arXiv subjects

Hao Shen

Publications and source records attributed to Hao Shen.

At least 55 records · Page 3Linked to original sources

arXiv2025

Langevin dynamics of lattice Yang-Mills-Higgs and applications

In this paper, we investigate the Langevin dynamics of various lattice formulations of the Yang--Mills--Higgs model, with an inverse Yang--Mills coupling $β$ and a Higgs parameter $κ$. The Higgs component is either a bounded field taking values in a compact target space, or an unbounded field taking values in a vector space in which case the model also has a Higgs mass parameter $m$. We study the regime where $(β,κ)$ are small in the first case or $(β,κ/m)$ are small in the second case. We prove the exponential ergodicity of the dynamics on the whole lattice via functional inequalities. We establish exponential decay of correlations for a broad class of observables, namely, the infinite volume measure exhibits a strictly positive mass gap. Moreover, when the target space of the Higgs field is compact, appropriately rescaled observables exhibit factorized correlations in the large $N$ limit. These extend the earlier results \cite{SZZ22} on pure lattice Yang--Mills to the case with a coupled Higgs field. Unlike pure lattice Yang--Mills where the field is always bounded, in the case where the coupled Higgs component is unbounded, the control of its behavior is much harder and requires new techniques. Our approach involves a disintegration argument and a delicate analysis of correlations to effectively control the unbounded Higgs component.

math.PR↗

arXiv2025

Isotropic Dirac fermion and anomalous oscillator strength of zeroth Landau level transition

Dirac fermions, characterized by their linear dispersion and relativistic nature, have emerged as a prominent class of quasiparticles in condensed matter physics. While the Dirac equation, initially developed in the context of high-energy physics, provides a remarkable framework for describing the electronic properties of these materials, the inherent symmetry constraints of condensed matter often lead to deviations from the idealized paradigm. In particular, three-dimensional Dirac fermions in solids often exhibit anisotropic behavior, challenging the notion of perfect symmetry inherent in the Dirac equation. Here, we report the observation of isotropic massive Dirac fermions in LaAlSi through Landau level spectroscopy. The presence of three-dimensional massive Dirac fermions across the Fermi energy is demonstrated by quantized and semiclassical analyses of the magnetic field evolution of Landau level transitions. The isotropic topological nature, Fermi velocity, and Dirac mass are evidenced by the identical magneto-infrared response among the Faraday and three Voigt geometries. Furthermore, we observe an unusually large oscillator strength in the zeroth Landau level transition of the Dirac fermion, compared to transitions with higher indices. This phenomenon, supported by model calculations, can be attributed to the combined effects of the partial excitation of Dirac fermion and the resonant dielectric coupling with the Weyl plasma. Our work provides a strategy for realizing ideal quasiparticle excitations and their coupling effects in condensed matter systems, offering a platform for exploring relativistic physics.

cond-mat.mtrl-sci↗

arXiv2025

A High-Flux and High-Efficiency Setup for Magneto-Infrared Spectroscopy

We report the design and implementation of a high-flux, high-efficiency magneto-infrared spectroscopy system optimized for broadband measurements in high magnetic fields. The setup integrates a Fourier transform infrared spectrometer, a 12 T cryogen-free superconducting magnet, precision-polished and gold-plated light tubes, custom-designed reflective focusing modules for Faraday and Voigt geometries, and an external multi-detector chamber with motorized selection. Optical throughput is maximized by reducing light tube loss from 65.5%/m to 22.0%/m via abrasive flow and mechanical polishing followed by gold electroplating, and by adopting a single-on-axis parabolic-mirror Faraday module that increases the effective numerical aperture from 0.14 to 0.36, enhancing collection efficiency by nearly an order of magnitude. An eight-position motorized sample stage and fully automated control over magnetic field, temperature, optical path, and detector choice enable high-throughput measurements without repeated warm-ups. The optimized configuration achieves a root-mean-square noise level of 0.0061% in a 2-minute integration for a 40% reflectivity sample, corresponding to a signal-to-noise ratio exceeding 16000. System capabilities are demonstrated by resolving weak replica bands in EuCd2As2 and faint Landau level transitions in LaAlSi.

cond-mat.mtrl-sci↗

arXiv2025

OPOR-Bench: Evaluating Large Language Models on Online Public Opinion Report Generation

Online Public Opinion Reports consolidate news and social media for timely crisis management by governments and enterprises. While large language models have made automated report generation technically feasible, systematic research in this specific area remains notably absent, particularly lacking formal task definitions and corresponding benchmarks. To bridge this gap, we define the Automated Online Public Opinion Report Generation (OPOR-GEN) task and construct OPOR-BENCH, an event-centric dataset covering 463 crisis events with their corresponding news articles, social media posts, and a reference summary. To evaluate report quality, we propose OPOR-EVAL, a novel agent-based framework that simulates human expert evaluation by analyzing generated reports in context. Experiments with frontier models demonstrate that our framework achieves high correlation with human judgments. Our comprehensive task definition, benchmark dataset, and evaluation framework provide a solid foundation for future research in this critical domain.

cs.CL↗

arXiv2025

Makeenko-Migdal equations for lattice Yang-Mills-Higgs

We derive a form of master loop equations for the lattice Yang-Mills-Higgs theory with structure group $SO(N)$, $U(N)$ or $SU(N)$. Compared to the pure Yang-Mills setting, several new operations arise. In fact, to obtain a closed recursion we must broaden the class of observables to include open Wilson lines. Our approach is based on the conditional Langevin dynamic and yields a concise proof via Itô's formula.

math.PR↗

arXiv2025

Resource-Efficient Adaptation of Large Language Models for Text Embeddings via Prompt Engineering and Contrastive Fine-tuning

Large Language Models (LLMs) have become a cornerstone in Natural Language Processing (NLP), achieving impressive performance in text generation. Their token-level representations capture rich, human-aligned semantics. However, pooling these vectors into a text embedding discards crucial information. Nevertheless, many non-generative downstream tasks, such as clustering, classification, or retrieval, still depend on accurate and controllable sentence- or document-level embeddings. We explore several adaptation strategies for pre-trained, decoder-only LLMs: (i) various aggregation techniques for token embeddings, (ii) task-specific prompt engineering, and (iii) text-level augmentation via contrastive fine-tuning. Combining these components yields competitive performance on the English clustering track of the Massive Text Embedding Benchmark (MTEB). An analysis of the attention map further shows that fine-tuning shifts focus from prompt tokens to semantically relevant words, indicating more effective compression of meaning into the final hidden state. Our experiments demonstrate that LLMs can be effectively adapted as text embedding models through a combination of prompt engineering and resource-efficient contrastive fine-tuning on synthetically generated positive pairs.

cs.CL↗

arXiv2025

White paper: Towards Human-centric and Sustainable 6G Services -- the fortiss Research Perspective

As a leading research institute in software-intensive systems, fortiss is actively shaping the vision of Sixth Generation Mobile Communication (6G). Our mission is to ensure that 6G technologies go beyond technical advancements and are aligned with societal needs. fortiss plays a key role in 6G initiatives worldwide, including contributions to standardization bodies and collaborative Research and Development programs. We focus on software-defined, AI-enabled, and sustainable communication services that prioritize human values and long-term impact. 6G will redefine digital connectivity through cognitive intelligence, decentralized orchestration, and sustainability-oriented architectures. As expectations rise for ultra-reliable low-latency communication (URLLC) and personalized digital services, 6G must outperform prior generations. It will rely on AI-native networking, Edge-Cloud resource orchestration, and energy-aware data frameworks, ensuring both technical performance and societal relevance. This white paper presents the fortiss vision for a human-centric, sustainable, and AI-integrated 6G network. It outlines key research domains such as semantic communication, green orchestration, and distributed AI, all linked to societal and technological challenges. The white paper is aimed at researchers, industry experts, policymakers, and developers. It articulates the strategic direction and contributions of fortiss to 6G, emphasizing responsible innovation and interdisciplinary collaboration toward a meaningful 2030 vision.

cs.NI↗

arXiv2025

VulStamp: Vulnerability Assessment using Large Language Model

Although modern vulnerability detection tools enable developers to efficiently identify numerous security flaws, indiscriminate remediation efforts often lead to superfluous development expenses. This is particularly true given that a substantial portion of detected vulnerabilities either possess low exploitability or would incur negligible impact in practical operational environments. Consequently, vulnerability severity assessment has emerged as a critical component in optimizing software development efficiency. Existing vulnerability assessment methods typically rely on manually crafted descriptions associated with source code artifacts. However, due to variability in description quality and subjectivity in intention interpretation, the performance of these methods is seriously limited. To address this issue, this paper introduces VulStamp, a novel intention-guided framework, to facilitate description-free vulnerability assessment. Specifically, VulStamp adopts static analysis together with Large Language Model (LLM) to extract the intention information of vulnerable code. Based on the intention information, VulStamp uses a prompt-tuned model for vulnerability assessment. Furthermore, to mitigate the problem of imbalanced data associated with vulnerability types, VulStamp integrates a Reinforcement Learning (RL)-based prompt-tuning method to train the assessment model.

cs.SE↗

arXiv2025

AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System Need

Large language model based multi-agent systems have demonstrated significant potential in social simulation and complex task resolution domains. However, current frameworks face critical challenges in system architecture design, cross-domain generalizability, and performance guarantees, particularly as task complexity and number of agents increases. We introduces AgentGroupChat-V2, a novel framework addressing these challenges through three core innovations: (1) a divide-and-conquer fully parallel architecture that decomposes user queries into hierarchical task forest structures enabling dependency management and distributed concurrent processing. (2) an adaptive collaboration engine that dynamically selects heterogeneous LLM combinations and interaction modes based on task characteristics. (3) agent organization optimization strategies combining divide-and-conquer approaches for efficient problem decomposition. Extensive experiments demonstrate AgentGroupChat-V2's superior performance across diverse domains, achieving 91.50% accuracy on GSM8K (exceeding the best baseline by 5.6 percentage points), 30.4% accuracy on competition-level AIME (nearly doubling other methods), and 79.20% pass@1 on HumanEval. Performance advantages become increasingly pronounced with higher task difficulty, particularly on Level 5 MATH problems where improvements exceed 11 percentage points compared to state-of-the-art baselines. These results confirm that AgentGroupChat-V2 provides a comprehensive solution for building efficient, general-purpose LLM multi-agent systems with significant advantages in complex reasoning scenarios. Code is available at https://github.com/MikeGu721/AgentGroupChat-V2.

cs.CL↗

arXiv2025

Application and Optimization of Large Models Based on Prompt Tuning for Fact-Check-Worthiness Estimation

In response to the growing problem of misinformation in the context of globalization and informatization, this paper proposes a classification method for fact-check-worthiness estimation based on prompt tuning. We construct a model for fact-check-worthiness estimation at the methodological level using prompt tuning. By applying designed prompt templates to large language models, we establish in-context learning and leverage prompt tuning technology to improve the accuracy of determining whether claims have fact-check-worthiness, particularly when dealing with limited or unlabeled data. Through extensive experiments on public datasets, we demonstrate that the proposed method surpasses or matches multiple baseline methods in the classification task of fact-check-worthiness estimation assessment, including classical pre-trained models such as BERT, as well as recent popular large models like GPT-3.5 and GPT-4. Experiments show that the prompt tuning-based method proposed in this study exhibits certain advantages in evaluation metrics such as F1 score and accuracy, thereby effectively validating its effectiveness and advancement in the task of fact-check-worthiness estimation.

cs.CL↗

arXiv2025

A Scalable Crawling Algorithm Utilizing Noisy Change-Indicating Signals

Web refresh crawling is the problem of keeping a cache of web pages fresh, that is, having the most recent copy available when a page is requested, given a limited bandwidth available to the crawler. Under the assumption that the change and request events, resp., to each web page follow independent Poisson processes, the optimal scheduling policy was derived by Azar et al. 2018. In this paper, we study an extension of this problem where side information indicating content changes, such as various types of web pings, for example, signals from sitemaps, content delivery networks, etc., is available. Incorporating such side information into the crawling policy is challenging, because (i) the signals can be noisy with false positive events and with missing change events; and (ii) the crawler should achieve a fair performance over web pages regardless of the quality of the side information, which might differ from web page to web page. We propose a scalable crawling algorithm which (i) uses the noisy side information in an optimal way under mild assumptions; (ii) can be deployed without heavy centralized computation; (iii) is able to crawl web pages at a constant total rate without spikes in the total bandwidth usage over any time interval, and automatically adapt to the new optimal solution when the total bandwidth changes without centralized computation. Experiments clearly demonstrate the versatility of our approach.

stat.ML↗

arXiv2025

Generative Multi-Agent Collaboration in Embodied AI: A Systematic Review

Embodied multi-agent systems (EMAS) have attracted growing attention for their potential to address complex, real-world challenges in areas such as logistics and robotics. Recent advances in foundation models pave the way for generative agents capable of richer communication and adaptive problem-solving. This survey provides a systematic examination of how EMAS can benefit from these generative capabilities. We propose a taxonomy that categorizes EMAS by system architectures and embodiment modalities, emphasizing how collaboration spans both physical and virtual contexts. Central building blocks, perception, planning, communication, and feedback, are then analyzed to illustrate how generative techniques bolster system robustness and flexibility. Through concrete examples, we demonstrate the transformative effects of integrating foundation models into embodied, multi-agent frameworks. Finally, we discuss challenges and future directions, underlining the significant promise of EMAS to reshape the landscape of AI-driven collaboration.

cs.MA↗

arXiv2025

Makeenko-Migdal equations for 2D Yang-Mills: from lattice to continuum

In this paper, we prove the convergence of the discrete Makeenko-Migdal equations for the Yang-Mills model on $(\varepsilon \mathbf{Z})^{2}$ to their continuum counterparts on the plane, in an appropriate sense. The key step in the proof is identifying the limits of the contributions from deformations as the area derivatives of the Wilson loop expectations.

math-ph↗

arXiv2024

Drift to Remember

Lifelong learning in artificial intelligence (AI) aims to mimic the biological brain's ability to continuously learn and retain knowledge, yet it faces challenges such as catastrophic forgetting. Recent neuroscience research suggests that neural activity in biological systems undergoes representational drift, where neural responses evolve over time, even with consistent inputs and tasks. We hypothesize that representational drift can alleviate catastrophic forgetting in AI during new task acquisition. To test this, we introduce DriftNet, a network designed to constantly explore various local minima in the loss landscape while dynamically retrieving relevant tasks. This approach ensures efficient integration of new information and preserves existing knowledge. Experimental studies in image classification and natural language processing demonstrate that DriftNet outperforms existing models in lifelong learning. Importantly, DriftNet is scalable in handling a sequence of tasks such as sentiment analysis and question answering using large language models (LLMs) with billions of parameters on a single Nvidia A100 GPU. DriftNet efficiently updates LLMs using only new data, avoiding the need for full dataset retraining. Tested on GPT-2 and RoBERTa, DriftNet is a robust, cost-effective solution for lifelong learning in LLMs. This study not only advances AI systems to emulate biological learning, but also provides insights into the adaptive mechanisms of biological neural systems, deepening our understanding of lifelong learning in nature.

cs.AI↗

arXiv2024

The Completeness of Accreting Neutron Star Binary Candidates from the Chinese Space Station Telescope

Neutron star (NS) has many extreme physical conditions, and one may obtain some important informations about NS via accreting neutron star binary (ANSB) systems. The upcoming Chinese Space Station Telescope (CSST) provides an opportunity to search for a large sample of ANSB candidates. Our goal is to check the completeness of the potential ANSB samples from CSST data. In this paper, we generate some ANSBs and normal binaries under CSST photometric system by binary evolution and binary population synthesis method and use a machine learning method to train a classification model. Although the Precision ($94.56~ \%$) of our machine learning model is as high as before study, the Recall is only about $63.29~ \%$. The Precision/Recall is mainly determined by the mass transfer rate between the NSs and their companions. In addition, we also find that the completeness of ANSB samples from CSST photometric data by the machine learning method also depends on the companion mass and the age of the system. ANSB candidates with low initial mass companion star ($0.1~ {\rm M}_\odot$ to $1~ {\rm M}_\odot$) have a relatively high Precision ($94.94~ \%$) and high Recall ($86.32~ \%$), whereas ANSB candidates with higher initial mass companion star ($1.1~ {\rm M}_\odot$ to $3~ {\rm M}_\odot$) have similar Precision ($93.88~ \%$) and quite low Recall ($42.67~ \%$). Our results indicate that although the machine learning method may obtain a relative pure sample of ANSBs, a completeness correction is necessary for one to obtain a complete sample.

astro-ph.SR↗

arXiv2024

Are Large Language Models Possible to Conduct Cognitive Behavioral Therapy?

In contemporary society, the issue of psychological health has become increasingly prominent, characterized by the diversification, complexity, and universality of mental disorders. Cognitive Behavioral Therapy (CBT), currently the most influential and clinically effective psychological treatment method with no side effects, has limited coverage and poor quality in most countries. In recent years, researches on the recognition and intervention of emotional disorders using large language models (LLMs) have been validated, providing new possibilities for psychological assistance therapy. However, are LLMs truly possible to conduct cognitive behavioral therapy? Many concerns have been raised by mental health experts regarding the use of LLMs for therapy. Seeking to answer this question, we collected real CBT corpus from online video websites, designed and conducted a targeted automatic evaluation framework involving the evaluation of emotion tendency of generated text, structured dialogue pattern and proactive inquiry ability. For emotion tendency, we calculate the emotion tendency score of the CBT dialogue text generated by each model. For structured dialogue pattern, we use a diverse range of automatic evaluation metrics to compare speaking style, the ability to maintain consistency of topic and the use of technology in CBT between different models . As for inquiring to guide the patient, we utilize PQA (Proactive Questioning Ability) metric. We also evaluated the CBT ability of the LLM after integrating a CBT knowledge base to explore the help of introducing additional knowledge to enhance the model's CBT counseling ability. Four LLM variants with excellent performance on natural language processing are evaluated, and the experimental result shows the great potential of LLMs in psychological counseling realm, especially after combining with other technological means.

cs.CL↗

arXiv2024

Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation

In practical applications of human pose estimation, low-resolution inputs frequently occur, and existing state-of-the-art models perform poorly with low-resolution images. This work focuses on boosting the performance of low-resolution models by distilling knowledge from a high-resolution model. However, we face the challenge of feature size mismatch and class number mismatch when applying knowledge distillation to networks with different input resolutions. To address this issue, we propose a novel cross-domain knowledge distillation (CDKD) framework. In this framework, we construct a scale-adaptive projector ensemble (SAPE) module to spatially align feature maps between models of varying input resolutions. It adopts a projector ensemble to map low-resolution features into multiple common spaces and adaptively merges them based on multi-scale information to match high-resolution features. Additionally, we construct a cross-class alignment (CCA) module to solve the problem of the mismatch of class numbers. By combining an easy-to-hard training (ETHT) strategy, the CCA module further enhances the distillation performance. The effectiveness and efficiency of our approach are demonstrated by extensive experiments on two common benchmark datasets: MPII and COCO. The code is made available in supplementary material.

cs.CV↗

arXiv2024

Focus on Low-Resolution Information: Multi-Granular Information-Lossless Model for Low-Resolution Human Pose Estimation

In real-world applications of human pose estimation, low-resolution input images are frequently encountered when the performance of the image acquisition equipment is limited or the shooting distance is too far. However, existing state-of-the-art models for human pose estimation perform poorly on low-resolution images. One key reason is the presence of downsampling layers in these models, e.g., strided convolutions and pooling layers. It further reduces the already insufficient image information. Another key reason is that the body skeleton and human kinematic information are not fully utilized. In this work, we propose a Multi-Granular Information-Lossless (MGIL) model to replace the downsampling layers to address the above issues. Specifically, MGIL employs a Fine-grained Lossless Information Extraction (FLIE) module, which can prevent the loss of local information. Furthermore, we design a Coarse-grained Information Interaction (CII) module to adequately leverage human body structural information. To efficiently fuse cross-granular information and thoroughly exploit the relationships among keypoints, we further introduce a Multi-Granular Adaptive Fusion (MGAF) mechanism. The mechanism assigns weights to features of different granularities based on the content of the image. The model is effective, flexible, and universal. We show its potential in various vision tasks with comprehensive experiments. It outperforms the SOTA methods by 7.7 mAP on COCO and performs well with different input resolutions, different backbones, and different vision tasks. The code is provided in supplementary material.

cs.CV↗