Searcharxiv⌕ Search

arXiv subjects

Xingyu Wu

Publications and source records attributed to Xingyu Wu.

At least 19 recordsLinked to original sources
arXiv2026

Diverge-Merge Formation and MAC Control in Structured Airspace

The rapid scaling of advanced air mobility (AAM) makes corridor-based structured airspace a promising infrastructure for high-density unmanned aerial vehicle (UAV) traffic. Formation flight can improve corridor capacity by suppressing shockwave propagation, but rigid formations become inefficient or unsafe during ramp branching, merging, and congestion. To address this problem, this paper proposes a task-driven diverge-merge control framework for UAV formations in structured airspace. At the beginning, a corridor-ramp branching structured airspace model is established to characterize the traffic dynamics and spatial constraints. Building upon this, a fast task-driven clustering mechanism integrates spatial connectivity, flight intent, and aerial task interactions to enable real-time diverge and merge for ramp branching and traffic reshaping. To make the diverge-merge reconfigurations executable at the media access control (MAC) layer of the formation, a cluster-aware distributed time division multiple access (CAD-TDMA) protocol is further designed. It protects intra-cluster control synchronization while conservatively reusing low-risk inter-cluster slots. Simulation results show that the proposed diverge-merge algorithm maintains near-zero geometrical misclassification under severe physical overlapping and congestion. With the formation diverge-merge traces, CAD-TDMA achieves the best delay--loss--throughput tradeoff over fixed TDMA and WiFi MAC. It shows that the proposed formation control framework can jointly support real-time formation reconfiguration and reliable communication in corridor-ramp structured airspace.

cs.NI↗
arXiv2026

How to Guide LLM Generation: Dual-Surrogate Guided Search for Automated Heuristic Design

Large language models (LLMs) have made automated heuristic design (AHD) increasingly practical by generating executable heuristic code from task descriptions and evaluator feedback. Yet under a limited query and evaluation budget, search efficiency depends critically on a pre-generation decision. Before each LLM query and black-box evaluation, the system must choose which archived heuristics to reuse as parents and which generation operator should transform them. Existing methods typically choose such actions with predefined rules, leaving the expected outcome of each concrete operator-parent action only indirectly modeled. Therefore, we propose \emph{\fullmethod{}} (\method{}), a surrogate-guided action-selection module for operator-parent selection in LLM-based AHD. \method{} guides the LLM code-generation process by scoring pre-generation actions with two complementary surrogates. Specifically, a transition surrogate is proposed to predict the latent distribution of the child representation induced by an operator-parent action, while an instance-conditioned utility surrogate is proposed to estimate the expected performance of sampled child latents. Moreover, we propose an uncertainty-aware acquisition rule that combines predicted utility, utility uncertainty, and transition uncertainty to select the next LLM generation action. Across a diverse heuristic-design suite, \method{} is competitive with strong LLM-AHD baselines, and ablation and action-selection analyses suggest that its behavior goes beyond simple archive ranking or fixed operator preferences.

cs.NE↗
arXiv2026

Semantics-Aware Bilevel Co-Evolution: Towards Automated Multicomponent Algorithm Design

LLM-assisted evolutionary search (LES) has emerged as a promising paradigm for automated algorithm design. However, existing methods usually suffer from two inherent limitations when facing the automated design of real-world complex algorithms that usually consist of multiple components. The first limitation is that they either focus on modifying entire algorithms, making it difficult to reuse high-quality components, or concentrate on component refinement within a limited set of predefined multicomponent configurations. The second limitation is the insufficient explicit modeling and exploitation of algorithm semantics. These limitations severely degrade search efficiency and hinder effective exploration of complex design spaces. Therefore, this paper proposes STABLE (Semantics-Aware Bilevel Co-Evolution), an LES method purpose-built for automated multicomponent algorithm design that introduces structural algorithm formulation and semantics-driven evolution. In STABLE, complex algorithms are organized into hierarchical and modular architectures rooted in domain knowledge, aligning the search space with their intrinsic compositional traits. Based on this structured algorithm formulation, STABLE simultaneously optimizes high-level multicomponent configurations and low-level functional components, enabling coordinated cross-level updates while maintaining suitable granularities for design space exploration. At each level, STABLE establishes a multi-faceted semantic model to assist LLMs in capturing structural correlations, functional compatibilities, and inherent rationalities among algorithm components. This semantic model serves as the core guidance for evolutionary search, enabling principled algorithm generation and algorithm evaluation. Extensive experiments demonstrate that STABLE outperform both human-designed baselines and those from advanced LES methods.

cs.NE↗
arXiv2026

Towards Adaptive Continual Model Merging via Manifold-Aware Expert Evolution

Continual Model Merging (CMM) sequentially integrates task-specific models into a unified architecture without intensive retraining. However, existing CMM methods are hindered by a fundamental saturation-redundancy dilemma: backbone-centric approaches face parameter saturation and representation interference within fixed capacities, whereas Mixture-of-Experts (MoE) variants resort to indiscriminate expansion, incurring expert redundancy and a routing bottleneck reliant on additional data-driven optimization. To resolve these challenges, we propose MADE-IT (Manifold-Aware Dynamic Expert Evolution and Implicit rouTing), an adaptive CMM method that orchestrates expert management and activation by grounding intrinsic expert representations in manifold geometry. We introduce a projection-based subspace affinity metric coupled with a distribution-aware adaptive threshold mechanism to guide autonomous expert evolution, harmonizing diversity with architectural parsimony. Furthermore, to bypass parameterized gating networks, we design a data-free and training-free implicit routing mechanism that activates experts via feature-subspace alignment. Extensive experiments demonstrate that MADE-IT consistently outperforms strong baselines in accuracy and robustness across long-horizon and shuffled task sequences, while significantly pruning redundant experts, particularly within generic modules and early layers.

cs.LG↗
arXiv2026

VecFormer: Towards Efficient and Generalizable Graph Transformer with Graph Token Attention

Graph Transformer has demonstrated impressive capabilities in the field of graph representation learning. However, existing approaches face two critical challenges: (1) most models suffer from exponentially increasing computational complexity, making it difficult to scale to large graphs; (2) attention mechanisms based on node-level operations limit the flexibility of the model and result in poor generalization performance in out-of-distribution (OOD) scenarios. To address these issues, we propose \textbf{VecFormer} (the \textbf{Vec}tor Quantized Graph Trans\textbf{former}), an efficient and highly generalizable model for node classification, particularly under OOD settings. VecFormer adopts a two-stage training paradigm. In the first stage, two codebooks are used to reconstruct the node features and the graph structure, aiming to learn the rich semantic \texttt{Graph Codes}. In the second stage, attention mechanisms are performed at the \texttt{Graph Token} level based on the transformed cross codebook, reducing computational complexity while enhancing the model's generalization capability. Extensive experiments on datasets of various sizes demonstrate that VecFormer outperforms the existing Graph Transformer in both performance and speed.

cs.LG↗
arXiv2026

Fine-Grained Model Merging via Modular Expert Recombination

Model merging constructs versatile models by integrating task-specific models without requiring labeled data or expensive joint retraining. Although recent methods improve adaptability to heterogeneous tasks by generating customized merged models for each instance, they face two critical limitations. First, the instance-specific merged models lack reusability, restricting the exploitation of high-quality merging configurations and efficient batch inference. Second, these methods treat each task-specific model as a monolithic whole, overlooking the diverse mergeability of homologous components such as attention and multilayer perceptron layers, and the differing merging sensitivities across components. To address these limitations, we propose MERGE (\underline{M}odular \underline{E}xpert \underline{R}ecombination for fine-\underline{G}rained m\underline{E}rging), a method that enables component-wise model merging and input-aware, on-demand module recombination at inference. MERGE formulates component-wise merging as a bi-objective optimization problem that balances cross-task performance and storage efficiency, and develops a surrogate-assisted evolutionary algorithm to efficiently identify Pareto-optimal merging configurations. These high-quality configurations underpin a reusable modular expert library, from which a lightweight routing network dynamically activates and recombines modular experts to assemble input-specific models and enable efficient inference under storage constraints. Extensive experiments across various model scales, task types, and fine-tuning strategies demonstrate that MERGE consistently outperforms strong baselines and generalizes effectively.

cs.LG↗
arXiv2025

High-Resolution Sensing via Quantum States Discrimination

High-resolution sensing plays a significant role in scientific research and industrial production, but the practical implementation is constrained by the physical mechanisms of the sensors. To address the critical limitation, we propose a high-resolution sensing approach based on quantum state discrimination. Distinct from conventional strategies, the proposed approach constructs measurement operators in the orthogonal complement space rather than eigenspace of the eigenstate, thereby notably improving the discriminability among quantum states. Moreover, the experimental results via an optical microcavity demonstrate a potential sensing resolution of 4 $\times$ 10\textsuperscript{-6} \degree C and 18 p$\epsilon$ respectively for temperature and strain, and further verify the feasibility of simultaneous sensing of the two parameters. This work establishs a universal approach for high-resolution sensing, and may be extended to different sensing platforms across various application scenarios.

physics.optics↗
arXiv2025

Information-Optimal Formation Geometry Design for Multimodal UAV Cooperative Perception

The efficacy of unmanned aerial vehicle (UAV) swarm cooperative perception fundamentally depends on three-dimensional (3D) formation geometry, which governs target observability and sensor complementarity. In the literature, the exploitation of formation geometry and its impact on UAV sensing have rarely been studied, which can significantly degrade multimodal cooperative perception in scenarios where heterogeneous payloads (vision cameras and LiDAR) should be geometrically arranged to exploit their complementary strengths while managing communication interference and hardware budgets. To bridge this critical gap, targeting the active tracking phase where a prior target estimate is available, we propose an information-optimal optimization framework that optimizes the allocation of UAVs and multimodal sensors, configures formation geometries, and executes flight control. The UAV-sensor allocation is optimized by the Fisher Information Matrix (FIM) determinant maximization. Under this framework, we introduce an equivalent formation transition strategy that enhances field-of-view (FOV) coverage and reduces dynamic communication interference without compromising perception accuracy. Furthermore, we design a novel Lyapunov-stable flight control scheme with logarithmic potential fields to generate energy-efficient trajectories for formation transitions. Extensive simulations demonstrate that our formation-aware design achieves 25.0\% improvement in FOV coverage, 104.2\% enhancement in communication signal strength, and 84.7\% reduction in energy consumption compared to conventional benchmarks. A high-fidelity Gazebo validation further shows up to 20.2\% gain in perception accuracy over hemispherically sampled formations. These results suggest that task-driven geometric allocation is an important rather than incidental component in next-generation UAV swarm perception systems.

eess.SY↗
arXiv2025

High-sensitivity Optical Microcavity Acoustic Sensor Covering Free Spectral Range

Optical whispering gallery mode microcavity acoustic sensors have emerged significant potential in high-sensitivity acoustic signal detection, but the narrow dynamic range limits the application prospect. To address the challenge, we propose and experimentally demonstrate a high-sensitivity acoustic sensor in optical whispering gallery mode microcavity. The proposed sensor integrates an extended Mach-Zehnder polarization interferometer with postselection, extending the dynamic range to the free spectral range. The sensing regions can be categorized into phase-drastic and phase-enhanced regions, both of which yield an optimal acoustic response that surpasses traditional transmission method. Experiment results demonstrate improvements of 57.87 dB in detection sensitivity and 26 times in minimal detectable acoustic pressure over the transmission method. Moreover, the application of coherent state and heterodyne detection can enhance response amplitude, further improving the detection sensitivity. Given the wide application range for acoustic dispersion and dissipation response, as well as the performance advantages of high sensitivity and wide dynamic range, the proposed WGM sensor offers a promising solution for acoustic sensing. Potentially, the structural design may be adaptable to other application scenarios involving time-varying signals through optical microcavity sensing.

physics.optics↗
arXiv2025

Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models

Large language models (LLMs) have demonstrated remarkable performance in reasoning tasks, where reinforcement learning (RL) serves as a key algorithm for enhancing their reasoning capabilities. Currently, there are two mainstream reward paradigms: model-based rewards and rule-based rewards. However, both approaches suffer from limitations: rule-based rewards lack robustness, while model-based rewards are vulnerable to reward hacking. To address these issues, we propose Cooper(Co-optimizing Policy Model and Reward Model), a RL framework that jointly optimizes both the policy model and the reward model. Cooper leverages the high precision of rule-based rewards when identifying correct responses, and dynamically constructs and selects positive-negative sample pairs for continued training the reward model. This design enhances robustness and mitigates the risk of reward hacking. To further support Cooper, we introduce a hybrid annotation strategy that efficiently and accurately generates training data for the reward model. We also propose a reference-based reward modeling paradigm, where the reward model takes a reference answer as input. Based on this design, we train a reward model named VerifyRM, which achieves higher accuracy on VerifyBench compared to other models of the same size. We conduct reinforcement learning using both VerifyRM and Cooper. Our experiments show that Cooper not only alleviates reward hacking but also improves end-to-end RL performance, for instance, achieving a 0.54% gain in average accuracy on Qwen2.5-1.5B-Instruct. Our findings demonstrate that dynamically updating reward model is an effective way to combat reward hacking, providing a reference for better integrating reward models into RL.

cs.CL↗
arXiv2025

LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization

Large reasoning models have achieved remarkable performance through extended chain-of-thought sequences, yet this computational freedom leads to excessive token generation even for simple problems. We present Length-Adaptive Policy Optimization (LAPO), a novel framework that transforms reasoning length control from an external constraint into an intrinsic model capability. Unlike existing approaches that impose rigid limits or rely on post-hoc interventions, LAPO enables models to internalize an understanding of appropriate reasoning depth through a two-stage reinforcement learning process. In the first stage, models learn natural reasoning patterns by discovering the statistical distribution of successful solution lengths. The second stage leverages these patterns as meta-cognitive guidance, embedding them directly within the model's reasoning context to ensure inference-time flexibility. Experiments on mathematical reasoning benchmarks demonstrate that LAPO reduces token usage by up to 40.9% while improving accuracy by 2.3%. Our analysis reveals that models trained with LAPO develop emergent abilities to allocate computational resources based on problem complexity, achieving efficient reasoning without sacrificing quality.

cs.AI↗
arXiv2025

Hierarchical Budget Policy Optimization for Adaptive Reasoning

Large reasoning models achieve remarkable performance through extensive chain-of-thought generation, yet they suffer from a critical inefficiency: applying uniformly extensive reasoning regardless of problem complexity. We present Hierarchical Budget Policy Optimization (HBPO), a reinforcement learning framework that enables models to learn problem-specific reasoning depths without sacrificing capability. Unlike existing approaches that impose rigid constraints or rely on discrete mode selection, HBPO partitions the exploration space into budget-constrained hierarchies (512-2560 tokens), each with differentiated reward structures that preserve both efficiency incentives and reasoning capabilities. This design addresses a fundamental challenge in efficient reasoning training: traditional length penalties systematically bias models away from necessary long reasoning paths, causing exploration space collapse. Through hierarchical sampling and budget-aware rewards, HBPO maintains exploration diversity while teaching models to recognize when extended deliberation is warranted. Extensive experiments demonstrate that HBPO reduces average token usage by up to 60.6% while improving accuracy by 3.14% across four reasoning benchmarks. Most notably, HBPO exhibits emergent adaptive behavior where models automatically adjust reasoning depth based on problem complexity. Our results suggest that reasoning efficiency and capability are not inherently conflicting, and can be simultaneously optimized through appropriately structured hierarchical training that preserves exploration diversity.

cs.AI↗
arXiv2025

When Large Language Models Meet Law: Dual-Lens Taxonomy, Technical Advances, and Ethical Governance

This paper establishes the first comprehensive review of Large Language Models (LLMs) applied within the legal domain. It pioneers an innovative dual lens taxonomy that integrates legal reasoning frameworks and professional ontologies to systematically unify historical research and contemporary breakthroughs. Transformer-based LLMs, which exhibit emergent capabilities such as contextual reasoning and generative argumentation, surmount traditional limitations by dynamically capturing legal semantics and unifying evidence reasoning. Significant progress is documented in task generalization, reasoning formalization, workflow integration, and addressing core challenges in text processing, knowledge integration, and evaluation rigor via technical innovations like sparse attention mechanisms and mixture-of-experts architectures. However, widespread adoption of LLM introduces critical challenges: hallucination, explainability deficits, jurisdictional adaptation difficulties, and ethical asymmetry. This review proposes a novel taxonomy that maps legal roles to NLP subtasks and computationally implements the Toulmin argumentation framework, thus systematizing advances in reasoning, retrieval, prediction, and dispute resolution. It identifies key frontiers including low-resource systems, multimodal evidence integration, and dynamic rebuttal handling. Ultimately, this work provides both a technical roadmap for researchers and a conceptual framework for practitioners navigating the algorithmic future, laying a robust foundation for the next era of legal artificial intelligence. We have created a GitHub repository to index the relevant papers: https://github.com/Kilimajaro/LLMs_Meet_Law.

cs.CL↗
arXiv2025

SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation

Large Language Models (LLMs) and Multimodal LLMs have shown promising capabilities for SVG processing, yet existing benchmarks suffer from limited real-world coverage, lack of complexity stratification, and fragmented evaluation paradigms. We introduce SVGenius, a comprehensive benchmark comprising 2,377 queries across three progressive dimensions: understanding, editing, and generation. Built on real-world data from 24 application domains with systematic complexity stratification, SVGenius evaluates models through 8 task categories and 18 metrics. We assess 22 mainstream models spanning different scales, architectures, training paradigms, and accessibility levels. Our analysis reveals that while proprietary models significantly outperform open-source counterparts, all models exhibit systematic performance degradation with increasing complexity, indicating fundamental limitations in current approaches; however, reasoning-enhanced training proves more effective than pure scaling for overcoming these limitations, though style transfer remains the most challenging capability across all model types. SVGenius establishes the first systematic evaluation framework for SVG processing, providing crucial insights for developing more capable vector graphics models and advancing automated graphic design applications. Appendix and supplementary materials (including all data and code) are available at https://zju-real.github.io/SVGenius.

cs.CV↗
arXiv2025

LLM Cannot Discover Causality, and Should Be Restricted to Non-Decisional Support in Causal Discovery

This paper critically re-evaluates LLMs' role in causal discovery and argues against their direct involvement in determining causal relationships. We demonstrate that LLMs' autoregressive, correlation-driven modeling inherently lacks the theoretical grounding for causal reasoning and introduces unreliability when used as priors in causal discovery algorithms. Through empirical studies, we expose the limitations of existing LLM-based methods and reveal that deliberate prompt engineering (e.g., injecting ground-truth knowledge) could overstate their performance, helping to explain the consistently favorable results reported in much of the current literature. Based on these findings, we strictly confined LLMs' role to a non-decisional auxiliary capacity: LLMs should not participate in determining the existence or directionality of causal relationships, but can assist the search process for causal graphs (e.g., LLM-based heuristic search). Experiments across various settings confirm that, by strictly isolating LLMs from causal decision-making, LLM-guided heuristic search can accelerate the convergence and outperform both traditional and LLM-based methods in causal structure learning. We conclude with a call for the community to shift focus from naively applying LLMs to developing specialized models and training method that respect the core principles of causal discovery.

cs.LG↗
arXiv2025

Diversity-Aware Policy Optimization for Large Language Model Reasoning

The reasoning capabilities of large language models (LLMs) have advanced rapidly, particularly following the release of DeepSeek R1, which has inspired a surge of research into data quality and reinforcement learning (RL) algorithms. Despite the pivotal role diversity plays in RL, its influence on LLM reasoning remains largely underexplored. To bridge this gap, this work presents a systematic investigation into the impact of diversity in RL-based training for LLM reasoning, and proposes a novel diversity-aware policy optimization method. Across evaluations on 12 LLMs, we observe a strong positive correlation between the solution diversity and Potential at k (a novel metric quantifying an LLM's reasoning potential) in high-performing models. This finding motivates our method to explicitly promote diversity during RL training. Specifically, we design a token-level diversity and reformulate it into a practical objective, then we selectively apply it to positive samples. Integrated into the R1-zero training framework, our method achieves a 3.5 percent average improvement across four mathematical reasoning benchmarks, while generating more diverse and robust solutions.

cs.LG↗
arXiv2025

Semi-Supervised Multi-Label Feature Selection with Consistent Sparse Graph Learning

In practical domains, high-dimensional data are usually associated with diverse semantic labels, whereas traditional feature selection methods are designed for single-label data. Moreover, existing multi-label methods encounter two main challenges in semi-supervised scenarios: (1). Most semi-supervised methods fail to evaluate the label correlations without enough labeled samples, which are the critical information of multi-label feature selection, making label-specific features discarded. (2). The similarity graph structure directly derived from the original feature space is suboptimal for multi-label problems in existing graph-based methods, leading to unreliable soft labels and degraded feature selection performance. To overcome them, we propose a consistent sparse graph learning method for multi-label semi-supervised feature selection (SGMFS), which can enhance the feature selection performance by maintaining space consistency and learning label correlations in semi-supervised scenarios. Specifically, for Challenge (1), SGMFS learns a low-dimensional and independent label subspace from the projected features, which can compatibly cross multiple labels and effectively achieve the label correlations. For Challenge (2), instead of constructing a fixed similarity graph for semi-supervised learning, SGMFS thoroughly explores the intrinsic structure of the data by performing sparse reconstruction of samples in both the label space and the learned subspace simultaneously. In this way, the similarity graph can be adaptively learned to maintain the consistency between label space and the learned subspace, which can promote propagating proper soft labels for unlabeled samples, facilitating the ultimate feature selection. An effective solution with fast convergence is designed to optimize the objective function. Extensive experiments validate the superiority of SGMFS.

cs.LG↗
arXiv2025

Precise Standard-Model predictions for polarised Z-boson pair production and decay at the LHC

Providing accurate theoretical predictions in the Standard Model for processes with polarised electroweak bosons is crucial to understand more in-depth the electroweak-symmetry breaking mechanism and to enhance the sensitivity to potential new-physics effects. Motivated by the rapidly increasing number of polarisation analyses of di-boson processes with LHC data, we carry out a comprehensive study of the inclusive production of two polarised Z bosons in the decay channel with four charged leptons. We perform a detailed comparison of fixed-order predictions obtained with various Monte Carlo programs which rely on different signal-definition strategies, assessing non-resonant and interference effects by contrasting polarised results with unpolarised and full off-shell ones. For the first time, we accomplish the combination of NNLO QCD and NLO EW corrections, setting the new state-of-the-art perturbative accuracy for polarised Z-boson pairs at the LHC. The impact of parton-shower matching and multi-jet merging is investigated by scrutinising calculations obtained with event generators that are typically used in experimental analyses. Integrated and differential results are discussed in a realistic fiducial setup and compared to publicly available ATLAS results.

hep-ph↗