arXiv subjects

Yan Wang

Publications and source records attributed to Yan Wang.

At least 343 records · Page 19Linked to original sources

arXiv2025

Path decompositions of Eulerian graphs

Gallai's conjecture asserts that every connected graph on $n$ vertices can be decomposed into $\frac{n+1}{2}$ paths. For general graphs (possibly disconnected), it was proved that every graph on $n$ vertices can be decomposed into $\frac{2n}{3}$ paths. This is also best possible (consider the graphs consisting of vertex-disjoint triangles). Lovász showed that every $n$-vertex graph with at most one vertex of even degree can be decomposed into $\frac{n}{2}$ paths. However, Gallai's conjecture is difficult for graphs with many vertices of even degrees. Favaron and Kouider verified Gallai's conjecture for all Eulerian graphs with maximum degree at most $4$. In this paper, we show if $G$ is an Eulerian graph on $n \ge 4$ vertices and the distance between any two triangles in $G$ is at least $3$, then $G$ can be decomposed into at most $\frac{3n}{5}$ paths.

math.CO↗

arXiv2025

Fiber-integrated NV Magnetometer with Microcontroller-based Software Lock-in Technique

Fiber-integrated nitrogen-vacancy (NV) magnetometers possess high sensitivity, integration, and flexibility, and thus have been explored extensively for industrial applications. While most studies have focused on the optimization of the quantum sensing head, less attention has been paid to the frequently employed professional, expensive, and bulky electronics, which hinder their practical applications. In this article, we fabricate a fiber-integrated NV magnetometer and develop a low-cost microcontroller-based software lock-in technique. In this technique, a microcontroller coordinates efficiently a microwave source chip and an analog-to-digital converter, and a program mimicking the lock-in mechanism realizes microwave frequency-modulated optically detected magnetic resonance of NV centers. As a result, with our setup and technique, we have realized the detection of weak magnetic field with a sensitivity of 93 nT/Hz^{1/2}, which is comparable to what obtained with bulky and professional devices. Furthermore, we demonstrated real-time magnetic field detection, achieving a standard deviation of 488 nT. Our work provides a novel and cost-effective technique for electronic miniaturization, thereby potentially accelerating the industrial application of NV magnetometers.

quant-ph↗

arXiv2025

Tight bounds for judicious 3-partitions of graphs

In this paper, we show that every graph with $m$ edges admits a 3-partition such that \[ \max_{1 \leq i \leq 3} e(V_i) \leq \frac{m}{9} + \frac{1}{9}h(m) \quad \text{and} \quad e(V_1, V_2, V_3) \geq \frac{2}{3}m + \frac{1}{3}h(m), \] where $h(m) = \sqrt{2m + 1/4} - 1/2$. This answers a problem of Bollobás and Scott affirmatively. We also solve several related problems of Bollobás and Scott. All of our results are tight.

math.CO↗

arXiv2025

Energy based diffusion generator for efficient sampling of Boltzmann distributions

Sampling from Boltzmann distributions, particularly those tied to high dimensional and complex energy functions, poses a significant challenge in many fields. In this work, we present the Energy-Based Diffusion Generator (EDG), a novel approach that integrates ideas from variational autoencoders and diffusion models. EDG uses a decoder to generate Boltzmann-distributed samples from simple latent variables, and a diffusion-based encoder to estimate the Kullback-Leibler divergence to the target distribution. Notably, EDG is simulation-free, eliminating the need to solve ordinary or stochastic differential equations during training. Furthermore, by removing constraints such as bijectivity in the decoder, EDG allows for flexible network design. Through empirical evaluation, we demonstrate the superior performance of EDG across a variety of sampling tasks with complex target distributions, outperforming existing methods.

cs.LG↗

arXiv2025

Incorporating the Refractory Period into Spiking Neural Networks through Spike-Triggered Threshold Dynamics

As the third generation of neural networks, spiking neural networks (SNNs) have recently gained widespread attention for their biological plausibility, energy efficiency, and effectiveness in processing neuromorphic datasets. To better emulate biological neurons, various models such as Integrate-and-Fire (IF) and Leaky Integrate-and-Fire (LIF) have been widely adopted in SNNs. However, these neuron models overlook the refractory period, a fundamental characteristic of biological neurons. Research on excitable neurons reveal that after firing, neurons enter a refractory period during which they are temporarily unresponsive to subsequent stimuli. This mechanism is critical for preventing over-excitation and mitigating interference from aberrant signals. Therefore, we propose a simple yet effective method to incorporate the refractory period into spiking LIF neurons through spike-triggered threshold dynamics, termed RPLIF. Our method ensures that each spike accurately encodes neural information, effectively preventing neuron over-excitation under continuous inputs and interference from anomalous inputs. Incorporating the refractory period into LIF neurons is seamless and computationally efficient, enhancing robustness and efficiency while yielding better performance with negligible overhead. To the best of our knowledge, RPLIF achieves state-of-the-art performance on Cifar10-DVS(82.40%) and N-Caltech101(83.35%) with fewer timesteps and demonstrates superior performance on DVS128 Gesture(97.22%) at low latency.

cs.CV↗

arXiv2025

Monodromy representation of graphs

It is well-known that every vertex-transitive graph admits a representation as a coset graph. In this paper, we extend this construction by introducing monodromy graphs defined through double cosets. Our main result establishes that every graph is isomorphic to a monodromy graph, providing a new combinatorial framework for graph representation. Moreover, we show that every graph gives rise to an arc-transitive graph through its monodromy representation. Inspired by the monodromy representation of graphs, we denote an algebraic map $\mathcal{M}(G;Ω,ρ,τ)$ by $\mathcal{M}(G;U,ρ,τ)$ where $U$ is a stabiliser in $G$. As an application, we prove an enumeration theorem for orientable maps with a given monodromy group. We underscore a fundamental triad in algebraic graph theory: Where there is a graph, there is a group, an arc-transitive graph, and an orientable regular map--each arising canonically from the underlying combinatorial and algebraic structures.

math.CO↗

arXiv2025

OneRec Technical Report

Recommender systems have been widely used in various large-scale user-oriented platforms for many years. However, compared to the rapid developments in the AI community, recommendation systems have not achieved a breakthrough in recent years. For instance, they still rely on a multi-stage cascaded architecture rather than an end-to-end approach, leading to computational fragmentation and optimization inconsistencies, and hindering the effective application of key breakthrough technologies from the AI community in recommendation scenarios. To address these issues, we propose OneRec, which reshapes the recommendation system through an end-to-end generative approach and achieves promising results. Firstly, we have enhanced the computational FLOPs of the current recommendation model by 10 $\times$ and have identified the scaling laws for recommendations within certain boundaries. Secondly, reinforcement learning techniques, previously difficult to apply for optimizing recommendations, show significant potential in this framework. Lastly, through infrastructure optimizations, we have achieved 23.7% and 28.8% Model FLOPs Utilization (MFU) on flagship GPUs during training and inference, respectively, aligning closely with the LLM community. This architecture significantly reduces communication and storage overhead, resulting in operating expense that is only 10.6% of traditional recommendation pipelines. Deployed in Kuaishou/Kuaishou Lite APP, it handles 25% of total queries per second, enhancing overall App Stay Time by 0.54% and 1.24%, respectively. Additionally, we have observed significant increases in metrics such as 7-day Lifetime, which is a crucial indicator of recommendation experience. We also provide practical lessons and insights derived from developing, optimizing, and maintaining a production-scale recommendation system with significant real-world impact.

cs.IR↗

arXiv2025

On the number of triangles in $K_4$-free graphs

Erdős asked whether for any $n$-vertex graph $G$, the parameter $p^*(G)=\min \sum_{i\ge 1} (|V(G_i)|-1)$ is at most $\lfloor n^2/4\rfloor$, where the minimum is taken over all edge decompositions of $G$ into edge-disjoint cliques $G_i$. In a restricted case (also conjectured independently by Erdős), Győri and Keszegh [Combinatorica, 37(6) (2017), 1113--1124] proved that $p^*(G)\leq \lfloor n^2/4\rfloor$ for all $K_4$-free graphs $G$. Motivated by their proof approach, they conjectured that for any $n$-vertex $K_4$-free graph $G$ with $e$ edges, and any greedy partition $P$ of $G$ of size $r$, the number of triangles in $G$ is at least $r(e-r(n-r))$. If true, this would imply a stronger bound on $p^*(G)$. In this paper, we disprove their conjecture by constructing infinitely many counterexamples with arbitrarily large gap. We further establish a corrected tight lower bound on the number of triangles in such graphs, which would recover the conjectured bound once some small counterexamples we identify are excluded.

math.CO↗

arXiv2025

A transformer-BiGRU-based framework with data augmentation and confident learning for network intrusion detection

In today's fast-paced digital communication, the surge in network traffic data and frequency demands robust and precise network intrusion solutions. Conventional machine learning methods struggle to grapple with complex patterns within the vast network intrusion datasets, which suffer from data scarcity and class imbalance. As a result, we have integrated machine learning and deep learning techniques within the network intrusion detection system to bridge this gap. This study has developed TrailGate, a novel framework that combines machine learning and deep learning techniques. By integrating Transformer and Bidirectional Gated Recurrent Unit (BiGRU) architectures with advanced feature selection strategies and supplemented by data augmentation techniques, TrailGate can identifies common attack types and excels at detecting and mitigating emerging threats. This algorithmic fusion excels at detecting common and well-understood attack types and has the unique ability to swiftly identify and neutralize emerging threats that stem from existing paradigms.

cs.LG↗

arXiv2025

An Automated Attack Investigation Approach Leveraging Threat-Knowledge-Augmented Large Language Models

Advanced Persistent Threats (APTs) are prolonged, stealthy intrusions by skilled adversaries that compromise high-value systems to steal data or disrupt operations. Reconstructing complete attack chains from massive, heterogeneous logs is essential for effective attack investigation, yet existing methods suffer from poor platform generality, limited generalization to evolving tactics, and an inability to produce analyst-ready reports. Large Language Models (LLMs) offer strong semantic understanding and summarization capabilities, but in this domain they struggle to capture the long-range, cross-log dependencies critical for accurate reconstruction. To solve these problems, we present an LLM-empowered attack investigation framework augmented with a dynamically adaptable Kill-Chain-aligned threat knowledge base. We organizes attack-relevant behaviors into stage-aware knowledge units enriched with semantic annotations, enabling the LLM to iteratively retrieve relevant intelligence, perform causal reasoning, and progressively expand the investigation context. This process reconstructs multi-phase attack scenarios and generates coherent, human-readable investigation reports. Evaluated on 15 attack scenarios spanning single-host and multi-host environments across Windows and Linux (over 4.3M log events, 7.2 GB of data), the system achieves an average True Positive Rate (TPR) of 97.1% and an average False Positive Rate (FPR) of 0.2%, significantly outperforming the SOTA method ATLAS, which achieves an average TPR of 79.2% and an average FPR of 29.1%.

cs.CR↗

arXiv2025

Constructing a Norm for Children's Scientific Drawing: Distribution Features Based on Semantic Similarity of Large Language Models

The use of children's drawings to examining their conceptual understanding has been proven to be an effective method, but there are two major problems with previous research: 1. The content of the drawings heavily relies on the task, and the ecological validity of the conclusions is low; 2. The interpretation of drawings relies too much on the subjective feelings of the researchers. To address this issue, this study uses the Large Language Model (LLM) to identify 1420 children's scientific drawings (covering 9 scientific themes/concepts), and uses the word2vec algorithm to calculate their semantic similarity. The study explores whether there are consistent drawing representations for children on the same theme, and attempts to establish a norm for children's scientific drawings, providing a baseline reference for follow-up children's drawing research. The results show that the representation of most drawings has consistency, manifested as most semantic similarity>0.8. At the same time, it was found that the consistency of the representation is independent of the accuracy (of LLM's recognition), indicating the existence of consistency bias. In the subsequent exploration of influencing factors, we used Kendall rank correlation coefficient to investigate the effects of "sample size", "abstract degree", and "focus points" on drawings, and used word frequency statistics to explore whether children represented abstract themes/concepts by reproducing what was taught in class. It was found that accuracy (of LLM's recognition) is the most sensitive indicator, and data such as sample size and semantic similarity are related to it; The consistency between classroom experiments and teaching purpose is also an important factor, many students focus more on the experiments themselves rather than what they explain.

cs.CL↗

arXiv2025

MambaIC: State Space Models for High-Performance Learned Image Compression

A high-performance image compression algorithm is crucial for real-time information transmission across numerous fields. Despite rapid progress in image compression, computational inefficiency and poor redundancy modeling still pose significant bottlenecks, limiting practical applications. Inspired by the effectiveness of state space models (SSMs) in capturing long-range dependencies, we leverage SSMs to address computational inefficiency in existing methods and improve image compression from multiple perspectives. In this paper, we integrate the advantages of SSMs for better efficiency-performance trade-off and propose an enhanced image compression approach through refined context modeling, which we term MambaIC. Specifically, we explore context modeling to adaptively refine the representation of hidden states. Additionally, we introduce window-based local attention into channel-spatial entropy modeling to reduce potential spatial redundancy during compression, thereby increasing efficiency. Comprehensive qualitative and quantitative results validate the effectiveness and efficiency of our approach, particularly for high-resolution image compression. Code is released at https://github.com/AuroraZengfh/MambaIC.

cs.CV↗

arXiv2025

Time Profile of U.S. Neighborhoods: Datasets of Time Use at Social Infrastructure Places

Social infrastructure plays a critical role in shaping neighborhood well-being by fostering social and cultural interaction, enabling service provision, and encouraging exposure to diverse environments. Despite the growing knowledge of its spatial accessibility, time use at social infrastructure places is underexplored due to the lack of a spatially resolved national dataset. We address this gap by developing scalable Social-Infrastructure Time Use measures (STU) that capture length and depth of engagement, activity diversity, and spatial inequality, supported by first-of-their-kind datasets spanning multiple geographic scales from census tracts to metropolitan areas. Our datasets leverage anonymized and aggregated foot traffic data collected between 2019 and 2024 across 49 continental U.S. states. The data description reveals variances in STU across time, space, and differing neighborhood sociodemographic characteristics. Validation demonstrates generally robust population representation, consistent with established national survey findings while revealing more nuanced patterns. Future analyses could link STU with public health outcomes and environmental factors to inform targeted interventions aimed at enhancing population well-being and guiding social infrastructure planning and usage.

cs.SI↗

arXiv2025

Learning Marked Temporal Point Process Explanations based on Counterfactual and Factual Reasoning

Neural network-based Marked Temporal Point Process (MTPP) models have been widely adopted to model event sequences in high-stakes applications, raising concerns about the trustworthiness of outputs from these models. This study focuses on Explanation for MTPP, aiming to identify the minimal and rational explanation, that is, the minimum subset of events in history, based on which the prediction accuracy of MTPP matches that based on full history to a great extent and better than that based on the complement of the subset. This study finds that directly defining Explanation for MTPP as counterfactual explanation or factual explanation can result in irrational explanations. To address this issue, we define Explanation for MTPP as a combination of counterfactual explanation and factual explanation. This study proposes Counterfactual and Factual Explainer for MTPP (CFF) to solve Explanation for MTPP with a series of deliberately designed techniques. Experiments demonstrate the correctness and superiority of CFF over baselines regarding explanation quality and processing efficiency.

cs.LG↗

arXiv2025

Animate-X++: Universal Character Image Animation with Dynamic Backgrounds

Character image animation, which generates high-quality videos from a reference image and target pose sequence, has seen significant progress in recent years. However, most existing methods only apply to human figures, which usually do not generalize well on anthropomorphic characters commonly used in industries like gaming and entertainment. Furthermore, previous methods could only generate videos with static backgrounds, which limits the realism of the videos. For the first challenge, our in-depth analysis suggests to attribute this limitation to their insufficient modeling of motion, which is unable to comprehend the movement pattern of the driving video, thus imposing a pose sequence rigidly onto the target character. To this end, this paper proposes Animate-X++, a universal animation framework based on DiT for various character types, including anthropomorphic characters. To enhance motion representation, we introduce the Pose Indicator, which captures comprehensive motion pattern from the driving video through both implicit and explicit manner. The former leverages CLIP visual features of a driving video to extract its gist of motion, like the overall movement pattern and temporal relations among motions, while the latter strengthens the generalization of DiT by simulating possible inputs in advance that may arise during inference. For the second challenge, we introduce a multi-task training strategy that jointly trains the animation and TI2V tasks. Combined with the proposed partial parameter training, this approach achieves not only character animation but also text-driven background dynamics, making the videos more realistic. Moreover, we introduce a new Animated Anthropomorphic Benchmark (A2Bench) to evaluate the performance of Animate-X++ on universal and widely applicable animation images. Extensive experiments demonstrate the superiority and effectiveness of Animate-X++.

cs.CV↗

arXiv2025

Urban-STA4CLC: Urban Theory-Informed Spatio-Temporal Attention Model for Predicting Post-Disaster Commercial Land Use Change

Natural disasters such as hurricanes and wildfires increasingly introduce unusual disturbance on economic activities, which are especially likely to reshape commercial land use pattern given their sensitive to customer visitation. However, current modeling approaches are limited in capturing such complex interplay between human activities and commercial land use change under and following disturbances. Such interactions have been more effectively captured in current resilient urban planning theories. This study designs and calibrates a Urban Theory-Informed Spatio-Temporal Attention Model for Predicting Post-Disaster Commercial Land Use Change (Urban-STA4CLC) to predict both the yearly decline and expansion of commercial land use at census block level under cumulative impact of disasters on human activities over two years. Guided by urban theories, Urban-STA4CLC integrates both spatial and temporal attention mechanisms with three theory-informed modules. Resilience theory guides a disaster-aware temporal attention module that captures visitation dynamics. Spatial economic theory informs a multi-relational spatial attention module for inter-block representation. Diffusion theory contributes a regularization term that constrains land use transitions. The model performs significantly better than non-theoretical baselines in predicting commercial land use change under the scenario of recurrent hurricanes, with around 19% improvement in F1 score (0.8763). The effectiveness of the theory-guided modules was further validated through ablation studies. The research demonstrates that embedding urban theory into commercial land use modeling models may substantially enhance the capacity to capture its gains and losses. These advances in commercial land use modeling contribute to land use research that accounts for cumulative impacts of recurrent disasters and shifts in economic activity patterns.

cs.CY↗

arXiv2025

Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning

Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Existing pre-trained model-based CIL methods often freeze the pre-trained network and adapt to incremental tasks using additional lightweight modules such as adapters. However, incorrect module selection during inference hurts performance, and task-specific modules often overlook shared general knowledge, leading to errors on distinguishing between similar classes across tasks. To address the aforementioned challenges, we propose integrating Task-Specific and Universal Adapters (TUNA) in this paper. Specifically, we train task-specific adapters to capture the most crucial features relevant to their respective tasks and introduce an entropy-based selection mechanism to choose the most suitable adapter. Furthermore, we leverage an adapter fusion strategy to construct a universal adapter, which encodes the most discriminative features shared across tasks. We combine task-specific and universal adapter predictions to harness both specialized and general knowledge during inference. Extensive experiments on various benchmark datasets demonstrate the state-of-the-art performance of our approach. Code is available at: https://github.com/LAMDA-CL/ICCV2025-TUNA

cs.CV↗

arXiv2025

Optimal $χ$-boundness of $\ell$-holed graphs

A graph is {\em{$\ell$-holed}} if all of its induced cycles of length at least four have length exactly $\ell$. In the paper, we prove that if $G$ is an $\ell$-holed graph with odd $\ell\geq 7$, then $χ(G)\leq {\lceil {\ell \over {\ell-1}}ω(G) \rceil}$. This result is sharp.

math.CO↗