Searcharxiv⌕ Search

arXiv subjects

Rui Wang

Publications and source records attributed to Rui Wang.

At least 217 records · Page 12Linked to original sources
arXiv2026

Light-Tunable Giant Anomalous Hall Effect in the Flat-Band Magnetic Weyl Semimetal $\mathrm{AlFe_2O_4}$

Achieving a giant anomalous Hall effect (AHE) and enabling its effective tuning are fundamental goals for topological spintronics. Magnetic Weyl semimetals hosting flat bands offer a promising route to maximize the AHE. However, while theoretical models are well-established, realistic material candidates remain scarce. Since the intrinsic anomalous Hall conductivity (AHC) is topologically dictated by the momentum separation ($κ$) between Weyl nodes, actively manipulating remains a key challenge. Here, through comprehensive first-principles calculations, we establish the inverse spinel $\mathrm{AlFe_2O_4}$ as a realistic ferromagnetic half-metallic platform integrating three-dimensional flat bands and Weyl physics. Spin-orbit coupling induces a single pair of Weyl nodes, yielding a giant intrinsic AHC of $398\ \mathrm{S}\cdot\mathrm{cm}^{-1}$. By constructing a symmetry-constrained tight-binding model, we uncover a deterministic relationship between microscopic electronic couplings and the macroscopic AHE. Exploiting this via Floquet engineering with circularly polarized light, we demonstrate that the effective couplings are dynamically suppressed. This optical modulation controllably enlarges $κ$, shortens the topological Fermi arcs, and drives a dramatic, quantitative suppression of the AHC, providing a practical blueprint for ultrafast, light-controlled topological transport.

cond-mat.mtrl-sci↗
arXiv2026

Anomalous Hall Conductivity as an Effective Means of Tracking the Floquet Weyl Nodes in Quasi-One-Dimensional $β$-Bi$_4$I$_4$

While Floquet engineering offers a powerful paradigm for manipulating topological phases, particularly Floquet Weyl semimetals, establishing an experimentally feasible strategy for tracking the dynamic evolution of such states remains a significant challenge. Here, we propose that the anomalous Hall effect (AHE), as a sensitive, all-electrical probe, can be used to track Floquet Weyl nodes. Using first-principles calculations and symmetry analysis on the quasi-one-dimensional material $β$-Bi$_4$I$_4$, we demonstrate that circularly polarized light breaks time-reversal symmetry, driving the system from a trivial insulator into a Floquet Weyl semimetal phase characterized by a nonzero Berry curvature flux. Crucially, by continuously tuning the polarization phase $φ$ of the driving field, we show that the trajectory of the induced Weyl nodes is highly controllable, leading to their migration and eventual annihilation at high-symmetry points. We reveal that the anomalous Hall conductivity maps directly onto this topological evolution, serving as a definitive fingerprint for the generation and dynamics of Weyl nodes.

cond-mat.mtrl-sci↗
arXiv2026

Ultralow-power coherent qubit control using AQFP logic at millikelvin temperatures

Qubit controllers are essential for scaling superconducting quantum processors, but implementing them at the 10 mK stage of a dilution refrigerator remains challenging due to stringent cooling constraints. Here we report an ultralow-power qubit controller using adiabatic quantum-flux-parametron (AQFP) logic, termed an AQFP-multiplexed qubit controller with virtual Z gates (AQFP QC-VZ). The AQFP QC-VZ generates multi-tone microwave pulses for qubit control with an ultralow power dissipation of 111 pW per qubit. By combining microwave and time-division multiplexing, the AQFP QC-VZ enables parallel application of X and virtual Z gates to multiple qubits using only a few control lines from room temperature. We demonstrate coherent single-qubit gates at the 10 mK stage using an AQFP mixer, a core component of the AQFP QC-VZ, without observable degradation in coherence.

quant-ph↗
arXiv2026

Interplay between non-Fermi liquid and non-Hermiticity: A multi-method study of non-Hermitian multichannel Kondo model

Non-Hermitian multichannel Kondo problems host both non-Fermi liquid and non-Hermitian physics, which provide a prototypical model to explore exotic collective quantum phenomena driven by the two different ingredients. Here, we first propose an experimental setup that realizes this model with exact channel symmetry as well as a controllable PT symmetry. Then, we perform a multi-method study of this model, focusing on the low-energy spectrum, the thermodynamic quantities, and the transport properties associated with different fixed points. Using the Bethe ansatz approach, we identify existence of the Yu-Shiba-Rusinov-like state previously found in the non-Hermitian single-channel Kondo model. Then, based on non-Hermitian numerical renormalization group calculations, we reveal clear numerical signatures of the Yu-Shiba-Rusinov state emerging in the relatively strong non-Hermiticity regime of the PT-asymmetric model. Furthermore, our boundary conformal field theory, which is found to be applicable for the PT-symmetric model, uncovers an anomalous temperature dependence of the Kondo conductance, which is beyond conventional Hermitian Kondo systems.

cond-mat.str-el↗
arXiv2026

A Pipelined Collaborative Speculative Decoding Framework for Efficient Edge-Cloud LLM Inference

Recent advancements and widespread adoption of Large Language Models (LLMs) in both industry and academia have catalyzed significant demand for LLM serving. However, traditional cloud services incur high costs, while on-device inference alone faces challenges due to limited resources. Edge-cloud collaboration emerges as a key research direction to combine the strengths of both paradigms, yet efficiently utilizing limited network bandwidth while fully leveraging and balancing the computational capabilities of edge devices and the cloud remains an open problem. To address these challenges, we propose Pipelined Collaborative Speculative Decoding Framework (PicoSpec), a novel, general-purpose, and training-free speculative decoding framework for LLM edge-cloud collaborative inference. We design an asynchronous pipeline that resolves the mutual waiting problem inherent in vanilla speculative decoding within edge collaboration scenarios, which concurrently executes a Small Language Model (SLM) on the edge device and a LLM in the cloud. Meanwhile, to mitigate the significant communication latency caused by transmitting vocabulary distributions, we introduce separate rejection sampling with sparse compression, which completes the rejection sampling with only a one-time cost of transmitting the compressed vocabulary. Experimental results demonstrate that our solution outperforms baseline and existing methods, achieving up to 2.9 speedup.

cs.DC↗
arXiv2026

QuitoBench: A High-Quality Open Time Series Forecasting Benchmark

Time series forecasting is critical across finance, healthcare, and cloud computing, yet progress is constrained by a fundamental bottleneck: the scarcity of large-scale, high-quality benchmarks. To address this gap, we introduce \textsc{QuitoBench}, a regime-balanced benchmark for time series forecasting with coverage across eight trend$\times$seasonality$\times$forecastability (TSF) regimes, designed to capture forecasting-relevant properties rather than application-defined domain labels. The benchmark is built upon \textsc{Quito}, a billion-scale time series corpus of application traffic from Alipay spanning nine business domains. Benchmarking 10 models from deep learning, foundation models, and statistical baselines across 232,200 evaluation instances, we report four key findings: (i) a context-length crossover where deep learning models lead at short context ($L=96$) but foundation models dominate at long context ($L \ge 576$); (ii) forecastability is the dominant difficulty driver, producing a $3.64 \times$ MAE gap across regimes; (iii) deep learning models match or surpass foundation models at $59 \times$ fewer parameters; and (iv) scaling the amount of training data provides substantially greater benefit than scaling model size for both model families. These findings are validated by strong cross-benchmark and cross-metric consistency. Our open-source release enables reproducible, regime-aware evaluation for time series forecasting research.

cs.LG↗
arXiv2026

OSA: Echocardiography Video Segmentation via Orthogonalized State Update and Anatomical Prior-aware Feature Enhancement

Accurate and temporally consistent segmentation of the left ventricle from echocardiography videos is essential for estimating the ejection fraction and assessing cardiac function. However, modeling spatiotemporal dynamics remains difficult due to severe speckle noise and rapid non-rigid deformations. Existing linear recurrent models offer efficient in-context associative recall for temporal tracking, but rely on unconstrained state updates, which cause progressive singular value decay in the state matrix, a phenomenon known as rank collapse, resulting in anatomical details being overwhelmed by noise. To address this, we propose OSA, a framework that constrains the state evolution on the Stiefel manifold. We introduce the Orthogonalized State Update (OSU) mechanism, which formulates the memory evolution as Euclidean projected gradient descent on the Stiefel manifold to prevent rank collapse and maintain stable temporal transitions. Furthermore, an Anatomical Prior-aware Feature Enhancement module explicitly separates anatomical structures from speckle noise through a physics-driven process, providing the temporal tracker with noise-resilient structural cues. Comprehensive experiments on the CAMUS and EchoNet-Dynamic datasets show that OSA achieves state-of-the-art segmentation accuracy and temporal stability, while maintaining real-time inference efficiency for clinical deployment. Codes are available at https://github.com/wangrui2025/OSA.

cs.CV↗
arXiv2026

Light-induced Odd-parity Magnetism in Conventional Collinear Antiferromagnets

Recent studies have drawn growing attention on non-relativistic odd-parity magnetism in the wake of altermagnets. Nevertheless, odd-parity spin splitting is often believed to appear in non-collinear magnetic configurations. Here, using symmetry arguments and effective model analysis, we show that Floquet engineering offers a universal strategy for achieving odd-parity magnetism in two-dimensional (2D) collinear antiferromagnets under irradiation of periodic driving light fields such as circularly polarized light, elliptically polarized light, and bicircular light. A comprehensive classification of potential candidates for collinear monolayer or bilayer antiferromagnets is established. Strikingly, the light-induced odd-parity spin splitting can be flexibly controlled by adjusting the crystalline symmetry or the polarization state of incident light, enabling the reversal or conversion of spin-splitting. By combining first-principles calculations and Floquet theorem, we present illustrative examples of 2D collinear antiferromagnetic (AFM) materials to verify the light-induced odd-parity magnetism. Our work not only offers a powerful approach for uniquely achieving odd-parity spin-splitting with high tunability, but also expands the potential of Floquet engineering in designing unconventional compensated magnetism.

cond-mat.mtrl-sci↗
arXiv2026

Dual-Domain Representation Alignment: Bridging 2D and 3D Vision via Geometry-Aware Architecture Search

Modern computer vision requires balancing predictive accuracy with real-time efficiency, yet the high inference cost of large vision models (LVMs) limits deployment on resource-constrained edge devices. Although Evolutionary Neural Architecture Search (ENAS) is well suited for multi-objective optimization, its practical use is hindered by two issues: expensive candidate evaluation and ranking inconsistency among subnetworks. To address them, we propose EvoNAS, an efficient distributed framework for multi-objective evolutionary architecture search. We build a hybrid supernet that integrates Vision State Space and Vision Transformer (VSS-ViT) modules, and optimize it with a Cross-Architecture Dual-Domain Knowledge Distillation (CA-DDKD) strategy. By coupling the computational efficiency of VSS blocks with the semantic expressiveness of ViT modules, CA-DDKD improves the representational capacity of the shared supernet and enhances ranking consistency, enabling reliable fitness estimation during evolution without extra fine-tuning. To reduce the cost of large-scale validation, we further introduce a Distributed Multi-Model Parallel Evaluation (DMMPE) framework based on GPU resource pooling and asynchronous scheduling. Compared with conventional data-parallel evaluation, DMMPE improves efficiency by over 70% through concurrent multi-GPU, multi-model execution. Experiments on COCO, ADE20K, KITTI, and NYU-Depth v2 show that the searched architectures, termed EvoNets, consistently achieve Pareto-optimal trade-offs between accuracy and efficiency. Compared with representative CNN-, ViT-, and Mamba-based models, EvoNets deliver lower inference latency and higher throughput under strict computational budgets while maintaining strong generalization on downstream tasks such as novel view synthesis. Code is available at https://github.com/EMI-Group/evonas

cs.CV↗
arXiv2026

F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World

We present F2LLM-v2, a new family of general-purpose, multilingual embedding models in 8 distinct sizes ranging from 80M to 14B. Trained on a newly curated composite of 60 million publicly available high-quality data samples, F2LLM-v2 supports more than 200 languages, with a particular emphasis on previously underserved mid- and low-resource languages. By integrating a two-stage LLM-based embedding training pipeline with matryoshka learning, model pruning, and knowledge distillation techniques, we present models that are far more efficient than previous LLM-based embedding models while retaining competitive performances. Extensive evaluations confirm that F2LLM-v2-14B ranks first on 11 MTEB benchmarks, while the smaller models in the family also set a new state of the art for resource-constrained applications. To facilitate open-source embedding model research, we release all models, data, code, and intermediate checkpoints.

cs.CL↗
arXiv2026

WiSLAT: A Simultaneous Device Localization and Target Tracking Method for Wi-Fi Systems

It has been shown that the channel state information (CSI) of a Wi-Fi system can be exploited to localize Wi-Fi devices or track trajectory of a moving target. In the existing literature, both sensing tasks are treated separately and some prior information is usually requested, including the signal fingerprints, the locations of some anchor devices in the Wi-Fi system, and etc. In the proposed WiSLAT method, however, it is shown that both sensing tasks can assist each other, such that the request on prior system information can be eliminated. Particularly, in a Wi-Fi system with an access point (AP) and at least three stations, where the locations of the stations are unknown, the WiSLAT is designed to detect the Doppler frequencies of the downlink CSI at the stations, such that their locations and the trajectory of the target with respect to the AP can be inferred. The joint detection can be conducted by searching the optimal stations' locations and target's trajectory, such that their corresponding Doppler frequencies fit the observed ones best. Due to the tremendous non-convex search space, a low-complexity sub-optimal algorithm integrating alternate optimization, extended Kalman filter and density-based clustering is proposed in WiSLAT. Experiments conducted in indoor environments demonstrate the effectiveness of WiSLAT, achieving a median trajectory-tracking error of 0.68 m.

eess.SP↗
arXiv2026

Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models

Multimodal Large Language Models (MLLMs) have made impressive progress in connecting vision and language, but they still struggle with spatial understanding and viewpoint-aware reasoning. Recent efforts aim to augment the input representations with geometric cues rather than explicitly teaching models to reason in 3D space. We introduce Loc3R-VLM, a framework that equips 2D Vision-Language Models with advanced 3D understanding capabilities from monocular video input. Inspired by human spatial cognition, Loc3R-VLM relies on two joint objectives: global layout reconstruction to build a holistic representation of the scene structure, and explicit situation modeling to anchor egocentric perspective. These objectives provide direct spatial supervision that grounds both perception and language in a 3D context. To ensure geometric consistency and metric-scale alignment, we leverage lightweight camera pose priors extracted from a pre-trained 3D foundation model. Loc3R-VLM achieves state-of-the-art performance in language-based localization and outperforms existing 2D- and video-based approaches on situated and general 3D question-answering benchmarks, demonstrating that our spatial supervision framework enables strong 3D understanding. Project page: https://kevinqu7.github.io/loc3r-vlm

cs.CV↗
arXiv2026

BoundAD: Boundary-Aware Negative Generation for Time Series Anomaly Detection

Contrastive learning methods for time series anomaly detection (TSAD) heavily depend on the quality of negative sample construction. However, existing strategies based on random perturbations or pseudo-anomaly injection often struggle to simultaneously preserve temporal semantic consistency and provide effective decision-boundary supervision. Most existing methods rely on prior anomaly injection, while overlooking the potential of generating hard negatives near the data manifold boundary directly from normal samples themselves. To address this issue, we propose a reconstruction-driven boundary negative generation framework that automatically constructs hard negatives through the reconstruction process of normal samples. Specifically, the method first employs a reconstruction network to capture normal temporal patterns, and then introduces a reinforcement learning strategy to adaptively adjust the optimization update magnitude according to the current reconstruction state. In this way, boundary-shifted samples close to the normal data manifold can be induced along the reconstruction trajectory and further used for subsequent contrastive representation learning. Unlike existing methods that depend on explicit anomaly injection, the proposed framework does not require predefined anomaly patterns, but instead mines more challenging boundary negatives from the model's own learning dynamics. Experimental results show that the proposed method effectively improves anomaly representation learning and achieves competitive detection performance on the current dataset.

cs.LG↗
arXiv2026

Efficient structure-preserving scheme for chemotaxis PDE system with singular sensitivity in crime and epidemic modeling

The chemotaxis PDE system with singular sensitivity was originally proposed by Short et al. (Math. Mod. Meth. Appl. Sci., 2008) as the continuum limit of a biased random walk model to account for the formation of crime hotspots and environmental feedback successfully. Recently, this idea has also been applied to epidemiology to model the impact of human social behaviors on disease transmission. In order to characterize the phase transition, pattern formation and statistical properties in the long-term dynamics, a stable and accurate numerical scheme is urgently demanded, which still remains challenging due to the positivity constraint on the singular sensitivity and the absence of an energy functional. In particular, the loss of positivity may produce nonphysical states and even cause spurious blow-up. To address these numerical challenges, this paper constructs an efficient positivity-preserving, implicit-explicit scheme with second-order accuracy. A rigorous error estimation is provided with the Lagrange multiplier correction to deal with the singular sensitivity. The whole framework is extended to a multi-agent epidemic model with degenerate diffusion, in which both positivity and mass conservation are achieved. Numerical experiments are performed to validate the theoretical results and demonstrate the necessity of the correction strategy. Our simulations reveal rich dynamical behaviors, including the phase transition between aggregation-dominated and dissipative regimes, as well as the nucleation, spread, and dissipation of crime hotspots. For the epidemic model, the results further show that spatial clustering of population density may accelerate virus transmission and significantly amplify the infectious wave.

math.NA↗
arXiv2026

Fold-CP: A Context Parallelism Framework for Biomolecular Modeling

Understanding cellular machinery requires atomic-scale reconstruction of large biomolecular assemblies. However, predicting the structures of these systems has been constrained by hardware memory requirements of models like AlphaFold 3, imposing a practical ceiling of a few thousand residues that can be processed on a single GPU. Here we present NVIDIA BioNeMo Fold-CP, a context parallelism framework that overcomes this barrier by distributing the inference and training pipelines of co-folding models across multiple GPUs. We use the Boltz models as open source reference architectures and implement custom multidimensional primitives that efficiently parallelize both the dense triangular updates and the irregular, data-dependent pattern of window-batched local attention. Our approach achieves efficient memory scaling; for an N-token input distributed across P GPUs, per-device memory scales as $O(N^2/P)$, enabling the structure prediction of assemblies exceeding 30,000 residues on 64 NVIDIA B300 GPUs. We demonstrate the scientific utility of this approach through successful developer use cases: Fold-CP enabled the scoring of over 90% of Comprehensive Resource of Mammalian protein complexes (CORUM) database, as well as folding of disease-relevant PI4KA lipid kinase complex bound to an intrinsically disordered region without cropping. By providing a scalable pathway for modeling massive systems with full global context, Fold-CP represents a significant step toward the realization of a virtual cell.

q-bio.QM↗
arXiv2026

ISAC-Enabled Multi-UAV Collaborative Target Sensing for Low-Altitude Economy

Integrated sensing and communication (ISAC) has attracted growing research interests to facilitate the large-scale development of the low-altitude economy (LAE). However, the high dynamics of low-altitude targets may overwhelm fixed ISAC systems, particularly at the edge of their coverage or in blind zones. Driven by high flexibility, unmanned aerial vehicle (UAV)-assisted ISAC can provide more freedom of design to enhance communication and sensing abilities. In this paper, we propose an ISAC-enabled multi-UAV dynamic collaborative target sensing scheme, where UAVs can dynamically adjust their flight and resource allocation for cooperative sensing of mobile target through communicating with the terrestrial cellular network with ISAC signals. To achieve the precise sensing of the dynamic target, the posterior Cramer-Rao bound (PCRB) for the target state is derived. Subsequently, the PCRB minimization problem is formulated by jointly optimizing the UAV-BS association, UAVs' trajectories and bandwidth allocation, subject to the communication requirements for the UAVs. However, the problem is challenging since it involves non-convex and implicit objective function with coupled optimization variables. For a fast implementation of sensing and tracking, we propose a low-complexity iterative algorithm that can efficiently obtain a sub-optimal solution to the problem. Specifically, the UAV-BS association is first determined by the communication-optimal solution. Then the UAVs' trajectories and bandwidth allocation are alternatively optimized based on the descent direction search algorithm. Finally, numerical results are provided to validate the superiority of our proposed designs as compared to various benchmarks.

eess.SY↗
arXiv2026

FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance

Recent advances in trajectory-controllable video generation have achieved remarkable progress. Previous methods mainly use adapter-based architectures for precise motion control along predefined trajectories. However, all these methods rely on a multi-step denoising process, leading to substantial time redundancy and computational overhead. While existing video distillation methods successfully distill multi-step generators into few-step, directly applying these approaches to trajectory-controllable video generation results in noticeable degradation in both video quality and trajectory accuracy. To bridge this gap, we introduce FlashMotion, a novel training framework designed for few-step trajectory-controllable video generation. We first train a trajectory adapter on a multi-step video generator for precise trajectory control. Then, we distill the generator into a few-step version to accelerate video generation. Finally, we finetune the adapter using a hybrid strategy that combines diffusion and adversarial objectives, aligning it with the few-step generator to produce high-quality, trajectory-accurate videos. For evaluation, we introduce FlashBench, a benchmark for long-sequence trajectory-controllable video generation that measures both video quality and trajectory accuracy across varying numbers of foreground objects. Experiments on two adapter architectures show that FlashMotion surpasses existing video distillation methods and previous multi-step models in both visual quality and trajectory consistency.

cs.CV↗
arXiv2026

CSST-PSFNet: A Point Spread Function Reconstruction Model for the CSST Based on Deep Learning

This paper presents CSST-PSFNet, a deep learning method for high-fidelity point spread function (PSF) reconstruction developed for the Chinese Space Station Survey Telescope (CSST). The model integrates a residual neural network, a lightweight Transformer architecture, and a variational latent representation to address key challenges in CSST imaging, including severe PSF undersampling, inter-band variability, and smooth spatial variation across the focal plane. Trained and validated on high-resolution star-PSF pairs generated by the CSST Main Survey Simulator, CSST-PSFNet achieves improved pixel-level accuracy and more precise recovery of shape parameters relevant to weak lensing compared to widely used PSFEx. On both the standard test dataset and a blurred dataset representing the upper bound of expected on-orbit PSF degradation, the model achieves a size residual precision below 0.005 and an ellipticity residual precision below 0.002. A weak-label adaptation experiment further shows that the model can recover PSFEx-level performance when the true PSF is unknown, demonstrating robustness in controlled degradation scenarios and weak-label adaptation experiments. These results indicate that CSST-PSFNet provides a flexible and extensible framework for future on-orbit PSF calibration in large-scale CSST surveys, with potential applications in weak-lensing cosmology and precision astrophysical measurements.

astro-ph.IM↗