arXiv subjects

Peng Cheng

Publications and source records attributed to Peng Cheng.

At least 91 records · Page 5Linked to original sources

arXiv2026

Intertwined atomic-nanoscale-microscale structures via intralayer anisotropic Fe-chains in the layered ferromagnet FePd2Te2

Controlling mesoscale and nanoscale material structures and properties through self-organized atomic behavior is essential for atomic-scale manufacturing. However, direct and visual studies on the cross-scale effects of such atomic self-organization on mesoscopic structures remain scarce. Here, we report the intertwined atomic-nanoscale-mesoscale structures via the intralayer Fe-chains in the sandwich-like layered FePd2Te2 crystal by scanning tunneling microscopy (STM) and atomic force microscopy (AFM). The hierarchical orthogonal corrugated morphologies are directly revealed and attributed to its chain-orientation-determined twinning-domain effect. Both Fe-chains of middle-sublayer and two kinds of Te atoms of top-sublayer are further atomically resolved at the sub-Å level, indicating the critical effects of Pd-atoms/voids on the intra-layer anisotropic Fe-chains and the interlayer structural alignment. The thermal-induced and strain-related structural transitions of surface layer are further investigated and discussed based on the proposed filling model of Pd-voids by the intralayer Pd-atoms. Our work not only provides deep understanding of this exotic layered magnetic material, and will inspire more perspectives for tailoring its anisotropic atomic-to-mesoscale structures and properties.

cond-mat.mtrl-sci↗

arXiv2026

Helicity Dependent Distribution Functions of the Proton and $Λ$ and $Σ^0$ Baryons

Using continuum Schwinger function methods, a coherent set of predictions for proton, $Λ$ and $Σ^0$ distribution functions (DFs) has been made available -- both helicity dependent and unpolarised. The results and comparisons between them reveal impacts of diquark correlations and SU$(3)$-flavour symmetry breaking, some of which are highlighted in this contribution. For instance: in-proton ratios of helicity-dependent/unpolarised valence-quark DFs are presented; it is highlighted that, were it not for the presence of axialvector diquarks in the $Σ^0$, the valence strange quark would carry none of the $Σ^0$ spin; and the sign and size of polarised gluon DFs is discussed -- at a scale typical of modern measurements, gluon partons carry roughly 40% of each octet baryon's spin.

hep-ph↗

arXiv2026

Revisiting Graph Analytics Benchmark

The rise of graph analytics platforms has led to the development of various benchmarks for evaluating and comparing platform performance. However, existing benchmarks often fall short of fully assessing performance due to limitations in core algorithm selection, data generation processes (and the corresponding synthetic datasets), as well as the neglect of API usability evaluation. To address these shortcomings, we propose a novel graph analytics benchmark. First, we select eight core algorithms by extensively reviewing both academic and industrial settings. Second, we design an efficient and flexible data generator and produce eight new synthetic datasets as the default datasets for our benchmark. Lastly, we introduce a multi-level large language model (LLM)-based framework for API usability evaluation-the first of its kind in graph analytics benchmarks. We conduct comprehensive experimental evaluations on existing platforms (GraphX, PowerGraph, Flash, Grape, Pregel+, Ligra and G-thinker). The experimental results demonstrate the superiority of our proposed benchmark.

cs.DB↗

arXiv2026

Federated Customization of Large Models: Approaches, Experiments, and Insights

In this article, we explore federated customization of large models and highlight the key challenges it poses within the federated learning framework. We review several popular large model customization techniques, including full fine-tuning, efficient fine-tuning, prompt engineering, prefix-tuning, knowledge distillation, and retrieval-augmented generation. Then, we discuss how these techniques can be implemented within the federated learning framework. Moreover, we conduct experiments on federated prefix-tuning, which, to the best of our knowledge, is the first trial to apply prefix-tuning in the federated learning setting. The conducted experiments validate its feasibility with performance close to centralized approaches. Further comparison with three other federated customization methods demonstrated its competitive performance, satisfactory efficiency, and consistent robustness.

cs.LG↗

arXiv2025

Sigma-MoE-Tiny Technical Report

Mixture-of-Experts (MoE) has emerged as a promising paradigm for foundation models due to its efficient and powerful scalability. In this work, we present Sigma-MoE-Tiny, an MoE language model that achieves the highest sparsity compared to existing open-source models. Sigma-MoE-Tiny employs fine-grained expert segmentation with up to 96 experts per layer, while activating only one expert for each token, resulting in 20B total parameters with just 0.5B activated. The major challenge introduced by such extreme sparsity lies in expert load balancing. We find that the widely-used load balancing loss tends to become ineffective in the lower layers under this setting. To address this issue, we propose a progressive sparsification schedule aiming to balance expert utilization and training stability. Sigma-MoE-Tiny is pre-trained on a diverse and high-quality corpus, followed by post-training to further unlock its capabilities. The entire training process remains remarkably stable, with no occurrence of irrecoverable loss spikes. Comprehensive evaluations reveal that, despite activating only 0.5B parameters, Sigma-MoE-Tiny achieves top-tier performance among counterparts of comparable or significantly larger scale. In addition, we provide an in-depth discussion of load balancing in highly sparse MoE models, offering insights for advancing sparsity in future MoE architectures. Project page: https://qghuxmu.github.io/Sigma-MoE-Tiny Code: https://github.com/microsoft/ltp-megatron-lm

cs.CL↗

arXiv2025

SIGMA: An AI-Empowered Training Stack on Early-Life Hardware

An increasing variety of AI accelerators is being considered for large-scale training. However, enabling large-scale training on early-life AI accelerators faces three core challenges: frequent system disruptions and undefined failure modes that undermine reliability; numerical errors and training instabilities that threaten correctness and convergence; and the complexity of parallelism optimization combined with unpredictable local noise that degrades efficiency. To address these challenges, SIGMA is an open-source training stack designed to improve the reliability, stability, and efficiency of large-scale distributed training on early-life AI hardware. The core of this initiative is the LUCIA TRAINING PLATFORM (LTP), the system optimized for clusters with early-life AI accelerators. Since its launch in March 2025, LTP has significantly enhanced training reliability and operational productivity. Over the past five months, it has achieved an impressive 94.45% effective cluster accelerator utilization, while also substantially reducing node recycling and job-recovery times. Building on the foundation of LTP, the LUCIA TRAINING FRAMEWORK (LTF) successfully trained SIGMA-MOE, a 200B MoE model, using 2,048 AI accelerators. This effort delivered remarkable stability and efficiency outcomes, achieving 21.08% MFU, state-of-the-art downstream accuracy, and encountering only one stability incident over a 75-day period. Together, these advances establish SIGMA, which not only tackles the critical challenges of large-scale training but also establishes a new benchmark for AI infrastructure and platform innovation, offering a robust, cost-effective alternative to prevailing established accelerator stacks and significantly advancing AI capabilities and scalability. The source code of SIGMA is available at https://github.com/microsoft/LuciaTrainingPlatform.

cs.DC↗

arXiv2025

Insights into Nucleon Resonances via Continuum Schwinger Function Methods

The first baryon resonance was discovered in the early 1950s. The Roper resonance joined the collection ten years later. Today, many baryon resonances are known and more are being discovered. As baryons, these states are the most fundamental three-body systems in Nature. They must all be understood, not just the isolated ground state nucleon. This contribution sketches applications of continuum Schwinger function methods to the baryon resonance problem. Whilst spectroscopy is of value, particular emphasis is placed on resonance electroproduction because transition form factors extracted from electroproduction data provide a keen tool for revealing resonance structure.

hep-ph↗

arXiv2025

A Survey of Operating System Kernel Fuzzing

The Operating System (OS) kernel is foundational in modern computing, especially with the proliferation of diverse computing devices. However, its development also comes with vulnerabilities that can lead to severe security breaches. Kernel fuzzing, a technique used to uncover these vulnerabilities, poses distinct challenges when compared to user-space fuzzing. These include the complexity of configuring the testing environment and addressing the statefulness inherent to both the kernel and the fuzzing process. Despite the significant interest from the community, a comprehensive understanding of kernel fuzzing remains lacking, hindering further progress in the field. In this paper, we present the first systematic study focused specifically on OS kernel fuzzing. We begin by outlining the unique challenges of kernel fuzzing, which distinguish it from those in user space. Following this, we summarize the progress of 107 academic studies from top-tier venues between 2017 and 2025. To structure this analysis, we introduce a stage-based fuzzing model and a novel fuzzing taxonomy that highlights nine core functionalities unique to kernel fuzzing. Each of these functionalities is examined in conjunction with the methodological approaches employed to address them. Finally, we identify remaining gaps in addressing challenges and outline promising directions to guide forthcoming research in kernel security.

cs.CR↗

arXiv2025

Evidence of a two-dimensional nitrogen crystalline structure on silver surfaces

Nitrogen, the most abundant element in Earth's atmosphere, exists as a diatomic gas under standard temperature and pressure. In the two-dimensional (2D) limit, atomically thin nitrogen, termed nitrogene, has been theoretically predicted to form crystalline materials with various polymorphic configurations, exhibiting diverse chemical and physical properties. However, the synthesis of nitrogene has remained elusive due to the strong nitrogen-nitrogen triple bonds. Here, we report experimental evidence of the formation of nitrogen-based crystalline structures compatible with nitrogene on silver surfaces via ion-beam-assisted epitaxy. Through a combination of scanning tunneling microscopy, angle-resolved photoemission spectroscopy, and first-principles calculations, we demonstrate that the nitrogene-like structure adopts a puckered honeycomb lattice. Notably, our calculations predict a nitrogene band gap of up to 7.5 eV, positioning it as a promising candidate for ultraviolet optoelectronic devices and high-k dielectric applications.

cond-mat.mtrl-sci↗

arXiv2025

Nonreciprocal spin wave in room-temperature van der Waals ferromagnet $(\rm Fe_{0.78}Co_{0.22})_{5}GeTe_{2}$

Here, we investigate the spin waves in room-temperature van der Waals ferromagnet $(\rm Fe_{0.78}Co_{0.22})_{5}GeTe_{2}$ by utilizing Brillouin light scattering technique. The spin wave dispersion in flakes of different thicknesses shows the key role of dipolar interaction in the spin waves of vdW ferromagnets, and the non-reciprocity of spin wave in thick flakes is observed, which is attributed to the bulk Dzyaloshinskii-Moriya interaction after excluding the influence of dynamic dipolar interaction. The measured bulk DMI parameter D is 0.08 $\rm mJ/m^2$, which is double that of pure $\rm Fe_5GeTe_2$. Our work shows that Co-doped $\rm Fe_5GeTe_2$ is a promising platform for investigating propagating spin wave and topological spin textures at room temperature.

cond-mat.mes-hall↗

arXiv2025

Near-Optimal Reinforcement Learning with Shuffle Differential Privacy

Reinforcement learning (RL) is a powerful tool for sequential decision-making, but its application is often hindered by privacy concerns arising from its interaction data. This challenge is particularly acute in advanced networked systems, where learning from operational and user data can expose systems to privacy inference attacks. Existing differential privacy (DP) models for RL are often inadequate: the centralized model requires a fully trusted server, creating a single point of failure risk, while the local model incurs significant performance degradation that is unsuitable for many networked applications. This paper addresses this gap by leveraging the emerging shuffle model of privacy, an intermediate trust model that provides strong privacy guarantees without a centralized trust assumption. We present Shuffle Differentially Private Policy Elimination (SDP-PE), the first generic policy elimination-based algorithm for episodic RL under the shuffle model. Our method introduces a novel exponential batching schedule and a ``forgetting'' mechanism to balance the competing demands of privacy and learning performance. Our analysis shows that SDP-PE achieves a near-optimal regret bound, demonstrating a superior privacy-regret trade-off with utility comparable to the centralized model while significantly outperforming the local model. The numerical experiments also corroborate our theoretical results and demonstrate the effectiveness of SDP-PE. This work establishes the viability of the shuffle model for secure data-driven decision-making in networked systems.

cs.LG↗

arXiv2025

FengHuang: Next-Generation Memory Orchestration for AI Inferencing

This document presents a vision for a novel AI infrastructure design that has been initially validated through inference simulations on state-of-the-art large language models. Advancements in deep learning and specialized hardware have driven the rapid growth of large language models (LLMs) and generative AI systems. However, traditional GPU-centric architectures face scalability challenges for inference workloads due to limitations in memory capacity, bandwidth, and interconnect scaling. To address these issues, the FengHuang Platform, a disaggregated AI infrastructure platform, is proposed to overcome memory and communication scaling limits for AI inference. FengHuang features a multi-tier shared-memory architecture combining high-speed local memory with centralized disaggregated remote memory, enhanced by active tensor paging and near-memory compute for tensor operations. Simulations demonstrate that FengHuang achieves up to 93% local memory capacity reduction, 50% GPU compute savings, and 16x to 70x faster inter-GPU communication compared to conventional GPU scaling. Across workloads such as GPT-3, Grok-1, and QWEN3-235B, FengHuang enables up to 50% GPU reductions while maintaining end-user performance, offering a scalable, flexible, and cost-effective solution for AI inference infrastructure. FengHuang provides an optimal balance as a rack-level AI infrastructure scale-up solution. Its open, heterogeneous design eliminates vendor lock-in and enhances supply chain flexibility, enabling significant infrastructure and power cost reductions.

cs.DC↗

arXiv2025

FedeCouple: Fine-Grained Balancing of Global-Generalization and Local-Adaptability in Federated Learning

In privacy-preserving mobile network transmission scenarios with heterogeneous client data, personalized federated learning methods that decouple feature extractors and classifiers have demonstrated notable advantages in enhancing learning capability. However, many existing approaches primarily focus on feature space consistency and classification personalization during local training, often neglecting the local adaptability of the extractor and the global generalization of the classifier. This oversight results in insufficient coordination and weak coupling between the components, ultimately degrading the overall model performance. To address this challenge, we propose FedeCouple, a federated learning method that balances global generalization and local adaptability at a fine-grained level. Our approach jointly learns global and local feature representations while employing dynamic knowledge distillation to enhance the generalization of personalized classifiers. We further introduce anchors to refine the feature space; their strict locality and non-transmission inherently preserve privacy and reduce communication overhead. Furthermore, we provide a theoretical analysis proving that FedeCouple converges for nonconvex objectives, with iterates approaching a stationary point as the number of communication rounds increases. Extensive experiments conducted on five image-classification datasets demonstrate that FedeCouple consistently outperforms nine baseline methods in effectiveness, stability, scalability, and security. Notably, in experiments evaluating effectiveness, FedeCouple surpasses the best baseline by a significant margin of 4.3%.

cs.CV↗

arXiv2025

Development of a 10.8-eV Tabletop Femtosecond Laser with Tunable Polarization for High-Resolution Angle-Resolved Photoemission Spectroscopy

The development of extreme ultraviolet sources is critical for advancing angleresolved photoemission spectroscopy (ARPES), a powerful technique for probing the electronic structure of materials. Here, we report the construction of a tabletop 10.8-eV femtosecond laser through cascaded third-harmonic generation, which operates at a repetition rate of 1 MHz and delivers a photon flux of approximately 1012 photons/s. The system achieves a high energy resolution of approximately 11.8 meV and tunable polarization. This flexibility enables detailed studies of orbitaland (pseudo)spin characteristics in quantum materials. We demonstrate the capabilities of this laser-ARPES system by investigating several prototypical materials, showcasing its potential for elucidating complex phenomena in quantum materials.

cond-mat.mtrl-sci↗

arXiv2025

WMCopier: Forging Invisible Image Watermarks on Arbitrary Images

Invisible Image Watermarking is crucial for ensuring content provenance and accountability in generative AI. While Gen-AI providers are increasingly integrating invisible watermarking systems, the robustness of these schemes against forgery attacks remains poorly characterized. This is critical, as forging traceable watermarks onto illicit content leads to false attribution, potentially harming the reputation and legal standing of Gen-AI service providers who are not responsible for the content. In this work, we propose WMCopier, an effective watermark forgery attack that operates without requiring any prior knowledge of or access to the target watermarking algorithm. Our approach first models the target watermark distribution using an unconditional diffusion model, and then seamlessly embeds the target watermark into a non-watermarked image via a shallow inversion process. We also incorporate an iterative optimization procedure that refines the reconstructed image to further trade off the fidelity and forgery efficiency. Experimental results demonstrate that WMCopier effectively deceives both open-source and closed-source watermark systems (e.g., Amazon's system), achieving a significantly higher success rate than existing methods. Additionally, we evaluate the robustness of forged samples and discuss the potential defenses against our attack.

cs.CR↗

arXiv2025

Learning from the Best, Differently: A Diversity-Driven Rethinking on Data Selection

High-quality pre-training data is crutial for large language models, where quality captures factual reliability and semantic value, and diversity ensures broad coverage and distributional heterogeneity. Existing approaches typically rely on single or multiple-dimensional score-based selection. However, directly selecting top-scored data often degrades performance, and sampling from a broader range is required to recover results. The above non-monotonicity between dataset scores and downstream benchmark results reveals a fundamental bias: score-based methods collapse correlated dimensions, causing top-scored data to appear high-quality while systematically overlooking diversity. We argue that ensuring diversity requires decomposing correlated metrics into orthogonal feature dimensions, from which the top-scored data can be directly selected. Therefore, we proposed the Orthogonal Diversity-Aware Selection (ODiS) algorithm, which preserves both quality and diversity during data selection. First, ODiS evaluates data from multiple dimensions, covering language quality, knowledge quality, and comprehension difficulty. The multi-dimensional scores are then decorrelated via Principal Component Analysis (PCA), yielding orthogonal evaluation dimensions. For each dimension, a Roberta-based scorer is trained to regress the data onto PCA-projected scores, enabling scalable inference on large corpora. Finally, ODiS constructs the training dataset by selecting top-scored data within each orthogonal dimension, thereby ensuring both quality and diversity. Empirical results show that ODiS-selected data exhibit less than 2\% inter-dimension overlap, confirming orthogonality between dimensions. More importantly, models trained with ODiS-selected data significantly outperform other baselines on downstream benchmarks, highlighting the necessity of orthogonal, diversity-aware data selection for LLMs.

cs.CL↗

arXiv2025

Approximate Nearest Neighbor Search of Large Scale Vectors on Distributed Storage

Approximate Nearest Neighbor Search (ANNS) in high-dimensional space is an essential operator in many online services, such as information retrieval and recommendation. Indices constructed by the state-of-the-art ANNS algorithms must be stored in single machine's memory or disk for high recall rate and throughput, suffering from substantial storage cost, constraint of limited scale and single point of failure. While distributed storage can provide a cost-effective and robust solution, there is no efficient and effective algorithms for indexing vectors in distributed storage scenarios. In this paper, we present a new graph-cluster hybrid indexing and search system which supports Distributed Storage Approximate Nearest Neighbor Search, called DSANN. DSANN can efficiently index, store, search billion-scale vector database in distributed storage and guarantee the high availability of index service. DSANN employs the concurrent index construction method to significantly reduces the complexity of index building. Then, DSANN applies Point Aggregation Graph to leverage the structural information of graph to aggregate similar vectors, optimizing storage efficiency and improving query throughput via asynchronous I/O in distributed storage. Through extensive experiments, we demonstrate DSANN can efficiently and effectively index, store and search large-scale vector datasets in distributed storage scenarios.

cs.DB↗

arXiv2025

Integral cubic form of 5D minimal supergravities and non-perturbative anomalies in 6D (1,0) theories

A five-dimensional minimal supergravity theory coupled to vector and hypermultiplets is specified by a set of trilinear couplings, given by an intersection form $C_{IJK}$, and gravitational couplings specified by an integer-valued vector $a_I$ and is consistent when these data define an integral cubic form. For every Calabi-Yau threefold reduction of M-theory, this condition is satisfied automatically. Via suitable redefinitions of the basis of 5D vectors, this is also shown to be the case for the circle reductions of six-dimensional anomaly-free (1,0) theories. When the 6D theory has a $\mathbb{Z}_k$ gauge symmetry, we point out that the consistency of the circle reduction with nontrivial $\mathbb{Z}_k$ holonomy is closely related to 6D constraints derived by Monnier and Moore. These constraints are extended to semidirect products with continuous gauge groups $\mathbb{Z}_k \ltimes G$ and CHL-like circle compactifications. When $\mathbb{Z}_k$ acts on anti-self-dual tensor fields of 6D supergravity, there should be a nontrivial action of holonomy on the topological Green-Schwarz terms.

hep-th↗