arXiv subjects

Yan Wen

Publications and source records attributed to Yan Wen.

17 recordsLinked to original sources

arXiv2026

Time Distribution Principle Using Measured Traveling Waves in Power Grid

Accurate time synchronization is essential for distributed systems. Conventional methods, such as satellite-based synchronization and communication-based approaches, face challenges including signal vulnerability and dependence on communication delay symmetry. This paper proposes a novel time synchronization principle based on traveling wave (TW) measurements in power grids. By leveraging the inherent symmetry of forward and backward TW propagation, the proposed method achieves high-precision time distribution without relying on external time references. The methodology is validated through electromagnetic transient simulations on a modified IEEE 14-bus system. The results demonstrate that under normal conditions, the proposed approach achieves microsecond-level synchronization accuracy. These findings suggest that the TW-based time synchronization principle is a potential alternative to traditional methods, offering improved security and reduced dependence on communication quality.

eess.SY↗

arXiv2026

Defending against Model Extraction for GNNs with Model Reprogramming

Graph Neural Networks (GNNs) serve as the backbone for high-stakes applications in Machine-Learning-as-a-Service (MLaaS). Still, their black-box deployment exposes them to Model Extraction (ME) attacks, in which adversaries steal intellectual property by querying APIs. Existing defenses suffer from a critical ''Euclidean bias'': they transfer image-based strategies (e.g., random noise) to graphs, ignoring the complex topological dependencies between nodes, which often results in severe utility degradation. Passive methods like watermarking also fail to prevent theft in real time. To bridge this gap, we propose GraphRP (Graph Reprogramming Protection), a proactive defense framework that repurposes Model Reprogramming for security. Unlike static perturbations, GraphRP introduces a Structure-Aware Gating Mechanism driven by learnable topological prototypes. This creates a dynamic ''structural firewall'' that selectively modulates the model's decision boundary: it preserves fidelity for benign queries residing on the training manifold, while maximizing the Fisher Information along the perturbation direction for adversarial queries. Under standard assumptions (bounded loss, optimal attacker, and local second-order approximation), we prove a lower bound on the attacker's estimation error that increases with the structural sensitivity of the reprogramming noise. Extensive experiments on both hard-label and soft-label ME attacks demonstrate that GraphRP significantly degrades attack effectiveness while preserving benign utility.

cs.LG↗

arXiv2026

Evolving Beyond Snapshots: Harmonizing Structure and Sequence via Entity State Tuning for Temporal Knowledge Graph Forecasting

Temporal knowledge graph (TKG) forecasting requires predicting future facts by jointly modeling structural dependencies within each snapshot and temporal evolution across snapshots. However, most existing methods are stateless: they recompute entity representations at each timestamp from a limited query window, leading to episodic amnesia and rapid decay of long-term dependencies. To address this limitation, we propose Entity State Tuning (EST), an encoder-agnostic framework that endows TKG forecasters with persistent and continuously evolving entity states. EST maintains a global state buffer and progressively aligns structural evidence with sequential signals via a closed-loop design. Specifically, a topology-aware state perceiver first injects entity-state priors into structural encoding. Then, a unified temporal context module aggregates the state-enhanced events with a pluggable sequence backbone. Subsequently, a dual-track evolution mechanism writes the updated context back to the global entity state memory, balancing plasticity against stability. Experiments on multiple benchmarks show that EST consistently improves diverse backbones and achieves state-of-the-art performance, highlighting the importance of state persistence for long-horizon TKG forecasting.

cs.AI↗

arXiv2025

Sequential Token Merging: Revisiting Hidden States

Vision Mambas (ViMs) achieve remarkable success with sub-quadratic complexity, but their efficiency remains constrained by quadratic token scaling with image resolution. While existing methods address token redundancy, they overlook ViMs' intrinsic Limited Directional Sequential Dependence (LDSD) - a critical information flow mechanism revealed in our analysis. We further identify Mamba's selective scan enables gradual information aggregation in hidden states. Based on these insights, we propose Sequential Token Merging (STM), featuring: 1) Bidirectional nearest neighbor merging to preserve sequential dependencies through symmetric spatial aggregation, and 2) Hidden states protection to stabilize the hidden states around the class token. STM strategically leverages Mamba's layer-wise loss convergence to convert temporal forgetfulness into stability. Experiments demonstrate STM's superiority: 1.0% accuracy drop for ViM-Ti at 20% token reduction, and only 1.4% degradation for ViM-S at 40% reduction. Our method achieves state-of-the-art efficiency with minimal complexity, while providing new insights into state-space model dynamics. Codes will be released soon.

cs.CV↗

arXiv2025

Flow-Modulated Scoring for Semantic-Aware Knowledge Graph Completion

Knowledge graph completion demands effective modeling of multifaceted semantic relationships between entities. Yet, prevailing methods, which rely on static scoring functions over learned embeddings, struggling to simultaneously capture rich semantic context and the dynamic nature of relations. To overcome this limitation, we propose the Flow-Modulated Scoring (FMS) framework, conceptualizing a relation as a dynamic evolutionary process governed by its static semantic environment. FMS operates in two stages: it first learns context-aware entity embeddings via a Semantic Context Learning module, and then models a dynamic flow between them using a Conditional Flow-Matching module. This learned flow dynamically modulates a base static score for the entity pair. By unifying context-rich static representations with a conditioned dynamic flow, FMS achieves a more comprehensive understanding of relational semantics. Extensive experiments demonstrate that FMS establishes a new state of the art across both canonical knowledge graph completion tasks: relation prediction and entity prediction. On the standard relation prediction benchmark FB15k-237, FMS achieves a near-perfect MRR of 99.8\% and Hits@1 of 99.7\% using a mere 0.35M parameters, while also attaining a 99.9\% MRR on WN18RR. Its dominance extends to entity prediction, where it secures a 25.2\% relative MRR gain in the transductive setting and substantially outperforms all baselines in challenging inductive settings. By unifying a dynamic flow mechanism with rich static contexts, FMS offers a highly effective and parameter-efficient new paradigm for knowledge graph completion. Code published at: https://github.com/yuanwuyuan9/FMS.

cs.CL↗

arXiv2025

Context-Driven Knowledge Graph Completion with Semantic-Aware Relational Message Passing

Semantic context surrounding a triplet $(h, r, t)$ is crucial for Knowledge Graph Completion (KGC), providing vital cues for prediction. However, traditional node-based message passing mechanisms, when applied to knowledge graphs, often introduce noise and suffer from information dilution or over-smoothing by indiscriminately aggregating information from all neighboring edges. To address this challenge, we propose a semantic-aware relational message passing. A core innovation of this framework is the introduction of a semantic-aware Top-K neighbor selection strategy. Specifically, this strategy first evaluates the semantic relevance between a central node and its incident edges within a shared latent space, selecting only the Top-K most pertinent ones. Subsequently, information from these selected edges is effectively fused with the central node's own representation using a multi-head attention aggregator to generate a semantically focused node message. In this manner, our model not only leverages the structure and features of edges within the knowledge graph but also more accurately captures and propagates the contextual information most relevant to the specific link prediction task, thereby effectively mitigating interference from irrelevant information. Extensive experiments demonstrate that our method achieves superior performance compared to existing approaches on several established benchmarks.

cs.AI↗

arXiv2025

Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning

Model quantization reduces the bit-width of weights and activations, improving memory efficiency and inference speed in diffusion models. However, achieving 4-bit quantization remains challenging. Existing methods, primarily based on integer quantization and post-training quantization fine-tuning, struggle with inconsistent performance. Inspired by the success of floating-point (FP) quantization in large language models, we explore low-bit FP quantization for diffusion models and identify key challenges: the failure of signed FP quantization to handle asymmetric activation distributions, the insufficient consideration of temporal complexity in the denoising process during fine-tuning, and the misalignment between fine-tuning loss and quantization error. To address these challenges, we propose the mixup-sign floating-point quantization (MSFP) framework, first introducing unsigned FP quantization in model quantization, along with timestep-aware LoRA (TALoRA) and denoising-factor loss alignment (DFA), which ensure precise and stable fine-tuning. Extensive experiments show that we are the first to achieve superior performance in 4-bit FP quantization for diffusion models, outperforming existing PTQ fine-tuning methods in 4-bit INT quantization.

cs.LG↗

arXiv2025

CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems

As large language models (LLMs) evolve into autonomous agents capable of collaborative reasoning and task execution, multi-agent LLM systems have emerged as a powerful paradigm for solving complex problems. However, these systems pose new challenges for copyright protection, particularly when sensitive or copyrighted content is inadvertently recalled through inter-agent communication and reasoning. Existing protection techniques primarily focus on detecting content in final outputs, overlooking the richer, more revealing reasoning processes within the agents themselves. In this paper, we introduce CoTGuard, a novel framework for copyright protection that leverages trigger-based detection within Chain-of-Thought (CoT) reasoning. Specifically, we can activate specific CoT segments and monitor intermediate reasoning steps for unauthorized content reproduction by embedding specific trigger queries into agent prompts. This approach enables fine-grained, interpretable detection of copyright violations in collaborative agent scenarios. We evaluate CoTGuard on various benchmarks in extensive experiments and show that it effectively uncovers content leakage with minimal interference to task performance. Our findings suggest that reasoning-level monitoring offers a promising direction for safeguarding intellectual property in LLM-based agent systems.

cs.CL↗

arXiv2025

Asymmetric Conflict and Synergy in Post-training for LLM-based Multilingual Machine Translation

The emergence of Large Language Models (LLMs) has advanced the multilingual machine translation (MMT), yet the Curse of Multilinguality (CoM) remains a major challenge. Existing work in LLM-based MMT typically mitigates this issue via scaling up training and computation budget, which raises a critical question: Is scaling up the training and computation budget truly necessary for high-quality MMT, or can a deeper understanding of CoM provide a more efficient solution? To explore this problem, we analyze the linguistic conflicts and synergy, the underlying mechanism of CoM during post-training phase. We identify an asymmetric phenomenon in linguistic conflicts and synergy: the dominance of conflicts and synergy varies in different translation directions, leading to sub-optimal adaptation in existing post-training methods. We further find that a significant bottleneck in MMT appears to lie in post-training rather than multilingual pre-training, suggesting the need for more effective adaptation strategies. Building on these new insights, we propose a direction-aware training approach, combined with group-wise model merging, to address asymmetry in linguistic conflicts and synergy explicitly. Leveraging this strategy, our method fine-tunes X-ALMA-13B-Pretrain-trained only with multilingual pre-training-achieving comparable performance to XALMA-13B (only SFT) while using only 20B pretraining tokens and 17B parameters-5.5x fewer pretraining-tokens and 1.7x fewer model size-with just 0.85 COMET drop on Flores-200 testsets of 50 languages.

cs.CL↗

arXiv2025

Multi-Level Decoupled Relational Distillation for Heterogeneous Architectures

Heterogeneous distillation is an effective way to transfer knowledge from cross-architecture teacher models to student models. However, existing heterogeneous distillation methods do not take full advantage of the dark knowledge hidden in the teacher's output, limiting their performance.To this end, we propose a novel framework named Multi-Level Decoupled Relational Knowledge Distillation (MLDR-KD) to unleash the potential of relational distillation in heterogeneous distillation. Concretely, we first introduce Decoupled Finegrained Relation Alignment (DFRA) in both logit and feature levels to balance the trade-off between distilled dark knowledge and the confidence in the correct category of the heterogeneous teacher model. Then, Multi-Scale Dynamic Fusion (MSDF) module is applied to dynamically fuse the projected logits of multiscale features at different stages in student model, further improving performance of our method in feature level. We verify our method on four architectures (CNNs, Transformers, MLPs and Mambas), two datasets (CIFAR-100 and Tiny-ImageNet). Compared with the best available method, our MLDR-KD improves student model performance with gains of up to 4.86% on CIFAR-100 and 2.78% on Tiny-ImageNet datasets respectively, showing robustness and generality in heterogeneous distillation. Code will be released soon.

cs.CV↗

arXiv2023

Efficient and Joint Hyperparameter and Architecture Search for Collaborative Filtering

Automated Machine Learning (AutoML) techniques have recently been introduced to design Collaborative Filtering (CF) models in a data-specific manner. However, existing works either search architectures or hyperparameters while ignoring the fact they are intrinsically related and should be considered together. This motivates us to consider a joint hyperparameter and architecture search method to design CF models. However, this is not easy because of the large search space and high evaluation cost. To solve these challenges, we reduce the space by screening out usefulness yperparameter choices through a comprehensive understanding of individual hyperparameters. Next, we propose a two-stage search algorithm to find proper configurations from the reduced space. In the first stage, we leverage knowledge from subsampled datasets to reduce evaluation costs; in the second stage, we efficiently fine-tune top candidate models on the whole dataset. Extensive experiments on real-world datasets show better performance can be achieved compared with both hand-designed and previous searched models. Besides, ablation and case studies demonstrate the effectiveness of our search framework.

cs.IR↗

arXiv2023

A marker-less human motion analysis system for motion-based biomarker discovery in knee disorders

In recent years the NHS has been having increased difficulty seeing all low-risk patients, this includes but not limited to suspected osteoarthritis (OA) patients. To help address the increased waiting lists and shortages of staff, we propose a novel method of automated biomarker identification for diagnosis of knee disorders and the monitoring of treatment progression. The proposed method allows for the measurement and analysis of biomechanics and analyse their clinical significance, in both a cheap and sensitive alternative to the currently available commercial alternatives. These methods and results validate the capabilities of standard RGB cameras in clinical environments to capture motion and show that when compared to alternatives such as depth cameras there is a comparable accuracy in the clinical environment. Biomarker identification using Principal Component Analysis (PCA) allows the reduction of the dimensionality to produce the most representative features from motion data, these new biomarkers can then be used to assess the success of treatment and track the progress of rehabilitation. This was validated by applying these techniques on a case study utilising the exploratory use of local anaesthetic applied on knee pain, this allows these new representative biomarkers to be validated as statistically significant (p-value < 0.05).

cs.CV↗

arXiv2022

Activity-assisted barrier-crossing of self-propelled colloids over parallel microgrooves

We report a systematic study of the dynamics of self-propelled particles (SPPs) over a one-dimensional periodic potential landscape, which is fabricated on a microgroove-patterned polydimethylsiloxane (PDMS) substrate. From the measured non-equilibrium probability density function of the SPPs, we find that the escape dynamics of the slow-rotating SPPs across the potential landscape can be described by an effective potential, once the self-propulsion force is included into the potential under the fixed angle approximation. This work demonstrates that the parallel microgrooves provide a versatile platform for a quantitative understanding of the interplay among the self-propulsion force, spatial confinement by the potential landscape, and thermal noise, as well as its effects on activity-assisted escape dynamics and transport of the SPPs.

cond-mat.soft↗

arXiv2022

Rethinking the transfer learning for FCN based polyp segmentation in colonoscopy

Besides the complex nature of colonoscopy frames with intrinsic frame formation artefacts such as light reflections and the diversity of polyp types/shapes, the publicly available polyp segmentation training datasets are limited, small and imbalanced. In this case, the automated polyp segmentation using a deep neural network remains an open challenge due to the overfitting of training on small datasets. We proposed a simple yet effective polyp segmentation pipeline that couples the segmentation (FCN) and classification (CNN) tasks. We find the effectiveness of interactive weight transfer between dense and coarse vision tasks that mitigates the overfitting in learning. And It motivates us to design a new training scheme within our segmentation pipeline. Our method is evaluated on CVC-EndoSceneStill and Kvasir-SEG datasets. It achieves 4.34% and 5.70% Polyp-IoU improvements compared to the state-of-the-art methods on the EndoSceneStill and Kvasir-SEG datasets, respectively.

cs.CV↗

arXiv2018

Giant Planar Hall Effect in the Dirac Semimetal ZrTe5

Recently, giant planar Hall effect originating from chiral anomaly has been predicted in nonmagnetic Dirac/Weyl semimetals. ZrTe5 is considered to be an intriguing Dirac semimetal at the boundary of weak topological insulators and strong topological insulators, though this claim still remains controversial. Here, we report the observation in ZrTe5 of the giant planar Hall resistivity that shows two different magnetic-field dependences as predicted by theory and a maximum at the Lifshitz transition temperature. We found that the giant planar Hall resistivity fades out with decreasing the thickness of ZrTe5 nanoplates, which may be ascribed to the vanishing of the 3D nature of the samples. In addition, we have observed a nontrivial Berry phase, chiral-anomaly-induced negative longitudinal magnetoresistance, and a giant in-plane anisotropic magnetoresistance in these ZrTe5 nanoplates. All the experimental observations demonstrated coherently that ZrTe5 is a Dirac semimetal.

cond-mat.mes-hall↗

arXiv2018

Thermally assisted skyrmions creation in Pt/Co/Ta multilayer films

Néel-type magnetic skyrmions in multilayer films have attracted significant amount of attention recently for their stability at room temperature and capability of motion driven by a low-density electrical current, which can be potentially applied to spintronic devices. However, the thermal effect on the formation of the skyrmions and their behavior has rarely been studied. Here, we report a study on the creation of skyrmions in [Pt/Co/Ta]10 multilayer samples at different temperatures using an in-situ Lorentz transmission electron microscopy. By imaging the magnetization reversal process from positive (negative) saturation to negative (positive) saturation, we found that the skyrmions can be created by nucleation from ferromagnetic saturation state and by breaking the labyrinth domains under certain external fields. By tuning the external fields, a maximum density of skyrmions was reached at different temperatures. The key finding is that the creation of the skyrmions in the multilayers depends critically on the temperature and thermal history.

cond-mat.mes-hall↗

arXiv2018

Determination of chirality and density control of Néel-type skyrmions with in-plane magnetic field

Magnetic skyrmions are topologically protected nanoscale spin textures exhibiting fascinating physical behaviors. Recent observations of room temperature Néel-type skyrmions in magnetic multilayer films are an important step towards their use in ultra-low power devices. We have investigated the magnetization reversal in a [Pt/Co/Ta]11 multilayer sample under a tilted magnetic field using the in-situ Lorentz tunneling electron microscopy. On decreasing the magnetic field individual skyrmions appear that subsequently evolve into snake-like structures growing in the direction opposite to the in-plane magnetic field. We show that this unusual relation between the velocity vector and the magnetic field is dominated by the chirality of the Néel-type skyrmions. It allows one to extract the sign of the Dzyaloshinskii-Moriya constant. We also demonstrate that high concentration of skyrmions can be achieved on increasing the in-plane component of the field. Our micromagnetic simulations agree with our experimental results.

cond-mat.mes-hall↗