arXiv subjects

Jiaqi Wu

Publications and source records attributed to Jiaqi Wu.

At least 55 records · Page 3Linked to original sources

arXiv2025

Joint Edge Server Deployment and Computation Offloading: A Multi-Timescale Stochastic Programming Framework

Mobile Edge Computing (MEC) is a promising approach for enhancing the quality-of-service (QoS) of AI-enabled applications in the B5G/6G era, by bringing computation capability closer to end-users at the network edge. In this work, we investigate the joint optimization of edge server (ES) deployment, service placement, and computation task offloading under the stochastic information scenario. Traditional approaches often treat these decisions as equal, disregarding the differences in information realization. However, in practice, the ES deployment decision must be made in advance and remain unchanged, prior to the complete realization of information, whereas the decisions regarding service placement and computation task offloading can be made and adjusted in real-time after information is fully realized. To address such temporal coupling between decisions and information realization, we introduce the stochastic programming (SP) framework, which involves a strategic-layer for deciding ES deployment based on (incomplete) stochastic information and a tactical-layer for deciding service placement and task offloading based on complete information realization. The problem is challenging due to the different timescales of two layers' decisions. To overcome this challenge, we propose a multi-timescale SP framework, which includes a large timescale (called period) for strategic-layer decision-making and a small timescale (called slot) for tactical-layer decision making. Moreover, we design a Lyapunov-based algorithm to solve the tactical-layer problem at each time slot, and a Markov approximation algorithm to solve the strategic-layer problem in every time period.

cs.NI↗

arXiv2025

Few Shot Semi-Supervised Learning for Abnormal Stop Detection from Sparse GPS Trajectories

Abnormal stop detection (ASD) in intercity coach transportation is critical for ensuring passenger safety, operational reliability, and regulatory compliance. However, two key challenges hinder ASD effectiveness: sparse GPS trajectories, which obscure short or unauthorized stops, and limited labeled data, which restricts supervised learning. Existing methods often assume dense sampling or regular movement patterns, limiting their applicability. To address data sparsity, we propose a Sparsity-Aware Segmentation (SAS) method that adaptively defines segment boundaries based on local spatial-temporal density. Building upon these segments, we introduce three domain-specific indicators to capture abnormal stop behaviors. To further mitigate the impact of sparsity, we develop Locally Temporal-Indicator Guided Adjustment (LTIGA), which smooths these indicators via local similarity graphs. To overcome label scarcity, we construct a spatial-temporal graph where each segment is a node with LTIGA-refined features. We apply label propagation to expand weak supervision across the graph, followed by a GCN to learn relational patterns. A final self-training module incorporates high-confidence pseudo-labels to iteratively improve predictions. Experiments on real-world coach data show an AUC of 0.854 and AP of 0.866 using only 10 labeled instances, outperforming prior methods. The code and dataset are publicly available at \href{https://github.com/pangjunbiao/Abnormal-Stop-Detection-SSL.git}

cs.LG↗

arXiv2025

Altermagnetic Shastry-Sutherland fullerene networks

The interplay between quantum magnetism and many-body physics is of fundamental importance in condensed matter physics. %Magnetic exchange interactions in frustrated lattices give rise to rich phase diagrams. Molecular building blocks provide a versatile platform for exploring the exotic quantum phases arising from complex orderings in frustrated lattices. Here we demonstrate a showcase system based on altermagnetic Shastry-Sutherland fullerene networks, which can be constructed from a C$_{40}$ molecular synthon with two effective spin-1/2 sites due to the resonance structures. The charge-neutral, pure-carbon systems exhibit an altermagnetic ground state with fully compensated spins arranged in alternating C$_{40}$ units in a 2D rutile-like lattice, leading to $d$-wave splitting of the spin-polarised electronic band structure and strong chiral-split magnons. We report a rich phase diagram including altermagentic, quantum spin liquid, plaquette, and dimer phases, which can be accessed via moderate strains. Our findings open a new avenue for exploring quantum many-body physics based on scalable, chemically-feasible, molecular quantum materials.

cond-mat.mtrl-sci↗

arXiv2025

Negative and positive anisotropic thermal expansion in 2D fullerene networks

We find a design principle for tailoring thermal expansion properties in nearly-spherical molecular networks. Using 2D fullerene networks as a representative system, we realize positive thermal expansion along intermolecular [2\,+\,2] cycloaddition bonds and negative thermal expansion along intermolecular C$-$C single bonds by varying the structural frameworks of molecules. The microscopic mechanism originates from a combination of the framework's geometric flexibility and its transverse vibrational characteristics. Based on this insight, we find molecular networks beyond C$_{60}$ with tunable thermal expansion. These findings shed light on the fundamental mechanisms governing thermal expansion in molecular networks towards rational materials design.

cond-mat.mes-hall↗

arXiv2025

A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networks

The proliferation of Internet of things (IoT) devices in smart cities, transportation, healthcare, and industrial applications, coupled with the explosive growth of AI-driven services, has increased demands for efficient distributed computing architectures and networks, driving cloud-edge-terminal collaborative intelligence (CETCI) as a fundamental paradigm within the artificial intelligence of things (AIoT) community. With advancements in deep learning, large language models (LLMs), and edge computing, CETCI has made significant progress with emerging AIoT applications, moving beyond isolated layer optimization to deployable collaborative intelligence systems for AIoT (CISAIOT), a practical research focus in AI, distributed computing, and communications. This survey describes foundational architectures, enabling technologies, and scenarios of CETCI paradigms, offering a tutorial-style review for CISAIOT beginners. We systematically analyze architectural components spanning cloud, edge, and terminal layers, examining core technologies including network virtualization, container orchestration, and software-defined networking, while presenting categorizations of collaboration paradigms that cover task offloading, resource allocation, and optimization across heterogeneous infrastructures. Furthermore, we explain intelligent collaboration learning frameworks by reviewing advances in federated learning, distributed deep learning, edge-cloud model evolution, and reinforcement learning-based methods. Finally, we discuss challenges (e.g., scalability, heterogeneity, interoperability) and future trends (e.g., 6G+, agents, quantum computing, digital twin), highlighting how integration of distributed computing and communication can address open issues and guide development of robust, efficient, and secure collaborative AIoT systems.

cs.NI↗

arXiv2025

From Imperfect Signals to Trustworthy Structure: Confidence-Aware Inference from Heterogeneous and Reliability-Varying Utility Data

Accurate distribution grid topology is essential for reliable modern grid operations. However, real-world utility data originates from multiple sources with varying characteristics and levels of quality. In this work, developed in collaboration with Oncor Electric Delivery, we propose a scalable framework that reconstructs a trustworthy grid topology by systematically integrating heterogeneous data. We observe that distribution topology is fundamentally governed by two complementary dimensions: the spatial layout of physical infrastructure (e.g., GIS and asset metadata) and the dynamic behavior of the system in the signal domain (e.g., voltage time series). When jointly leveraged, these dimensions support a complete and physically coherent reconstruction of network connectivity. To address the challenge of uneven data quality without compromising observability, we introduce a confidence-aware inference mechanism that preserves structurally informative yet imperfect inputs, while quantifying the reliability of each inferred connection for operator interpretation. This soft handling of uncertainty is tightly coupled with hard enforcement of physical feasibility: we embed operational constraints, such as transformer capacity limits and radial topology requirements, directly into the learning process. Together, these components ensure that inference is both uncertainty-aware and structurally valid, enabling rapid convergence to actionable, trustworthy topologies under real-world deployment conditions. The proposed framework is validated using data from over 8000 meters across 3 feeders in Oncor's service territory, demonstrating over 95% accuracy in topology reconstruction and substantial improvements in confidence calibration and computational efficiency relative to baseline methods.

cs.LG↗

arXiv2025

Score-based Generative Diffusion Models to Synthesize Full-dose FDG Brain PET from MRI in Epilepsy Patients

Fluorodeoxyglucose (FDG) PET to evaluate patients with epilepsy is one of the most common applications for simultaneous PET/MRI, given the need to image both brain structure and metabolism, but is suboptimal due to the radiation dose in this young population. Little work has been done synthesizing diagnostic quality PET images from MRI data or MRI data with ultralow-dose PET using advanced generative AI methods, such as diffusion models, with attention to clinical evaluations tailored for the epilepsy population. Here we compared the performance of diffusion- and non-diffusion-based deep learning models for the MRI-to-PET image translation task for epilepsy imaging using simultaneous PET/MRI in 52 subjects (40 train/2 validate/10 hold-out test). We tested three different models: 2 score-based generative diffusion models (SGM-Karras Diffusion [SGM-KD] and SGM-variance preserving [SGM-VP]) and a Transformer-Unet. We report results on standard image processing metrics as well as clinically relevant metrics, including congruency measures (Congruence Index and Congruency Mean Absolute Error) that assess hemispheric metabolic asymmetry, which is a key part of the clinical analysis of these images. The SGM-KD produced the best qualitative and quantitative results when synthesizing PET purely from T1w and T2 FLAIR images with the least mean absolute error in whole-brain specific uptake value ratio (SUVR) and highest intraclass correlation coefficient. When 1% low-dose PET images are included in the inputs, all models improve significantly and are interchangeable for quantitative performance and visual quality. In summary, SGMs hold great potential for pure MRI-to-PET translation, while all 3 model types can synthesize full-dose FDG-PET accurately using MRI and ultralow-dose PET.

eess.IV↗

arXiv2025

Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models

Standing in 2025, at a critical juncture in the pursuit of Artificial General Intelligence (AGI), reinforcement fine-tuning (RFT) has demonstrated significant potential in enhancing the reasoning capability of large language models (LLMs) and has led to the development of cutting-edge AI models such as OpenAI-o1 and DeepSeek-R1. Moreover, the efficient application of RFT to enhance the reasoning capability of multimodal large language models (MLLMs) has attracted widespread attention from the community. In this position paper, we argue that reinforcement fine-tuning powers the reasoning capability of multimodal large language models. To begin with, we provide a detailed introduction to the fundamental background knowledge that researchers interested in this field should be familiar with. Furthermore, we meticulously summarize the improvements of RFT in powering reasoning capability of MLLMs into five key points: diverse modalities, diverse tasks and domains, better training algorithms, abundant benchmarks and thriving engineering frameworks. Finally, we propose five promising directions for future research that the community might consider. We hope that this position paper will provide valuable insights to the community at this pivotal stage in the advancement toward AGI. Summary of works done on RFT for MLLMs is available at https://github.com/Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs.

cs.CL↗

arXiv2025

SafeInt: Shielding Large Language Models from Jailbreak Attacks via Safety-Aware Representation Intervention

With the widespread real-world deployment of large language models (LLMs), ensuring their behavior complies with safety standards has become crucial. Jailbreak attacks exploit vulnerabilities in LLMs to induce undesirable behavior, posing a significant threat to LLM safety. Previous defenses often fail to achieve both effectiveness and efficiency simultaneously. Defenses from a representation perspective offer new insights, but existing interventions cannot dynamically adjust representations based on the harmfulness of the queries. To address this limitation, we propose SafeIntervention (SafeInt), a novel defense method that shields LLMs from jailbreak attacks through safety-aware representation intervention. Built on our analysis of the representations of jailbreak samples, the core idea of SafeInt is to relocate jailbreak-related representations into the rejection region. This is achieved by intervening in the representation distributions of jailbreak samples to align them with those of unsafe samples. We conduct comprehensive experiments covering six jailbreak attacks, two jailbreak datasets, and two utility benchmarks. Experimental results demonstrate that SafeInt outperforms all baselines in defending LLMs against jailbreak attacks while largely maintaining utility. Additionally, we evaluate SafeInt against adaptive attacks and verify its effectiveness in mitigating real-time attacks.

cs.CL↗

arXiv2025

Uncertainty-aware Long-tailed Weights Model the Utility of Pseudo-labels for Semi-supervised Learning

Current Semi-supervised Learning (SSL) adopts the pseudo-labeling strategy and further filters pseudo-labels based on confidence thresholds. However, this mechanism has notable drawbacks: 1) setting the reasonable threshold is an open problem which significantly influences the selection of the high-quality pseudo-labels; and 2) deep models often exhibit the over-confidence phenomenon which makes the confidence value an unreliable indicator for assessing the quality of pseudo-labels due to the scarcity of labeled data. In this paper, we propose an Uncertainty-aware Ensemble Structure (UES) to assess the utility of pseudo-labels for unlabeled samples. We further model the utility of pseudo-labels as long-tailed weights to avoid the open problem of setting the threshold. Concretely, the advantage of the long-tailed weights ensures that even unreliable pseudo-labels still contribute to enhancing the model's robustness. Besides, UES is lightweight and architecture-agnostic, easily extending to various computer vision tasks, including classification and regression. Experimental results demonstrate that combining the proposed method with DualPose leads to a 3.47% improvement in Percentage of Correct Keypoints (PCK) on the Sniffing dataset with 100 data points (30 labeled), a 7.29\% improvement in PCK on the FLIC dataset with 100 data points (50 labeled), and a 3.91% improvement in PCK on the LSP dataset with 200 data points (100 labeled). Furthermore, when combined with FixMatch, the proposed method achieves a 0.2% accuracy improvement on the CIFAR-10 dataset with 40 labeled data points and a 0.26% accuracy improvement on the CIFAR-100 dataset with 400 labeled data points.

cs.CV↗

arXiv2025

CLIP-Optimized Multimodal Image Enhancement via ISP-CNN Fusion for Coal Mine IoVT under Uneven Illumination

Clear monitoring images are crucial for the safe operation of coal mine Internet of Video Things (IoVT) systems. However, low illumination and uneven brightness in underground environments significantly degrade image quality, posing challenges for enhancement methods that often rely on difficult-to-obtain paired reference images. Additionally, there is a trade-off between enhancement performance and computational efficiency on edge devices within IoVT systems.To address these issues, we propose a multimodal image enhancement method tailored for coal mine IoVT, utilizing an ISP-CNN fusion architecture optimized for uneven illumination. This two-stage strategy combines global enhancement with detail optimization, effectively improving image quality, especially in poorly lit areas. A CLIP-based multimodal iterative optimization allows for unsupervised training of the enhancement algorithm. By integrating traditional image signal processing (ISP) with convolutional neural networks (CNN), our approach reduces computational complexity while maintaining high performance, making it suitable for real-time deployment on edge devices.Experimental results demonstrate that our method effectively mitigates uneven brightness and enhances key image quality metrics, with PSNR improvements of 2.9%-4.9%, SSIM by 4.3%-11.4%, and VIF by 4.9%-17.8% compared to seven state-of-the-art algorithms. Simulated coal mine monitoring scenarios validate our method's ability to balance performance and computational demands, facilitating real-time enhancement and supporting safer mining operations.

cs.CV↗

arXiv2025

Exploring Bridges Between Algorithmic and AI-generated Art

In this paper, we bridge algorithmic and AI art by adding functionality to the creative coding environment. We create two systems that demonstrate how AI features can enhance algorithmic art and, conversely, how AI art can be styled based on algorithmically-generated artifacts. The first library, GenP5, extends p5.js to allow the artist to apply diffusion models to style and 'condition' their algorithmically-constructed art. The second, P52Style, can learn the 'style' of an algorithmically generated artifact and apply that when creating new AI art.

cs.HC↗

arXiv2025

In-Distribution Consistency Regularization Improves the Generalization of Quantization-Aware Training

Although existing Quantization-Aware Training (QAT) methods intensively depend on knowledge distillation to guarantee performance, QAT still suffers from severe performance drop. The experiments have shown that vanilla quantization is sensitive to the perturbation from both the input and weights. Therefore, we assume that the generalization ability of QAT is predominantly caused by both the intrinsic instability (training time) and the limited generalization ability (testing time). In this paper, we address both issues from a new perspective by leveraging Consistency Regularization (CR) to improve the generalization ability of QAT. Empirical results and theoretical analysis verify that CR would bring a good generalization ability to different network architectures and various QAT methods. Extensive experiments demonstrate that our approach significantly outperforms current state-of-the-art QAT methods and even the FP counterparts. On CIFAR-10, the proposed method improves by 3.79% compared to the baseline method using ResNet18, and improves by 3.84% compared to the baseline method using the lightweight model MobileNet.

cs.CV↗

arXiv2025

Tuning electronic and optical properties of 2D polymeric C$_{60}$ by stacking two layers

Benefiting from improved stability due to stronger interlayer van der Waals interactions, few-layer fullerene networks are experimentally more accessible compared to monolayer polymeric C$_{60}$. However, there is a lack of systematic theoretical studies on the material properties of few-layer C$_{60}$ networks. Here, we compare the structural, electronic and optical properties of bilayer and monolayer fullerene networks. The band gap and band-edge positions remain mostly unchanged after stacking two layers into a bilayer, enabling the bilayer to be almost as efficient a photocatalyst as the monolayer. The effective mass ratio along different directions is varied for conduction band states due to interlayer interactions,leading to enhanced anisotropy in carrier transport. Additionally, stronger exciton absorption is found in the bilayer than that in the monolayer over the entire visible light range, rendering the bilayer a more promising candidate for photovoltaics. Moreoever, the polarisation dependence of optical absorption in the bilayer is increased in the red-yellow light range, offering unique opportunities in photonics and display technologies with tailored optical properties over specific directions. Our study provides strategies to tune electronic and optical properties of 2D polymeric C$_{60}$ via the introduction of stacking degrees of freedom.

cond-mat.mtrl-sci↗

arXiv2024

Efficient Detection Framework Adaptation for Edge Computing: A Plug-and-play Neural Network Toolbox Enabling Edge Deployment

Edge computing has emerged as a key paradigm for deploying deep learning-based object detection in time-sensitive scenarios. However, existing edge detection methods face challenges: 1) difficulty balancing detection precision with lightweight models, 2) limited adaptability of generalized deployment designs, and 3) insufficient real-world validation. To address these issues, we propose the Edge Detection Toolbox (ED-TOOLBOX), which utilizes generalizable plug-and-play components to adapt object detection models for edge environments. Specifically, we introduce a lightweight Reparameterized Dynamic Convolutional Network (Rep-DConvNet) featuring weighted multi-shape convolutional branches to enhance detection performance. Additionally, we design a Sparse Cross-Attention (SC-A) network with a localized-mapping-assisted self-attention mechanism, enabling a well-crafted joint module for adaptive feature transfer. For real-world applications, we incorporate an Efficient Head into the YOLO framework to accelerate edge model optimization. To demonstrate practical impact, we identify a gap in helmet detection -- overlooking band fastening, a critical safety factor -- and create the Helmet Band Detection Dataset (HBDD). Using ED-TOOLBOX-optimized models, we address this real-world task. Extensive experiments validate the effectiveness of ED-TOOLBOX, with edge detection models outperforming six state-of-the-art methods in visual surveillance simulations, achieving real-time and accurate performance. These results highlight ED-TOOLBOX as a superior solution for edge object detection.

cs.CV↗

arXiv2024

Smallest [5,6]fullerene as building blocks for 2D networks with superior stability and enhanced photocatalytic performance

The assembly of molecules to form covalent networks can create varied lattice structures with distinct physical and chemical properties from conventional atomic lattices. Using the smallest stable [5,6]fullerene units as building blocks, various 2D C$_{24}$ networks can be formed with superior stability and strength compared to the recently synthesised monolayer polymeric C$_{60}$. Monolayer C$_{24}$ harnesses the properties of both carbon crystals and fullerene molecules, such as stable chemical bonds, suitable band gaps and large surface area, facilitating photocatalytic water splitting. The electronic band gaps of C$_{24}$ are comparable to TiO$_2$, providing appropriate band edges with sufficient external potential for overall water splitting over the acidic and neutral pH range. Upon photoexcitation, strong solar absorption enabled by strongly bound bright excitons can generate carriers effectively, while the type-II band alignment between C$_{24}$ and other 2D monolayers can separate electrons and holes in individual layers simultaneously. Additionally, the number of surface active sites of C$_{24}$ monolayers are three times more than that of their C$_{60}$ counterparts in a much wider pH range, providing spontaneous reaction pathways for hydrogen evolution reaction. Our work provides insights into materials design using tunable building blocks of fullerene units with tailored functions for energy generation, conversion and storage.

cond-mat.mtrl-sci↗

arXiv2024

FedDTPT: Federated Discrete and Transferable Prompt Tuning for Black-Box Large Language Models

In recent years, large language models (LLMs) have significantly advanced the field of natural language processing (NLP). By fine-tuning LLMs with data from specific scenarios, these foundation models can better adapt to various downstream tasks. However, the fine-tuning process poses privacy leakage risks, particularly in centralized data processing scenarios. To address user privacy concerns, federated learning (FL) has been introduced to mitigate the risks associated with centralized data collection from multiple sources. Nevertheless, the privacy of LLMs themselves is equally critical, as potential malicious attacks challenge their security, an issue that has received limited attention in current research. Consequently, establishing a trusted multi-party model fine-tuning environment is essential. Additionally, the local deployment of large LLMs incurs significant storage costs and high computational demands. To address these challenges, we propose for the first time a federated discrete and transferable prompt tuning, namely FedDTPT, for black-box large language models. In the client optimization phase, we adopt a token-level discrete prompt optimization method that leverages a feedback loop based on prediction accuracy to drive gradient-free prompt optimization through the MLM API. For server optimization, we employ an attention mechanism based on semantic similarity to filter all local prompt tokens, along with an embedding distance elbow detection and DBSCAN clustering strategy to enhance the filtering process. Experimental results demonstrate that, compared to state-of-the-art methods, our approach achieves higher accuracy, reduced communication overhead, and robustness to non-iid data in a black-box setting. Moreover, the optimized prompts are transferable.

cs.CL↗

arXiv2024

Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment

As the volume of image data grows, data-oriented cloud computing in Internet of Video Things (IoVT) systems encounters latency issues. Task-oriented edge computing addresses this by shifting data analysis to the edge. However, limited computational power of edge devices poses challenges for executing visual tasks. Existing methods struggle to balance high model performance with low resource consumption; lightweight neural networks often underperform, while device-specific models designed by Neural Architecture Search (NAS) fail to adapt to heterogeneous devices. For these issues, we propose a novel co-design framework to optimize neural network architecture and deployment strategies during inference for high-throughput. Specifically, it implements a dynamic model structure based on re-parameterization, coupled with a Roofline-based model partitioning strategy to enhance the computational performance of edge devices. We also employ a multi-objective co-optimization approach to balance throughput and accuracy. Additionally, we derive mathematical consistency and convergence of partitioned models. Experimental results demonstrate significant improvements in throughput (12.05\% on MNIST, 18.83\% on ImageNet) and superior classification accuracy compared to baseline algorithms. Our method consistently achieves stable performance across different devices, underscoring its adaptability. Simulated experiments further confirm its efficacy in high-accuracy, real-time detection for small objects in IoVT systems.

cs.CV↗