arXiv subjects

Yuan Gao

Publications and source records attributed to Yuan Gao.

At least 253 records · Page 14Linked to original sources

arXiv2025

AI-Powered Agile Analog Circuit Design and Optimization

Artificial intelligence (AI) techniques are transforming analog circuit design by automating device-level tuning and enabling system-level co-optimization. This paper integrates two approaches: (1) AI-assisted transistor sizing using Multi-Objective Bayesian Optimization (MOBO) for direct circuit parameter optimization, demonstrated on a linearly tunable transconductor; and (2) AI-integrated circuit transfer function modeling for system-level optimization in a keyword spotting (KWS) application, demonstrated by optimizing an analog bandpass filter within a machine learning training loop. The combined insights highlight how AI can improve analog performance, reduce design iteration effort, and jointly optimize analog components and application-level metrics.

cs.AR↗

arXiv2025

Personalized Risks and Regulatory Strategies of Large Language Models in Digital Advertising

Although large language models have demonstrated the potential for personalized advertising recommendations in experimental environments, in actual operations, how advertising recommendation systems can be combined with measures such as user privacy protection and data security is still an area worthy of in-depth discussion. To this end, this paper studies the personalized risks and regulatory strategies of large language models in digital advertising. This study first outlines the principles of Large Language Model (LLM), especially the self-attention mechanism based on the Transformer architecture, and how to enable the model to understand and generate natural language text. Then, the BERT (Bidirectional Encoder Representations from Transformers) model and the attention mechanism are combined to construct an algorithmic model for personalized advertising recommendations and user factor risk protection. The specific steps include: data collection and preprocessing, feature selection and construction, using large language models such as BERT for advertising semantic embedding, and ad recommendations based on user portraits. Then, local model training and data encryption are used to ensure the security of user privacy and avoid the leakage of personal data. This paper designs an experiment for personalized advertising recommendation based on a large language model of BERT and verifies it with real user data. The experimental results show that BERT-based advertising push can effectively improve the click-through rate and conversion rate of advertisements. At the same time, through local model training and privacy protection mechanisms, the risk of user privacy leakage can be reduced to a certain extent.

cs.CL↗

arXiv2025

Hyper-parameter Optimization for Wireless Network Traffic Prediction Models with A Novel Meta-Learning Framework

This paper proposes a novel meta-learning based hyper-parameter optimization framework for wireless network traffic prediction (NTP) models. The primary objective is to accumulate and leverage the acquired hyper-parameter optimization experience, enabling the rapid determination of optimal hyper-parameters for new tasks. In this paper, an attention-based deep neural network (ADNN) is employed as the base-learner to address specific NTP tasks. The meta-learner is an innovative framework that integrates meta-learning with the k-nearest neighbor algorithm (KNN), genetic algorithm (GA), and gated residual network (GRN). Specifically, KNN is utilized to identify a set of candidate hyper-parameter selection strategies for a new task, which then serves as the initial population for GA, while a GRN-based chromosome screening module accelerates the validation of offspring chromosomes, ultimately determining the optimal hyper-parameters. Experimental results demonstrate that, compared to traditional methods such as Bayesian optimization (BO), GA, and particle swarm optimization (PSO), the proposed framework determines optimal hyper-parameters more rapidly, significantly reduces optimization time, and enhances the performance of the base-learner. It achieves an optimal balance between optimization efficiency and prediction accuracy.

cs.NI↗

arXiv2025

Intelligent Mode-Locked Single-Cavity Dual-Comb Laser Utilizing Time-Stretch Dispersive Fourier Transform Spectroscopy

As dual combs play a significant role in numerous high-precision measurements, their efficient generation has been widely researched. Although the single-cavity dual-comb generation can avoid the complex active stabilization methods, achieving and maintaining stable dual-comb mode locking within a single cavity remains a critical challenge. To break through this constraint, a two-part evaluation criterion containing a fitness function and a CNN-Transformer network is employed to achieve mode locking and classify the dual-comb mode-locked state. Simulated time-stretch dispersive Fourier transform (DFT) spectra are used as datasets, which simplifies the optimization process and does not rely on specific experimental data. A developed evolutionary algorithm (EA) for paddle-based motorized polarization controllers (MPCs) is proposed, enabling the intelligent attainment of dual-comb mode-locked states. A real-time library stores fitness and MPC angles, facilitating mode-locked state achievement within 2 seconds. Finally, long term running of dual-comb mode locking is ensured by a random collision algorithm utilizing an evaluation criterion of weak soliton peaks.

physics.optics↗

arXiv2025

AdaViP: Aligning Multi-modal LLMs via Adaptive Vision-enhanced Preference Optimization

Preference alignment through Direct Preference Optimization (DPO) has demonstrated significant effectiveness in aligning multimodal large language models (MLLMs) with human preferences. However, existing methods focus primarily on language preferences while neglecting the critical visual context. In this paper, we propose an Adaptive Vision-enhanced Preference optimization (AdaViP) that addresses these limitations through two key innovations: (1) vision-based preference pair construction, which integrates multiple visual foundation models to strategically remove key visual elements from the image, enhancing MLLMs' sensitivity to visual details; and (2) adaptive preference optimization that dynamically balances vision- and language-based preferences for more accurate alignment. Extensive evaluations across different benchmarks demonstrate our effectiveness. Notably, our AdaViP-7B achieves 93.7% and 96.4% reductions in response-level and mentioned-level hallucination respectively on the Object HalBench, significantly outperforming current state-of-the-art methods.

cs.CV↗

arXiv2025

Bounds and Optimal Constructions of Generalized Merge-Convertible Codes for Code Conversion into LRCs

Error-correcting codes are essential for ensuring fault tolerance in modern distributed data storage systems. However, in practice, factors such as the failure rates of storage devices can vary significantly over time, resulting in changes to the optimal code parameters. To reduce storage cost while maintaining efficiency, Maturana and Rashmi introduced a theoretical framework known as code conversion, which enables dynamic adjustment of code parameters according to device performance. In this paper, we focus exclusively on the bounds and constructions of generalized merge-convertible codes. First, we establish a new lower bound on the access cost when the final code is an $(r,δ)$-LRC. This bound unifies and generalizes all previously known bounds for merge conversion, where the initial and final codes are either LRCs or MDS codes. We then construct a family of access-optimal MDS convertible codes by leveraging subgroups of the automorphism group of a rational function field. It is worth noting that our construction is also per-symbol read access-optimal. Next, we further extend our MDS-based construction to design access-optimal convertible codes for the conversion between $(r,δ)$-LRCs with parameters that have not been previously reported. Finally, using the parity-check matrix approach, we present a construction of access-optimal convertible codes that enable merge conversion from MDS codes to an $(r,δ)$-LRC. To the best of our knowledge, this is the first explicit optimal construction of code conversion between MDS codes and LRCs. All of our constructions are performed over finite fields whose sizes grow linearly with the code length.

cs.IT↗

arXiv2025

Giant Magnetocaloric Effect in Spin Supersolid Candidate Na$_2$BaCo(PO$_4$)$_2$

Supersolid, an exotic quantum state of matter that consists of particles forming an incompressible solid structure while simultaneously showing superfluidity of zero viscosity [1], is one of the long-standing pursuits in fundamental research [2, 3]. Although the initial report of $^4$He supersolid turned out to be an artifact [4], this intriguing quantum matter has inspired enthusiastic investigations into ultracold quantum gases [5-8]. Nevertheless, the realization of supersolidity in condensed matter remains elusive. Here we find evidence for a quantum magnetic analogue of supersolid -- the spin supersolid -- in the recently synthesized triangular-lattice antiferromagnet Na$_2$BaCo(PO$_4$)$_2$ [9]. Notably, a giant magnetocaloric effect related to the spin supersolidity is observed in the demagnetization cooling process, manifesting itself as two prominent valley-like regimes, with the lowest temperature attaining below 100 mK. Not only is there an experimentally determined series of critical fields but the demagnetization cooling profile also shows excellent agreement with the theoretical simulations with an easy-axis Heisenberg model. Neutron diffractions also successfully locate the proposed spin supersolid phases by revealing the coexistence of three-sublattice spin solid order and interlayer incommensurability indicative of the spin superfluidity. Thus, our results indicate a strong entropic effect of the spin supersolid phase in a frustrated quantum magnet and open up a viable and promising avenue for applications in sub-Kelvin refrigeration, especially in the context of persistent concerns about helium shortages [10, 11].

cond-mat.str-el↗

arXiv2025

Accelerated Distributed Optimization with Compression and Error Feedback

Modern machine learning tasks often involve massive datasets and models, necessitating distributed optimization algorithms with reduced communication overhead. Communication compression, where clients transmit compressed updates to a central server, has emerged as a key technique to mitigate communication bottlenecks. However, the theoretical understanding of stochastic distributed optimization with contractive compression remains limited, particularly in conjunction with Nesterov acceleration -- a cornerstone for achieving faster convergence in optimization. In this paper, we propose a novel algorithm, ADEF (Accelerated Distributed Error Feedback), which integrates Nesterov acceleration, contractive compression, error feedback, and gradient difference compression. We prove that ADEF achieves the first accelerated convergence rate for stochastic distributed optimization with contractive compression in the general convex regime. Numerical experiments validate our theoretical findings and demonstrate the practical efficacy of ADEF in reducing communication costs while maintaining fast convergence.

math.OC↗

arXiv2025

ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural Networks

Graph Neural Networks (GNNs) have gained traction in Graph-based Machine Learning as a Service (GMLaaS) platforms, yet they remain vulnerable to graph-based model extraction attacks (MEAs), where adversaries reconstruct surrogate models by querying the victim model. Existing defense mechanisms, such as watermarking and fingerprinting, suffer from poor real-time performance, susceptibility to evasion, or reliance on post-attack verification, making them inadequate for handling the dynamic characteristics of graph-based MEA variants. To address these limitations, we propose ATOM, a novel real-time MEA detection framework tailored for GNNs. ATOM integrates sequential modeling and reinforcement learning to dynamically detect evolving attack patterns, while leveraging $k$-core embedding to capture the structural properties, enhancing detection precision. Furthermore, we provide theoretical analysis to characterize query behaviors and optimize detection strategies. Extensive experiments on multiple real-world datasets demonstrate that ATOM outperforms existing approaches in detection performance, maintaining stable across different time steps, thereby offering a more effective defense mechanism for GMLaaS environments.

cs.LG↗

arXiv2025

Temperature inhomogeneity in non-equilibrium field theory for electrons in a nanowire: thermodynamic and transport properties

A nanowire with its two ends fixed at two different temperatures by external baths is the simplest example of a fermionic system with a temperature inhomogeneity, and could be an easy platform to study thermodynamic and transport properties of a boundary-driven open quantum system. Starting with a temperature-dependent pseudo free energy derived from an exact reduced density matrix and assuming a small temperature gradient $γ$ across the wire, we show within perturbation theory that electron dispersion relation and therefore the Fermi distribution becomes $γ$ and space coordinates dependent, leading to non-linear effects of the temperature inhomogeneity. In particular, we show that in the non-linear response regime, the Widemann-Franz Law for the ratio of thermal and electrical conductivities is generalized, and that the thermopower increases with increasing temperature gradient $γ$.

cond-mat.mes-hall↗

arXiv2025

Non-equilibrium field theory with a temperature gradient: Thermal current in a nanowire

A perturbative framework is developed within the standard non-equilibrium field theory techniques to incorporate a temperature gradient across a thermoelectric device. The framework uses a temperature-dependent pseudo-Hamiltonian generated from the exact density matrix in the presence of non-uniform temperatures. We develop a perturbation theory for small temperature gradients in long wires and obtain the non-linear thermal conductance as a function of temperature difference. The framework should be adaptable to more general cases of temperature inhomogeneities in either fermionic or bosonic systems.

cond-mat.mes-hall↗

arXiv2025

Enhancing Vision-Language Pre-training with Rich Supervisions

We propose Strongly Supervised pre-training with ScreenShots (S4) - a novel pre-training paradigm for Vision-Language Models using data from large-scale web screenshot rendering. Using web screenshots unlocks a treasure trove of visual and textual cues that are not present in using image-text pairs. In S4, we leverage the inherent tree-structured hierarchy of HTML elements and the spatial localization to carefully design 10 pre-training tasks with large scale annotated data. These tasks resemble downstream tasks across different domains and the annotations are cheap to obtain. We demonstrate that, compared to current screenshot pre-training objectives, our innovative pre-training method significantly enhances performance of image-to-text model in nine varied and popular downstream tasks - up to 76.1% improvements on Table Detection, and at least 1% on Widget Captioning.

cs.CV↗

arXiv2025

X2CT-CLIP: Enable Multi-Abnormality Detection in Computed Tomography from Chest Radiography via Tri-Modal Contrastive Learning

Computed tomography (CT) is a key imaging modality for diagnosis, yet its clinical utility is marred by high radiation exposure and long turnaround times, restricting its use for larger-scale screening. Although chest radiography (CXR) is more accessible and safer, existing CXR foundation models focus primarily on detecting diseases that are readily visible on the CXR. Recently, works have explored training disease classification models on simulated CXRs, but they remain limited to recognizing a single disease type from CT. CT foundation models have also emerged with significantly improved detection of pathologies in CT. However, the generalized application of CT-derived labels on CXR has remained illusive. In this study, we propose X2CT-CLIP, a tri-modal knowledge transfer learning framework that bridges the modality gap between CT and CXR while reducing the computational burden of model training. Our approach is the first work to enable multi-abnormality classification in CT, using CXR, by transferring knowledge from 3D CT volumes and associated radiology reports to a CXR encoder via a carefully designed tri-modal alignment mechanism in latent space. Extensive evaluations on three multi-label CT datasets demonstrate that our method outperforms state-of-the-art baselines in cross-modal retrieval, few-shot adaptation, and external validation. These results highlight the potential of CXR, enriched with knowledge derived from CT, as a viable efficient alternative for disease detection in resource-limited settings.

cs.CV↗

arXiv2025

Remote Sensing Object Counting with Online Knowledge Learning

Efficient models for remote sensing object counting are urgently required for applications in scenarios with limited computing resources, such as drones or embedded systems. A straightforward yet powerful technique to achieve this is knowledge distillation, which steers the learning of student networks by leveraging the experience of already-trained teacher networks. However, it faces a pair of challenges: Firstly, due to its two-stage training nature, a longer training period is essential, especially as the training samples increase. Secondly, despite the proficiency of teacher networks in transmitting assimilated knowledge, they tend to overlook the latent insights gained during their learning process. To address these challenges, we introduce an online distillation learning method for remote sensing object counting. It builds an end-to-end training framework that seamlessly integrates two distinct networks into a unified one. It comprises a shared shallow module, a teacher branch, and a student branch. The shared module serving as the foundation for both branches is dedicated to learning some primitive information. The teacher branch utilizes prior knowledge to reduce the difficulty of learning and guides the student branch in online learning. In parallel, the student branch achieves parameter reduction and rapid inference capabilities by means of channel reduction. This design empowers the student branch not only to receive privileged insights from the teacher branch but also to tap into the latent reservoir of knowledge held by the teacher branch during the learning process. Moreover, we propose a relation-in-relation distillation method that allows the student branch to effectively comprehend the evolution of the relationship of intra-layer teacher features among different inter-layer features. Extensive experiments demonstrate the effectiveness of our method.

cs.CV↗

arXiv2025

C2S-AE: CSI to Sensing enabled by an Auto-Encoder-based Framework

Next-generation mobile networks are set to utilize integrated sensing and communication (ISAC) as a critical technology, providing significant support for sectors like the industrial Internet of Things (IIoT), extended reality (XR), and smart home applications. A key challenge in ISAC implementation is the extraction of sensing parameters from radio signals, a task that conventional methods struggle to achieve due to the complexity of acquiring sensing channel data. In this paper, we introduce a novel auto-encoder (AE)-based framework to acquire sensing information using channel state information (CSI). Specifically, our framework, termed C2S (CSI to sensing)-AE, learns the relationship between CSI and the delay power spectrum (DPS), from which the range information can be readily accessed. To validate our framework's performance, we conducted measurements of DPS and CSI in real-world scenarios and introduced the dataset 'SHU7'. Our extensive experiments demonstrate that the framework excels in C2S extrapolation, surpassing existing methods in terms of accuracy for both delay and signal strength of individual paths. This innovative approach holds the potential to greatly enhance sensing capabilities in future mobile networks, paving the way for more robust and versatile ISAC applications.

eess.SP↗

arXiv2025

A MIMO Wireless Channel Foundation Model via CIR-CSI Consistency

In the field of artificial intelligence, self-supervised learning has demonstrated superior generalization capabilities by leveraging large-scale unlabeled datasets for pretraining, which is especially critical for wireless communication models to adapt to a variety of scenarios. This paper innovatively treats Channel State Information (CSI) and Channel Impulse Response (CIR) as naturally aligned multi-modal data and proposes the first MIMO wireless channel foundation model, named CSI-CLIP. By effectively capturing the joint representations of both CIR and CSI, CSI-CLIP exhibits remarkable adaptability across scenarios and robust feature extraction capabilities. Experimental results show that in positioning task, CSI-CLIP reduces the mean error distance by 22%; in beam management task, it increases accuracy by 1% compared to traditional supervised methods, as well as in the channel identification task. These improvements not only highlight the potential and value of CSI-CLIP in integrating sensing and communication but also demonstrate its significant advantages over existing techniques. Moreover, viewing CSI and CIR as multi-modal pairs and contrastive learning for wireless channel foundation model open up new research directions in the domain of MIMO wireless communications.

eess.SP↗

arXiv2025

MTCA: Multi-Task Channel Analysis for Wireless Communication

In modern wireless communication systems, the effective processing of Channel State Information (CSI) is crucial for enhancing communication quality and reliability. However, current methods often handle different tasks in isolation, thereby neglecting the synergies among various tasks and leading to extract CSI features inadequately for subsequent analysis. To address these limitations, this paper introduces a novel Multi-Task Channel Analysis framework named MTCA, aimed at improving the performance of wireless communication even sensing. MTCA is designed to handle four critical tasks, including channel prediction, antenna-domain channel extrapolation, channel identification, and scenario classification. Experiments conducted on a multi-scenario, multi-antenna dataset tailored for UAV-based communications demonstrate that the proposed MTCA exhibits superior comprehension of CSI, achieving enhanced performance across all evaluated tasks. Notably, MTCA reached 100% prediction accuracy in channel identification and scenario classification. Compared to the previous state-of-the-art methods, MTCA improved channel prediction performance by 20.1% and antenna-domain extrapolation performance by 54.5%.

eess.SP↗

arXiv2025

BeamVQ: Beam Search with Vector Quantization to Mitigate Data Scarcity in Physical Spatiotemporal Forecasting

In practice, physical spatiotemporal forecasting can suffer from data scarcity, because collecting large-scale data is non-trivial, especially for extreme events. Hence, we propose \method{}, a novel probabilistic framework to realize iterative self-training with new self-ensemble strategies, achieving better physical consistency and generalization on extreme events. Following any base forecasting model, we can encode its deterministic outputs into a latent space and retrieve multiple codebook entries to generate probabilistic outputs. Then BeamVQ extends the beam search from discrete spaces to the continuous state spaces in this field. We can further employ domain-specific metrics (e.g., Critical Success Index for extreme events) to filter out the top-k candidates and develop the new self-ensemble strategy by combining the high-quality candidates. The self-ensemble can not only improve the inference quality and robustness but also iteratively augment the training datasets during continuous self-training. Consequently, BeamVQ realizes the exploration of rare but critical phenomena beyond the original dataset. Comprehensive experiments on different benchmarks and backbones show that BeamVQ consistently reduces forecasting MSE (up to 39%), enhancing extreme events detection and proving its effectiveness in handling data scarcity.

cs.LG↗