arXiv subjects

Kai Li

Publications and source records attributed to Kai Li.

At least 163 records · Page 9Linked to original sources

arXiv2025

Multi-Objective Infeasibility Diagnosis for Routing Problems Using Large Language Models

In real-world routing problems, users often propose conflicting or unreasonable requirements, which result in infeasible optimization models due to overly restrictive or contradictory constraints, leading to an empty feasible solution set. Existing Large Language Model (LLM)-based methods attempt to diagnose infeasible models, but modifying such models often involves multiple potential adjustments that these methods do not consider. To fill this gap, we introduce Multi-Objective Infeasibility Diagnosis (MOID), which combines LLM agents and multi-objective optimization within an automatic routing solver, to provide a set of representative actionable suggestions. Specifically, MOID employs multi-objective optimization to consider both path cost and constraint violation, generating a set of trade-off solutions, each encompassing varying degrees of model adjustments. To extract practical insights from these solutions, MOID utilizes LLM agents to generate a solution analysis function for the infeasible model. This function analyzes these distinct solutions to diagnose the original infeasible model, providing users with diverse diagnostic insights and suggestions. Finally, we compare MOID with several LLM-based methods on 50 types of infeasible routing problems. The results indicate that MOID automatically generates multiple diagnostic suggestions in a single run, providing more practical insights for restoring model feasibility and decision-making compared to existing methods.

cs.AI↗

arXiv2025

Timely Requesting for Time-Critical Content Users in Decentralized F-RANs

With the rising demand for high-rate and timely communications, fog radio access networks (F-RANs) offer a promising solution. This work investigates age of information (AoI) performance in F-RANs, consisting of multiple content users (CUs), enhanced remote radio heads (eRRHs), and content providers (CPs). Time-critical CUs need rapid content updates from CPs but cannot communicate directly with them; instead, eRRHs act as intermediaries. CUs decide whether to request content from a CP and which eRRH to send the request to, while eRRHs decide whether to command CPs to update content or use cached content. We study two general classes of policies: (i) oblivious policies, where decision-making is independent of historical information, and (ii) non-oblivious policies, where decisions are influenced by historical information. First, we obtain closed-form expressions for the average AoI of eRRHs under both policy types. Due to the complexity of calculating closed-form expressions for CUs, we then derive general upper bounds for their average AoI. Next, we identify optimal policies for both types. Under both optimal policies, each CU requests content from each CP at an equal rate, consolidating all requests to a single eRRH when demand is low or resources are limited, and distributing requests evenly among eRRHs when demand is high and resources are ample. eRRHs command content from each CP at an equal rate under an optimal oblivious policy, while prioritize the CP with the highest age under an optimal non-oblivious policy. Our numerical results validate these theoretical findings.

eess.SP↗

arXiv2025

Enhancing Spectrogram Realism in Singing Voice Synthesis via Explicit Bandwidth Extension Prior to Vocoder

This paper addresses the challenge of enhancing the realism of vocoder-generated singing voice audio by mitigating the distinguishable disparities between synthetic and real-life recordings, particularly in high-frequency spectrogram components. Our proposed approach combines two innovations: an explicit linear spectrogram estimation step using denoising diffusion process with DiT-based neural network architecture optimized for time-frequency data, and a redesigned vocoder based on Vocos specialized in handling large linear spectrograms with increased frequency bins. This integrated method can produce audio with high-fidelity spectrograms that are challenging for both human listeners and machine classifiers to differentiate from authentic recordings. Objective and subjective evaluations demonstrate that our streamlined approach maintains high audio quality while achieving this realism. This work presents a substantial advancement in overcoming the limitations of current vocoding techniques, particularly in the context of adversarial attacks on fake spectrogram detection.

cs.SD↗

arXiv2025

Graph Representation-based Model Poisoning on Federated Large Language Models

Federated large language models (FedLLMs) enable powerful generative capabilities within wireless networks while preserving data privacy. Nonetheless, FedLLMs remain vulnerable to model poisoning attacks. This article first reviews recent advancements in model poisoning techniques and existing defense mechanisms for FedLLMs, underscoring critical limitations, especially when dealing with non-IID textual data distributions. Current defense strategies predominantly employ distance or similarity-based outlier detection mechanisms, relying on the assumption that malicious updates markedly differ from benign statistical patterns. However, this assumption becomes inadequate against adaptive adversaries targeting billion-parameter LLMs. The article further investigates graph representation-based model poisoning (GRMP), an emerging attack paradigm that exploits higher-order correlations among benign client gradients to craft malicious updates indistinguishable from legitimate ones. GRMP can effectively circumvent advanced defense systems, causing substantial degradation in model accuracy and overall performance. Moreover, the article outlines a forward-looking research roadmap that emphasizes the necessity of graph-aware secure aggregation methods, specialized vulnerability metrics tailored for FedLLMs, and evaluation frameworks to enhance the robustness of federated language model deployments.

cs.CR↗

arXiv2025

BSN-III: The First Multiband Photometric Study on the Eight Total Eclipse Contact Binary Stars

This study continues our in-depth investigation of total-eclipse W Ursae Majoris-type contact binaries by analyzing eight new systems, complementing our previous work. Multiband $BVR_cI_c$ photometric data were acquired through ground-based observations at an observatory in Mexico, from which new times of minima were determined. Our analysis of orbital period variations using the O-C method revealed that one system shows no long-term variation, four systems exhibit a secular decrease in their orbital periods, and two systems exhibit a secular increase, suggesting mass transfer between the components. Notably, one system displays a cyclic variation with an amplitude of 0.00865 days and a period of 10.49 years, which we attribute to the light travel time effect induced by a tertiary companion, possibly a brown dwarf. We modeled the light curves using the PHOEBE Python code. Six of the target systems required the inclusion of a cold starspot on one of the system's stars due to the asymmetry observed in the maxima of their light curves. Absolute parameters were estimated using the Gaia DR3 parallax method. Using the components' effective temperatures and masses, we classified five of the systems as W-subtype and three as A-subtype. The stellar evolution was illustrated through the mass-radius and mass-luminosity diagrams. Furthermore, we investigated the dynamical stability of two systems with extremely low mass ratios.

astro-ph.SR↗

arXiv2025

Chaos dynamics of charged particles near Gibbons-Maeda-Garfinkle-Horowitz-Strominger black holes

The Gibbons-Maeda-Garfinkle-Horowitz-Strominger (GMGHS) dilatonic black hole, a key solution in low-energy string theory, exhibits previously unexplored chaotic dynamics for charged test particles under electromagnetic influence. While characterizing such chaos necessitates high-precision numerical solutions, our prior research confirms the explicit symplectic algorithm as the optimal numerical integration tool for strongly curved gravitational celestial systems. Leveraging the Hamiltonian formulation of the GMGHS black hole, we develop an optimized fourth-order symplectic algorithm $PR{K_6}4$. This algorithm enables a systematic investigation of the chaotic motion employing four distinct chaos indicators: Shannon entropy, Poincare sections, the maximum Lyapunov exponents, and the Fast Lyapunov indicators. Our results demonstrate a critical dependence of chaos on both electric charge ($Q$, characterized by the Coulomb parameter $Q^*$) and magnetic charge ($Q_m$). Specifically, in electrically charged backgrounds, order-to-chaos transitions arise with increasing $Q$ or decreasing $Q^*$. Conversely, in magnetically charged backgrounds, chaos emerges as $Q_m$ increases. These findings validate Shannon entropy as a robust chaos indicator within relativistic frameworks and provide novel insights on the dynamics of string-theoretic black holes.

hep-th↗

arXiv2025

Learning-Enhanced Variational Regularization for Electrical Impedance Tomography via Calderón's Method

This paper aims to numerically solve the two-dimensional electrical impedance tomography (EIT) with Cauchy data. This inverse problem is highly challenging due to its severe ill-posed nature and strong nonlinearity, which necessitates appropriate regularization strategies. Choosing a regularization approach that effectively incorporates the \textit{a priori} information of the conductivity distribution (or its contrast) is therefore essential. In this work, we propose a deep learning-based method to capture the \textit{a priori} information about the shape and location of the unknown contrast using Calderón's method. The learned \textit{a priori} information is then used to construct the regularization functional of the variational regularization method for solving the inverse problem. The resulting regularized variational problem for EIT reconstruction is then solved using the Gauss-Newton method. Extensive numerical experiments demonstrate that the proposed inversion algorithm achieves accurate reconstruction results, even in high-contrast cases, and exhibits strong generalization capabilities. Additionally, some stability and convergence analysis of the variational regularization method underscores the importance of incorporating \textit{a priori} information about the support of the unknown contrast.

math.NA↗

arXiv2025

DHEvo: Data-Algorithm Based Heuristic Evolution for Generalizable MILP Solving

Primal heuristics play a critical role in improving the efficiency of mixed integer programming (MILP) solvers. As large language models (LLMs) have demonstrated superior code generation abilities, recent MILP works are devoted to leveraging the evolutionary computation approaches with LLMs to generate effective primal heuristics. Although the generated heuristics have achieved better solving performance than the hand-crafted ones with little adaptability, the advantage of current LLM-based methods is limited to few MILP instances in one problem class, as they fail to capture the instance characteristics in the problem class (the MILP instances generated from the same mathematical model are defined as a problem class). Since MILP instances often differ significantly in structure and feature distribution, the neglect of their characteristics in the evolution process results in poor generalization within the same problem class. To overcome this challenge, we propose a data-algorithm co-evolution framework (DHEvo) that iteratively selects representative instances and evolves corresponding heuristics. With the initial instance distribution, we develop an LLM-based multi-agent system to generate data-code pairs simultaneously. These data-code pairs are iteratively refined based on their fitness scores, leading to the identification of the most effective heuristic over the entire problem class. Extensive experiments across diverse MILP benchmarks demonstrate that our approach significantly outperforms both human-designed heuristics and existing LLM-based methods.

cs.NE↗

arXiv2025

Chaotic motion of the charged test particle in a Kerr-MOG black hole with explicit symplectic algorithms

The Kerr-MOG black hole has recently attracted significant research attention and has been extensively applied in various fields. To accurately characterize the long-term dynamical evolution of charged particles around Kerr-MOG black hole, it is essential to utilize numerical algorithms that are high-precision, stable, and capable of preserving the inherent physical structural properties. In this study, we employ explicit symplectic algorithms combined with the Hamiltonian splitting technique to numerically solve the equations of motion for charged particles. Initially, by decomposing the Hamiltonian into five integrable components, three distinct explicit symplectic algorithms ($S2$, $S4$, and $PR{K_6}4$) are constructed. Numerical experiments reveal that the $PR{K_6}4$ algorithm achieves superior accuracy. Subsequently, we utilize Poincaré sections and the Fast Lyapunov Indicator (FLI) to investigate the dynamic evolution of the particle. Our numerical results demonstrate that the energy $E$, angular momentum $L$, magnetic field parameter $β$, black hole spin parameter $a$, and MOG parameter $α$ all significantly influence the particle's motion. Specifically, the chaotic region expands with increases in $E$, $β$, or $α$, but contracts with increases in $a$ or $L$. Furthermore, when any two of these five parameters are varied simultaneously, it becomes evident that $a$ and $L$ predominantly dictate the system's behavior. This study not only offers novel insights into the chaotic dynamics associated with Kerr-MOG black holes but also extends the application of symplectic algorithms in strong gravitational field.

gr-qc↗

arXiv2025

ADPv2: A Hierarchical Histological Tissue Type-Annotated Dataset for Potential Biomarker Discovery of Colorectal Disease

Computational pathology (CoPath) leverages histopathology images to enhance diagnostic precision and reproducibility in clinical pathology. However, publicly available datasets for CoPath that are annotated with extensive histological tissue type (HTT) taxonomies at a granular level remain scarce due to the significant expertise and high annotation costs required. Existing datasets, such as the Atlas of Digital Pathology (ADP), address this by offering diverse HTT annotations generalized to multiple organs, but limit the capability for in-depth studies on specific organ diseases. Building upon this foundation, we introduce ADPv2, a novel dataset focused on gastrointestinal histopathology. Our dataset comprises 20,004 image patches derived from healthy colon biopsy slides, annotated according to a hierarchical taxonomy of 32 distinct HTTs of 3 levels. Furthermore, we train a multilabel representation learning model following a two-stage training procedure on our ADPv2 dataset. We leverage the VMamba architecture and achieving a mean average precision (mAP) of 0.88 in multilabel classification of colon HTTs. Finally, we show that our dataset is capable of an organ-specific in-depth study for potential biomarker discovery by analyzing the model's prediction behavior on tissues affected by different colon diseases, which reveals statistical patterns that confirm the two pathological pathways of colon cancer development. Our dataset is publicly available at https://zenodo.org/records/15307021

eess.IV↗

arXiv2025

Efficient Multi-Task Reinforcement Learning with Cross-Task Policy Guidance

Multi-task reinforcement learning endeavors to efficiently leverage shared information across various tasks, facilitating the simultaneous learning of multiple tasks. Existing approaches primarily focus on parameter sharing with carefully designed network structures or tailored optimization procedures. However, they overlook a direct and complementary way to exploit cross-task similarities: the control policies of tasks already proficient in some skills can provide explicit guidance for unmastered tasks to accelerate skills acquisition. To this end, we present a novel framework called Cross-Task Policy Guidance (CTPG), which trains a guide policy for each task to select the behavior policy interacting with the environment from all tasks' control policies, generating better training trajectories. In addition, we propose two gating mechanisms to improve the learning efficiency of CTPG: one gate filters out control policies that are not beneficial for guidance, while the other gate blocks tasks that do not necessitate guidance. CTPG is a general framework adaptable to existing parameter sharing approaches. Empirical evaluations demonstrate that incorporating CTPG with these approaches significantly enhances performance in manipulation and locomotion benchmarks.

cs.LG↗

arXiv2025

Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning

Offline multi-task reinforcement learning aims to learn a unified policy capable of solving multiple tasks using only pre-collected task-mixed datasets, without requiring any online interaction with the environment. However, it faces significant challenges in effectively sharing knowledge across tasks. Inspired by the efficient knowledge abstraction observed in human learning, we propose Goal-Oriented Skill Abstraction (GO-Skill), a novel approach designed to extract and utilize reusable skills to enhance knowledge transfer and task performance. Our approach uncovers reusable skills through a goal-oriented skill extraction process and leverages vector quantization to construct a discrete skill library. To mitigate class imbalances between broadly applicable and task-specific skills, we introduce a skill enhancement phase to refine the extracted skills. Furthermore, we integrate these skills using hierarchical policy learning, enabling the construction of a high-level policy that dynamically orchestrates discrete skills to accomplish specific tasks. Extensive experiments on diverse robotic manipulation tasks within the MetaWorld benchmark demonstrate the effectiveness and versatility of GO-Skill.

cs.LG↗

arXiv2025

Large-Language-Model Enabled Semantic Communication Systems

Large language models (LLMs) have recently demonstrated state-of-the-art performance across various natural language processing (NLP) tasks, achieving near-human levels in multiple language understanding challenges and aligning closely with the core principles of semantic communication. Inspired by LLMs' advancements in semantic processing, we propose an innovative LLM-enabled semantic communication system framework, named LLM-SC, that applies LLMs directly to the physical layer coding and decoding for the first time. By analyzing the relationship between the training process of LLMs and the optimization objectives of semantic communication, we propose training a semantic encoder through LLMs' tokenizer training and establishing a semantic knowledge base via the LLMs' unsupervised pre-training process. This knowledge base aids in constructing the optimal decoder by providing the prior probability of the transmitted language sequence. Based on this foundation, we derive the optimal decoding criterion for the receiver and introduce the beam search algorithm to further reduce the complexity. Furthermore, we assert that existing LLMs can be employed directly for LLM-SC without additional re-training or fine-tuning. Simulation results demonstrate that LLM-SC outperforms classical DeepSC at signal-to-noise ratios (SNR) exceeding 3 dB, enabling error-free transmission of semantic information under high SNR, which is unattainable by DeepSC. In addition to semantic-level performance, LLM-SC demonstrates compatibility with technical-level performance, achieving approximately 8 dB coding gain for a bit error ratio (BER) of $10^{-3}$ without any channel coding while maintaining the same joint source-channel coding rate as traditional communication systems.

eess.SP↗

arXiv2025

EAGLE: An Efficient Global Attention Lesion Segmentation Model for Hepatic Echinococcosis

Hepatic echinococcosis (HE) is a widespread parasitic disease in underdeveloped pastoral areas with limited medical resources. While CNN-based and Transformer-based models have been widely applied to medical image segmentation, CNNs lack global context modeling due to local receptive fields, and Transformers, though capable of capturing long-range dependencies, are computationally expensive. Recently, state space models (SSMs), such as Mamba, have gained attention for their ability to model long sequences with linear complexity. In this paper, we propose EAGLE, a U-shaped network composed of a Progressive Visual State Space (PVSS) encoder and a Hybrid Visual State Space (HVSS) decoder that work collaboratively to achieve efficient and accurate segmentation of hepatic echinococcosis (HE) lesions. The proposed Convolutional Vision State Space Block (CVSSB) module is designed to fuse local and global features, while the Haar Wavelet Transformation Block (HWTB) module compresses spatial information into the channel dimension to enable lossless downsampling. Due to the lack of publicly available HE datasets, we collected CT slices from 260 patients at a local hospital. Experimental results show that EAGLE achieves state-of-the-art performance with a Dice Similarity Coefficient (DSC) of 89.76%, surpassing MSVM-UNet by 1.61%.

eess.IV↗

arXiv2025

The investigation of 84 TESS totally eclipsing contact binaries

Based on the eclipsing binary catalog provided by \cite{2022ApJS..258...16P}, 84 totally eclipsing contact binaries with stable light curves were selected. The TESS light curves of these 84 targets were studied using the Physics Of Eclipsing Binaries code. The results indicate that there are 18 deep contact binaries, 39 moderate contact binaries, and 27 shallow contact binaries. Among them, 43 targets exhibit the O'Connell effect, which is attributed to the presence of star-spot on the component's surface. 15 targets are low-mass ratio deep contact binaries and may be contact binary merging candidates. Based on the relationship between the period and semi-major axis of contact binaries, their absolute physical parameters such as mass, radius, and luminosity were derived. The evolutionary status of these 84 targets was studied using the mass-luminosity and mass-radius relation diagrams. Their initial masses were also estimated. Our results are compared with those of targets that have been historically studied. Among the 84 targets, 44 targets have been studied before, and 21 of these have mass ratios $q$ that are consistent with historical values within a 10\% difference. For the inconsistent targets, we conducted a detailed investigation and found that the main reasons are poor quality of historical data, or the fact that the machine learning methods used in historical studies might not accurately determine the physical parameters for individual targets.

astro-ph.SR↗

arXiv2025

Segment Concealed Objects with Incomplete Supervision

Incompletely-Supervised Concealed Object Segmentation (ISCOS) involves segmenting objects that seamlessly blend into their surrounding environments, utilizing incompletely annotated data, such as weak and semi-annotations, for model training. This task remains highly challenging due to (1) the limited supervision provided by the incompletely annotated training data, and (2) the difficulty of distinguishing concealed objects from the background, which arises from the intrinsic similarities in concealed scenarios. In this paper, we introduce the first unified method for ISCOS to address these challenges. To tackle the issue of incomplete supervision, we propose a unified mean-teacher framework, SEE, that leverages the vision foundation model, ``\emph{Segment Anything Model (SAM)}'', to generate pseudo-labels using coarse masks produced by the teacher model as prompts. To mitigate the effect of low-quality segmentation masks, we introduce a series of strategies for pseudo-label generation, storage, and supervision. These strategies aim to produce informative pseudo-labels, store the best pseudo-labels generated, and select the most reliable components to guide the student model, thereby ensuring robust network training. Additionally, to tackle the issue of intrinsic similarity, we design a hybrid-granularity feature grouping module that groups features at different granularities and aggregates these results. By clustering similar features, this module promotes segmentation coherence, facilitating more complete segmentation for both single-object and multiple-object images. We validate the effectiveness of our approach across multiple ISCOS tasks, and experimental results demonstrate that our method achieves state-of-the-art performance. Furthermore, SEE can serve as a plug-and-play solution, enhancing the performance of existing models.

cs.CV↗

arXiv2025

Synergizing Reinforcement Learning and Genetic Algorithms for Neural Combinatorial Optimization

Combinatorial optimization problems are notoriously challenging due to their discrete structure and exponentially large solution space. Recent advances in deep reinforcement learning (DRL) have enabled the learning heuristics directly from data. However, DRL methods often suffer from limited exploration and susceptibility to local optima. On the other hand, evolutionary algorithms such as Genetic Algorithms (GAs) exhibit strong global exploration capabilities but are typically sample inefficient and computationally intensive. In this work, we propose the Evolutionary Augmentation Mechanism (EAM), a general and plug-and-play framework that synergizes the learning efficiency of DRL with the global search power of GAs. EAM operates by generating solutions from a learned policy and refining them through domain-specific genetic operations such as crossover and mutation. These evolved solutions are then selectively reinjected into the policy training loop, thereby enhancing exploration and accelerating convergence. We further provide a theoretical analysis that establishes an upper bound on the KL divergence between the evolved solution distribution and the policy distribution, ensuring stable and effective policy updates. EAM is model-agnostic and can be seamlessly integrated with state-of-the-art DRL solvers such as the Attention Model, POMO, and SymNCO. Extensive results on benchmark problems (e.g., TSP, CVRP, PCTSP, and OP) demonstrate that EAM significantly improves both solution quality and training efficiency over competitive baselines.

cs.LG↗

arXiv2025

DrSR: LLM based Scientific Equation Discovery with Dual Reasoning from Data and Experience

Symbolic regression is a fundamental tool for discovering interpretable mathematical expressions from data, with broad applications across scientific and engineering domains. Recently, large language models (LLMs) have demonstrated strong performance in this task, leveraging embedded scientific priors and reasoning capabilities to surpass traditional methods. However, existing LLM-based approaches, such as LLM-SR, often over-rely on internal priors, lacking explicit data understanding and systematic reflection during equation generation. To address these limitations, we propose DrSR (Dual Reasoning Symbolic Regression), a framework that combines data-driven insight with reflective learning to enhance both robustness and discovery capability. Specifically, DrSR guides LLMs to analyze structural relationships (e.g., monotonicity, nonlinearity, and correlation) within the data to generate structured descriptions. Simultaneously, it monitors equation performance and establishes a feedback loop to refine subsequent generations. By integrating data understanding and generation reflection in a closed loop, DrSR enables more efficient exploration of the symbolic expression space. Experiments across interdisciplinary datasets in physics, chemistry, biology, and materials science demonstrate that DrSR substantially improves the valid equation rate and consistently outperforms both classical and recent LLM-based methods in terms of accuracy, generalization, and search efficiency. These results underscore its potential for scientific equation discovery.

cs.LG↗