arXiv subjects

Yan Zhang

Publications and source records attributed to Yan Zhang.

At least 181 records · Page 10Linked to original sources

arXiv2025

RecIS: Sparse to Dense, A Unified Training Framework for Recommendation Models

In this paper, we propose RecIS, a unified Sparse-Dense training framework designed to achieve two primary goals: 1. Unified Framework To create a Unified sparse-dense training framework based on the PyTorch ecosystem that meets the training needs of industrial-grade recommendation models that integrated with large models. 2.System Optimization To optimize the sparse component, offering superior efficiency over the TensorFlow-based recommendation models. The dense component, meanwhile, leverages existing optimization technologies within the PyTorch ecosystem. Currently, RecIS is being used in Alibaba for numerous large-model enhanced recommendation training tasks, and some traditional sparse models have also begun training in it.

cs.IR↗

arXiv2025

Integrating Object Interaction Self-Attention and GAN-Based Debiasing for Visual Question Answering

Visual Question Answering (VQA) presents a unique challenge by requiring models to understand and reason about visual content to answer questions accurately. Existing VQA models often struggle with biases introduced by the training data, leading to over-reliance on superficial patterns and inadequate generalization to diverse questions and images. This paper presents a novel model, IOG-VQA, which integrates Object Interaction Self-Attention and GAN-Based Debiasing to enhance VQA model performance. The self-attention mechanism allows our model to capture complex interactions between objects within an image, providing a more comprehensive understanding of the visual context. Meanwhile, the GAN-based debiasing framework generates unbiased data distributions, helping the model to learn more robust and generalizable features. By leveraging these two components, IOG-VQA effectively combines visual and textual information to address the inherent biases in VQA datasets. Extensive experiments on the VQA-CP v1 and VQA-CP v2 datasets demonstrate that our model shows excellent performance compared with the existing methods, particularly in handling biased and imbalanced data distributions highlighting the importance of addressing both object interactions and dataset biases in advancing VQA tasks. Our code is available at https://github.com/HubuKG/IOG-VQA.

cs.CV↗

arXiv2025

A statistical study of type II outbursts of XRPs: Brighter accreting pulsars rotate faster

X-ray pulsars (XRPs) consist of a magnetized neutron star (NS) and an optical donor star. The NS accretes matter from the donor star producing pulsed X-ray emission. In most cases the donor stars are Be stars, and accretion is episodic, that is, the NSs are generally X-ray dim, but occasionally experience outbursts. Here, we carry out a statistical study with the X-ray monitoring data, and obtain strong correlations between the spin periods of the NSs and the outburst parameters for the first time. We show that XRPs containing faster rotating NSs tend to display more violent eruptions. In addition, pulsating ultraluminous X-ray sources in nearby galaxies follow the similar relationship. We demonstrate that most of these systems are close to the spin equilibrium, and that brighter pulsars have acquired more angular momentum by accreting matter from their companion stars, resulting in faster rotating NSs.

astro-ph.HE↗

arXiv2025

PPORLD-EDNetLDCT: A Proximal Policy Optimization-Based Reinforcement Learning Framework for Adaptive Low-Dose CT Denoising

Low-dose computed tomography (LDCT) is critical for minimizing radiation exposure, but it often leads to increased noise and reduced image quality. Traditional denoising methods, such as iterative optimization or supervised learning, often fail to preserve image quality. To address these challenges, we introduce PPORLD-EDNetLDCT, a reinforcement learning-based (RL) approach with Encoder-Decoder for LDCT. Our method utilizes a dynamic RL-based approach in which an advanced posterior policy optimization (PPO) algorithm is used to optimize denoising policies in real time, based on image quality feedback, trained via a custom gym environment. The experimental results on the low dose CT image and projection dataset demonstrate that the proposed PPORLD-EDNetLDCT model outperforms traditional denoising techniques and other DL-based methods, achieving a peak signal-to-noise ratio of 41.87, a structural similarity index measure of 0.9814 and a root mean squared error of 0.00236. Moreover, in NIH-AAPM-Mayo Clinic Low Dose CT Challenge dataset our method achieved a PSNR of 41.52, SSIM of 0.9723 and RMSE of 0.0051. Furthermore, we validated the quality of denoising using a classification task in the COVID-19 LDCT dataset, where the images processed by our method improved the classification accuracy to 94%, achieving 4% higher accuracy compared to denoising without RL-based denoising.

cs.CV↗

arXiv2025

Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving

Mixture-of-Experts (MoE) models challenge serving infrastructures with dynamic, sparse expert utilization, causing instability on conventional systems designed for dense architectures. We propose EaaS, a novel serving system to enable efficient, scalable, and robust MoE deployment. Our system disaggregates MoE modules into independent, stateless services. This design enables fine-grained resource scaling and provides inherent fault tolerance by decoupling compute units. The architecture is powered by a high-performance, CPU-free peer-to-peer communication library that ensures minimal overhead and high throughput. Experiments confirm EaaS's scalability and efficiency, achieving performance comparable to monolithic systems while providing robust fault tolerance and strong scalability. EaaS incurs less than a 2% throughput reduction under simulated hardware failures that would otherwise halt monolithic architectures. It further saves up to 37.5% of computing resources through dynamic fine-grained adaptation to serving traffic, demonstrating strong resilience for large-scale MoE deployment in production.

cs.DC↗

arXiv2025

Few-Shot Image Quality Assessment via Adaptation of Vision-Language Models

Image Quality Assessment (IQA) remains an unresolved challenge in computer vision due to complex distortions, diverse image content, and limited data availability. Existing Blind IQA (BIQA) methods largely rely on extensive human annotations, which are labor-intensive and costly due to the demanding nature of creating IQA datasets. To reduce this dependency, we propose the Gradient-Regulated Meta-Prompt IQA Framework (GRMP-IQA), designed to efficiently adapt the visual-language pre-trained model, CLIP, to IQA tasks, achieving high accuracy even with limited data. GRMP-IQA consists of two core modules: (i) Meta-Prompt Pre-training Module and (ii) Quality-Aware Gradient Regularization. The Meta Prompt Pre-training Module leverages a meta-learning paradigm to pre-train soft prompts with shared meta-knowledge across different distortions, enabling rapid adaptation to various IQA tasks. On the other hand, the Quality-Aware Gradient Regularization is designed to adjust the update gradients during fine-tuning, focusing the model's attention on quality-relevant features and preventing overfitting to semantic information. Extensive experiments on standard BIQA datasets demonstrate the superior performance to the state-of-the-art BIQA methods under limited data setting. Notably, utilizing just 20% of the training data, GRMP-IQA is competitive with most existing fully supervised BIQA approaches.

cs.CV↗

arXiv2025

ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge

We introduce ESGenius, a comprehensive benchmark for evaluating and enhancing the proficiency of Large Language Models (LLMs) in Environmental, Social, and Governance (ESG) and sustainability-focused question answering. ESGenius comprises two key components: (i) ESGenius-QA, a collection of 1,136 Multiple-Choice Questions (MCQs) generated by LLMs and rigorously validated by domain experts, covering a broad range of ESG pillars and sustainability topics. Each question is systematically linked to its corresponding source text, enabling transparent evaluation and supporting Retrieval-Augmented Generation (RAG) methods; and (ii) ESGenius-Corpus, a meticulously curated repository of 231 foundational frameworks, standards, reports, and recommendation documents from 7 authoritative sources. Moreover, to fully assess the capabilities and adaptation potential of LLMs, we implement a rigorous two-stage evaluation protocol -- Zero-Shot and RAG. Extensive experiments across 50 LLMs (0.5B to 671B) demonstrate that state-of-the-art models achieve only moderate performance in zero-shot settings, with accuracies around 55--70%, highlighting a significant knowledge gap for LLMs in this specialized, interdisciplinary domain. However, models employing RAG demonstrate significant performance improvements, particularly for smaller models. For example, DeepSeek-R1-Distill-Qwen-14B improves from 63.82% (zero-shot) to 80.46% with RAG. These results demonstrate the necessity of grounding responses in authoritative sources for enhanced ESG understanding. To the best of our knowledge, ESGenius is the first comprehensive QA benchmark designed to rigorously evaluate LLMs on ESG and sustainability knowledge, providing a critical tool to advance trustworthy AI in this vital domain.

cs.CL↗

arXiv2025

Grid-Agent: An LLM-Powered Multi-Agent System for Power Grid Control

Modern power grids face unprecedented complexity from Distributed Energy Resources (DERs), Electric Vehicles (EVs), and extreme weather, while also being increasingly exposed to cyberattacks that can trigger grid violations. This paper introduces Grid-Agent, an autonomous AI-driven framework that leverages Large Language Models (LLMs) within a multi-agent system to detect and remediate violations. Grid-Agent integrates semantic reasoning with numerical precision through modular agents: a planning agent generates coordinated action sequences using power flow solvers, while a validation agent ensures stability and safety through sandboxed execution with rollback mechanisms. To enhance scalability, the framework employs an adaptive multi-scale network representation that dynamically adjusts encoding schemes based on system size and complexity. Violation resolution is achieved through optimizing switch configurations, battery deployment, and load curtailment. Our experiments on IEEE and CIGRE benchmark networks, including the IEEE 69-bus, CIGRE MV, IEEE 30-bus test systems, demonstrate superior mitigation performance, highlighting Grid-Agent's suitability for modern smart grids requiring rapid, adaptive response.

cs.MA↗

arXiv2025

Cross3DReg: Towards a Large-scale Real-world Cross-source Point Cloud Registration Benchmark

Cross-source point cloud registration, which aims to align point cloud data from different sensors, is a fundamental task in 3D vision. However, compared to the same-source point cloud registration, cross-source registration faces two core challenges: the lack of publicly available large-scale real-world datasets for training the deep registration models, and the inherent differences in point clouds captured by multiple sensors. The diverse patterns induced by the sensors pose great challenges in robust and accurate point cloud feature extraction and matching, which negatively influence the registration accuracy. To advance research in this field, we construct Cross3DReg, the currently largest and real-world multi-modal cross-source point cloud registration dataset, which is collected by a rotating mechanical lidar and a hybrid semi-solid-state lidar, respectively. Moreover, we design an overlap-based cross-source registration framework, which utilizes unaligned images to predict the overlapping region between source and target point clouds, effectively filtering out redundant points in the irrelevant regions and significantly mitigating the interference caused by noise in non-overlapping areas. Then, a visual-geometric attention guided matching module is proposed to enhance the consistency of cross-source point cloud features by fusing image and geometric information to establish reliable correspondences and ultimately achieve accurate and robust registration. Extensive experiments show that our method achieves state-of-the-art registration performance. Our framework reduces the relative rotation error (RRE) and relative translation error (RTE) by $63.2\%$ and $40.2\%$, respectively, and improves the registration recall (RR) by $5.4\%$, which validates its effectiveness in achieving accurate cross-source registration.

cs.CV↗

arXiv2025

On a surprising behavior of the likelihood ratio test in non-parametric mixture models

We study the likelihood ratio test in general mixture models where the base density is parametric, the null is a known fixed mixing distribution, and the alternative is a general mixing distribution supported on a bounded parameter space. For Gaussian location mixtures and Poisson mixtures, we show a surprising result: the non-parametric likelihood ratio test statistic converges to a tight limit if and only if the null distribution is a finite mixture, and diverges to infinity otherwise. We further demonstrate that the likelihood ratio test diverges for a fairly general class of distributions when the null mixing distribution is not finitely discrete.

math.ST↗

arXiv2025

Know What, Know Why: Semantic Hazard Communication for Intelligent V2X Systems

In current vehicle-to-everything (V2X) communication systems, roadside units (RSUs) broadcast brief warning messages that alert nearby vehicles to avoid potential hazards. However, these messages lack contextual information on why a warning is issued, leading to excessive caution or inefficient driving behaviors. To avoid such a situation, we propose a semantic-enhanced and explainable V2X (SEE-V2X) system. In the proposed system, RSUs equipped with smart cameras detect obstructions and transmit context-aware messages to vehicles. By understanding both what the hazard is and why it occurs, drivers can make more intelligent decisions based on their specific driving situation. Furthermore, through a real-field demonstration, we show the new "see-through" feature in the proposed system, which enables drivers to visualize hidden pedestrians behind obstacles. We also perform simulations to compare traditional V2X with SEE-V2X under different traffic conditions. The results show that SEE-V2X significantly improves traffic efficiency and reduces unnecessary deceleration.

eess.SP↗

arXiv2025

Bi-SCORE for Weighted Bipartite Networks with Application in Knowledge Source Discovery

Community detection in citation networks offers a powerful approach to understanding knowledge flow and identifying core research areas within academic disciplines. This study focuses on knowledge source discovery in statistics by analyzing a weighted bipartite journal citation network constructed from 16,119 articles published in eight core journals from 2001 to 2023. To capture the inherent asymmetry of citation behavior, we explicitly preserve the bipartite structure of the network, distinguishing between citing and cited journals. For this task, we propose Bi-SCORE (Bipartite Spectral Clustering on Ratios-of-Eigenvectors), a computationally efficient and initialization-free spectral method designed for community detection in weighted bipartite networks with degree heterogeneity. We establish rigorous theoretical guarantees for the performance of Bi-SCORE under the weighted bipartite degree-corrected stochastic block model. Furthermore, simulation studies demonstrate its robustness across varying levels of sparsity and degree heterogeneity, where it outperforms existing methods. When applied to the real-world citation network, Bi-SCORE uncovers a six-community structure corresponding to key research areas in statistics, including applied statistics, methodology, theory, computation, and econometrics. These findings provide valuable insights into the intricate citation patterns and knowledge flow among statistical journals.

stat.ME↗

arXiv2025

Unraveling the Redox Mechanisms Underlying FLASH Radiotherapy: Critical Dose Thresholds and NRF2-Driven Tissue Sparing

FLASH radiotherapy (FLASH-RT) achieves tumor control comparable to conventional dose-rate irradiation (CONV-RT) while significantly reducing radiation damage to normal tissues. However, the physical conditions triggering the FLASH sparing effect remain unclear, and mechanisms related to oxidative stress and redox regulation are poorly understood. This study utilizes a murine acute intestinal toxicity model to investigate how beam parameters influence the FLASH sparing effect and tumor control using innovative FLASH-RT and CONV-RT combined irradiation. Results demonstrate for the first time that a substantially reduced FLASH dose can still elicit sparing effect, provided a total dose threshold is met. Kinetic simulation and experimental validation demonstrate that FLASH-RT enhances peroxyl radical recombination, reducing reactive oxygen species (ROS) and malondialdehyde levels. Antioxidant interventions further confirm the essential role of free radicals. RNA sequencing and molecular analyses reveal that FLASH-RT activates the nuclear factor E2-related factor 2 (NRF2) antioxidant pathway while suppressing extracellular signal-regulated kinases (ERK) signaling, thereby enhancing cellular redox defenses, reducing apoptosis, and mitigating ROS-mediated tissue injury. These findings highlight the feasibility of optimizing the FLASH-RT therapeutic window through redox modulation and provide a foundation for developing free radical-targeted strategies to improve its therapeutic efficacy.

physics.med-ph↗

arXiv2025

Knowing or Guessing? Robust Medical Visual Question Answering via Joint Consistency and Contrastive Learning

In high-stakes medical applications, consistent answering across diverse question phrasings is essential for reliable diagnosis. However, we reveal that current Medical Vision-Language Models (Med-VLMs) exhibit concerning fragility in Medical Visual Question Answering, as their answers fluctuate significantly when faced with semantically equivalent rephrasings of medical questions. We attribute this to two limitations: (1) insufficient alignment of medical concepts, leading to divergent reasoning patterns, and (2) hidden biases in training data that prioritize syntactic shortcuts over semantic understanding. To address these challenges, we construct RoMed, a dataset built upon original VQA datasets containing 144k questions with variations spanning word-level, sentence-level, and semantic-level perturbations. When evaluating state-of-the-art (SOTA) models like LLaVA-Med on RoMed, we observe alarming performance drops (e.g., a 40\% decline in Recall) compared to original VQA benchmarks, exposing critical robustness gaps. To bridge this gap, we propose Consistency and Contrastive Learning (CCL), which integrates two key components: (1) knowledge-anchored consistency learning, aligning Med-VLMs with medical knowledge rather than shallow feature patterns, and (2) bias-aware contrastive learning, mitigating data-specific priors through discriminative representation refinement. CCL achieves SOTA performance on three popular VQA benchmarks and notably improves answer consistency by 50\% on the challenging RoMed test set, demonstrating significantly enhanced robustness. Code will be released.

cs.CL↗

arXiv2025

SCOUT: Semi-supervised Camouflaged Object Detection by Utilizing Text and Adaptive Data Selection

The difficulty of pixel-level annotation has significantly hindered the development of the Camouflaged Object Detection (COD) field. To save on annotation costs, previous works leverage the semi-supervised COD framework that relies on a small number of labeled data and a large volume of unlabeled data. We argue that there is still significant room for improvement in the effective utilization of unlabeled data. To this end, we introduce a Semi-supervised Camouflaged Object Detection by Utilizing Text and Adaptive Data Selection (SCOUT). It includes an Adaptive Data Augment and Selection (ADAS) module and a Text Fusion Module (TFM). The ADSA module selects valuable data for annotation through an adversarial augment and sampling strategy. The TFM module further leverages the selected valuable data by combining camouflage-related knowledge and text-visual interaction. To adapt to this work, we build a new dataset, namely RefTextCOD. Extensive experiments show that the proposed method surpasses previous semi-supervised methods in the COD field and achieves state-of-the-art performance. Our code will be released at https://github.com/Heartfirey/SCOUT.

cs.CV↗

arXiv2025

Gather and Trace: Rethinking Video TextVQA from an Instance-oriented Perspective

Video text-based visual question answering (Video TextVQA) aims to answer questions by explicitly reading and reasoning about the text involved in a video. Most works in this field follow a frame-level framework which suffers from redundant text entities and implicit relation modeling, resulting in limitations in both accuracy and efficiency. In this paper, we rethink the Video TextVQA task from an instance-oriented perspective and propose a novel model termed GAT (Gather and Trace). First, to obtain accurate reading result for each video text instance, a context-aggregated instance gathering module is designed to integrate the visual appearance, layout characteristics, and textual contents of the related entities into a unified textual representation. Then, to capture dynamic evolution of text in the video flow, an instance-focused trajectory tracing module is utilized to establish spatio-temporal relationships between instances and infer the final answer. Extensive experiments on several public Video TextVQA datasets validate the effectiveness and generalization of our framework. GAT outperforms existing Video TextVQA methods, video-language pretraining methods, and video large language models in both accuracy and inference speed. Notably, GAT surpasses the previous state-of-the-art Video TextVQA methods by 3.86\% in accuracy and achieves ten times of faster inference speed than video large language models. The source code is available at https://github.com/zhangyan-ucas/GAT.

cs.CV↗

arXiv2025

PRIMAL: Physically Reactive and Interactive Motor Model for Avatar Learning

We formulate the motor system of an interactive avatar as a generative motion model that can drive the body to move through 3D space in a perpetual, realistic, controllable, and responsive manner. Although human motion generation has been extensively studied, many existing methods lack the responsiveness and realism of real human movements. Inspired by recent advances in foundation models, we propose PRIMAL, which is learned with a two-stage paradigm. In the pretraining stage, the model learns body movements from a large number of sub-second motion segments, providing a generative foundation from which more complex motions are built. This training is fully unsupervised without annotations. Given a single-frame initial state during inference, the pretrained model not only generates unbounded, realistic, and controllable motion, but also enables the avatar to be responsive to induced impulses in real time. In the adaptation phase, we employ a novel ControlNet-like adaptor to fine-tune the base model efficiently, adapting it to new tasks such as few-shot personalized action generation and spatial target reaching. Evaluations show that our proposed method outperforms state-of-the-art baselines. We leverage the model to create a real-time character animation system in Unreal Engine that feels highly responsive and natural. Code, models, and more results are available at: https://yz-cnsdqz.github.io/eigenmotion/PRIMAL

cs.CV↗

arXiv2025

MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces

In the latest advancements in multimodal learning, effectively addressing the spatial and semantic losses of visual data after encoding remains a critical challenge. This is because the performance of large multimodal models is positively correlated with the coupling between visual encoders and large language models. Existing approaches often face issues such as vector gaps or semantic disparities, resulting in information loss during the propagation process. To address these issues, we propose MAGE (Multimodal Alignment and Generation Enhancement), a novel framework that bridges the semantic spaces of vision and text through an innovative alignment mechanism. By introducing the Intelligent Alignment Network (IAN), MAGE achieves dimensional and semantic alignment. To reduce the gap between synonymous heterogeneous data, we employ a training strategy that combines cross-entropy and mean squared error, significantly enhancing the alignment effect. Moreover, to enhance MAGE's "Any-to-Any" capability, we developed a fine-tuning dataset for multimodal tool-calling instructions to expand the model's output capability boundaries. Finally, our proposed multimodal large model architecture, MAGE, achieved significantly better performance compared to similar works across various evaluation benchmarks, including MME, MMBench, and SEED. Complete code and appendix are available at: https://github.com/GTCOM-NLP/MAGE.

cs.CV↗