arXiv subjects

Yu Wang

Publications and source records attributed to Yu Wang.

At least 595 records · Page 33Linked to original sources

arXiv2025

Lightweight Deep Learning Framework for Accurate Particle Flow Energy Reconstruction

Under extreme operating conditions, characterized by high particle multiplicity and heavily overlapping shower energy deposits, classical particle flow algorithms encounter pronounced limitations in resolution, efficiency, and accuracy. To address this challenge, this paper proposes and systematically evaluates a deep learning reconstruction framework: For multichannel sparse features, we design a hybrid loss function combining weighted mean squared error with structural similarity index, effectively balancing pixel-level accuracy and structural fidelity. By integrating 3D convolutions, Squeeze-and-Excitation channel attention, and Offset self-attention modules into baseline convolutional neural networks, we enhance the model's capability to capture cross-modal spatiotemporal correlations and energy-displacement nonlinearities. Validated on custom-constructed simulation data and Pythia jet datasets, the framework's 90K-parameter lightweight variant approaches the performance of 5M-parameter baselines, while the 25M-parameter 3D model achieves state-of-the-art results in both interpolation and extrapolation tasks. Comprehensive experiments quantitatively evaluate component contributions and provide performance-parameter trade-off guidelines. All core code and data processing scripts are open-sourced on a GitHub repository to facilitate community reproducibility and extension.

physics.ins-det↗

arXiv2025

The Sound of Populism: Distinct Linguistic Features Across Populist Variants

This study explores the sound of populism by integrating the classic Linguistic Inquiry and Word Count (LIWC) features, which capture the emotional and stylistic tones of language, with a fine-tuned RoBERTa model, a state-of-the-art context-aware language model trained to detect nuanced expressions of populism. This approach allows us to uncover the auditory dimensions of political rhetoric in U.S. presidential inaugural and State of the Union addresses. We examine how four key populist dimensions (i.e., left-wing, right-wing, anti-elitism, and people-centrism) manifest in the linguistic markers of speech, drawing attention to both commonalities and distinct tonal shifts across these variants. Our findings reveal that populist rhetoric consistently features a direct, assertive ``sound" that forges a connection with ``the people'' and constructs a charismatic leadership persona. However, this sound is not simply informal but strategically calibrated. Notably, right-wing populism and people-centrism exhibit a more emotionally charged discourse, resonating with themes of identity, grievance, and crisis, in contrast to the relatively restrained emotional tones of left-wing and anti-elitist expressions.

cs.CL↗

arXiv2025

Generative-Contrastive Heterogeneous Graph Neural Network

Heterogeneous Graphs (HGs) effectively model complex relationships in the real world through multi-type nodes and edges. In recent years, inspired by self-supervised learning (SSL), contrastive learning (CL)-based Heterogeneous Graphs Neural Networks (HGNNs) have shown great potential in utilizing data augmentation and contrastive discriminators for downstream tasks. However, data augmentation remains limited due to the graph data's integrity. Furthermore, the contrastive discriminators suffer from sampling bias and lack local heterogeneous information. To tackle the above limitations, we propose a novel Generative-Contrastive Heterogeneous Graph Neural Network (GC-HGNN). Specifically, we propose a heterogeneous graph generative learning method that enhances CL-based paradigm. This paradigm includes: 1) A contrastive view augmentation strategy using a masked autoencoder. 2) Position-aware and semantics-aware positive sample sampling strategy for generating hard negative samples. 3) A hierarchical contrastive learning strategy aimed at capturing local and global information. Furthermore, the hierarchical contrastive learning and sampling strategies aim to constitute an enhanced contrastive discriminator under the generative-contrastive perspective. Finally, we compare our model with seventeen baselines on eight real-world datasets. Our model outperforms the latest baselines on node classification and link prediction tasks.

cs.LG↗

arXiv2025

SimAug: Enhancing Recommendation with Pretrained Language Models for Dense and Balanced Data Augmentation

Deep Neural Networks (DNNs) are extensively used in collaborative filtering due to their impressive effectiveness. These systems depend on interaction data to learn user and item embeddings that are crucial for recommendations. However, the data often suffers from sparsity and imbalance issues: limited observations of user-item interactions can result in sub-optimal performance, and a predominance of interactions with popular items may introduce recommendation bias. To address these challenges, we employ Pretrained Language Models (PLMs) to enhance the interaction data with textual information, leading to a denser and more balanced dataset. Specifically, we propose a simple yet effective data augmentation method (SimAug) based on the textual similarity from PLMs, which can be seamlessly integrated to any systems as a lightweight, plug-and-play component in the pre-processing stage. Our experiments across nine datasets consistently demonstrate improvements in both utility and fairness when training with the augmented data generated by SimAug. The code is available at https://github.com/YuyingZhao/SimAug.

cs.IR↗

arXiv2025

Amplifying Your Social Media Presence: Personalized Influential Content Generation with LLMs

The remarkable advancements in Large Language Models (LLMs) have revolutionized the content generation process in social media, offering significant convenience in writing tasks. However, existing applications, such as sentence completion and fluency enhancement, do not fully address the complex challenges in real-world social media contexts. A prevalent goal among social media users is to increase the visibility and influence of their posts. This paper, therefore, delves into the compelling question: Can LLMs generate personalized influential content to amplify a user's presence on social media? We begin by examining prevalent techniques in content generation to assess their impact on post influence. Acknowledging the critical impact of underlying network structures in social media, which are instrumental in initiating content cascades and highly related to the influence/popularity of a post, we then inject network information into prompt for content generation to boost the post's influence. We design multiple content-centric and structure-aware prompts. The empirical experiments across LLMs validate their ability in improving the influence and draw insights on which strategies are more effective. Our code is available at https://github.com/YuyingZhao/LLM-influence-amplifier.

cs.SI↗

arXiv2025

Existence and non-existence of the CLT for a family of SDEs driven by stable process

Stochastic differential equations (SDEs) without global Lipschitz drift often demonstrate unusual phenomena. In this paper, we consider the following SDE on $\mathbb R^d$: \begin{align*} \mathrm{d} \mathbf{X}_t=\mathbf{b}(\mathbf{X}_t) \mathrm{d} t+ \mathrm{d}\mathbf{Z}_t, \quad \mathbf{X}_0=\mathbf{x} \in \mathbb{R}^d, \end{align*} where $\mathbf{Z}_t$ is the rotationally symmetric $α$-stable process with $α\in(1,2)$ and $\mathbf{b}:\mathbb{R}^d \rightarrow \mathbb{R}^d$ is a differentiable function satisfying the following condition: there exist some $θ\ge 0$, and $K_1 , K_2 , L>0$, so that $$\langle \mathbf{b}(\mathbf{x})-\mathbf{b}(\mathbf{y}), \mathbf{x}-\mathbf{y}\rangle \leqslant K_1 |\mathbf{x}-\mathbf{y}|^2, \ \ \forall \ \ |\mathbf{x}-\mathbf{y}| \leqslant L, $$ $$\langle \mathbf{b}(\mathbf{x})-\mathbf{b}(\mathbf{y}), \mathbf{x}-\mathbf{y}\rangle \leqslant -K_2 |\mathbf{x}-\mathbf{y}|^{2+θ}, \ \ \forall \ \ |\mathbf{x}-\mathbf{y}| > L.$$ Under this assumption, the SDE admits a unique invariant measure $μ$. We investigate the normal central limit theorem (CLT) of the empirical measures $$ \mathcal{E}_t^\mathbf{x}(\cdot)=\frac{1}{t} \int_0^t δ_{\mathbf{X}_s }(\cdot) \mathrm{d} s, \ \ \ \ \mathbf{X}_0=\mathbf{x} \in \mathbb{R}^d, \ \ t>0, $$ where $δ_{\mathbf{x}}(\cdot)$ is the Dirac delta measure. Our results reveal that, for the bounded measurable function $h$, $$\sqrt t \left(\mathcal{E}_t^\mathbf{x}(h)-μ(h)\right)=\frac{1}{\sqrt t} \int_0^t \left(h\left(\mathbf{X}_s^\mathbf{x}\right)-μ(h)\right) \mathrm{d} s$$ admits a normal CLT for $θ\geqslant 0$. For the Lipschitz continuous function $h$, the normal CLT does not necessarily hold when $θ=0$, but it is satisfied for $θ>1-\fracα{2}$.

math.PR↗

arXiv2025

semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage

Existing large language model (LLM) serving systems fall into two categories: 1) a unified system where prefill phase and decode phase are co-located on the same GPU, sharing the unified computational resource and storage, and 2) a disaggregated system where the two phases are disaggregated to different GPUs. The design of the disaggregated system addresses the latency interference and sophisticated scheduling issues in the unified system but leads to storage challenges including 1) replicated weights for both phases that prevent flexible deployment, 2) KV cache transfer overhead between the two phases, 3) storage imbalance that causes substantial wasted space of the GPU capacity, and 4) suboptimal resource adjustment arising from the difficulties in migrating KV cache. Such storage inefficiency delivers poor serving performance under high request rates. In this paper, we identify that the advantage of the disaggregated system lies in the disaggregated computation, i.e., partitioning the computational resource to enable the asynchronous computation of two phases. Thus, we propose a novel LLM serving system, semi-PD, characterized by disaggregated computation and unified storage. In semi-PD, we introduce a computation resource controller to achieve disaggregated computation at the streaming multi-processor (SM) level, and a unified memory manager to manage the asynchronous memory access from both phases. semi-PD has a low-overhead resource adjustment mechanism between the two phases, and a service-level objective (SLO) aware dynamic partitioning algorithm to optimize the SLO attainment. Compared to state-of-the-art systems, semi-PD maintains lower latency at higher request rates, reducing the average end-to-end latency per request by 1.27-2.58x on DeepSeek series models, and serves 1.55-1.72x more requests adhering to latency constraints on Llama series models.

cs.CL↗

arXiv2025

An Inverse Source Problem for Semilinear Stochastic Hyperbolic Equations

This paper investigates an inverse source problem for general semilinear stochastic hyperbolic equations. Motivated by the challenges arising from both randomness and nonlinearity, we develop a globally convergent iterative regularization method that combines Carleman estimate with fixed-point iteration. Our approach enables the reconstruction of the unknown source function from partial lateral Cauchy data, without requiring a good initial guess. We establish a new Carleman estimate for stochastic hyperbolic equations and prove the convergence of the proposed method in weighted spaces. Furthermore, we design an efficient numerical algorithm that avoids solving backward stochastic partial differential equations and is robust to randomness in both the model and the data. Numerical experiments are provided to demonstrate the effectiveness of the method.

math.AP↗

arXiv2025

Towards Distribution Matching between Collaborative and Language Spaces for Generative Recommendation

Generative recommendation aims to learn the underlying generative process over the entire item set to produce recommendations for users. Although it leverages non-linear probabilistic models to surpass the limited modeling capacity of linear factor models, it is often constrained by a trade-off between representation ability and tractability. With the rise of a new generation of generative methods based on pre-trained language models (LMs), incorporating LMs into general recommendation with implicit feedback has gained considerable attention. However, adapting them to generative recommendation remains challenging. The core reason lies in the mismatch between the input-output formats and semantics of generative models and LMs, making it challenging to achieve optimal alignment in the feature space. This work addresses this issue by proposing a model-agnostic generative recommendation framework called DMRec, which introduces a probabilistic meta-network to bridge the outputs of LMs with user interactions, thereby enabling an equivalent probabilistic modeling process. Subsequently, we design three cross-space distribution matching processes aimed at maximizing shared information while preserving the unique semantics of each space and filtering out irrelevant information. We apply DMRec to three different types of generative recommendation methods and conduct extensive experiments on three public datasets. The experimental results demonstrate that DMRec can effectively enhance the recommendation performance of these generative models, and it shows significant advantages over mainstream LM-enhanced recommendation methods.

cs.IR↗

arXiv2025

VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation

Speech large language models (LLMs) have emerged as a prominent research focus in speech processing. We introduce VocalNet-1B and VocalNet-8B, a series of high-performance, low-latency speech LLMs enabled by a scalable and model-agnostic training framework designed for real-time voice interaction. Central to our contribution is the first application of multi-token prediction (MTP) to speech LLMs. This approach represents a paradigm shift from standard next-token prediction (NTP), offering simultaneous improvements in generation speed and quality. Informed by analysis of MTP's effect on speech generation and experimental comparisons, we designed a straightforward and highly effective MTP implementation. Experiments demonstrate that VocalNet performs on par with mainstream Omni LLMs even with limited training data, and significantly surpasses existing open-source speech LLMs. To foster reproducibility and community advancement, all model weights, inference code, training data, and framework implementations have been made publicly available at https://github.com/SJTU-OmniAgent/VocalNet

cs.CL↗

arXiv2025

A Non-Invasive Load Monitoring Method for Edge Computing Based on MobileNetV3 and Dynamic Time Regulation

In recent years, non-intrusive load monitoring (NILM) technology has attracted much attention in the related research field by virtue of its unique advantage of utilizing single meter data to achieve accurate decomposition of device-level energy consumption. Cutting-edge methods based on machine learning and deep learning have achieved remarkable results in load decomposition accuracy by fusing time-frequency domain features. However, these methods generally suffer from high computational costs and huge memory requirements, which become the main obstacles for their deployment on resource-constrained microcontroller units (MCUs). To address these challenges, this study proposes an innovative Dynamic Time Warping (DTW) algorithm in the time-frequency domain and systematically compares and analyzes the performance of six machine learning techniques in home electricity scenarios. Through complete experimental validation on edge MCUs, this scheme successfully achieves a recognition accuracy of 95%. Meanwhile, this study deeply optimizes the frequency domain feature extraction process, which effectively reduces the running time by 55.55% and the storage overhead by about 34.6%. The algorithm performance will be further optimized in future research work. Considering that the elimination of voltage transformer design can significantly reduce the cost, the subsequent research will focus on this direction, and is committed to providing more cost-effective solutions for the practical application of NILM, and providing a solid theoretical foundation and feasible technical paths for the design of efficient NILM systems in edge computing environments.

eess.SP↗

arXiv2025

NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results

This paper reviews the NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images. This challenge received a wide range of impressive solutions, which are developed and evaluated using our collected real-world Raindrop Clarity dataset. Unlike existing deraining datasets, our Raindrop Clarity dataset is more diverse and challenging in degradation types and contents, which includes day raindrop-focused, day background-focused, night raindrop-focused, and night background-focused degradations. This dataset is divided into three subsets for competition: 14,139 images for training, 240 images for validation, and 731 images for testing. The primary objective of this challenge is to establish a new and powerful benchmark for the task of removing raindrops under varying lighting and focus conditions. There are a total of 361 participants in the competition, and 32 teams submitting valid solutions and fact sheets for the final testing phase. These submissions achieved state-of-the-art (SOTA) performance on the Raindrop Clarity dataset. The project can be found at https://lixinustc.github.io/CVPR-NTIRE2025-RainDrop-Competition.github.io/.

cs.CV↗

arXiv2025

Meta-Learning and Knowledge Discovery based Physics-Informed Neural Network for Remaining Useful Life Prediction

Predicting the remaining useful life (RUL) of rotating machinery is critical for industrial safety and maintenance, but existing methods struggle with scarce target-domain data and unclear degradation dynamics. We propose a Meta-Learning and Knowledge Discovery-based Physics-Informed Neural Network (MKDPINN) to address these challenges. The method first maps noisy sensor data to a low-dimensional hidden state space via a Hidden State Mapper (HSM). A Physics-Guided Regulator (PGR) then learns unknown nonlinear PDEs governing degradation evolution, embedding these physical constraints into the PINN framework. This integrates data-driven and physics-based approaches. The framework uses meta-learning, optimizing across source-domain meta-tasks to enable few-shot adaptation to new target tasks. Experiments on industrial data and the C-MAPSS benchmark show MKDPINN outperforms baselines in generalization and accuracy, proving its effectiveness for RUL prediction under data scarcity

cs.LG↗

arXiv2025

Sleep-time Compute: Beyond Inference Scaling at Test-time

Scaling test-time compute has emerged as a key ingredient for enabling large language models (LLMs) to solve difficult problems, but comes with high latency and inference cost. We introduce sleep-time compute, which allows models to "think" offline about contexts before queries are presented: by anticipating what queries users might ask and pre-computing useful quantities, we can significantly reduce the compute requirements at test-time. To demonstrate the efficacy of our method, we create modified versions of two reasoning tasks - Stateful GSM-Symbolic and Stateful AIME. We find that sleep-time compute can reduce the amount of test-time compute needed to achieve the same accuracy by ~ 5x on Stateful GSM-Symbolic and Stateful AIME and that by scaling sleep-time compute we can further increase accuracy by up to 13% on Stateful GSM-Symbolic and 18% on Stateful AIME. Furthermore, we introduce Multi-Query GSM-Symbolic, which extends GSM-Symbolic by including multiple related queries per context. By amortizing sleep-time compute across related queries about the same context using Multi-Query GSM-Symbolic, we can decrease the average cost per query by 2.5x. We then conduct additional analysis to understand when sleep-time compute is most effective, finding the predictability of the user query to be well correlated with the efficacy of sleep-time compute. Finally, we conduct a case-study of applying sleep-time compute to a realistic agentic SWE task.

cs.AI↗

arXiv2025

Enhancing Contrastive Learning Inspired by the Philosophy of "The Blind Men and the Elephant"

Contrastive learning is a prevalent technique in self-supervised vision representation learning, typically generating positive pairs by applying two data augmentations to the same image. Designing effective data augmentation strategies is crucial for the success of contrastive learning. Inspired by the story of the blind men and the elephant, we introduce JointCrop and JointBlur. These methods generate more challenging positive pairs by leveraging the joint distribution of the two augmentation parameters, thereby enabling contrastive learning to acquire more effective feature representations. To the best of our knowledge, this is the first effort to explicitly incorporate the joint distribution of two data augmentation parameters into contrastive learning. As a plug-and-play framework without additional computational overhead, JointCrop and JointBlur enhance the performance of SimCLR, BYOL, MoCo v1, MoCo v2, MoCo v3, SimSiam, and Dino baselines with notable improvements.

cs.CV↗

arXiv2025

VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate

Diffusion Transformer(DiT)-based generation models have achieved remarkable success in video generation. However, their inherent computational demands pose significant efficiency challenges. In this paper, we exploit the inherent temporal non-uniformity of real-world videos and observe that videos exhibit dynamic information density, with high-motion segments demanding greater detail preservation than static scenes. Inspired by this temporal non-uniformity, we propose VGDFR, a training-free approach for Diffusion-based Video Generation with Dynamic Latent Frame Rate. VGDFR adaptively adjusts the number of elements in latent space based on the motion frequency of the latent space content, using fewer tokens for low-frequency segments while preserving detail in high-frequency segments. Specifically, our key contributions are: (1) A dynamic frame rate scheduler for DiT video generation that adaptively assigns frame rates for video segments. (2) A novel latent-space frame merging method to align latent representations with their denoised counterparts before merging those redundant in low-resolution space. (3) A preference analysis of Rotary Positional Embeddings (RoPE) across DiT layers, informing a tailored RoPE strategy optimized for semantic and local information capture. Experiments show that VGDFR can achieve a speedup up to 3x for video generation with minimal quality degradation.

cs.CV↗

arXiv2025

QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models

In typical multimodal tasks, such as Visual Question Answering (VQA), adversarial attacks targeting a specific image and question can lead large vision-language models (LVLMs) to provide incorrect answers. However, it is common for a single image to be associated with multiple questions, and LVLMs may still answer other questions correctly even for an adversarial image attacked by a specific question. To address this, we introduce the query-agnostic visual attack (QAVA), which aims to create robust adversarial examples that generate incorrect responses to unspecified and unknown questions. Compared to traditional adversarial attacks focused on specific images and questions, QAVA significantly enhances the effectiveness and efficiency of attacks on images when the question is unknown, achieving performance comparable to attacks on known target questions. Our research broadens the scope of visual adversarial attacks on LVLMs in practical settings, uncovering previously overlooked vulnerabilities, particularly in the context of visual adversarial threats. The code is available at https://github.com/btzyd/qava.

cs.CV↗

arXiv2025

Generation of Relativistic Structured Spin-Polarized Lepton Beams

Relativistic structured spin-polarized (SSP) particle beams, characterized by polarization structures, are of critical importance in a wide range of applications, such as material properties investigation, imaging, and information storage. However, generation of relativistic SSP beams faces significant challenges. Here, we put forward a novel method for generating relativistic SSP lepton beams via employing a moderate-intensity terahertz (THz) wave. Building upon our foundational work on velocity-matched spin rotation in dielectric-lined waveguides [Phys. Rev. Lett. 134, 075001 (2025)], we present the first demonstration of spin-polarization mode matching - a novel mechanism that establishes a direct relation between waveguide modes and beam polarization states. This breakthrough enables precise spatial control over spin structures at relativistic energies, generating customizable spin-polarization configurations such as spider-like, azimuthal, and helical structures, etc. Such SSP beams have the potential to generate high-energy structured photon beams and open a new avenue for research on relativistic structured particle beams, especially in nuclear physics, high-energy physics, materials science and atomic physics.

physics.optics↗