arXiv subjects

Yan Lyu

Publications and source records attributed to Yan Lyu.

At least 19 recordsLinked to original sources

arXiv2026

Semantic Signal-Assisted Inspection and Recovery Allocation in Reverse Logistics

Reverse-logistics operators often decide how to inspect and route returned assets before their condition is fully observed, while full inspection consumes scarce labor. Semantic Signal-Assisted Decision Support converts return notes into a condition factor and a signal-quality score that guide inspection depth and recovery allocation under shared labor capacity. We evaluate the framework in three synthetic benchmark scenarios spanning information technology decommissioning, aircraft maintenance, and consumer-electronics returns. Across 30 paired simulation seeds, the keyword implementation improves net recovery value relative to a structured-feature comparator with noisy full inspection while reducing inspection cost in all three scenarios. A risk-blind comparator that skips inspection altogether still records higher value under the benchmark's purely economic objective. At matched inspection cost, score-guided targeting adds 53.9 thousand United States dollars per batch in the aircraft scenario but has little economic effect in the other two configurations; phrase and large language model extractors provide further gains in the aircraft scenario. These results show how narrative evidence can support inspection allocation before recovery decisions are made.

cs.AI↗

arXiv2026

DACRI: Decision-Aware Causal Intervention Ranking for Critical Supply Chains

Detecting or attributing a supply-chain disruption is not the same as selecting the intervention that maximizes recoverable net value. We present CriticalSCM-Bench v1, a controlled synthetic benchmark with causal ground truth, paired factual/counterfactual rollouts, and an explicit net-value objective. Relative to a full-information train-selected static benchmark, LambdaMART improves median normalized net value by 5.7--16.2\%, with paired statistical support on the semiconductor and critical-material archetypes but not on digital infrastructure. On digital infrastructure, a domain-informed constant-buffer policy remains stronger, showing that greater model complexity is not uniformly justified. Across partial and delayed settings, LambdaMART retains 33--75\% of full-clamp value. Stress tests further show that intervention fidelity, timing, cost, and held-out disruptions can alter policy ordering. Critical materials show the weakest out-of-distribution retention. Separately, a guarded explanation study over 540 generations preserves every fixed intervention decision after deterministic validation and template fallback, although exact wording remains unstable. Within this controlled setting, the results identify regimes in which adaptive ranking adds value and those in which simpler structural policies remain preferable.

cs.LG↗

arXiv2026

GeoTopoDiff: Learning Geometry--Topology Graph Priors through Boundary-Constrained Mixed Diffusion for Sparse-Slice 3D Porous Reconstruction

Diffusion-based voxel prior modelling is challenging for the reconstruction of large-scale 3D porous microstructures. Due to the demanding requirements for simultaneously modelling both the continuous pore morphology and the discrete pore-throat topology, the diffusion models require fully observed CT scans to provide topology-faithful priors, which results in an inherent trade-off among throughput, topological fidelity, and field of view in practical industrial applications. We propose GeoTopoDiff, a graph diffusion-based framework for reconstructing 3D porous microstructures from sparse CT slices. GeoTopoDiff transfers the learning of diffusion priors from a voxel-based space to a mixed graph state space, which simultaneously encompasses continuous pore geometry and discrete pore-throat topology. A topology-aware partial graph prior from sparsely observed CT slices is introduced to constrain the reverse denoising process. Experiments on anisotropic PTFE and Fontainebleau sandstone show that GeoTopoDiff reduces morphology-related errors by 19.8% and topology-sensitive transport errors by 36.5% on average. Our findings suggest that the mixed graph state space promotes the diffusion denoising process to reduce posterior uncertainty under a sparse observations. All models and code have been made publicly available to facilitate the exploration of diffusion models in the field of 3D porous microstructures simulation.

cs.CV↗

arXiv2026

One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control

Industrial anomaly detection (AD) is characterized by an abundance of normal images but a scarcity of anomalous ones. Although numerous few-shot anomaly synthesis methods have been proposed to augment anomalous data for downstream AD tasks, most existing approaches require time-consuming training and struggle to learn distributions that are faithful to real anomalies, thereby restricting the efficacy of AD models trained on such data. To address these limitations, we propose a training-free few-shot anomaly generation method, namely O2MAG, which leverages the self-attention in One reference anomalous image to synthesize More realistic anomalies, supporting effective downstream anomaly detection. Specifically, O2MAG manipulates three parallel diffusion processes via self-attention grafting and incorporates the anomaly mask to mitigate foreground-background query confusion, synthesizing text-guided anomalies that closely adhere to real anomalous distributions. To bridge the semantic gap between the encoded anomaly text prompts and the true anomaly semantics, Anomaly-Guided Optimization is further introduced to align the synthesis process with the target anomalous distribution, steering the generation toward realistic and text-consistent anomalies. Moreover, to mitigate faint anomaly synthesis inside anomaly masks, Dual-Attention Enhancement is adopted during generation to reinforce both self- and cross-attention on masked regions. Extensive experiments validate the effectiveness of O2MAG, demonstrating its superior performance over prior state-of-the-art methods on downstream AD tasks.

cs.CV↗

arXiv2026

$\bar{D}$-meson Nucleon Scattering from Lattice QCD at the Physical Point

We report the first lattice QCD study of the $s$-wave scattering of the $\bar{D}$-meson and the nucleon at the physical point, utilizing (2+1)-flavor configurations generated by the HAL QCD collaboration with a pion mass of $m_\pi\simeq 137$ MeV and a lattice spacing of $a\simeq0.084$ fm. By applying the HAL QCD method to the four-point correlation function of the $\bar{D}N$ system, we obtain a leading-order potential of the derivative expansion of the interaction kernel, which is then used to extract the $s$-wave phase shifts of low-energy $\bar{D}N$ scattering. Both the isospin $I=0$ and $I=1$ channels have a short-range repulsive core and a shallow attractive pocket in the intermediate to long-range region, though the $I=0$ channel is more attractive than the $I=1$ channel. We also observe that the $\bar{D}N$ potential exhibits more attraction than the $KN$ potential, which is its analog in the strange sector. In terms of the $s$-wave phase shifts, the $I=0$ channel shows a weak attractive behavior in the low-energy region with a positive scattering length of $0.246 \pm 0.105 (_{-0.051}^{+0.084})$ fm, whereas the $I=1$ channel shows repulsion with a negative scattering length of $-0.086 \pm 0.050 (_{-0.001}^{+0.037})$ fm. No bound states are found in both isospin channels, indicating the absence of a pentaquark state in the $s$-wave $\bar{D}N$ system.

hep-lat↗

arXiv2026

Refine and Purify: Orthogonal Basis Optimization with Null-Space Denoising for Conditional Representation Learning

Conditional representation learning aims to extract criterion-specific features for customized tasks. Recent studies project universal features onto the conditional feature subspace spanned by an LLM-generated text basis to obtain conditional representations. However, such methods face two key limitations: sensitivity to subspace basis and vulnerability to inter-subspace interference. To address these challenges, we propose OD-CRL, a novel framework integrating Adaptive Orthogonal Basis Optimization (AOBO) and Null-Space Denoising Projection (NSDP). Specifically, AOBO constructs orthogonal semantic bases via singular value decomposition with a curvature-based truncation. NSDP suppresses non-target semantic interference by projecting embeddings onto the null space of irrelevant subspaces. Extensive experiments conducted across customized clustering, customized classification, and customized retrieval tasks demonstrate that OD-CRL achieves a new state-of-the-art performance with superior generalization.

cs.AI↗

arXiv2025

Dense-Jump Flow Matching with Non-Uniform Time Scheduling for Robotic Policies: Mitigating Multi-Step Inference Degradation

Flow matching has emerged as a competitive framework for learning high-quality generative policies in robotics; however, we find that generalisation arises and saturates early along the flow trajectory, in accordance with recent findings in the literature. We further observe that increasing the number of Euler integration steps during inference counter-intuitively and universally degrades policy performance. We attribute this to (i) additional, uniformly spaced integration steps oversample the late-time region, thereby constraining actions towards the training trajectories and reducing generalisation; and (ii) the learned velocity field becoming non-Lipschitz as integration time approaches 1, causing instability. To address these issues, we propose a novel policy that utilises non-uniform time scheduling (e.g., U-shaped) during training, which emphasises both early and late temporal stages to regularise policy training, and a dense-jump integration schedule at inference, which uses a single-step integration to replace the multi-step integration beyond a jump point, to avoid unstable areas around 1. Essentially, our policy is an efficient one-step learner that still pushes forward performance through multi-step integration, yielding up to 23.7% performance gains over state-of-the-art baselines across diverse robotic tasks.

cs.RO↗

arXiv2025

Recent progress on charmed hadron interactions from lattice QCD

Recent years have witnessed rapid progress in charmed hadron physics, driven by numerous experimental discoveries of exotic states such as $T^+_{cc}$ and $P_c$. These findings have highlighted the importance of understanding charmed hadron interactions. With significant advances in theory and computation, lattice QCD has become a reliable tool for studying nonperturbative dynamics of low-energy QCD. In this talk, I review recent lattice QCD studies of charmed hadron interactions, focusing on three representative systems: $D^*$-$D$, $N$-$c\bar c$, and $\Omega_{ccc}$-$\Omega_{ccc}$.

hep-lat↗

arXiv2025

$S$-wave kaon-nucleon interactions from lattice QCD at the physical point

We investigate S-wave kaon-nucleon ($KN$) interactions with strangeness $S=+1$ in lattice QCD using the time-dependent HAL QCD method. Employing the $(2+1)$-flavor gauge configuration with $m_{\pi}\approx 137~\textrm{MeV}$ and $m_{K}\approx 502~\textrm{MeV}$, we calculate the $KN$ potentials at the leading order in the derivative expansion. The potentials in both isospin channels ($I=1$ and $I=0$) exhibit repulsion at short distances, while only the $I=0$ potential has a small attractive pocket at intermediate distances. From these potentials, we compute the phase shifts as well as the low-energy scattering parameters. The obtained phase shifts show no signals corresponding to resonances or bound states in both isospin channels, suggesting the absence of the $\Theta^{+}(1540)$ pentaquark in the S-wave $KN$ systems. The results for $I=0$ suggest that the scattering amplitudes in this channel are dominated by P-wave components rather than S-wave.

hep-lat↗

arXiv2025

Probing Nucleon-$\Omega_{\rm ccc}$Interaction via Lattice QCD at Physical Quark Masses

We study the S-wave interactions between the nucleon ($N$) and the triply charmed Omega baryon ($\Omega_{\mathrm{ccc}}$) using (2+1)-flavor lattice QCD with a physical pion mass ($m_\pi \simeq 137.1$ MeV) on a lattice volume $\simeq (8.1~\mathrm{fm})^3$. The charm quark is implemented with a relativistic heavy-quark action at its physical mass. Employing the time-dependent HAL QCD method, the $N$-$\Omega_{\mathrm{ccc}}$ potentials in the spin-1 ($^3\mathrm{S}_1$) and spin-2 ($^5\mathrm{S}_2$) channels are extracted. In both channels, overall attraction is found with the scattering parameters, $a_0 = 0.56(0.13)\left(^{+0.26}_{-0.03}\right)$ fm and $r_{\mathrm{eff}} = 1.60(0.05)\left(^{+0.04}_{-0.12}\right)$ fm for the $^3\mathrm{S}_1$ channel, and $a_0 = 0.38(0.12)\left(^{+0.25}_{-0.00}\right)$ fm and $r_{\mathrm{eff}} = 2.04(0.10)\left(^{+0.03}_{-0.22}\right)$ fm for the $^5\mathrm{S}_2$ channel, indicating the absence of a dibaryon bound state. The extracted potentials are further decomposed into spin-independent and spin-dependent components. The spin-independent potential is a dominant component and features a short-range attractive core and a long-range attractive tail, while the spin-dependent potential shows short-range attraction (repulsion) in the spin-1 (spin-2) channel. Qualitative comparisons with previous studies of the $N$-$J/\psi$ and $N$-$\Omega_{\rm{sss}}$ systems at $m_\pi \simeq 146$ MeV are provided, emphasizing the role of heavy-hadron chromo-polarizability arising from soft-gluon exchange between the nucleon and flavor-singlet hadrons. The charm quark mass dependence of the $N$-$\Omega_{\rm ccc}$ potential is investigated as well.

hep-lat↗

arXiv2025

UGOD: Uncertainty-Guided Differentiable Opacity and Soft Dropout for Enhanced Sparse-View 3DGS

3D Gaussian Splatting (3DGS) has become a competitive approach for novel view synthesis (NVS) due to its advanced rendering efficiency through 3D Gaussian projection and blending. However, Gaussians are treated equally weighted for rendering in most 3DGS methods, making them prone to overfitting, which is particularly the case in sparse-view scenarios. To address this, we investigate how adaptive weighting of Gaussians affects rendering quality, which is characterised by learned uncertainties proposed. This learned uncertainty serves two key purposes: first, it guides the differentiable update of Gaussian opacity while preserving the 3DGS pipeline integrity; second, the uncertainty undergoes soft differentiable dropout regularisation, which strategically transforms the original uncertainty into continuous drop probabilities that govern the final Gaussian projection and blending process for rendering. Extensive experimental results over widely adopted datasets demonstrate that our method outperforms rivals in sparse-view 3D synthesis, achieving higher quality reconstruction with fewer Gaussians in most datasets compared to existing sparse-view approaches, e.g., compared to DropGaussian, our method achieves 3.27\% PSNR improvements on the MipNeRF 360 dataset.

cs.CV↗

arXiv2025

Decoding Two-Particle States in QCD with Spatial Wavefunctions

A systematic framework for constructing optimized interpolating operators strongly coupled to QCD two-particle states is developed, which is achieved by incorporating inter-hadron spatial wavefunctions. To efficiently implement these operators in lattice QCD, a novel quark smearing technique utilizing noise vectors is proposed. Applied to the $\Omega_{ccc}\Omega_{ccc}$ system, these optimized operators prove superior to combinations of limited plane-wave operators, enabling the resolution of distinct eigenstates separated by only $\sim 5$ MeV near the threshold $2m_{\Omega_{ccc}} \simeq 9700$ MeV. This exceptional resolving power opens new possibilities for studies of a wide range of hadronic systems in QCD.

hep-lat↗

arXiv2025

Wavefunction-based operator optimization for two-hadron systems in lattice QCD

A systematic way to constructing optimized interpolating operators for two-hadron systems is developed by incorporating inter-hadron spatial wavefunctions. The wavefunctions can be obtained from an iterative process with an appropriate initial guess. To implement these operators, a novel quark smearing technique utilizing $Z_3$ noise vectors is proposed, which allows for effectively incorporating inter-hadron spatial wavefunctions at the source without using all-to-all quark propagators. Proof-of-principle application to the $\Omega_{ccc}\Omega_{ccc}$ system using physical-point lattice configurations with a large size $La\simeq8.1$~fm demonstrates that optimized operators outperform combinations of limited plane-wave operators in the variational analysis, enabling clear identification of states around $2m_{\Omega_{ccc}}\simeq 9700$ MeV with the energy gap as narrow as $\sim 5$ MeV. A comparison on correlation functions, effective energies, and HAL QCD potentials between unoptimized operators and optimized operators is given, with a special emphasis on the effects from nearby elastic scattering states. Potential applicability of the optimized operator to various two-hadron systems and its relation to the variational method are also discussed.

hep-lat↗

arXiv2025

Personalized Federated Learning via Learning Dynamic Graphs

Personalized Federated Learning (PFL) aims to train a personalized model for each client that is tailored to its local data distribution, learning fails to perform well on individual clients due to variations in their local data distributions. Most existing PFL methods focus on personalizing the aggregated global model for each client, neglecting the fundamental aspect of federated learning: the regulation of how client models are aggregated. Additionally, almost all of them overlook the graph structure formed by clients in federated learning. In this paper, we propose a novel method, Personalized Federated Learning with Graph Attention Network (pFedGAT), which captures the latent graph structure between clients and dynamically determines the importance of other clients for each client, enabling fine-grained control over the aggregation process. We evaluate pFedGAT across multiple data distribution scenarios, comparing it with twelve state of the art methods on three datasets: Fashion MNIST, CIFAR-10, and CIFAR-100, and find that it consistently performs well.

cs.LG↗

arXiv2025

$NJ/\psi$ and $N\eta_c$ interactions from lattice QCD

The interaction between nucleon and charmonia ($J/\psi$ and $\eta_c$) is expected to deepen our understanding of various aspects in nonperturbative QCD ranging from the origin of nucleon mass to $J/\psi$ mass modification in nuclear medium and properties of hidden-charm pentaquark states. Here, we present the low-energy $NJ/\psi$ and $N\eta_c$ interactions based on ($2+1$) flavor lattice QCD simulations with nearly physical pion mass $m_\pi=146$ MeV. The interactions, extracted from the spacetime correlations of the nucleon and charmonium system by using the HAL QCD method, are found to be attractive in all distances and manifest a characteristic long-range tail consistent with the two-pion exchange interaction. The resulting scattering lengths are around $0.3$ fm, $0.4$ fm and $0.2$ fm for $NJ/\psi$ with spin $3/2$, with spin $1/2$, and $N\eta_c$, respectively. Our results are orders of magnitude larger than those from the photoproduction experiments assuming the vector meson dominance.

hep-lat↗

arXiv2025

Left-hand cut and the HAL QCD method

We investigate how the left-hand cut (LHC) problem is treated in the HAL QCD method. For this purpose, we first consider the effect of the LHC to the scattering problem in non-relativistic quantum mechanics with potentials. We show that the $S$-matrix or the scattering phase shift obtained from the potential including the Yukawa term ($e^{- m_\pi r}/r$) with the infra-red (IR) cutoff $R$ is well-defined even for the complex momentum $k$ as long as $R$ is finite, and they are compared with those obtained by the analytic continuation without the IR cutoff. In the $R\to\infty$ limit, the phase shift approaches the result from the analytic continuation at ${\rm Im}\, k < m_\pi/2$, while they differ at ${\rm Im}\, k > m_\pi/2$, except $k= k_b$, where $k_b$ is the binding momentum. We also observe that $k_b$ can be correctly obtained even at finite but large $R$. Using knowledge obtained in the non-relativistic quantum mechanics, we present how we should treat the LHC in the HAL QCD potential method.

hep-lat↗

arXiv2024

Nucleon-charmonium interactions from lattice QCD

We present a realistic lattice QCD study on low-energy $N$-$J/\psi$ and $N$-$\eta_c$ interactions based on (2+1) flavor configurations with nearly physical pion mass $m_\pi=146$ MeV. The interactions, extracted from the spacetime correlations of nucleon and charmonium system by using the HAL QCD method, are found to be attractive in all distances and possess a characteristic long-range tail consistent with the two-pion exchange potential. The resulting $S$-wave scattering lengths are $0.30(2)\left(^{+0}_{-2}\right)$ fm, $0.38(4)\left(^{+0}_{-3}\right)$ fm, and $0.21(2)\left(^{+0}_{-1}\right)$ fm for spin-$3/2$ $N$-$J/\psi$, spin-$1/2$ $N$-$J/\psi$, and spin-$1/2$ $N$-$\eta_c$, respectively. Our results are orders of magnitude larger than those from the photoproduction experiments assuming the vector meson dominance. Our findings may provide deeper understanding of the nonperturbative QCD phenomena ranging from the origin of nucleon mass to the in-medium $J/\psi$ mass modification as well as the properties of hidden-charm pentaquark states.

hep-lat↗

arXiv2024

Building Hadron Potentials from Lattice QCD with Deep Neural Networks

In this study, we develop a deep learning method to learn hadronic interactions unsupervisedly from the correlation functions calculated in lattice QCD simulations. We present our approach of using deep neural networks to model the inter-hadron potentials that are learned from Nambu-Bethe-Salpeter (NBS) wave functions. This enables the incorporation of most general forms of potentials into the Schr\"odinger-type equation for detailed analysis of hadronic interactions. Our results include validations with separable potentials, as well as the local and non-local potentials for the $\Omega_{ccc}-\Omega_{ccc}$ system. The neural networks accurately capture the essential features of these interactions, providing a reliable tool for predicting and analyzing hadron scattering properties, potentially bridging the experimental observables and lattice QCD data.

hep-lat↗