arXiv subjects

Yan Cheng

Publications and source records attributed to Yan Cheng.

At least 19 recordsLinked to original sources

arXiv2026

Wuying-Browser-Agent: Real-World Centric Fundamental Long-Horizon Browser Agents

Browser agents perform well on short, clean demonstrations, but real deployment is fundamentally different: agents must sustain dozens of decisions on live websites while recovering from mistakes and navigating complex UIs. We argue that closing this gap requires alignment at every level of the pipeline, including execution, supervision, optimization, and evaluation, rather than scale alone. We present Wuying-Browser-Agent, a unified framework that addresses each of these levels. A structured browser harness provides stable execution primitives and decision-oriented context management. Reflection and UI-specialized Curriculum SFT (RUIC-SFT) explicitly trains on recovery trajectories and complex-UI interactions. Divergence-Aware Online GRPO (DAO-GRPO) improves long-horizon credit assignment through potential-based reward shaping and divergence-aware step weighting. Finally, we introduce BrowserBench, a bilingual real-web benchmark of 350 tasks averaging 37.9 steps, because most existing benchmarks are too short to expose long-horizon failure modes. Wuying-Browser-Agent-27B achieves 80.6\% on WebVoyager, 66.7\% on Online-Mind2Web, and 65.1\% on BrowserBench, establishing a new open-source state of the art on browser-use benchmarks. The same pipeline also transfers beyond browser use, demonstrating strong general agentic ability and reaching an average score of 73.8 on Tau2-Bench, Claw-Eval, and BFCL-v4.

cs.AI↗

arXiv2026

Scores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM Agents

As LLM agents increasingly depend on diverse external services such as search engines, databases, and connectors, agent harnesses face a fundamental tool-selection challenge: acquiring too few tools leaves the task under-informed, while too many adds cost, context load, and privacy exposure. Routers and retrievers can rank candidate tools by relevance, but a ranking alone does not determine how many are worth selecting. Existing approaches leave acquisition under heterogeneous costs unaddressed. We formulate this decision as cost-aware marginal decision-focused stopping (CAM-DF) over ranked tool prefixes, with CAM-DF-lite as a compact interpretable variant. We train directly on the offline gap between stopping now and the best continuation: its sign labels the decision, its magnitude weights each error by the payoff at stake. We prove this objective is Bayes-aligned with the stopping target and that score-only rules are suboptimal under heterogeneous costs. We evaluate on 1,343 tasks across five tool-use domains. On $\tau$-bench Retail, CAM-DF attains the highest payoff among deployable methods, with gains over a predict-then-threshold baseline across all five ranking sources and two cost regimes. Our approach is state-of-the-art under heterogeneous costs and high cost pressure, with larger gains under weaker rankings. In live execution, CAM-DF exposes the agent to 37\% fewer tools than full access while maintaining comparable task success. The CAM-DF family is a lightweight pre-execution plugin that turns existing tool rankings into lower-cost acquisition decisions without fine-tuning the underlying LLM.

cs.LG↗

arXiv2026

Chosen-Plaintext Attacks of Double Random Phase Encryption with Nonlinear Optical Media

This paper studies an inverse problem in nonlinear optical encryption. We examine chosen-plaintext attacks (CPA) on a nonlinear optical encryption strategy that integrates double random phase encryption (DRPE) into a nonlinear optical propagation model to enhance the security of the combined system. We first demonstrate that the system's phase information can be decoded from carefully designed differential CPA data. We then demonstrate that the strength of the optical device's nonlinearity can also be recovered from CPA data, indicating that including this parameter as an additional security key does not enhance protection against CPA attacks, although numerical simulations show that strong nonlinearity still poses significant challenges for CPA attacks. Finally, we provide a stability analysis to demonstrate that small errors in decoded security keys result in only small errors in the decrypted text, even though the encryption process is nonlinear.

physics.optics↗

arXiv2026

Privacy-Preserving Federated Fraud Detection in Payment Transactions with NVIDIA FLARE

Fraud-related financial losses continue to rise, while regulatory, privacy, and data-sovereignty constraints increasingly limit the feasibility of centralized fraud detection systems. Federated Learning (FL) has emerged as a promising paradigm for enabling collaborative model training across institutions without sharing raw transaction data. Yet, its practical effectiveness under realistic, non-IID financial data distributions remains insufficiently validated. In this work, we present a multi-institution, industry-oriented proof-of-concept study evaluating federated anomaly detection for payment transactions using the NVIDIA FLARE framework. We simulate a realistic federation of heterogeneous financial institutions, each observing distinct fraud typologies and operating under strict data isolation. Using a deep neural network trained via federated averaging (FedAvg), we demonstrate that federated models achieve a mean F1-score of 0.903 - substantially outperforming locally trained models (0.643) and closely approaching centralized training performance (0.925), while preserving full data sovereignty. We further analyze convergence behavior, showing that strong performance is achieved within 10 federated communication rounds, highlighting the operational viability of FL in latency- and cost-sensitive financial environments. To support deployment in regulated settings, we evaluate model interpretability using Shapley-based feature attribution and confirm that federated models rely on semantically coherent, domain-relevant decision signals. Finally, we incorporate sample-level differential privacy via DP-SGD and demonstrate favorable privacy-utility trade-offs...

cs.LG↗

arXiv2026

YASA: Scalable Multi-Language Taint Analysis on the Unified AST at Ant Group

Modern enterprises increasingly adopt diverse technology stacks with various programming languages, posing significant challenges for static application security testing (SAST). Existing taint analysis tools are predominantly designed for single languages, requiring substantial engineering effort that scales with language diversity. While multi-language tools like CodeQL, Joern, and WALA attempt to address these challenges, they face limitations in intermediate representation design, analysis precision, and extensibility, which make them difficult to scale effectively for large-scale industrial applications at Ant Group. To bridge this gap, we present YASA (Yet Another Static Analyzer), a unified multi-language static taint analysis framework designed for industrial-scale deployment. Specifically, YASA introduces the Unified Abstract Syntax Tree (UAST) that provides a unified abstraction for compatibility across diverse programming languages. Building on the UAST, YASA performs point-to analysis and taint propagation, leveraging a unified semantic model to manage language-agnostic constructs, while incorporating language-specific semantic models to handle other unique language features. When compared to 6 single- and 2 multi-language static analyzers on an industry-standard benchmark, YASA consistently outperformed all baselines across Java, JavaScript, Python, and Go. In real-world deployment within Ant Group, YASA analyzed over 100 million lines of code across 7.3K internal applications. It identified 314 previously unknown taint paths, with 92 of them confirmed as 0-day vulnerabilities. All vulnerabilities were responsibly reported, with 76 already patched by internal development teams, demonstrating YASA's practical effectiveness for securing large-scale industrial software systems.

cs.SE↗

arXiv2025

Optimizing Federated Learning in the Era of LLMs: Message Quantization and Streaming

Federated Learning (FL) offers a promising solution for training machine learning models across distributed data sources while preserving data privacy. However, FL faces critical challenges related to communication overhead and local resource constraints, especially in the era of Large Language Models (LLMs) with billions of parameters. The sheer size of these models exacerbates both memory and communication constraints, making efficient transmission and processing essential for practical deployment. NVIDIA FLARE, an open-source SDK for federated learning, addresses these challenges by introducing advanced communication capabilities. Building upon existing solutions for large object streaming, we enhance FL workflows for LLMs through two key techniques: message quantization and container/file streaming. Quantization reduces message size, while streaming enables efficient memory management, improving scalability and integration with existing workflows. These advancements significantly enhance the robustness and efficiency of FL with LLMs, ensuring better performance in real-world federated learning scenarios.

cs.DC↗

arXiv2025

CONTINA: Confidence Interval for Traffic Demand Prediction with Coverage Guarantee

Accurate short-term traffic demand prediction is critical for the operation of traffic systems. Besides point estimation, the confidence interval of the prediction is also of great importance. Many models for traffic operations, such as shared bike rebalancing and taxi dispatching, take into account the uncertainty of future demand and require confidence intervals as the input. However, existing methods for confidence interval modeling rely on strict assumptions, such as unchanging traffic patterns and correct model specifications, to guarantee enough coverage. Therefore, the confidence intervals provided could be invalid, especially in a changing traffic environment. To fill this gap, we propose an efficient method, CONTINA (Conformal Traffic Intervals with Adaptation) to provide interval predictions that can adapt to external changes. By collecting the errors of interval during deployment, the method can adjust the interval in the next step by widening it if the errors are too large or shortening it otherwise. Furthermore, we theoretically prove that the coverage of the confidence intervals provided by our method converges to the target coverage level. Experiments across four real-world datasets and prediction models demonstrate that the proposed method can provide valid confidence intervals with shorter lengths. Our method can help traffic management personnel develop a more reasonable and robust operation plan in practice. And we release the code, model and dataset in \href{ https://github.com/xiannanhuang/CONTINA/}{ Github}.

cs.LG↗

arXiv2025

Secure Federated XGBoost with CUDA-accelerated Homomorphic Encryption via NVIDIA FLARE

Federated learning (FL) enables collaborative model training across decentralized datasets. NVIDIA FLARE's Federated XGBoost extends the popular XGBoost algorithm to both vertical and horizontal federated settings, facilitating joint model development without direct data sharing. However, the initial implementation assumed mutual trust over the sharing of intermediate gradient statistics produced by the XGBoost algorithm, leaving potential vulnerabilities to honest-but-curious adversaries. This work introduces "Secure Federated XGBoost", an efficient solution to mitigate these risks. We implement secure federated algorithms for both vertical and horizontal scenarios, addressing diverse data security patterns. To secure the messages, we leverage homomorphic encryption (HE) to protect sensitive information during training. A novel plugin and processor interface seamlessly integrates HE into the Federated XGBoost pipeline, enabling secure aggregation over ciphertexts. We present both CPU-based and CUDA-accelerated HE plugins, demonstrating significant performance gains. Notably, our CUDA-accelerated HE implementation achieves up to 30x speedups in vertical Federated XGBoost compared to existing third-party solutions. By securing critical computation steps and encrypting sensitive assets, Secure Federated XGBoost provides robust data privacy guarantees, reinforcing the fundamental benefits of federated learning while maintaining high performance.

cs.CR↗

arXiv2024

C-FedRAG: A Confidential Federated Retrieval-Augmented Generation System

Organizations seeking to utilize Large Language Models (LLMs) for knowledge querying and analysis often encounter challenges in maintaining an LLM fine-tuned on targeted, up-to-date information that keeps answers relevant and grounded. Retrieval Augmented Generation (RAG) has quickly become a feasible solution for organizations looking to overcome the challenges of maintaining proprietary models and to help reduce LLM hallucinations in their query responses. However, RAG comes with its own issues regarding scaling data pipelines across tiered-access and disparate data sources. In many scenarios, it is necessary to query beyond a single data silo to provide richer and more relevant context for an LLM. Analyzing data sources within and across organizational trust boundaries is often limited by complex data-sharing policies that prohibit centralized data storage, therefore, inhibit the fast and effective setup and scaling of RAG solutions. In this paper, we introduce Confidential Computing (CC) techniques as a solution for secure Federated Retrieval Augmented Generation (FedRAG). Our proposed Confidential FedRAG system (C-FedRAG) enables secure connection and scaling of a RAG workflows across a decentralized network of data providers by ensuring context confidentiality. We also demonstrate how to implement a C-FedRAG system using the NVIDIA FLARE SDK and assess its performance using the MedRAG toolkit and MIRAGE benchmarking dataset.

cs.DC↗

arXiv2024

Phase retrieval via media diversity

This work studies phase retrieval for wave fields, aiming to recover the phase of an incoming wave from multi-plane intensity measurements behind different types of linear and nonlinear media. We show that unique phase retrieval can be achieved by utilizing intensity data produced by multiple media. This uniqueness does not require prescribed boundary conditions for the phase in the incidence plane, in contrast to existing phase retrieval methods based on the transport of intensity equation. Moreover, the uniqueness proofs lead to explicit phase reconstruction algorithms. Numerical simulations are presented to validate the theory.

physics.optics↗

arXiv2024

Incorporating Long-term Data in Training Short-term Traffic Prediction Model

Short-term traffic volume prediction is crucial for intelligent transportation system and there are many researches focusing on this field. However, most of these existing researches concentrated on refining model architecture and ignored amount of training data. Therefore, there remains a noticeable gap in thoroughly exploring the effect of augmented dataset, especially extensive historical data in training. In this research, two datasets containing taxi and bike usage spanning over eight years in New York were used to test such effects. Experiments were conducted to assess the precision of models trained with data in the most recent 12, 24, 48, and 96 months. It was found that the training set encompassing 96 months, at times, resulted in diminished accuracy, which might be owing to disparities between historical traffic patterns and present ones. An analysis was subsequently undertaken to discern potential sources of inconsistent patterns, which may include both covariate shift and concept shift. To address these shifts, we proposed an innovative approach that aligns covariate distributions using a weighting scheme to manage covariate shift, coupled with an environment aware learning method to tackle the concept shift. Experiments based on real word datasets demonstrate the effectiveness of our method which can significantly decrease testing errors and ensure an improvement in accuracy when training with large-scale historical data. As far as we know, this work is the first attempt to assess the impact of contiguously expanding training dataset on the accuracy of traffic prediction models. Besides, our training method is able to be incorporated into most existing short-term traffic prediction models and make them more suitable for long term historical training dataset.

cs.LG↗

arXiv2024

Structure evolution path of ferroelectric hafnium zirconium oxide nanocrystals under in-situ biasing

Fluorite-type $\mathrm{HfO_2}$-based ferroelectric (FE) oxides have rekindled interest in FE memories due to their compatibility with silicon processing and potential for high-density integration. The polarization characteristics of FE devices are governed by the dynamics of metastable domain structure evolution. Insightful design of FE devices for encoding and storage necessitates a comprehensive understanding of the internal structural evolution. Here, we demonstrate the evolution of domain structures through a transient polar orthorhombic (O)-$Pmn2_1$-like configuration via $in$-$situ$ biasing on $\mathrm{TiN/Hf_{0.5}Zr_{0.5}O_2/TiN}$ capacitors within spherical aberration-corrected transmission electron microscope, combined with theoretical calculations. Furthermore, it is directly evidenced that the non-FE O-$Pbca$ transforms into the FE O-$Pca2_1$ phase under electric field, with the polar axis of the FE-phase aligning towards the bias direction through ferroelastic transformation, thereby enhancing FE polarization. As cycling progresses further, however, the polar axis collapses, leading to FE degradation. These novel insights into the intricate structural evolution path under electrical field cycling facilitate optimization and design strategies for $\mathrm{HfO_2}$-based FE memory devices.

cond-mat.mtrl-sci↗

arXiv2024

Supercharging Federated Learning with Flower and NVIDIA FLARE

Several open-source systems, such as Flower and NVIDIA FLARE, have been developed in recent years while focusing on different aspects of federated learning (FL). Flower is dedicated to implementing a cohesive approach to FL, analytics, and evaluation. Over time, Flower has cultivated extensive strategies and algorithms tailored for FL application development, fostering a vibrant FL community in research and industry. Conversely, FLARE has prioritized the creation of an enterprise-ready, resilient runtime environment explicitly designed for FL applications in production environments. In this paper, we describe our initial integration of both frameworks and show how they can work together to supercharge the FL ecosystem as a whole. Through the seamless integration of Flower and FLARE, applications crafted within the Flower framework can effortlessly operate within the FLARE runtime environment without necessitating any modifications. This initial integration streamlines the process, eliminating complexities and ensuring smooth interoperability between the two platforms, thus enhancing the overall efficiency and accessibility of FL applications.

cs.DC↗

arXiv2024

Phase transitions in typical fluorite-type ferroelectrics

While ferroelectric hafnia ($\mathrm{HfO_2}$) has become a technically important material for microelectronics, the physical origin of its ferroelectricity remains poorly understood. The tetragonal $P4_2/nmc$ phase is commonly assigned as its paraelectric mother phase but has no soft mode at the Brillouin zone center. In this work, we propose that the paraelectric-ferroelectric transition in hafnia-like $Pca2_1$ ferroelectric family can be described by a $Pcca$-$Pca2_1$ transition, where the $Pcca$ mother phase will evolve into either the $Pca2_1$ ferroelectric phase or the centrosymmetric $P2_1/c$ monoclinic phase, depending on the strain conditions. The $Pcca$ phase is directly linked to both phases in the context of continuous phase transition. Hafnia is regarded as a special case of this family, in that it has accidental atomic degeneracy because all anions are oxygen. The theory is also correlated to the seven-coordination theory that explains the ferroelectricity in hafnia from a chemical perspective. In addition, the strain conditions to promote the ferroelectric phase in hafnia are discussed.

cond-mat.mtrl-sci↗

arXiv2024

DART: Depth-Enhanced Accurate and Real-Time Background Matting

Matting with a static background, often referred to as ``Background Matting" (BGM), has garnered significant attention within the computer vision community due to its pivotal role in various practical applications like webcasting and photo editing. Nevertheless, achieving highly accurate background matting remains a formidable challenge, primarily owing to the limitations inherent in conventional RGB images. These limitations manifest in the form of susceptibility to varying lighting conditions and unforeseen shadows. In this paper, we leverage the rich depth information provided by the RGB-Depth (RGB-D) cameras to enhance background matting performance in real-time, dubbed DART. Firstly, we adapt the original RGB-based BGM algorithm to incorporate depth information. The resulting model's output undergoes refinement through Bayesian inference, incorporating a background depth prior. The posterior prediction is then translated into a "trimap," which is subsequently fed into a state-of-the-art matting algorithm to generate more precise alpha mattes. To ensure real-time matting capabilities, a critical requirement for many real-world applications, we distill the backbone of our model from a larger and more versatile BGM network. Our experiments demonstrate the superior performance of the proposed method. Moreover, thanks to the distillation operation, our method achieves a remarkable processing speed of 33 frames per second (fps) on a mid-range edge-computing device. This high efficiency underscores DART's immense potential for deployment in mobile applications}

cs.CV↗

arXiv2024

Empowering Federated Learning for Massive Models with NVIDIA FLARE

In the ever-evolving landscape of artificial intelligence (AI) and large language models (LLMs), handling and leveraging data effectively has become a critical challenge. Most state-of-the-art machine learning algorithms are data-centric. However, as the lifeblood of model performance, necessary data cannot always be centralized due to various factors such as privacy, regulation, geopolitics, copyright issues, and the sheer effort required to move vast datasets. In this paper, we explore how federated learning enabled by NVIDIA FLARE can address these challenges with easy and scalable integration capabilities, enabling parameter-efficient and full supervised fine-tuning of LLMs for natural language processing and biopharmaceutical applications to enhance their accuracy and robustness.

cs.LG↗

arXiv2023

A fast normal splitting preconditioner for attractive coupled nonlinear Schr\"odinger equations with fractional Laplacian

A linearly implicit conservative difference scheme is applied to discretize the attractive coupled nonlinear Schr\"odinger equations with fractional Laplacian. Complex symmetric linear systems can be obtained, and the system matrices are indefinite and Toeplitz-plus-diagonal. Neither efficient preconditioned iteration method nor fast direct method is available to deal with these systems. In this paper, we propose a novel matrix splitting iteration method based on a normal splitting of an equivalent real block form of the complex linear systems. This new iteration method converges unconditionally, and the quasi-optimal iteration parameter is deducted. The corresponding new preconditioner is obtained naturally, which can be constructed easily and implemented efficiently by fast Fourier transform. Theoretical analysis indicates that the eigenvalues of the preconditioned system matrix are tightly clustered. Numerical experiments show that the new preconditioner can significantly accelerate the convergence rate of the Krylov subspace iteration methods. Specifically, the convergence behavior of the related preconditioned GMRES iteration method is spacial mesh-size-independent, and almost fractional order insensitive. Moreover, the linearly implicit conservative difference scheme in conjunction with the preconditioned GMRES iteration method conserves the discrete mass and energy in terms of a given precision.

math.NA↗

arXiv2023

Edge-Assisted On-Device Model Update for Video Analytics in Adverse Environments

While large deep neural networks excel at general video analytics tasks, the significant demand on computing capacity makes them infeasible for real-time inference on resource-constrained end cam-eras. In this paper, we propose an edge-assisted framework that continuously updates the lightweight model deployed on the end cameras to achieve accurate predictions in adverse environments. This framework consists of three modules, namely, a key frame extractor, a trigger controller, and a retraining manager. The low-cost key frame extractor obtains frames that can best represent the current environment. Those frames are then transmitted and buffered as the retraining data for model update at the edge server. Once the trigger controller detects a significant accuracy drop in the selected frames, the retraining manager outputs the optimal retraining configuration balancing the accuracy and time cost. We prototype our system on two end devices of different computing capacities with one edge server. The results demonstrate that our approach significantly improves accuracy across all tested adverse environment scenarios (up to 24%) and reduces more than 50% of the retraining time compared to existing benchmarks.

cs.MM↗