arXiv subjects

Li Ma

Publications and source records attributed to Li Ma.

At least 55 records · Page 3Linked to original sources

arXiv2026

Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios

Large language models (LLMs) have demonstrated exceptional potential in complex reasoning,pioneering a new paradigm for autonomous agent decision making in dynamic settings. However, in Real-Time Strategy (RTS) scenarios, LLMs suffer from a critical speed-quality trade-off. Specifically expansive state spaces and time limits render inference delays prohibitive, while stochastic planning errors undermine logical consistency. To address these challenges, we present SEMA (Self-Evolving Multi-Agent), a novel framework designed for high-performance, low-latency decision-making in RTS environments. This collaborative multi-agent framework facilitates self-evolution by adaptively calibrating model bias through in-episode assessment and cross-episode analysis. We further incorporate dynamic observation pruning based on structural entropy to model game states topologically. By distilling high dimensional data into core semantic information, this approach significantly reduces inference time. We also develop a hybrid knowledge-memory mechanism that integrates micro-trajectories, macro-experience, and hierarchical domain knowledge, thereby enhancing both strategic adaptability and decision consistency. Experiments across multiple StarCraft II maps demonstrate that SEMA achieves superior win rates while reducing average decision latency by over 50%, validating its efficiency and robustness in complex RTS scenarios.

cs.MA↗

arXiv2026

Tunable intersublattice exchange coupling drives magnetic evolution in Mn$_{3+x}$Ga$_{1-x}$C ($0 \le x \le 0.60$)

We investigate the magnetic and transport evolution in Mn$_{3+x}$Ga$_{1-x}$C ($0 \le x \le 0.60$), where Mn substitution at corner Ga sites induces lattice contraction and suppresses the antiferromagnetic order of Mn$_3$GaC. As $x$ increases, the magnetic ground state of the system undergoes a sequential transition from an antiferromagnetic state, via a canted ferrimagnetic state, to a robust ferrimagnetic state, accompanied by a surge in the magnetic ordering temperature. Saturation magnetic moments reaches a maximum of 3.63~$μ_{\mathrm{B}}$/f.u. at $x = 0.10$, whereas the topological Hall resistivity peaks at 1.47~$μΩ\cdot$cm for $x = 0.20$ before decreasing with further doping. First-principles calculations demonstrate a $\sim\!40^{\circ}$ canting of face-centered Mn moments at $x = 0.20$, signifying spin frustration, and an eventual antiparallel alignment of face-centered and corner-site Mn moments at higher $x$. These results reveal that intersublattice antiferromagnetic coupling governs the magnetic transformation and emergent transport phenomena, thus providing a microscopic foundation for designing high-ordering-temperature antiperovskites.

cond-mat.mtrl-sci↗

arXiv2026

Lattice-Expansion-Driven Stabilization of Helical Magnetic Order in Ru-Doped MnP

The practical utilization of MnP in chiral spintronic devices is fundamentally constrained by its low helical ordering temperature ($T_{\rm S}$). Here, we demonstrate that Ru substitution in Mn$_{1-x}$Ru$_x$P single crystals drives a highly anisotropic lattice expansion, where the $b$-axis elongation is one-quarter that of the $a$- and $c$-axes ($\sim$ 0.04 Å). This structural distortion profoundly stabilizes the helical ground state, elevating $T_{\rm S}$ from 51~K to 215~K and the critical field along the [010] direction at 5~K from 2.3 to 30.0~kOe, while suppressing the Curie temperature ($T_{\rm C}$) from 291~K to 215~K. Synthesizing these results with reported data on Mo- and W-doped analogues reveals that $T_{\rm S}$ and $T_{\rm C}$ are governed primarily by the $b$-axis parameter, exhibiting universal linear scaling relationships ($dT_{\rm S}/db = 1.59 \times 10^4\ \text{KÅ}^{-1}$, $dT_{\rm C}/db = 0.69 \times 10^4\ \text{KÅ}^{-1}$) far greater than those associated with the $a$- or $c$-axes. First-principles calculations reveal that the lattice expansion selectively attenuates ferromagnetic coupling while preserving antiferromagnetic interactions between nearest-neighbor Mn atoms, thereby enhancing magnetic frustration and stabilizing helimagnetism. These findings establish chemical pressure via directed $b$-axis engineering as a robust, generalizable paradigm for stabilizing helimagnetism in MnP.

cond-mat.mtrl-sci↗

arXiv2026

Recoil corrections to pentaquark molecules with an SU(3) anti-triplet heavy baryon

Recoil corrections, which appear at order $\mathcal{O}(\frac{1}{M})$, turn out to be crucial for the pentaquark molecules with heavy flavor. In the past, such corrections were typically regarded as negligible for the formation of heavy molecules. However, our research manifests the important impacts on the spectra of possible baryon-meson bound states. In certain cases, the binding energy sharply decreases after considering the recoil corrections. Using the one-boson-exchange (OBE) model, we have studied a series of double heavy and hidden heavy pentaquark states with an SU(3) anti-triplet baryon, including $Ξ_{c}\bar{D}^{(*)}$, $Λ_{c}\bar{D}^{(*)}$, $Ξ_{c}D^{(*)}$, $Λ_{c}D^{(*)}$, along with their bottom analogues. Considering both the $S$\--{}$D$ wave mixing effect and the recoil corrections, we find that recoil corrections, working against the stability of bound states in certain isospin-singlet channels, which cannot be ignored. For the $Ξ_{c}\bar{D}$ and $Ξ_{c}D$ systems with $I(J^P)=0(\frac{1}{2}^{-})$, the $Ξ_{c}\bar{D}^{*}$ and $Ξ_{c}D^{*}$ systems, as well as their bottom counterparts, with $I(J^P)=0(\frac{1}{2}^{-})$ and $0(\frac{3}{2}^{-})$, and the $Λ_{b}\bar{B}^{*}$ system with $I(J^P)=\frac{1}{2}(\frac{1}{2}^{-})$ and $\frac{1}{2}(\frac{3}{2}^{-})$, although the bound state solution can be found both with and without considering the recoil corrections, the inclusion of recoil corrections weakens the attraction of the molecules. This phenomenon arising from recoil corrections is especially prominent in the $Ξ_{c}\bar{D}^{*}$ and $Ξ_{c}D^{*}$ systems.

hep-ph↗

arXiv2026

On the number of non-cyclic subgroups of finite p-groups

Let $G$ be a finite $p$-group and $δ(G)$ denote the number of all non-cyclic subgroups of $G$. In this paper, an upper bound for $δ(G)$ is obtained. Furthermore, we prove that $δ(G)\leq δ(M_p(1, 1, 1) \times C_{p}^{n-3})$ (if $p=2$, then $δ(G)\leq δ(D_8\times C_{2}^{n-3})$), for any non-elementary abelian $p$-group $G$ of order $p^n$.

math.GR↗

arXiv2026

Giant Full-Space Anomalous Hall Effect Induced by Non-Coplanar Spin State in Mn-Rich Mn3Sn

Antiferromagnets are promising candidates for next-generation spintronic devices owing to their negligible stray fields and ultrafast spin dynamics. The noncollinear antiferromagnet $\mathrm{Mn}_{3}\mathrm{Sn}$ exhibits a large anomalous Hall effect (AHE). However, its specific noncollinear spin configuration leads to the forbiddance of the anomalous Hall conductivity from the (0001) basal plane, $σ_{(0001)}$, limiting practical applications. Here, using first-principles density functional theory, we demonstrate that Mn enrichment in $\mathrm{Mn}_{3}\mathrm{Sn}$ drives a magnetic transition from the coplanar $120^\circ$ spin configuration to a non-coplanar state with moments tilted toward the $c$-axis. This transition is primarily mediated by four-spin ring exchange interaction in the local triangular lattice, which breaks the time-reversal symmetry and generates a giant intrinsic anomalous Hall conductivity over the full three-dimensional space in $\mathrm{Mn}_{3}\mathrm{Sn}$. We predict that $σ_{(0001)}$ reaches as high as $\sim\!-468~Ω^{-1}\cdot\mathrm{cm}^{-1}$, and an enhanced $σ_{(01\bar{1}0)}$ of $\sim\!-229~Ω^{-1}\cdot\mathrm{cm}^{-1}$ is expected in light Mn self-doping of $\mathrm{Mn}_{3}\mathrm{Sn}$ ($\mathrm{Mn}_{3.125}\mathrm{Sn}_{0.875}$). Unlike previously reported mechanisms relying on external magnetic fields or strain, our approach exploits intrinsic compositional tuning to stabilize a non-coplanar magnetic ground state for realizing a strong full-space AHE in antiferromagnets, providing another viable pathway toward high-performance, low-power spintronic devices.

cond-mat.mtrl-sci↗

arXiv2026

RAG vs. GraphRAG: A Systematic Evaluation and Key Insights

Retrieval-Augmented Generation (RAG) improves large language models (LLMs) by retrieving relevant information from external sources and has been widely adopted for text-based tasks. For structured data, such as knowledge graphs, Graph Retrieval-Augmented Generation (GraphRAG) retrieves and aggregates information along graph structures. More recently, GraphRAG has been extended to general text settings by organizing unstructured text into graph representations, showing promise for reasoning and grounding. Despite these advances, existing GraphRAG systems for text data are often tailored to specific tasks, datasets, and system designs, resulting in heterogeneous evaluation protocols. Consequently, a systematic understanding of the relative strengths, limitations, and trade-offs between RAG and GraphRAG on widely used text benchmarks remains limited. In this paper, we present a comprehensive benchmark study comparing RAG and GraphRAG on established text-based tasks, including question answering and query-based summarization. We introduce a unified evaluation protocol that standardizes data preprocessing, retrieval configurations, and generation settings, enabling fair and reproducible comparisons. Our results highlight the distinct strengths of RAG and GraphRAG across different tasks and evaluation perspectives. Building on these findings, we explore selection and integration strategies that combine the strengths of both paradigms, leading to consistent performance improvements. We further analyze failure modes, efficiency trade-offs, and evaluation biases, and highlight key considerations for designing and evaluating retrieval-augmented generation systems.

cs.IR↗

arXiv2026

Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphs

Reasoning over structured graphs remains a fundamental challenge for Large Language Models (LLMs), particularly when scaling to large graphs. Existing approaches typically follow the retrieval-augmented generation (RAG) paradigm: first retrieving subgraphs relevant to the query and then generating answers conditioned on the retrieved subgraphs. However, such two-phase pipelines often struggle to faithfully incorporate graph structure, since the generation process is ultimately constrained by the quality and completeness of the retrieved subgraph. Although many advanced retrievers have been proposed recently to mitigate this issue, they are usually tailored to the training graphs and generalize poorly to unseen graphs, which limits their practical applicability. In this work, we propose Reasoning by Exploration (RoE), a novel approach that unifies retrieval and generation by framing reasoning over graphs as a process of graph exploration. At each step, the LLM selects candidate nodes and edges to explore, gradually constructing reasoning paths and generating answers along the way. To enable effective exploration, RoE is trained in two stages: supervised fine-tuning (SFT) on gold reasoning paths, followed by reinforcement learning (RL) to enhance exploration effectiveness and generalization. Experiments on benchmark datasets demonstrate that RoE achieves substantial overall improvements over baselines, while also generalizing effectively to unseen graphs.

cs.IR↗

arXiv2026

Survey of Video Diffusion Models: Foundations, Implementations, and Applications

Recent advances in diffusion models have revolutionized video generation, offering superior temporal consistency and visual quality compared to traditional generative adversarial networks-based approaches. While this emerging field shows tremendous promise in applications, it faces significant challenges in motion consistency, computational efficiency, and ethical considerations. This survey provides a comprehensive review of diffusion-based video generation, examining its evolution, technical foundations, and practical applications. We present a systematic taxonomy of current methodologies, analyze architectural innovations and optimization strategies, and investigate applications across low-level vision tasks such as denoising and super-resolution. Additionally, we explore the synergies between diffusionbased video generation and related domains, including video representation learning, question answering, and retrieval. Compared to the existing surveys (Lei et al., 2024a;b; Melnik et al., 2024; Cao et al., 2023; Xing et al., 2024c) which focus on specific aspects of video generation, such as human video synthesis (Lei et al., 2024a) or long-form content generation (Lei et al., 2024b), our work provides a broader, more updated, and more fine-grained perspective on diffusion-based approaches with a special section for evaluation metrics, industry solutions, and training engineering techniques in video generation. This survey serves as a foundational resource for researchers and practitioners working at the intersection of diffusion models and video generation, providing insights into both the theoretical frameworks and practical implementations that drive this rapidly evolving field. A structured list of related works involved in this survey is also available on https://github.com/Eyeline-Research/Survey-Video-Diffusion.

cs.CV↗

arXiv2026

Wavelet Tree Ensembles for Triangulable Manifolds

We develop unbalanced Haar (UH) wavelet tree ensembles for regression on triangulable manifolds. Given data sampled on a triangulated manifold, we construct UH wavelet trees whose atoms are supported on geodesic triangles and form an orthonormal system in $L^2(μ_n)$, where $μ_n$ is the empirical measure on the sample, which allows us to use UH trees as weak learners in additive ensembles. Our construction extends classical UH wavelet trees from regular Euclidean grids to generic triangulable manifolds while preserving three key properties: (i) orthogonality and exact reconstruction at the sampled locations, (ii) recursive, data-driven partitions adapted to the geometry of the manifold via geodesic triangulations, and (iii) compatibility with optimization-based and Bayesian ensemble building. In Euclidean settings, the framework reduces to standard UH wavelet tree regression and provides a baseline for comparison. We illustrate the method on synthetic regression on the sphere and on climate anomaly fields on a spherical mesh, where UH ensembles on triangulated manifolds substantially outperform classical tree ensembles and non-adaptive mesh-based wavelets. For completeness, we also report results on image denoising on regular grids. A Bayesian variant (RUHWT) provides posterior uncertainty quantification for function estimates on manifolds. Our implementation is available at http://www.github.com/hrluo/WaveletTrees.

stat.ME↗

arXiv2026

AR-LIF: Adaptive reset leaky integrate-and-fire neuron for spiking neural networks

Spiking neural networks offer low energy consumption due to their event-driven nature. Beyond binary spike outputs, their intrinsic floating-point dynamics merit greater attention. Neuronal threshold levels and reset modes critically determine spike count and timing. Hard reset cause information loss, while soft reset apply uniform treatment to neurons. To address these issues, we design an adaptive reset neuron that establishes relationships between inputs, outputs, and reset, while integrating a simple yet effective threshold adjustment strategy. Experimental results demonstrate that our method achieves excellent performance while maintaining lower energy consumption. In particular, it attains state-of-the-art accuracy on Tiny-ImageNet and CIFAR10-DVS. Codes are available at https://github.com/2ephyrus/AR-LIF.

cs.NE↗

arXiv2026

Interference-governed electromagnetic-thermal coupling and heat transport in pulse EUV-irradiated multilayer nanofilms

Mo-Si multilayer mirrors are central to extreme ultraviolet lithography, where nanoscale optical interference and heat accumulation together constrain reflectivity and operational stability. Here we develop an analytical electromagnetic-thermal coupling model that directly links transfer-matrix-based interference-controlled energy deposition with transient heat conduction in EUV-irradiated multilayers. The model reveals a fundamental trade-off whereby increasing the multilayer period number enhances reflectivity but simultaneously elevates temperature by impeding heat dissipation. Interference-driven volumetric absorption further gives rise to pronounced axial temperature gradients and a post-pulse downward migration of the heat-flux maximum, a delayed-heating effect inaccessible to conventional surface-flux-based models. Systematic analysis establishes scaling laws connecting interfacial thermal resistance, beam size, and incident energy density to thermal confinement and temperature rise. By incorporating interfacial compaction kinetics, the model enables a quantitative assessment of mirror lifetime. This work offers a theoretical tool for thermal-optical co-design of multilayer nanostructures including EUV mirrors under pulsed irradiation across a wide spectral range.

physics.app-ph↗

arXiv2026

PEAR: Planner-Executor Agent Robustness Benchmark

Large Language Model (LLM)-based Multi-Agent Systems (MAS) have emerged as a powerful paradigm for tackling complex, multi-step tasks across diverse domains. However, despite their impressive capabilities, MAS remain susceptible to adversarial manipulation. Existing studies typically examine isolated attack surfaces or specific scenarios, leaving a lack of holistic understanding of MAS vulnerabilities. To bridge this gap, we introduce PEAR, a benchmark for systematically evaluating both the utility and vulnerability of planner-executor MAS. While compatible with various MAS architectures, our benchmark focuses on the planner-executor structure, which is a practical and widely adopted design. Through extensive experiments, we find that (1) a weak planner degrades overall clean task performance more severely than a weak executor; (2) while a memory module is essential for the planner, having a memory module for the executor does not impact the clean task performance; (3) there exists a trade-off between task performance and robustness; and (4) attacks targeting the planner are particularly effective at misleading the system. These findings offer actionable insights for enhancing the robustness of MAS and lay the groundwork for principled defenses in multi-agent settings.

cs.LG↗

arXiv2026

FlexiVoice: Enabling Flexible Style Control in Zero-Shot TTS with Natural Language Instructions

This study proposes FlexiVoice, a text-to-speech (TTS) synthesis system capable of flexible style control with zero-shot voice cloning. The speaking style is controlled by a natural-language instruction and the voice timbre is provided by a speech reference in zero-shot manner. FlexiVoice is built with an LLM core, which takes text as input, and also takes an optional natural language instruction and an optional speech reference to control style and timbre, respectively. FlexiVoice is equipped with a novel Progressive Post-Training (PPT) scheme that progressively unlocks accurate and flexible controllability. In particular, it first employs Direct Preference Optimization (DPO) to enable FlexiVoice to accurately follow both natural language instruction and speech reference simultaneously. It then uses a multi-objective Group Relative Policy Optimization (GRPO) to disentangle style instruction, reference timbre, and textual content. Finally, it adapts instruction GRPO for more advanced instruction following. Experimental results show that FlexiVoice surpasses competing baselines and demonstrates strong capability in decoupling control factors. Human evaluations further confirm its naturalness, controllability, and robustness. Audio samples are available at https://flexi-voice.github.io.

cs.SD↗

arXiv2025

Distributional Evaluation of Generative Models via Relative Density Ratio

We propose a function-valued evaluation metric for generative models based on the relative density ratio (RDR) designed to characterize distributional differences between real and generated samples. As an evaluation metric, the RDR function preserves $ϕ$-divergence between two distributions, enables sample-level evaluation that facilitates downstream investigations of feature-specific distributional differences, and has a bounded range that affords clear interpretability and numerical stability. Function estimation of the RDR is achieved efficiently through optimization on the variational form of $ϕ$-divergence. We provide theoretical convergence rate guarantees for general estimators based on M-estimator theory, as well as the convergence rate of neural network-based estimators when the true ratio is in the anisotropic Besov space. We demonstrate the power of the proposed RDR-based evaluation through numerical experiments on MNIST, CelebA64, and the American Gut project microbiome data. We show that the estimated RDR enables not only effective overall comparison of competing generative models, but also a convenient way to reveal the underlying nature of goodness-of-fit. This enables one to assess support overlap, coverage, and fidelity while pinpointing regions of the sample space where generators concentrate and revealing the features that drive the most salient distributional differences.

stat.ME↗

arXiv2025

Improving Low-Latency Learning Performance in Spiking Neural Networks via a Change-Perceptive Dendrite-Soma-Axon Neuron

Spiking neurons, the fundamental information processing units of Spiking Neural Networks (SNNs), have the all-or-zero information output form that allows SNNs to be more energy-efficient compared to Artificial Neural Networks (ANNs). However, the hard reset mechanism employed in spiking neurons leads to information degradation due to its uniform handling of diverse membrane potentials. Furthermore, the utilization of overly simplified neuron models that disregard the intricate biological structures inherently impedes the network's capacity to accurately simulate the actual potential transmission process. To address these issues, we propose a dendrite-soma-axon (DSA) neuron employing the soft reset strategy, in conjunction with a potential change-based perception mechanism, culminating in the change-perceptive dendrite-soma-axon (CP-DSA) neuron. Our model contains multiple learnable parameters that expand the representation space of neurons. The change-perceptive (CP) mechanism enables our model to achieve competitive performance in short time steps utilizing the difference information of adjacent time steps. Rigorous theoretical analysis is provided to demonstrate the efficacy of the CP-DSA model and the functional characteristics of its internal parameters. Furthermore, extensive experiments conducted on various datasets substantiate the significant advantages of the CP-DSA model over state-of-the-art approaches.

cs.NE↗

arXiv2025

Partially Bayes p-values for large scale inference

We seek to conduct statistical inference for a large collection of primary parameters, each with its own nuisance parameters. Our approach is partially Bayesian, in that we treat the primary parameters as fixed while we model the nuisance parameters as random and drawn from an unknown distribution which we endow with a nonparametric prior. We compute partially Bayes p-values by conditioning on nuisance parameter statistics, that is, statistics that are ancillary for the primary parameters and informative about the nuisance parameters. The proposed p-values have a Bayesian interpretation as tail areas computed with respect to the posterior distribution of the nuisance parameters. Similarly to the conditional predictive p-values of Bayarri and Berger, the partially Bayes p-values avoid double use of the data (unlike posterior predictive p-values). A key ingredient of our approach is that we model nuisance parameters hierarchically across problems; the sharing of information across problems leads to improved calibration. We illustrate the proposed partially Bayes p-values in two applications: the normal means problem with unknown variances and a location-scale model with unknown distribution shape. We model the scales via Dirichlet processes in both examples and the distribution shape via Pólya trees in the second. Our proposed partially Bayes p-values increase power and calibration compared to purely frequentist alternatives.

stat.ME↗

arXiv2025

Stable high-charge vortex dissipative solitons in azimuthally modulated waveguide arrays with localized gain

We study the existence and dynamical properties of vortex solitons in Kerr media supported by azimuthally modulated waveguide lattices with localized gain and nonlinear loss. In this dissipative system, we find that the accessible topological charge of vortex solitons is strongly determined by the number of waveguide channels, with higher-order charges requiring progressively larger arrays. Power curves of vortex solitons with different charges exhibit clear separation in large arrays but become less distinguishable in smaller ones. Furthermore, these robust vortex solitons can be excited with nearly vanishing power thresholds, and higher-charge vortices display enhanced propagation stability compared with lower-charge states. These findings expand the family of dissipative vortex solitons supported by waveguide lattices and provide a route to the realization of stable high-symmetry vortex states.

physics.optics↗