arXiv subjects

Jian Cao

Publications and source records attributed to Jian Cao.

At least 55 records · Page 3Linked to original sources

arXiv2025

EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO

Industrial anomaly detection (IAD) plays a crucial role in maintaining the safety and reliability of manufacturing systems. While multimodal large language models (MLLMs) show strong vision-language reasoning abilities, their effectiveness in IAD remains limited without domain-specific adaptation. In this work, we propose EMIT, a unified framework that enhances MLLMs for IAD via difficulty-aware group relative policy optimization (GRPO). EMIT constructs a multi-task IAD dataset and utilizes GPT-generated object text descriptions to compensate for missing defective images. For few-shot anomaly detection, it integrates a soft prompt and heatmap-guided contrastive embeddings derived from patch-level comparisons. To better handle difficult data samples, i.e., cases where the MLLM struggles to generate correct answers, we propose a difficulty-aware GRPO that extends the original GRPO by incorporating a response resampling strategy to ensure the inclusion of correct answers in the sampled responses, as well as an advantage reweighting mechanism to strengthen learning from such difficult data samples. Extensive experiments on the MMAD benchmark demonstrate that EMIT significantly enhances the IAD performance of MLLMs, achieving an average improvement of 7.77\% over the base model (InternVL3-8B) across seven tasks.

cs.CV↗

arXiv2025

Single-layer silicon metalens for broadband achromatic focusing and wide field of view

Achieving simultaneous broadband achromatic focusing and a wide field of view remains a significant challenge for metalenses. In this work, we begin with a quadratic phase profile, enabling full field-of-view designs, and apply dispersion engineering to minimize variations of the focal length across wavelengths, thereby substantially reducing both longitudinal and transverse chromatic aberrations. This is accomplished using only the propagation phase in waveguide-like rectangular meta-atoms, without relying on geometric phase contributions. The fabricated singlet metalens experimentally demonstrates a field of view of 86{\textdegree}, along with a tenfold reduction in focal length variations with wavelength compared to a conventional quadratic metalens, achieving a measured relative shift as low as 1.3% across the 1.5 $μ$m - 1.6 $μ$m range (limited by our experimental setup). This improvement also leads to a twofold increase in focusing efficiency relative to the reference metalens. These experimental results validate the effectiveness of our design strategy in simultaneously enhancing the operational bandwidth and field of view of metalenses. The demonstrated performance can directly benefit beam steering applications in the near-infrared wavelength range and provides a path toward achromatic, wide field-of-view metalenses in the visible range for imaging systems

physics.optics↗

arXiv2025

Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy

Machine Unlearning (MU) technology facilitates the removal of the influence of specific data instances from trained models on request. Despite rapid advancements in MU technology, its vulnerabilities are still underexplored, posing potential risks of privacy breaches through leaks of ostensibly unlearned information. Current limited research on MU attacks requires access to original models containing privacy data, which violates the critical privacy-preserving objective of MU. To address this gap, we initiate an innovative study on recalling the forgotten class memberships from unlearned models (ULMs) without requiring access to the original one. Specifically, we implement a Membership Recall Attack (MRA) framework with a teacher-student knowledge distillation architecture, where ULMs serve as noisy labelers to transfer knowledge to student models. Then, it is translated into a Learning with Noisy Labels (LNL) problem for inferring the correct labels of the forgetting instances. Extensive experiments on state-of-the-art MU methods with multiple real datasets demonstrate that the proposed MRA strategy exhibits high efficacy in recovering class memberships of unlearned instances. As a result, our study and evaluation have established a benchmark for future research on MU vulnerabilities.

cs.LG↗

arXiv2025

COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement

Large deep learning models have achieved significant success in various tasks. However, the performance of a model can significantly degrade if it is needed to train on datasets with noisy labels with misleading or ambiguous information. To date, there are limited investigations on how to restore performance when model degradation has been incurred by noisy label data. Inspired by the ``forgetting mechanism'' in neuroscience, which enables accelerating the relearning of correct knowledge by unlearning the wrong knowledge, we propose a robust model restoration and refinement (MRR) framework COLUR, namely Confidence-Oriented Learning, Unlearning and Relearning. Specifically, we implement COLUR with an efficient co-training architecture to unlearn the influence of label noise, and then refine model confidence on each label for relearning. Extensive experiments are conducted on four real datasets and all evaluation results show that COLUR consistently outperforms other SOTA methods after MRR.

cs.LG↗

arXiv2025

Atys: An Efficient Profiling Framework for Identifying Hotspot Functions in Large-scale Cloud Microservices

To handle the high volume of requests, large-scale services are comprised of thousands of instances deployed in clouds. These services utilize diverse programming languages and are distributed across various nodes as encapsulated containers. Given their vast scale, even minor performance enhancements can lead to significant cost reductions. In this paper, we introduce Atys1, an efficient profiling framework specifically designed to identify hotspot functions within large-scale distributed services. Atys presents four key features. First, it implements a language-agnostic adaptation mechanism for multilingual microservices. Second, a two-level aggregation method is introduced to provide a comprehensive overview of flamegraphs. Third, we propose a function selective pruning (FSP) strategy to enhance the efficiency of aggregating profiling results. Finally, we develop a frequency dynamic adjustment (FDA) scheme that dynamically modifies sampling frequency based on service status, effectively minimizing profiling cost while maintaining accuracy. Cluster-scale experiments on two benchmarks show that the FSP strategy achieves a 6.8% reduction in time with a mere 0.58% mean average percentage error (MAPE) in stack traces aggregation. Additionally, the FDA scheme ensures that the mean squared error (MSE) remains on par with that at high sampling rates, while achieving an 87.6% reduction in cost.

cs.PF↗

arXiv2025

The charmonium-like exotic hadron productions in $e^+e^-$ collisions at the BESIII energy with the PACIAE model

Inspired by the BESIII observation of exotic hadron $G$(3900) in $e^+e^-\rightarrow D\bar D$ process [PRL 133(2024)081901], we use the parton and hadron cascade model PACIAE to simulate the productions of charmonium-like exotic hadrons including $X(3872)$, $Z_{c}(3900)^0$ and $G(3900)$ in the $e^+e^-$ annihilations at $\sqrt s$=4.95 GeV. The charmonium-like candidates are recombined by Dynamically Constrained Phase-space Coalescence model using component mesons $D\bar D$ (for $G(3900)$) or $D\bar D^*/\bar DD^*$ (for $X(3872)$, $Z_{c}(3900)^0$ and $G(3900)$) in the PACIAE simulated final hadronic state. We then calculate, for the first time, the charmonium-like candidate's orbital angular momentum quantum number in its rest frame and perform the spectral classification for each of the above candidates. For $G(3900)$, as its $J^{PC}$ is $1^{--}$, it is identified as the $P$-wave $D\bar D$ or $D\bar D^*/\bar DD^*$ state. Meanwhile, for $X(3872)$ and $Z_{c}(3900)^0$, as their $J^{PC}$s are, respectively, $1^{++}$ and $1^{+-}$, they are identified as the $S$-wave $D\bar D^*/\bar DD^*$ candidates. It is observed that the yield of the $P$-wave $G(3900)$ composed of $D\bar D^*/\bar DD^*$ is significantly larger than that composed of $D\bar D$. Moreover, in the $D\bar D^*/\bar DD^*$ channel, the yield of the $P$-wave $G(3900)$ is around three times as large as the yield of the $S$-wave $Z_{c}(3900)^0$, and it is around two orders of magnitude as large as the yield of the $S$-wave $X(3872)$. Finally, significant discrepancies are observed in the transverse momentum spectra and the rapidity distributions among the $X(3872)$, $Z_{c}(3900)^0$ and $G(3900)$ states. These discrepancies are proposed as valuable criteria for identifying the different charmonium-like exotic hadrons from each other.

hep-ph↗

arXiv2025

HtFLlib: A Comprehensive Heterogeneous Federated Learning Library and Benchmark

As AI evolves, collaboration among heterogeneous models helps overcome data scarcity by enabling knowledge transfer across institutions and devices. Traditional Federated Learning (FL) only supports homogeneous models, limiting collaboration among clients with heterogeneous model architectures. To address this, Heterogeneous Federated Learning (HtFL) methods are developed to enable collaboration across diverse heterogeneous models while tackling the data heterogeneity issue at the same time. However, a comprehensive benchmark for standardized evaluation and analysis of the rapidly growing HtFL methods is lacking. Firstly, the highly varied datasets, model heterogeneity scenarios, and different method implementations become hurdles to making easy and fair comparisons among HtFL methods. Secondly, the effectiveness and robustness of HtFL methods are under-explored in various scenarios, such as the medical domain and sensor signal modality. To fill this gap, we introduce the first Heterogeneous Federated Learning Library (HtFLlib), an easy-to-use and extensible framework that integrates multiple datasets and model heterogeneity scenarios, offering a robust benchmark for research and practical applications. Specifically, HtFLlib integrates (1) 12 datasets spanning various domains, modalities, and data heterogeneity scenarios; (2) 40 model architectures, ranging from small to large, across three modalities; (3) a modularized and easy-to-extend HtFL codebase with implementations of 10 representative HtFL methods; and (4) systematic evaluations in terms of accuracy, convergence, computation costs, and communication costs. We emphasize the advantages and potential of state-of-the-art HtFL methods and hope that HtFLlib will catalyze advancing HtFL research and enable its broader applications. The code is released at https://github.com/TsingZ0/HtFLlib.

cs.LG↗

arXiv2025

PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIs

The rise of generative APIs has fueled interest in privacy-preserving synthetic data generation. While the Private Evolution (PE) algorithm generates Differential Privacy (DP) synthetic images using diffusion model APIs, it struggles with few-shot private data due to the limitations of its DP-protected similarity voting approach. In practice, the few-shot private data challenge is particularly prevalent in specialized domains like healthcare and industry. To address this challenge, we propose a novel API-assisted algorithm, Private Contrastive Evolution (PCEvolve), which iteratively mines inherent inter-class contrastive relationships in few-shot private data beyond individual data points and seamlessly integrates them into an adapted Exponential Mechanism (EM) to optimize DP's utility in an evolution loop. We conduct extensive experiments on four specialized datasets, demonstrating that PCEvolve outperforms PE and other API-assisted baselines. These results highlight the potential of leveraging API access with private data for quality evaluation, enabling the generation of high-quality DP synthetic images and paving the way for more accessible and effective privacy-preserving generative API applications. Our code is available at https://github.com/TsingZ0/PCEvolve.

cs.CR↗

arXiv2025

Adaptive Guidance for Local Training in Heterogeneous Federated Learning

Model heterogeneity poses a significant challenge in Heterogeneous Federated Learning (HtFL). In scenarios with diverse model architectures, directly aggregating model parameters is impractical, leading HtFL methods to incorporate an extra objective alongside the original local objective on each client to facilitate collaboration. However, this often results in a mismatch between the extra and local objectives. To resolve this, we propose Federated Learning-to-Guide (FedL2G), a method that adaptively learns to guide local training in a federated manner, ensuring the added objective aligns with each client's original goal. With theoretical guarantees, FedL2G utilizes only first-order derivatives w.r.t. model parameters, achieving a non-convex convergence rate of O(1/T). We conduct extensive experiments across two data heterogeneity and six model heterogeneity settings, using 14 heterogeneous model architectures (e.g., CNNs and ViTs). The results show that FedL2G significantly outperforms seven state-of-the-art methods.

cs.LG↗

arXiv2025

LKD-KGC: Domain-Specific KG Construction via LLM-driven Knowledge Dependency Parsing

Knowledge Graphs (KGs) structure real-world entities and their relationships into triples, enhancing machine reasoning for various tasks. While domain-specific KGs offer substantial benefits, their manual construction is often inefficient and requires specialized knowledge. Recent approaches for knowledge graph construction (KGC) based on large language models (LLMs), such as schema-guided KGC and reference knowledge integration, have proven efficient. However, these methods are constrained by their reliance on manually defined schema, single-document processing, and public-domain references, making them less effective for domain-specific corpora that exhibit complex knowledge dependencies and specificity, as well as limited reference knowledge. To address these challenges, we propose LKD-KGC, a novel framework for unsupervised domain-specific KG construction. LKD-KGC autonomously analyzes document repositories to infer knowledge dependencies, determines optimal processing sequences via LLM driven prioritization, and autoregressively generates entity schema by integrating hierarchical inter-document contexts. This schema guides the unsupervised extraction of entities and relationships, eliminating reliance on predefined structures or external knowledge. Extensive experiments show that compared with state-of-the-art baselines, LKD-KGC generally achieves improvements of 10% to 20% in both precision and recall rate, demonstrating its potential in constructing high-quality domain-specific KGs.

cs.CL↗

arXiv2025

Real-Time Decision-Making for Digital Twin in Additive Manufacturing with Model Predictive Control using Time-Series Deep Neural Networks

Digital Twin -- a virtual replica of a physical system enabling real-time monitoring, model updating, prediction, and decision-making -- combined with recent advances in machine learning, offers new opportunities for proactive control strategies in autonomous manufacturing. However, achieving real-time decision-making with Digital Twins requires efficient optimization driven by accurate predictions of highly nonlinear manufacturing systems. This paper presents a simultaneous multi-step Model Predictive Control (MPC) framework for real-time decision-making, using a multivariate deep neural network, named Time-Series Dense Encoder (TiDE), as the surrogate model. Unlike conventional MPC models which only provide one-step ahead prediction, TiDE is capable of predicting future states within the prediction horizon in one shot (multi-step), significantly accelerating the MPC. Using Directed Energy Deposition (DED) additive manufacturing as a case study, we demonstrate the effectiveness of the proposed MPC in achieving melt pool temperature tracking to ensure part quality, while reducing porosity defects by regulating laser power to maintain melt pool depth constraints. In this work, we first show that TiDE is capable of accurately predicting melt pool temperature and depth. Second, we demonstrate that the proposed MPC achieves precise temperature tracking while satisfying melt pool depth constraints within a targeted dilution range (10\%-30\%), reducing potential porosity defects. Compared to PID controller, the MPC results in smoother and less fluctuating laser power profiles with competitive or superior melt pool temperature control performance. This demonstrates the MPC's proactive control capabilities, leveraging time-series prediction and real-time optimization, positioning it as a powerful tool for future Digital Twin applications and real-time process optimization in manufacturing.

cs.LG↗

arXiv2025

Tensor-decomposition-based A Priori Surrogate (TAPS) modeling for ultra large-scale simulations

A data-free, predictive scientific AI model, Tensor-decomposition-based A Priori Surrogate (TAPS), is proposed for tackling ultra large-scale engineering simulations with significant speedup, memory savings, and storage gain. TAPS can effectively obtain surrogate models for high-dimensional parametric problems with equivalent zetta-scale ($10^{21}$) degrees of freedom (DoFs). TAPS achieves this by directly obtaining reduced-order models through solving governing equations with multiple independent variables such as spatial coordinates, parameters, and time. The paper first introduces an AI-enhanced finite element-type interpolation function called convolution hierarchical deep-learning neural network (C-HiDeNN) with tensor decomposition (TD). Subsequently, the generalized space-parameter-time Galerkin weak form and the corresponding matrix form are derived. Through the choice of TAPS hyperparameters, an arbitrary convergence rate can be achieved. To show the capabilities of this framework, TAPS is then used to simulate a large-scale additive manufacturing process as an example and achieves around 1,370x speedup, 14.8x memory savings, and 955x storage gain compared to the finite difference method with $3.46$ billion spatial degrees of freedom (DoFs). As a result, the TAPS framework opens a new avenue for many challenging ultra large-scale engineering problems, such as additive manufacturing and integrated circuit design, among others.

cs.CE↗

arXiv2025

PFLlib: A Beginner-Friendly and Comprehensive Personalized Federated Learning Library and Benchmark

Amid the ongoing advancements in Federated Learning (FL), a machine learning paradigm that allows collaborative learning with data privacy protection, personalized FL (pFL)has gained significant prominence as a research direction within the FL domain. Whereas traditional FL (tFL) focuses on jointly learning a global model, pFL aims to balance each client's global and personalized goals in FL settings. To foster the pFL research community, we started and built PFLlib, a comprehensive pFL library with an integrated benchmark platform. In PFLlib, we implemented 37 state-of-the-art FL algorithms (8 tFL algorithms and 29 pFL algorithms) and provided various evaluation environments with three statistically heterogeneous scenarios and 24 datasets. At present, PFLlib has gained more than 1600 stars and 300 forks on GitHub.

cs.LG↗

arXiv2024

Large Language Models for Constructing and Optimizing Machine Learning Workflows: A Survey

Building effective machine learning (ML) workflows to address complex tasks is a primary focus of the Automatic ML (AutoML) community and a critical step toward achieving artificial general intelligence (AGI). Recently, the integration of Large Language Models (LLMs) into ML workflows has shown great potential for automating and enhancing various stages of the ML pipeline. This survey provides a comprehensive and up-to-date review of recent advancements in using LLMs to construct and optimize ML workflows, focusing on key components encompassing data and feature engineering, model selection and hyperparameter optimization, and workflow evaluation. We discuss both the advantages and limitations of LLM-driven approaches, emphasizing their capacity to streamline and enhance ML workflow modeling process through language understanding, reasoning, interaction, and generation. Finally, we highlight open challenges and propose future research directions to advance the effective application of LLMs in ML workflows.

cs.LG↗

arXiv2024

Security and Privacy of Digital Twins for Advanced Manufacturing: A Survey

In Industry 4.0, the digital twin is one of the emerging technologies, offering simulation abilities to predict, refine, and interpret conditions and operations, where it is crucial to emphasize a heightened concentration on the associated security and privacy risks. To be more specific, the adoption of digital twins in the manufacturing industry relies on integrating technologies like cyber-physical systems, the Industrial Internet of Things, virtualization, and advanced manufacturing. The interactions of these technologies give rise to numerous security and privacy vulnerabilities that remain inadequately explored. Towards that end, this paper analyzes the cybersecurity threats of digital twins for advanced manufacturing in the context of data collection, data sharing, machine learning and deep learning, and system-level security and privacy. We also provide several solutions to the threats in those four categories that can help establish more trust in digital twins.

eess.SY↗

arXiv2024

Eliminating Domain Bias for Federated Learning in Representation Space

Recently, federated learning (FL) is popular for its privacy-preserving and collaborative learning abilities. However, under statistically heterogeneous scenarios, we observe that biased data domains on clients cause a representation bias phenomenon and further degenerate generic representations during local training, i.e., the representation degeneration phenomenon. To address these issues, we propose a general framework Domain Bias Eliminator (DBE) for FL. Our theoretical analysis reveals that DBE can promote bi-directional knowledge transfer between server and client, as it reduces the domain discrepancy between server and client in representation space. Besides, extensive experiments on four datasets show that DBE can greatly improve existing FL methods in both generalization and personalization abilities. The DBE-equipped FL method can outperform ten state-of-the-art personalized FL methods by a large margin. Our code is public at https://github.com/TsingZ0/DBE.

cs.LG↗

arXiv2024

Interpolating neural network: A novel unification of machine learning and interpolation theory

Artificial intelligence (AI) has revolutionized software development, shifting from task-specific codes (Software 1.0) to neural network-based approaches (Software 2.0). However, applying this transition in engineering software presents challenges, including low surrogate model accuracy, the curse of dimensionality in inverse design, and rising complexity in physical simulations. We introduce an interpolating neural network (INN), grounded in interpolation theory and tensor decomposition, to realize Engineering Software 2.0 by advancing data training, partial differential equation solving, and parameter calibration. INN offers orders of magnitude fewer trainable/solvable parameters for comparable model accuracy than traditional multi-layer perceptron (MLP) or physics-informed neural networks (PINN). Demonstrated in metal additive manufacturing, INN rapidly constructs an accurate surrogate model of Laser Powder Bed Fusion (L-PBF) heat transfer simulation, achieving sub-10-micrometer resolution for a 10 mm path in under 15 minutes on a single GPU. This makes a transformative step forward across all domains essential to engineering software.

cs.LG↗

arXiv2024

Non-extensive (3+1)-dimensional hydrodynamics for relativistic heavy-ion collisions

A non-extensive (3+1)-dimensional hydrodynamic model for multi-particle production processes, NEX-CLVisc, is developed in the framework of CLVisc where the viscous corrections are turned off. It assumes that the non-extensive effects consistently exist in the initial conditions set by the optical Glauber model, the equation of state and the hadron kinetic freeze-out procedure. The model is then applied to simulate the pseudo-rapidity ($η$) distribution, the transverse momentum ($p_{\rm T}$) spectra and the $p_{\rm T}$-differential elliptic flow ($v_2$) of charged particles in Pb-Pb collisions at $\sqrt{s_{\rm NN}}=$ 2.76 TeV and 5.02 TeV, respectively. It is found that the model can reasonably well reproduce the experimental data of the $η$ distribution and the charged-particle spectra in a $p_{\rm T}$ range up to 6-8 GeV/c. When compared with the ideal hydrodynamic model, the $p_{\rm T}$-differential $v_2$ of charged particles is suppressed in the NEX-CLVisc model, which is similar to that observed in the hydrodynamic model with a shear viscous correction. Moreover, due to the lack of the viscous corrections and the event-by-event fluctuation, the model can only describe the $p_{\rm T}$-differential $v_2$ up to 3-4 GeV/c, which is smaller than its applicable range for the particle $p_{\rm T}$ spectra.

nucl-th↗