arXiv subjects

Meng Li

Publications and source records attributed to Meng Li.

At least 199 records · Page 11Linked to original sources

arXiv2025

Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Survey

Over recent decades, machine learning has significantly advanced network communication, enabling improved decision-making, user behavior analysis, and fault detection. Decentralized approaches, where participants exchange computation results instead of raw private data, mitigate these risks but introduce challenges related to trust and verifiability. A critical issue arises: How can one ensure the integrity and validity of computation results shared by other participants? Existing survey articles predominantly address security and privacy concerns in decentralized machine learning, whereas this survey uniquely highlights the emerging issue of verifiability. Recognizing the critical role of zero-knowledge proofs in ensuring verifiability, we present a comprehensive review of Zero-Knowledge Proof-based Verifiable Machine Learning (ZKP-VML). To clarify the research problem, we present a definition of ZKP-VML consisting of four algorithms, along with several corresponding key security properties. Besides, we provide an overview of the current research landscape by systematically organizing the research timeline and categorizing existing schemes based on their security properties. Furthermore, through an in-depth analysis of each existing scheme, we summarize their technical contributions and optimization strategies, aiming to uncover common design principles underlying ZKP-VML schemes. Building on the reviews and analysis presented, we identify current research challenges and suggest future research directions. To the best of our knowledge, this is the most comprehensive survey to date on verifiable decentralized machine learning and ZKP-VML.

cs.LG↗

arXiv2025

SCALES: Boost Binary Neural Network for Image Super-Resolution with Efficient Scalings

Deep neural networks for image super-resolution (SR) have demonstrated superior performance. However, the large memory and computation consumption hinders their deployment on resource-constrained devices. Binary neural networks (BNNs), which quantize the floating point weights and activations to 1-bit can significantly reduce the cost. Although BNNs for image classification have made great progress these days, existing BNNs for SR still suffer from a large performance gap between the FP SR networks. To this end, we observe the activation distribution in SR networks and find much larger pixel-to-pixel, channel-to-channel, layer-to-layer, and image-to-image variation in the activation distribution than image classification networks. However, existing BNNs for SR fail to capture these variations that contain rich information for image reconstruction, leading to inferior performance. To address this problem, we propose SCALES, a binarization method for SR networks that consists of the layer-wise scaling factor, the spatial re-scaling method, and the channel-wise re-scaling method, capturing the layer-wise, pixel-wise, and channel-wise variations efficiently in an input-dependent manner. We evaluate our method across different network architectures and datasets. For CNN-based SR networks, our binarization method SCALES outperforms the prior art method by 0.2dB with fewer parameters and operations. With SCALES, we achieve the first accurate binary Transformer-based SR network, improving PSNR by more than 1dB compared to the baseline method.

cs.CV↗

arXiv2025

DeepSeek-V3 Technical Report

We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2. Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free strategy for load balancing and sets a multi-token prediction training objective for stronger performance. We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages to fully harness its capabilities. Comprehensive evaluations reveal that DeepSeek-V3 outperforms other open-source models and achieves performance comparable to leading closed-source models. Despite its excellent performance, DeepSeek-V3 requires only 2.788M H800 GPU hours for its full training. In addition, its training process is remarkably stable. Throughout the entire training process, we did not experience any irrecoverable loss spikes or perform any rollbacks. The model checkpoints are available at https://github.com/deepseek-ai/DeepSeek-V3.

cs.CL↗

arXiv2025

Classification of Major Depressive Disorder Using Vertex-Wise Brain Sulcal Depth, Curvature, and Thickness with a Deep and a Shallow Learning Model

Major depressive disorder (MDD) is a complex psychiatric disorder that affects the lives of hundreds of millions of individuals around the globe. Even today, researchers debate if morphological alterations in the brain are linked to MDD, likely due to the heterogeneity of this disorder. The application of deep learning tools to neuroimaging data, capable of capturing complex non-linear patterns, has the potential to provide diagnostic and predictive biomarkers for MDD. However, previous attempts to demarcate MDD patients and healthy controls (HC) based on segmented cortical features via linear machine learning approaches have reported low accuracies. Here, we used globally representative data from the ENIGMA-MDD working group containing 7,012 participants from 30 sites (N=2,772 MDD and N=4,240 HC), which allows a comprehensive analysis with generalizable results. Based on the hypothesis that integration of vertex-wise cortical features can improve classification performance, we evaluated the classification of a DenseNet and a Support Vector Machine (SVM), with the expectation that the former would outperform the latter. We found that both classifiers exhibited close to chance performance (balanced accuracy DenseNet: 51%; SVM: 53%), when estimated on unseen sites. Slightly higher classification performance (balanced accuracy DenseNet: 58%; SVM: 55%) was found when the cross-validation folds contained subjects from all sites, indicating site effect. In conclusion, the integration of vertex-wise morphometric features and the use of the non-linear classifier did not lead to the differentiability between MDD and HC. Our results support the notion that MDD classification on this combination of such features and classifiers is unfeasible. Perhaps more sophisticated integration of multimodal information may lead to a higher performance in this diagnostic task.

q-bio.QM↗

arXiv2025

Structure-preserving parametric finite element methods for anisotropic surface diffusion flow with minimal deformation formulation

High mesh quality plays a crucial role in maintaining the stability of solutions in geometric flow problems. Duan and Li [Duan & Li, SIAM J. Sci. Comput. 46 (1) (2024) A587-A608] applied the minimal deformation (MD) formulation to propose an artificial tangential velocity determined by harmonic mapping to improve mesh quality. In this work, we extend the method to anisotropic surface diffusion flows, which, similar to isotropic curvature flow, also preserves excellent mesh quality. Furthermore, developing a numerical algorithm for the flow with MD formulation that guarantees volume conservation and energy stability remains a challenging task. We, in this paper, successfully construct several structure-preserving algorithms, including first-order and high-order temporal discretization methods. Extensive numerical experiments show that our methods effectively preserve mesh quality for anisotropic SDFs, ensuring high-order temporal accuracy, volume conservation or/and energy stability.

math.NA↗

arXiv2025

SMamba: Sparse Mamba for Event-based Object Detection

Transformer-based methods have achieved remarkable performance in event-based object detection, owing to the global modeling ability. However, they neglect the influence of non-event and noisy regions and process them uniformly, leading to high computational overhead. To mitigate computation cost, some researchers propose window attention based sparsification strategies to discard unimportant regions, which sacrifices the global modeling ability and results in suboptimal performance. To achieve better trade-off between accuracy and efficiency, we propose Sparse Mamba (SMamba), which performs adaptive sparsification to reduce computational effort while maintaining global modeling capability. Specifically, a Spatio-Temporal Continuity Assessment module is proposed to measure the information content of tokens and discard uninformative ones by leveraging the spatiotemporal distribution differences between activity and noise events. Based on the assessment results, an Information-Prioritized Local Scan strategy is designed to shorten the scan distance between high-information tokens, facilitating interactions among them in the spatial dimension. Furthermore, to extend the global interaction from 2D space to 3D representations, a Global Channel Interaction module is proposed to aggregate channel information from a global spatial perspective. Results on three datasets (Gen1, 1Mpx, and eTram) demonstrate that our model outperforms other methods in both performance and efficiency.

cs.CV↗

arXiv2025

Data and System Perspectives of Sustainable Artificial Intelligence

Sustainable AI is a subfield of AI for concerning developing and using AI systems in ways of aiming to reduce environmental impact and achieve sustainability. Sustainable AI is increasingly important given that training of and inference with AI models such as large langrage models are consuming a large amount of computing power. In this article, we discuss current issues, opportunities and example solutions for addressing these issues, and future challenges to tackle, from the data and system perspectives, related to data acquisition, data processing, and AI model training and inference.

cs.AI↗

arXiv2025

Willmore regularized sharp-interface model for strongly anisotropic solid-state dewetting with axisymmetric geometry: modeling and simulation

In this work, we consider the three-dimensional solid-state dewetting with strongly anisotropic surface energy, assuming an axisymmetric morphology of the thin film. However, when surface energy exhibits strong anisotropy, certain orientations may be missing from the equilibrium shapes, which will lead to an ill-posed governing equation. By incorporating the Willmore energy, we define a regularized total free energy and rigorously derive a sharp-interface model based on thermodynamic variations. We further develop a numerical scheme for the sharp-interface model that can preserve two important structural properties, including both the volume-conservation and energy-stability laws. We conclude by presenting a series of numerical simulations that illustrate the accuracy and structure-preserving properties. More importantly, extensive numerical simulations clearly demonstrate that our schemes can significantly enhance mesh quality, which is beneficial for long-term computations.

math.NA↗

arXiv2025

DNA: Differentiable Network-Accelerator Co-Search

Powerful yet complex deep neural networks (DNNs) have fueled a booming demand for efficient DNN solutions to bring DNN-powered intelligence into numerous applications. Jointly optimizing the networks and their accelerators are promising in providing optimal performance. However, the great potential of such solutions have yet to be unleashed due to the challenge of simultaneously exploring the vast and entangled, yet different design spaces of the networks and their accelerators. To this end, we propose DNA, a Differentiable Network-Accelerator co-search framework for automatically searching for matched networks and accelerators to maximize both the task accuracy and acceleration efficiency. Specifically, DNA integrates two enablers: (1) a generic design space for DNN accelerators that is applicable to both FPGA- and ASIC-based DNN accelerators and compatible with DNN frameworks such as PyTorch to enable algorithmic exploration for more efficient DNNs and their accelerators; and (2) a joint DNN network and accelerator co-search algorithm that enables simultaneously searching for optimal DNN structures and their accelerators' micro-architectures and mapping methods to maximize both the task accuracy and acceleration efficiency. Experiments and ablation studies based on FPGA measurements and ASIC synthesis show that the matched networks and accelerators generated by DNA consistently outperform state-of-the-art (SOTA) DNNs and DNN accelerators (e.g., 3.04x better FPS with a 5.46% higher accuracy on ImageNet), while requiring notably reduced search time (up to 1234.3x) over SOTA co-exploration methods, when evaluated over ten SOTA baselines on three datasets. All codes will be released upon acceptance.

cs.LG↗

arXiv2025

CPT: Efficient Deep Neural Network Training via Cyclic Precision

Low-precision deep neural network (DNN) training has gained tremendous attention as reducing precision is one of the most effective knobs for boosting DNNs' training time/energy efficiency. In this paper, we attempt to explore low-precision training from a new perspective as inspired by recent findings in understanding DNN training: we conjecture that DNNs' precision might have a similar effect as the learning rate during DNN training, and advocate dynamic precision along the training trajectory for further boosting the time/energy efficiency of DNN training. Specifically, we propose Cyclic Precision Training (CPT) to cyclically vary the precision between two boundary values which can be identified using a simple precision range test within the first few training epochs. Extensive simulations and ablation studies on five datasets and eleven models demonstrate that CPT's effectiveness is consistent across various models/tasks (including classification and language modeling). Furthermore, through experiments and visualization we show that CPT helps to (1) converge to a wider minima with a lower generalization error and (2) reduce training variance which we believe opens up a new design knob for simultaneously improving the optimization and efficiency of DNN training. Our codes are available at: https://github.com/RICE-EIC/CPT.

cs.LG↗

arXiv2025

DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks

Efficient deep neural network (DNN) models equipped with compact operators (e.g., depthwise convolutions) have shown great potential in reducing DNNs' theoretical complexity (e.g., the total number of weights/operations) while maintaining a decent model accuracy. However, existing efficient DNNs are still limited in fulfilling their promise in boosting real-hardware efficiency, due to their commonly adopted compact operators' low hardware utilization. In this work, we open up a new compression paradigm for developing real-hardware efficient DNNs, leading to boosted hardware efficiency while maintaining model accuracy. Interestingly, we observe that while some DNN layers' activation functions help DNNs' training optimization and achievable accuracy, they can be properly removed after training without compromising the model accuracy. Inspired by this observation, we propose a framework dubbed DepthShrinker, which develops hardware-friendly compact networks via shrinking the basic building blocks of existing efficient DNNs that feature irregular computation patterns into dense ones with much improved hardware utilization and thus real-hardware efficiency. Excitingly, our DepthShrinker framework delivers hardware-friendly compact networks that outperform both state-of-the-art efficient DNNs and compression techniques, e.g., a 3.06% higher accuracy and 1.53$\times$ throughput on Tesla V100 over SOTA channel-wise pruning method MetaPruning. Our codes are available at: https://github.com/facebookresearch/DepthShrinker.

cs.LG↗

arXiv2025

Solid-state dewetting of axisymmetric thin film on axisymmetric curved-surface substrates: modeling and simulation

In this work, we consider the solid-state dewetting of an axisymmetric thin film on a curved-surface substrate, with the assumption that the substrate morphology is also axisymmetric. Under the assumptions of axisymmetry, the surface evolution problem on a curved-surface substrate can be reduced to a curve evolution problem on a static curved substrate. Based on the thermodynamic variation of the anisotropic surface energy, we thoroughly derive a sharp-interface model that is governed by anisotropic surface diffusion, along with appropriate boundary conditions. The continuum system satisfies the laws of energy decay and volume conservation, which motivates the design of a structure-preserving numerical algorithm for simulating the mathematical model. By introducing a symmetrized surface energy matrix, we derive a novel symmetrized variational formulation. Then, by carefully discretizing the boundary terms of the variational formulation, we establish an unconditionally energy-stable parametric finite element approximation of the axisymmetric system. By applying an ingenious correction method, we further develop another structure-preserving method that can preserve both the energy stability and volume conservation properties. Finally, we present extensive numerical examples to demonstrate the convergence and structure-preserving properties of our proposed numerical scheme. Additionally, several interesting phenomena are explored, including the migration of 'small' particles on a curved-surface substrate generated by curves with positive or negative curvature, pinch-off events, and edge retraction.

math.NA↗

arXiv2024

Convergence analysis of PM-BDF2 method for quasiperiodic parabolic equations

Numerically solving parabolic equations with quasiperiodic coefficients is a significant challenge due to the potential formation of space-filling quasiperiodic structures that lack translational symmetry or decay. In this paper, we introduce a highly accurate numerical method for solving time-dependent quasiperiodic parabolic equations. We discretize the spatial variables using the projection method (PM) and the time variable with the second-order backward differentiation formula (BDF2). We provide a complexity analysis for the resulting PM-BDF2 method. Furthermore, we conduct a detailed convergence analysis, demonstrating that the proposed method exhibits spectral accuracy in space and second-order accuracy in time. Numerical results in both one and two dimensions validate these convergence results, highlighting the PM-BDF2 method as a highly efficient algorithm for addressing quasiperiodic parabolic equations.

math.NA↗

arXiv2024

A Vehicle Size-Based Dynamic Model of Artificial Driving Risk Potential Fields and Vehicle Interaction Analysis for Highway Driving

Traditional driving risk potential field model generally assumes uniform vehicle sizes, which fails to reflect the heterogeneity in real-world traffic environment. This study aims to develop an improved model by introducing the vehicle dimensions into the driving risk potential field framework. Vehicles are categorized based on size into standard-sized vehicles, medium-sized vehicles, and large-sized vehicles. And the interactions between two vehicles and the force field excited by the driving risk potential field are investigated in this paper. Our analysis of the risk field contours at various vehicle speeds and sizes reveals that larger and faster vehicles generate more intense and expansive risk fields, necessitating increased following distances. For larger vehicles, the risk field extends into adjacent lanes. Force field analysis demonstrates that vehicles traveling in adjacent lanes undergo changes in their motion state due to the influence of the force field emanating from the neighboring larger vehicles. The model effectively points out that, for adjacent lanes, the regions surrounding the tail and head of high-speed vehicles represent highly risky zones.

physics.soc-ph↗

arXiv2024

A Comprehensive Study on Dark Patterns

As digital interfaces become increasingly prevalent, certain manipulative design elements have emerged that may harm user interests, raising associated ethical concerns and bringing dark patterns into focus as a significant research topic. Manipulative design strategies are widely used in user interfaces (UI) primarily to guide user behavior in ways that favor service providers, often at the cost of the users themselves. This paper addresses three main challenges in dark pattern research: inconsistencies and incompleteness in classification, limitations of detection tools, and insufficient comprehensiveness in existing datasets. In this study, we propose a comprehensive analytical framework--the Dark Pattern Analysis Framework (DPAF). Using this framework, we developed a taxonomy comprising 68 types of dark patterns, each annotated in detail to illustrate its impact on users, potential scenarios, and real-world examples, validated through industry surveys. Furthermore, we evaluated the effectiveness of current detection tools and assessed the completeness of available datasets. Our findings indicate that, among the 8 detection tools studied, only 31 types of dark patterns are identifiable, resulting in a coverage rate of just 45.5%. Similarly, our analysis of four datasets, encompassing 5,561 instances, reveals coverage of only 30 types of dark patterns, with an overall coverage rate of 44%. Based on the available datasets, we standardized classifications and merged datasets to form a unified image dataset and a unified text dataset. These results highlight significant room for improvement in the field of dark pattern detection. This research not only deepens our understanding of dark pattern classification and detection tools but also offers valuable insights for future research and practice in this domain.

cs.HC↗

arXiv2024

SoK: Detection and Repair of Accessibility Issues

There is an increasing global emphasis on information accessibility, with numerous researchers actively developing automated tools to detect and repair accessibility issues, thereby ensuring that individuals with diverse abilities can independently access software products and services. However, current research still encounters significant challenges in two key areas: the absence of a comprehensive taxonomy of accessibility issue types, and the lack of comprehensive analysis of the capabilities of detection and repair tools, as well as the status of corresponding datasets. To address these challenges, this paper introduces the Accessibility Issue Analysis (AIA) framework. Utilizing this framework, we develop a comprehensive taxonomy that categorizes 55 types of accessibility issues across four pivotal dimensions: Perceivability, Operability, Understandability, and Robustness. This taxonomy has been rigorously recognized through a questionnaire survey (n=130). Building on this taxonomy, we conduct an in-depth analysis of existing detection and repair tools, as well as the status of corresponding datasets. In terms of tools, our findings indicate that 14 detection tools can identify 31 issue types, achieving a 56.3% rate (31/55). Meanwhile, 9 repair tools address just 13 issue types, with a 23.6% rate. In terms of datasets, those for detection tools cover 21 issue types, at a 38.1% coverage rate, whereas those for repair tools cover only 7 types, at a 12.7% coverage rate.

cs.SE↗

arXiv2024

LLM-SmartAudit: Advanced Smart Contract Vulnerability Detection

The immutable nature of blockchain technology, while revolutionary, introduces significant security challenges, particularly in smart contracts. These security issues can lead to substantial financial losses. Current tools and approaches often focus on specific types of vulnerabilities. However, a comprehensive tool capable of detecting a wide range of vulnerabilities with high accuracy is lacking. This paper introduces LLM-SmartAudit, a novel framework leveraging the advanced capabilities of Large Language Models (LLMs) to detect and analyze vulnerabilities in smart contracts. Using a multi-agent conversational approach, LLM-SmartAudit employs a collaborative system with specialized agents to enhance the audit process. To evaluate the effectiveness of LLM-SmartAudit, we compiled two distinct datasets: a labeled dataset for benchmarking against traditional tools and a real-world dataset for assessing practical applications. Experimental results indicate that our solution outperforms all traditional smart contract auditing tools, offering higher accuracy and greater efficiency. Furthermore, our framework can detect complex logic vulnerabilities that traditional tools have previously overlooked. Our findings demonstrate that leveraging LLM agents provides a highly effective method for automated smart contract auditing.

cs.CR↗

arXiv2024

PrivCirNet: Efficient Private Inference via Block Circulant Transformation

Homomorphic encryption (HE)-based deep neural network (DNN) inference protects data and model privacy but suffers from significant computation overhead. We observe transforming the DNN weights into circulant matrices converts general matrix-vector multiplications into HE-friendly 1-dimensional convolutions, drastically reducing the HE computation cost. Hence, in this paper, we propose \method, a protocol/network co-optimization framework based on block circulant transformation. At the protocol level, PrivCirNet customizes the HE encoding algorithm that is fully compatible with the block circulant transformation and reduces the computation latency in proportion to the block size. At the network level, we propose a latency-aware formulation to search for the layer-wise block size assignment based on second-order information. PrivCirNet also leverages layer fusion to further reduce the inference cost. We compare PrivCirNet with the state-of-the-art HE-based framework Bolt (IEEE S\&P 2024) and the HE-friendly pruning method SpENCNN (ICML 2023). For ResNet-18 and Vision Transformer (ViT) on Tiny ImageNet, PrivCirNet reduces latency by $5.0\times$ and $1.3\times$ with iso-accuracy over Bolt, respectively, and improves accuracy by $4.1\%$ and $12\%$ over SpENCNN, respectively. For MobileNetV2 on ImageNet, PrivCirNet achieves $1.7\times$ lower latency and $4.2\%$ better accuracy over Bolt and SpENCNN, respectively. Our code and checkpoints are available on Git Hub.

cs.CR↗