arXiv subjects

Ning Wang

Publications and source records attributed to Ning Wang.

At least 91 records · Page 5Linked to original sources

arXiv2025

Step-GUI Technical Report

Recent advances in multimodal large language models unlock unprecedented opportunities for GUI automation. However, a fundamental challenge remains: how to efficiently acquire high-quality training data while maintaining annotation reliability? We introduce a self-evolving training pipeline powered by the Calibrated Step Reward System, which converts model-generated trajectories into reliable training signals through trajectory-level calibration, achieving >90% annotation accuracy with 10-100x lower cost. Leveraging this pipeline, we introduce Step-GUI, a family of models (4B/8B) that achieves state-of-the-art GUI performance (8B: 80.2% AndroidWorld, 48.5% OSWorld, 62.6% ScreenShot-Pro) while maintaining robust general capabilities. As GUI agent capabilities improve, practical deployment demands standardized interfaces across heterogeneous devices while protecting user privacy. To this end, we propose GUI-MCP, the first Model Context Protocol for GUI automation with hierarchical architecture that combines low-level atomic operations and high-level task delegation to local specialist models, enabling high-privacy execution where sensitive data stays on-device. Finally, to assess whether agents can handle authentic everyday usage, we introduce AndroidDaily, a benchmark grounded in real-world mobile usage patterns with 3146 static actions and 235 end-to-end tasks across high-frequency daily scenarios (8B: static 89.91%, end-to-end 52.50%). Our work advances the development of practical GUI agents and demonstrates strong potential for real-world deployment in everyday digital interactions.

cs.CV↗

arXiv2025

A power-in-bucket model enabled designs of nanostructure-enhanced waveguides for highly efficient wide-angle light couplings

Well-designed nanostructures on fiber facets can boost wide-angle light coupling and thus gain considerable attention because of the potential for intensive applications. However, previous theories commonly concentrate on the configurations of the bare waveguide, lacking full consideration of structure-assisted couplings. Here, a power-in-bucket (PIB) model is introduced to explore the coupling behavior of structure-modified waveguides. The analytical model investigates two representative coupling scenarios,including Gaussian beam and plane wave excitation. The PIB-computed coefficient η enhancements agree well with the experimental values, especially for the multiple-mode fibers under large-angle illuminations. Using PIB to optimize the beam-fiber parameters, we show that at the incidence angle of 37 degree, η could increase from 0.3320 to 0.5102 by the identical ring gratings. Overall, the proposed model provides a useful account of the mechanism of grating-aided light couplings. These findings would be of great help in designing structure-enhanced probes for wide-angle broadband light collection applications.

physics.optics↗

arXiv2025

Referring Video Object Segmentation with Cross-Modality Proxy Queries

Referring video object segmentation (RVOS) is an emerging cross-modality task that aims to generate pixel-level maps of the target objects referred by given textual expressions. The main concept involves learning an accurate alignment of visual elements and language expressions within a semantic space. Recent approaches address cross-modality alignment through conditional queries, tracking the target object using a query-response based mechanism built upon transformer structure. However, they exhibit two limitations: (1) these conditional queries lack inter-frame dependency and variation modeling, making accurate target tracking challenging amid significant frame-to-frame variations; and (2) they integrate textual constraints belatedly, which may cause the video features potentially focus on the non-referred objects. Therefore, we propose a novel RVOS architecture called ProxyFormer, which introduces a set of proxy queries to integrate visual and text semantics and facilitate the flow of semantics between them. By progressively updating and propagating proxy queries across multiple stages of video feature encoder, ProxyFormer ensures that the video features are focused on the object of interest. This dynamic evolution also enables the establishment of inter-frame dependencies, enhancing the accuracy and coherence of object tracking. To mitigate high computational costs, we decouple cross-modality interactions into temporal and spatial dimensions. Additionally, we design a Joint Semantic Consistency (JSC) training strategy to align semantic consensus between the proxy queries and the combined video-text pairs. Comprehensive experiments on four widely used RVOS benchmarks demonstrate the superiority of our ProxyFormer to the state-of-the-art methods.

cs.CV↗

arXiv2025

Prompt-guided Disentangled Representation for Action Recognition

Action recognition is a fundamental task in video understanding. Existing methods typically extract unified features to process all actions in one video, which makes it challenging to model the interactions between different objects in multi-action scenarios. To alleviate this issue, we explore disentangling any specified actions from complex scenes as an effective solution. In this paper, we propose Prompt-guided Disentangled Representation for Action Recognition (ProDA), a novel framework that disentangles any specified actions from a multi-action scene. ProDA leverages Spatio-temporal Scene Graphs (SSGs) and introduces Dynamic Prompt Module (DPM) to guide a Graph Parsing Neural Network (GPNN) in generating action-specific representations. Furthermore, we design a video-adapted GPNN that aggregates information using dynamic weights. Experiments in video action recognition demonstrate the effectiveness of our approach when compared with the state-of-the-art methods. Our code can be found in https://github.com/iamsnaping/ProDA.git

cs.CV↗

arXiv2025

The Triple-C Paradigm: Cooperative, Complementary, and Competitive Modes for TBS-HAPS-LEO Integration

The growing demands of ubiquitous and resilient global coverage have pushed existing networks to their operational limits, making it increasingly difficult to meet all requirements on their own. Integrating \emph{Terrestrial Base Stations (TBS), High Altitude Platform Stations (HAPS)} and \emph{Low-Earth-Orbit (LEO)} satellites is envisioned as a promising solution, yet the coordination across these heterogeneous platforms remains an open challenge. This paper proposes a novel unifying \emph{Triple-C framework: Cooperation, Complementarity, and Competition}, that systematically defines the TBS-HAPS-LEO interaction to deliver seamless resilient and scalable connectivity. For each C, we detail the architectural methodology, required pre-requisites, and measurable deliverables that govern when and how the three layers should collaborate, complement each other, or contend. We further identify the enabling technologies across physical, logical, and cognitive layers to operationalize the proposed 3C paradigm. A rich portfolio of use cases and targeted applications demonstrates how this technological leap will make such integration both feasible and impactful. Comprehensive performance analysis and emulation results quantify the trade-offs of such integrated networks. In addition, we examine the economical, environmental, safety, privacy, standardization, and regulatory implications that shape the real-world implementation of the proposed framework. eventually, we provide the gap analysis, outline key technical/non-technical challenges, and a road-map of future research directions needed to unlock the full potential of Cooperation, Complementarity, and Competition operations in TBS-HAPS-LEO integrated networks.

eess.SP↗

arXiv2025

REAP: Enhancing RAG with Recursive Evaluation and Adaptive Planning for Multi-Hop Question Answering

Retrieval-augmented generation (RAG) has been extensively employed to mitigate hallucinations in large language models (LLMs). However, existing methods for multi-hop reasoning tasks often lack global planning, increasing the risk of falling into local reasoning impasses. Insufficient exploitation of retrieved content and the neglect of latent clues fail to ensure the accuracy of reasoning outcomes. To overcome these limitations, we propose Recursive Evaluation and Adaptive Planning (REAP), whose core idea is to explicitly maintain structured sub-tasks and facts related to the current task through the Sub-task Planner (SP) and Fact Extractor (FE) modules. SP maintains a global perspective, guiding the overall reasoning direction and evaluating the task state based on the outcomes of FE, enabling dynamic optimization of the task-solving trajectory. FE performs fine-grained analysis over retrieved content to extract reliable answers and clues. These two modules incrementally enrich a logically coherent representation of global knowledge, enhancing the reliability and the traceability of the reasoning process. Furthermore, we propose a unified task paradigm design that enables effective multi-task fine-tuning, significantly enhancing SP's performance on complex, data-scarce tasks. We conduct extensive experiments on multiple public multi-hop datasets, and the results demonstrate that our method significantly outperforms existing RAG methods in both in-domain and out-of-domain settings, validating its effectiveness in complex multi-hop reasoning tasks.

cs.CL↗

arXiv2025

Critical Path Aware Timing-Driven Global Placement for Large-Scale Heterogeneous FPGAs

Timing optimization during global placement is critical for achieving optimal circuit performance and remains a key challenge in modern Field Programmable Gate Array (FPGA) design. As FPGA designs scale and heterogeneous resources increase, dense interconnects introduce significant resistive and capacitive effects, making timing closure increasingly difficult. Existing methods face challenges in constructing accurate timing models due to multi-factor nonlinear constraints as well as load and crosstalk coupling effects arising in multi-pin driving scenarios. To address these challenges, we propose TD-Placer, a critical path aware, timing-driven global placement framework. It leverages graph-based representations to capture global net interactions and employs a nonlinear model to integrate diverse timing-related features for precise delay prediction, thereby improving the overall placement quality for FPGAs. TD-Placer adopts a quadratic placement objective that minimizes wirelength while incorporating a timing term constructed by a lightweight algorithm, enabling efficient and high-quality timing optimization. Regarding net-level timing contention, it also employs a finer-grained weighting scheme to facilitate smooth reduction of the Critical Path Delay (CPD). Extensive experiments were carried out on seven real-world open-source FPGA projects with LUT counts ranging from 60K to 400K. The results demonstrate that TD-Placer achieves an average 10% improvement in Worst Negative Slack (WNS) and a 5% reduction in CPD compared to the state-of-the-art method, with an average CPD comparable (*1.01) to the commercial AMD Vivado across five versions (2020.2-2024.2). Its code and dataset are publicly available.

cs.AR↗

arXiv2025

Multi-Granularity Mutual Refinement Network for Zero-Shot Learning

Zero-shot learning (ZSL) aims to recognize unseen classes with zero samples by transferring semantic knowledge from seen classes. Current approaches typically correlate global visual features with semantic information (i.e., attributes) or align local visual region features with corresponding attributes to enhance visual-semantic interactions. Although effective, these methods often overlook the intrinsic interactions between local region features, which can further improve the acquisition of transferable and explicit visual features. In this paper, we propose a network named Multi-Granularity Mutual Refinement Network (Mg-MRN), which refine discriminative and transferable visual features by learning decoupled multi-granularity features and cross-granularity feature interactions. Specifically, we design a multi-granularity feature extraction module to learn region-level discriminative features through decoupled region feature mining. Then, a cross-granularity feature fusion module strengthens the inherent interactions between region features of varying granularities. This module enhances the discriminability of representations at each granularity level by integrating region representations from adjacent hierarchies, further improving ZSL recognition performance. Extensive experiments on three popular ZSL benchmark datasets demonstrate the superiority and competitiveness of our proposed Mg-MRN method. Our code is available at https://github.com/NingWang2049/Mg-MRN.

cs.CV↗

arXiv2025

First experimental proof of PET imaging based on multi-anode MCP-PMTs with Cherenkov radiator-integrated window

Improving the coincidence time resolution (CTR) of time-of-flight positron emission tomography (TOF-PET) systems to achieve a higher signal-to-noise ratio (SNR) gain or even direct positron emission imaging (dPEI) is of paramount importance for many advanced new clinical applications of PET imaging. This places higher demands on the timing performance of all aspects of PET systems. One effective approach is to use microchannel plate photomultiplier tubes (MCP-PMTs) for prompt Cherenkov photon detection. In this study, we developed a dual-module Cherenkov PET imaging experimental platform, utilising our proprietary 8 * 8-anode Cherenkov radiator-integrated window MCP-PMTs in combination with custom-designed multi-channel electronics, and designed a specific calibration and correction method for the platform. Using this platform, a CTR of 103 ps FWHM was achieved. We overcame the limitations of single-anode detectors in previous experiments, significantly enhanced imaging efficiency and achieved module-level Cherenkov PET imaging for the first time. Imaging experiments involving radioactive sources and phantoms of various shapes and types were conducted, which preliminarily validated the feasibility and advancement of this imaging method. In addition, the effects of normalisation correction and the interaction probability between the gamma rays and the MCP on the images and experimental results were analysed and verified.

physics.ins-det↗

arXiv2025

Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understanding

Recent advances in deep learning have led to increasingly complex models with deeper layers and more parameters, reducing interpretability and making their decisions harder to understand. While many methods explain black-box reasoning, most lack effective interventions or only operate at sample-level without modifying the model itself. To address this, we propose the Concept Bottleneck Model for Enhancing Human-Neural Network Mutual Understanding (CBM-HNMU). CBM-HNMU leverages the Concept Bottleneck Model (CBM) as an interpretable framework to approximate black-box reasoning and communicate conceptual understanding. Detrimental concepts are automatically identified and refined (removed/replaced) based on global gradient contributions. The modified CBM then distills corrected knowledge back into the black-box model, enhancing both interpretability and accuracy. We evaluate CBM-HNMU on various CNN and transformer-based models across Flower-102, CIFAR-10, CIFAR-100, FGVC-Aircraft, and CUB-200, achieving a maximum accuracy improvement of 2.64% and a maximum increase in average accuracy across 1.03%. Source code is available at: https://github.com/XiGuaBo/CBM-HNMU.

cs.CV↗

arXiv2025

A Deep-Learning-Driven Optimization-Based Inverse Solver for Accelerating the Marchenko Method

The Marchenko method is a powerful tool for reconstructing full-wavefield Green's functions using surface-recorded seismic data. These Green's functions can then be utilized to produce subsurface images that are not affected by artifacts caused by internal multiples. Despite its advantages, the method is computationally demanding, primarily due to the iterative nature of estimating the focusing functions, which links the Green's functions to the surface reflection response. To address this limitation, an optimization-based solver is proposed to estimate focusing functions in an efficient way. This is achieved by training a network to approximate the forward modeling problem on a small subset of pre-computed focusing function pairs, mapping final up-going focusing functions obtained via the conventional iterative scheme to their initial estimates. Once trained, the network is fixed and used as the forward operator within the Marchenko framework. For a given target location, an input is initialized and iteratively updated through backpropagation to minimize the mismatch between the output of the fixed network and the known initial up-going focusing function. The resulting estimate is then used to compute the corresponding down-going focusing function and the full Green's functions based on the Marchenko equations. This strategy significantly reduces the computational cost compared to the traditional Marchenko method based on conventional iterative scheme. Tests on a synthetic model, using only 0.8% of the total imaging points for training, show that the proposed approach accelerates the imaging process while maintaining relatively good imaging results, which is better than reverse time migration. Application to the Volve field data further demonstrates the method's robustness and practicality, highlighting its potential for efficient, large scale seismic imaging.

physics.geo-ph↗

arXiv2025

Comparative Performance Analysis of Different Hybrid NOMA Schemes

Hybrid non-orthogonal multiple access (H-NOMA), which combines the advantages of pure NOMA and conventional OMA organically, has emerged as a highly promising multiple access technology for future wireless networks. Recent studies have proposed various H-NOMA systems by employing different successive interference cancellation (SIC) methods for the NOMA transmission phase. However, existing analyses typically assume a fixed channel gain order between paired users, despite the fact that channel coefficients follow random distribution, leading to their magnitude relationships inherently stochastic and time varying. This paper analyzes the performance of three H-NOMA schemes under stochastic channel gain ordering: a) fixed order SIC (FSIC) aided H-NOMA scheme; b) hybrid SIC with non-power adaptation (HSIC-NPA) aided H-NOMA scheme; c) hybrid SIC with power adaptation (HSIC-PA) aided H-NOMA scheme. Theoretical analysis derives closed-form expressions for the probability that H-NOMA schemes underperform conventional OMA. Asymptotic results in the high signal-to-noise ratio (SNR) regime are also developed. Simulation results validate our analysis and demonstrate the performance of H-NOMA schemes across different SNR scenarios, providing a theoretical foundation for the deployment of H-NOMA in next-generation wireless systems.

eess.SP↗

arXiv2025

Combinatorial optimization enhanced by shallow quantum circuits with 104 superconducting qubits

A pivotal task for quantum computing is to speed up solving problems that are both classically intractable and practically valuable. Among these, combinatorial optimization problems have attracted tremendous attention due to their broad applicability and natural fitness to Ising Hamiltonians. Here we propose a quantum sampling strategy, based on which we design an algorithm for accelerating solving the ground states of Ising model, a class of NP-hard problems in combinatorial optimization. The algorithm employs a hybrid quantum-classical workflow, with a shallow-circuit quantum sampling subroutine dedicated to navigating the energy landscape. Using up to 104 superconducting qubits, we demonstrate that this algorithm outputs favorable solutions against even a highly-optimized classical simulated annealing (SA) algorithm. Furthermore, we illustrate the path toward quantum speedup based on the time-to-solution metric against SA running on a single-core CPU with just 100 qubits. Our results indicate a promising alternative to classical heuristics for combinatorial optimization, a paradigm where quantum advantage might become possible on near-term superconducting quantum processors with thousands of qubits and without the assistance of error correction.

quant-ph↗

arXiv2025

Refinement of an analytical capture cross section formula

An analytical formula with high accuracy is proposed for a systematic description of the capture cross sections at near-barrier energies from light to superheavy reaction systems. Based on the empirical barrier distribution (EBD) method, three key input quantities are refined by introducing nuclear surface correction to the Coulomb parameter $z$ for calculating the barrier height, incorporating the reaction $Q$-value and shell correction into the barrier distribution width calculations, and considering the deep inelastic scattering effects of superheavy systems on the barrier radius. With these refinements, not only the accuracy of the calculated barrier height but also the accuracy of the predicted capture cross sections, is substantially improved. The average deviation (in logarithmic scale) between the predicted cross sections and the experimental data for a total of 426 reaction systems with $ 35 < Z_1 Z_2 < 2600$ is sharply reduced from 3.485 to 0.113.

nucl-th↗

arXiv2025

ARSP: Automated Repair of Verilog Designs via Semantic Partitioning

Debugging functional Verilog bugs consumes a significant portion of front-end design time. While Large Language Models (LLMs) have demonstrated great potential in mitigating this effort, existing LLM-based automated debugging methods underperform on industrial-scale modules. A major reason for this is bug signal dilution in long contexts, where a few bug-relevant tokens are overwhelmed by hundreds of unrelated lines, diffusing the model's attention. To address this issue, we introduce ARSP, a two-stage system that mitigates dilution via semantics-guided fragmentation. A Partition LLM splits a module into semantically tight fragments; a Repair LLM patches each fragment; edits are merged without altering unrelated logic. A synthetic data framework generates fragment-level training pairs spanning bug types, design styles, and scales to supervise both models. Experiments show that ARSP achieves 77.92% pass@1 and 83.88% pass@5, outperforming mainstream commercial LLMs including Claude-3.7 and SOTA automated Verilog debugging tools Strider and MEIC. Also, semantic partitioning improves pass@1 by 11.6% and pass@5 by 10.2% over whole-module debugging, validating the effectiveness of fragment-level scope reduction in LLM-based Verilog debugging.

cs.SE↗

arXiv2025

A CLIP-based Uncertainty Modal Modeling (UMM) Framework for Pedestrian Re-Identification in Autonomous Driving

Re-Identification (ReID) is a critical technology in intelligent perception systems, especially within autonomous driving, where onboard cameras must identify pedestrians across views and time in real-time to support safe navigation and trajectory prediction. However, the presence of uncertain or missing input modalities--such as RGB, infrared, sketches, or textual descriptions--poses significant challenges to conventional ReID approaches. While large-scale pre-trained models offer strong multimodal semantic modeling capabilities, their computational overhead limits practical deployment in resource-constrained environments. To address these challenges, we propose a lightweight Uncertainty Modal Modeling (UMM) framework, which integrates a multimodal token mapper, synthetic modality augmentation strategy, and cross-modal cue interactive learner. Together, these components enable unified feature representation, mitigate the impact of missing modalities, and extract complementary information across different data types. Additionally, UMM leverages CLIP's vision-language alignment ability to fuse multimodal inputs efficiently without extensive finetuning. Experimental results demonstrate that UMM achieves strong robustness, generalization, and computational efficiency under uncertain modality conditions, offering a scalable and practical solution for pedestrian re-identification in autonomous driving scenarios.

cs.CV↗

arXiv2025

Beyond Predictions: A Study of AI Strength and Weakness Transparency Communication on Human-AI Collaboration

The promise of human-AI teaming lies in humans and AI working together to achieve performance levels neither could accomplish alone. Effective communication between AI and humans is crucial for teamwork, enabling users to efficiently benefit from AI assistance. This paper investigates how AI communication impacts human-AI team performance. We examine AI explanations that convey an awareness of its strengths and limitations. To achieve this, we train a decision tree on the model's mistakes, allowing it to recognize and explain where and why it might err. Through a user study on an income prediction task, we assess the impact of varying levels of information and explanations about AI predictions. Our results show that AI performance insights enhance task performance, and conveying AI awareness of its strengths and weaknesses improves trust calibration. These findings highlight the importance of considering how information delivery influences user trust and reliance in AI-assisted decision-making.

cs.HC↗

arXiv2025

Efficient Upside-Down Rayleigh-Marchenko Imaging through Self-Supervised Focusing Function Estimation

The Upside-Down Rayleigh-Marchenko (UD-RM) method has recently emerged as a powerful tool for retrieving subsurface wavefields and images free from artifacts caused by both internal and surface-related multiples. Its ability to handle acquisition setups with large cable spacing or sparse node geometries makes it particularly suitable for ocean-bottom seismic data processing. However, the widespread application of the method is limited by the high computational cost required to estimate the focusing functions, especially when dealing with large imaging domains. To address this limitation, a self-supervised learning approach is proposed to accelerate the estimation of the focusing functions. Specifically, a U-Net network is trained on a small subset of image points from within the target area of interest, whose focusing functions are pre-computed using the conventional iterative scheme. The network is tasked to predict both the up- and down-going focusing functions from an initial estimate of the subsurface wavefields. Once trained, the network generalizes to remaining unseen imaging locations, enabling direct prediction of the focusing functions. Validation on a synthetic dataset with both dense and sparse receiver sampling using progressively fewer training points demonstrates the method's effectiveness. In both cases, the resulting images closely match those obtained from the UD-RM method with focusing functions retrieved by the conventional iterative approach at a much lower cost and significantly outperform mirror migration (when the same input dataset is used). Finally, an application to the Volve field data confirms the method's robustness in practical scenarios. The proposed approach enables seismic imaging at a fraction of the computational cost of the conventional UD-RM approach while maintaining imaging quality, underscoring its potential for large-scale seismic applications.

physics.geo-ph↗