasurfaces (SIMs) have recently emerged as a key enabler for realizing electromagnetic wave-domain signal processing in next-generation wireless networks. However, practical SIM implementations often suffer from noticeable mismatches between theoretical models and measured responses due to fabrication and assembly imperfections. This article systematically investigates the problem of interlayer error calibration in SIMs. We first classify representative modeling and hardware-induced imperfections. Then, we outline the major challenges in SIM calibration and further develop a general framework that integrates a calibration protocol with the relevant solution strategies. Moreover, we investigate the effectiveness of the multi-stage calibration approach in mitigating geometric deviations and improving the alignment between the calibrated and practical propagation coefficients. Finally, we elaborate on key research opportunities and practical challenges toward realizing physically consistent and hardware-compliant SIM implementations for future research.

eess.SP↗

arXiv2026

A Generalizable Physics-guided Causal Model for Trajectory Prediction in Autonomous Driving

Trajectory prediction for traffic agents is critical for safe autonomous driving. However, achieving effective zero-shot generalization in previously unseen domains remains a significant challenge. Motivated by the consistent nature of kinematics across diverse domains, we aim to incorporate domain-invariant knowledge to enhance zero-shot trajectory prediction capabilities. The key challenges include: 1) effectively extracting domain-invariant scene representations, and 2) integrating invariant features with kinematic models to enable generalized predictions. To address these challenges, we propose a novel generalizable Physics-guided Causal Model (PCM), which comprises two core components: a Disentangled Scene Encoder, which adopts intervention-based disentanglement to extract domain-invariant features from scenes, and a CausalODE Decoder, which employs a causal attention mechanism to effectively integrate kinematic models with meaningful contextual information. Extensive experiments on real-world autonomous driving datasets demonstrate our method's superior zero-shot generalization performance in unseen cities, significantly outperforming competitive baselines. The source code is released at https://github.com/ZY-Zong/Physics-guided-Causal-Model.

cs.AI↗

arXiv2026

GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attention

3D semantic occupancy prediction is essential for achieving safe, reliable autonomous driving and robotic navigation. Compared to camera-only perception systems, multi-modal pipelines, especially LiDAR-camera fusion methods, can produce more accurate and fine-grained predictions. Although voxel-based scene representations are widely used for semantic occupancy prediction, 3D Gaussians have emerged as a continuous and significantly more compact alternative. In this work, we propose a multi-modal Gaussian-based semantic occupancy prediction framework utilizing 3D deformable attention, namely GaussianFormer3D. We introduce a voxel-to-Gaussian initialization strategy that provides 3D Gaussians with accurate geometry priors from LiDAR data, and design a LiDAR-guided 3D deformable attention mechanism to refine these Gaussians using LiDAR-camera fusion features in a lifted 3D space. Extensive experiments on real-world on-road and off-road autonomous driving datasets demonstrate that GaussianFormer3D achieves state-of-the-art prediction performance with reduced memory consumption and improved efficiency.

cs.CV↗

arXiv2026

Bit-Efficient Quantisation for Two-Channel Modulo-Sampling Systems

Two-channel modulo analog-to-digital converters (ADCs) enable high-dynamic-range signal sensing at the Nyquist rate per channel, but existing designs quantise both channel outputs independently, incurring redundant bitrate costs. This paper proposes a bit-efficient quantisation scheme that exploits the integer-valued structure of inter-channel differences, transmitting one quantised channel output together with a compact difference index. We prove that this approach requires only 1-2 bits per signal sample overhead relative to conventional ADCs, despite operating with a much smaller per-channel dynamic range. Simulations confirm the theoretical error bounds and bitrate analysis, while hardware experiments demonstrate substantial bitrate savings compared with existing modulo sampling schemes, while maintaining comparable reconstruction accuracy. These results highlight a practical path towards high-resolution, bandwidth-efficient modulo ADCs for bitrate-constrained systems.

eess.SP↗

arXiv2025

STATE-NAV: Stability-Aware Traversability Estimation for Bipedal Navigation on Rough Terrain

Bipedal robots have advantages in maneuvering human-centered environments, but face greater failure risk compared to other stable mobile platforms such as wheeled or quadrupedal robots. While learning-based traversability has been widely studied for these platforms, bipedal traversability has instead relied on manually designed rules with limited consideration of locomotion stability on rough terrain. In this work, we present the first learning-based traversability estimation and risk-sensitive navigation framework for bipedal robots operating in diverse, uneven environments. TravFormer, a transformer-based neural network, is trained to predict bipedal instability with uncertainty, enabling risk-aware and adaptive planning. Based on the network, we define traversability as stability-aware command velocity-the fastest command velocity that keeps instability below a user-defined limit. This velocity-based traversability is integrated into a hierarchical planner that combines traversability-informed Rapid Random Tree Star (TravRRT*) for time-efficient planning and Model Predictive Control (MPC) for safe execution. We validate our method in MuJoCo simulation and the real world, demonstrating improved navigation performance, with enhanced robustness and time efficiency across varying terrains compared to existing methods.

cs.RO↗

arXiv2025

FPGA-Enabled Modulo ADC with x100 Dynamic-Range Expansion: Hardware Design and Performance Evaluation

Conventional analog-to-digital converters (ADCs) fail to capture high-dynamic-range (HDR) signals due to clipping. Modulo ADCs circumvent this limitation by folding the input prior to quantization and algorithmically reconstructing the original waveform. This work presents a field-programmable gate array (FPGA)-based modulo ADC platform for systematic HDR performance evaluation. The mixed-signal architecture integrates a precision analog front end with a 200-MHz FPGA control loop that incorporates multi-bit updates and digital under-compensation calibration, ensuring stable folding and accurate feedback generation. The system achieves more than a hundred-fold dynamic-range expansion within a 400-kHz bandwidth while maintaining fidelity comparable to that of a conventional ADC. A system-on-chip (SoC)-like implementation enables on-board real-time recovery and supports benchmarking of state-of-the-art reconstruction algorithms, providing a compact and practical framework for HDR signal acquisition and evaluation.

eess.SP↗

arXiv2025

Moduli Selection in Robust Chinese Remainder Theorem: Closed-Form Solutions and Layered Design

We study the fundamental problem of \emph{moduli selection} in the Robust Chinese Remainder Theorem (RCRT), where each residue may be perturbed by a bounded error. Consider $L$ moduli of the form $m_i = Γ_i m$ ($1 \le i \le L$), where $Γ_i$ are pairwise coprime integers and $m \in \mathbb{R}^+$ is a common scaling factor. For small $L$ ($L = 2, 3, 4$), we obtain exact solutions that maximize the robustness margin under dynamic-range and modulus-bound constraints. We also introduce a Fibonacci-inspired \emph{layered} construction (for $L = 2$) that produces exactly $K$ robust decoding layers, enabling predictable trade-offs between error tolerance and dynamic range. We further analyze how robustness and range evolve across layers and provide a closed-form expression to estimate the success probability under common data and noise models. The results are promising for various applications, such as sub-Nyquist sampling, phase unwrapping, range estimation, modulo analog-to-digital converters (ADCs), and robust residue-number-system (RNS)-based accelerators for deep learning. Our framework thus establishes a general theory of moduli design for RCRT, complementing prior algorithmic work and underscoring the broad relevance of robust moduli design across diverse information-processing domains.

eess.SP↗

arXiv2025

Modular, On-Site Solutions with Lightweight Anomaly Detection for Sustainable Nutrient Management in Agriculture

Efficient nutrient management is critical for crop growth and sustainable resource consumption (e.g., nitrogen, energy). Current approaches require lengthy analyses, preventing real-time optimization; similarly, imaging facilitates rapid phenotyping but can be computationally intensive, preventing deployment under resource constraints. This study proposes a flexible, tiered pipeline for anomaly detection and status estimation (fresh weight, dry mass, and tissue nutrients), including a comprehensive energy analysis of approaches that span the efficiency-accuracy spectrum. Using a nutrient depletion experiment with three treatments (T1-100%, T2-50%, and T3-25% fertilizer strength) and multispectral imaging (MSI), we developed a hierarchical pipeline using an autoencoder (AE) for early warning. Further, we compared two status estimation modules of different complexity for more detailed analysis: vegetation index (VI) features with machine learning (Random Forest, RF) and raw whole-image deep learning (Vision Transformer, ViT). Results demonstrated high-efficiency anomaly detection (73% net detection of T3 samples 9 days after transplanting) at substantially lower energy than embodied energy in wasted nitrogen. The state estimation modules show trade-offs, with ViT outperforming RF on phosphorus and calcium estimation (R2 0.61 vs. 0.58, 0.48 vs. 0.35) at higher energy cost. With our modular pipeline, this work opens opportunities for edge diagnostics and practical opportunities for agricultural sustainability.

cs.CV↗

arXiv2025

Diffusion-Denoised Hyperspectral Gaussian Splatting

Hyperspectral imaging (HSI) has been widely used in agricultural applications for non-destructive estimation of plant nutrient composition and precise quantification of sample nutritional elements. Recently, 3D reconstruction methods, such as Neural Radiance Field (NeRF), have been used to create implicit neural representations of HSI scenes. This capability enables the rendering of hyperspectral channel compositions at every spatial location, thereby helping localize the target object's nutrient composition both spatially and spectrally. However, it faces limitations in training time and rendering speed. In this paper, we propose Diffusion-Denoised Hyperspectral Gaussian Splatting (DD-HGS), which enhances the state-of-the-art 3D Gaussian Splatting (3DGS) method with wavelength-aware spherical harmonics, a Kullback-Leibler divergence-based spectral loss, and a diffusion-based denoiser to enable 3D explicit reconstruction of the hyperspectral scenes for the entire spectral range. We present extensive evaluations on diverse real-world hyperspectral scenes from the Hyper-NeRF dataset to show the effectiveness of our DD-HGS. The results demonstrate that DD-HGS achieves the new state-of-the-art performance compared to all the previously published methods. Project page: https://dragonpg2000.github.io/DDHGS-website/

cs.CV↗

arXiv2025

SynTTS-Commands: A Public Dataset for On-Device KWS via TTS-Synthesized Multilingual Speech

The development of high-performance, on-device keyword spotting (KWS) systems for ultra-low-power hardware is critically constrained by the scarcity of specialized, multi-command training datasets. Traditional data collection through human recording is costly, slow, and lacks scalability. This paper introduces SYNTTS-COMMANDS, a novel, multilingual voice command dataset entirely generated using state-of-the-art Text-to-Speech (TTS) synthesis. By leveraging the CosyVoice 2 model and speaker embeddings from public corpora, we created a scalable collection of English and Chinese commands. Extensive benchmarking across a range of efficient acoustic models demonstrates that our synthetic dataset enables exceptional accuracy, achieving up to 99.5\% on English and 98\% on Chinese command recognition. These results robustly validate that synthetic speech can effectively replace human-recorded audio for training KWS classifiers. Our work directly addresses the data bottleneck in TinyML, providing a practical, scalable foundation for building private, low-latency, and energy-efficient voice interfaces on resource-constrained edge devices. The dataset and source code are publicly available at https://github.com/lugan113/SynTTS-Commands-Official.

cs.SD↗

arXiv2025

GSAP-ERE: Fine-Grained Scholarly Entity and Relation Extraction Focused on Machine Learning

Research in Machine Learning (ML) and AI evolves rapidly. Information Extraction (IE) from scientific publications enables to identify information about research concepts and resources on a large scale and therefore is a pathway to improve understanding and reproducibility of ML-related research. To extract and connect fine-grained information in ML-related research, e.g. method training and data usage, we introduce GSAP-ERE. It is a manually curated fine-grained dataset with 10 entity types and 18 semantically categorized relation types, containing mentions of 63K entities and 35K relations from the full text of 100 ML publications. We show that our dataset enables fine-tuned models to automatically extract information relevant for downstream tasks ranging from knowledge graph (KG) construction, to monitoring the computational reproducibility of AI research at scale. Additionally, we use our dataset as a test suite to explore prompting strategies for IE using Large Language Models (LLM). We observe that the performance of state-of-the-art LLM prompting methods is largely outperformed by our best fine-tuned baseline model (NER: 80.6%, RE: 54.0% for the fine-tuned model vs. NER: 44.4%, RE: 10.1% for the LLM). This disparity of performance between supervised models and unsupervised usage of LLMs suggests datasets like GSAP-ERE are needed to advance research in the domain of scholarly information extraction.

cs.CL↗

arXiv2025

Information Theoretic Learning for Diffusion Models with Warm Start

Generative models that maximize model likelihood have gained traction in many practical settings. Among them, perturbation based approaches underpin many strong likelihood estimation models, yet they often face slow convergence and limited theoretical understanding. In this paper, we derive a tighter likelihood bound for noise driven models to improve both the accuracy and efficiency of maximum likelihood learning. Our key insight extends the classical KL divergence Fisher information relationship to arbitrary noise perturbations, going beyond the Gaussian assumption and enabling structured noise distributions. This formulation allows flexible use of randomized noise distributions that naturally account for sensor artifacts, quantization effects, and data distribution smoothing, while remaining compatible with standard diffusion training. Treating the diffusion process as a Gaussian channel, we further express the mismatched entropy between data and model, showing that the proposed objective upper bounds the negative log-likelihood (NLL). In experiments, our models achieve competitive NLL on CIFAR-10 and SOTA results on ImageNet across multiple resolutions, all without data augmentation, and the framework extends naturally to discrete data.

cs.IT↗

arXiv2025

Flexible Intelligent Metasurface for Reconfiguring Radio Environments

Flexible intelligent metasurface (FIM) technology holds immense potential for increasing the spectral efficiency and energy efficiency of wireless networks. In contrast to traditional rigid reconfigurable intelligent surfaces (RIS), an FIM consists of an array of elements, each capable of independently tuning electromagnetic signals, while flexibly adjusting its position along the direction perpendicular to the surface. In contrast to traditional rigid metasurfaces, FIM is capable of morphing its surface shape to attain better channel conditions. In this paper, we investigate the single-input single-output (SISO) and multiple-input single-output (MISO) communication systems aided by a transmissive FIM. In the SISO scenario, we jointly optimize the FIM phase shift matrix and surface shape to maximize the end-to-end channel gain. First, we derive the optimal phase-shift matrix for each tentative FIM surface shape to decompose the high-dimensional non-convex optimization problem into multiple one-dimensional subproblems. Then, we utilize the particle swarm optimization (PSO) algorithm and the multi-interval gradient descent (MIGD) method for updating the FIM's surface shape to maximize the channel gain. In the MISO scenario, we jointly optimize the transmit beamforming, the FIM surface shape, and the phase shift matrix to maximize the channel gain. To tackle this complex problem with multiple highly coupled variables, an efficient alternating optimization algorithm is proposed. Simulation results demonstrate that FIM significantly improves channel gain compared to traditional RIS and exhibits good adaptability to multipath channels.

eess.SP↗

arXiv2025

Difference-Based Recovery for Modulo Sampling: Tightened Bounds and Robustness Guarantees

Conventional analog-to-digital converters (ADCs) clip when signals exceed their input range. Modulo (unlimited) sampling overcomes this limitation by folding the signal before digitization, but existing recovery methods are either computationally intensive or constrained by loose oversampling bounds that demand high sampling rates. In addition, none account for sampling jitter, which is unavoidable in practice. This paper revisits difference-based recovery and establishes new theoretical and practical guarantees. In the noiseless setting, we prove that arbitrarily high difference order reduces the sufficient oversampling factor from $2πe$ to $π$, substantially tightening classical bounds. For fixed order $N$, we derive a noise-aware sampling condition that guarantees stable recovery. For second-order difference-based recovery ($N=2$), we further extend the analysis to non-uniform sampling, proving robustness under bounded jitter. An FPGA-based hardware prototype demonstrates reliable reconstruction with amplitude expansion up to $ρ= 108$, confirming the feasibility of high-performance unlimited sensing with a simple and robust recovery pipeline.

eess.SP↗

arXiv2025

Performance Analysis of RIS-Aided High-Mobility Wireless Systems

Reconfigurable intelligent surface (RIS) technology holds immense potential for increasing the performance of wireless networks. Therefore, RIS is also regarded as one of the solutions to address communication challenges in high-mobility scenarios, such as Doppler shift and fast fading. This paper investigates a high-speed train (HST) multiple-input single-output (MISO) communication system aided by a RIS. We propose a block coordinate descent (BCD) algorithm to jointly optimize the RIS phase shifts and the transmit beamforming vectors to maximize the channel gain. Numerical results are provided to demonstrate that the proposed algorithm significantly enhances the system performance, achieving an average channel gain improvement of 15 dB compared to traditional schemes. Additionally, the introduction of RIS eliminates outage probability and improves key performance metrics such as achievable rate, channel capacity, and bit error rate (BER). These findings highlight the critical role of RIS in enhancing HST communication systems.

eess.SP↗

arXiv2025

Flexible Intelligent Metasurface for Enhancing Multi-Target Wireless Sensing

Flexible intelligent metasurface (FIM) has emerged as a transformative technology to enhance wireless sensing by dynamically morphing its three-dimensional (3D) surface shape and electromagnetic response. Unlike conventional rigid arrays, an FIM consists of low-cost radiating elements that can independently adjust their positions and radiation characteristics, thereby allowing for real-time optimization of the sensing environment. This paper investigates the impact of FIM on wireless sensing performance. Specifically, we focus on the maximization of the cumulated power of the probing signals at the target locations under the per-antenna power constraint by jointly optimizing the transmit covariance matrix and the surface shape of the transmitting FIM. We propose a block coordinate descend (BCD) algorithm to find a locally optimal solution, by alternatively updating the FIM surface shape and the transmit covariance matrix, while keeping the other one fixed at each step. Furthermore, we analyze the computational complexity and convergence properties of the proposed algorithm and demonstrate that FIM enhances wireless sensing by providing a new design degree-of-freedom to coordinate the correlation between steering vectors at different angles. Numerical results demonstrate that FIM significantly improves wireless sensing performance under the considered multi-target scenario.

cs.IT↗

arXiv2025

A Curated and Re-annotated Peripheral Blood Cell Dataset Integrating Four Public Resources

We present TXL-PBC, a curated and re-annotated peripheral blood cell dataset constructed by integrating four publicly available resources: Blood Cell Count and Detection (BCCD), Blood Cell Detection Dataset (BCDD), Peripheral Blood Cells (PBC), and Raabin White Blood Cell (Raabin-WBC). Through rigorous sample selection, semi-automatic annotation using the YOLOv8n model, and comprehensive manual review, we ensured high annotation accuracy and consistency. The final dataset contains 1,260 images and 18,143 bounding box annotations for three major blood cell types: white blood cells (WBC), red blood cells (RBC), and platelets. We provide detailed visual analyses of the data distribution, demonstrating the diversity and balance of the dataset. To further validate the quality and utility of TXL-PBC, we trained several mainstream object detection models, including YOLOv5s, YOLOv8s, YOLOv11s, SSD300, Faster R-CNN, and RetinaNet, and report their baseline performance. The TXL-PBC dataset is openly available on Figshare and GitHub, offering a valuable resource for the development and benchmarking of blood cell detection models and related machine learning research.

cs.CV↗

arXiv2025

Stacked Intelligent Metasurfaces for Multi-Modal Semantic Communications

Semantic communication (SemCom) powered by generative artificial intelligence enables highly efficient and reliable information transmission. However, it still necessitates the transmission of substantial amounts of data when dealing with complex scene information. In contrast, the stacked intelligent metasurface (SIM), leveraging wave-domain computing, provides a cost-effective solution for directly imaging complex scenes. Building on this concept, we propose an innovative SIM-aided multi-modal SemCom system. Specifically, an SIM is positioned in front of the transmit antenna for transmitting visual semantic information of complex scenes via imaging on the uniform planar array at the receiver. Furthermore, the simple scene description that contains textual semantic information is transmitted via amplitude-phase modulation over electromagnetic waves. To simultaneously transmit multi-modal information, we optimize the amplitude and phase of meta-atoms in the SIM using a customized gradient descent algorithm. The optimization aims to gradually minimize the mean squared error between the normalized energy distribution on the receiver array and the desired pattern corresponding to the visual semantic information. By combining the textual and visual semantic information, a conditional generative adversarial network is used to recover the complex scene accurately. Extensive numerical results verify the effectiveness of the proposed multi-modal SemCom system in reducing bandwidth overhead as well as the capability of the SIM for imaging the complex scene.

cs.IT↗