arXiv subjects

Guangyi Zhang

Publications and source records attributed to Guangyi Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Ultrasound-Based Prediction of Cirrhosis Decompensation Using Large-Scale Computer Vision Models

Decompensation represents a critical transition in the course of cirrhosis, yet clinicians have limited non-invasive tools to reliably predict its onset. In this study, we propose a novel imaging-based approach that leverages large-scale computer vision models to analyze routine abdominal ultrasound images and extract predictive features beyond those captured by traditional laboratory-based risk scores. Ultrasound is widely available, low cost, and suitable for longitudinal surveillance, making it an attractive modality for scalable risk stratification and long-term follow-up. Our framework integrates automated ultrasound data processing with modern deep learning architectures to identify patients at high risk of decompensation prior to the occurrence of clinical deterioration. This non-invasive strategy offers a practical complement to existing clinical scoring systems and may enable earlier, more proactive management of patients with compensated cirrhosis.

eess.IV↗

arXiv2026

Development and Evaluation of Ultrasound Image Learning Pipelines for MASLD Risk Stratification

Metabolic dysfunction-associated steatotic liver disease (MASLD) affects approximately 30% of the general population. Ultrasound-based imaging, including B-mode imaging and shear wave elastography (SWE), is widely used for noninvasive fibrosis assessment; however, the role of deep learning-based ultrasound image learning for MASLD risk stratification remains insufficiently characterized. In this study, we developed and evaluated ultrasound image learning pipelines using B-mode and SWE images for fibrosis staging and identification of patients with at-risk metabolic dysfunction-associated steatohepatitis (MASH). A total of 250 ultrasound examinations, one exam per subject, were included. Model performance was evaluated using 3-fold cross-validation with area under the receiver operating characteristic curve (AUROC). End-to-end SWE image learning achieved performance comparable to operator-guided SWE across fibrosis stages. Overall, SWE-based learning consistently outperformed B-mode image learning in fibrosis staging, with AUROC improvements from 0.64 (95%CI: [0.56, 0.72]) to 0.72 (95% CI: [0.65, 0.79]) for F>=2 (significant fibrosis, p=0.11), from 0.67 (95%CI: [0.58, 0.75]) to 0.78 (95% CI:[0.72, 0.85]) for F>=3 (advanced fibrosis, p=0.02), and from 0.69 (95%CI: [0.56, 0.82]) to 0.80 (95%CI: [0.72, 0.89]) for F4 (cirrhosis, p=0.10). These findings highlight the potential of SWE image learning for MASLD risk stratification.

eess.IV↗

arXiv2026

Can Large Language Models Execute Parent Orders?

Parent-order execution is a core problem in algorithmic trading, where the goal is to split a large order into smaller orders while reducing execution costs. Existing approaches either rely on pre-specified market assumptions that may not hold in practice, or require task-specific training that limits adaptability to new settings. To overcome these limitations, we present the first systematic study of large language models (LLMs) for parent-order execution. This extends the use of LLMs in finance from what to trade to how to execute. We propose PACE (Plan-Ahead Controlled Execution), a hierarchical framework that decomposes parent-order execution into long-horizon planning and short-horizon execution, requiring neither explicit market assumptions nor task-specific training. Experiments on Shenzhen Stock Exchange Level-1 data show that PACE outperforms TWAP, Almgren-Chriss, and learning-based baselines, exceeding the strongest baseline by 0.65 bps. Behavioral analysis reveals that LLMs make execution decisions differently from human investors: higher model confidence predicts better performance rather than worse returns, and the model trades earlier rather than procrastinating toward the deadline. These findings suggest that LLMs can complement human traders in execution decisions.

cs.CE↗

arXiv2026

Cache-Aware I/O Cost Modeling for Disk-Based Learned Indexes

Learned indexes have shown attractive space-time trade-offs in main-memory settings, yet a principled I/O cost model for their disk-resident deployments is still missing, which is a prerequisite for index tuning and query optimization. The practically employed page buffer makes the problem even harder: under typical cache policies, many of the logical page references issued by the index are served by the buffer rather than reaching disk, so the effective physical I/O depends jointly on the workload, the cache policy, and the index configuration. In this paper, we propose CAM, the \textit{first} cache-aware I/O cost model for learned indexes that takes practical cache eviction policies into consideration. CAM is not tied to a particular learned index design: it estimates page access distributions without full trace replay for mainstream learned index designs, and then combines them with I/O cost models to estimate effective physical I/Os. This formulation enables principled knob tuning by explicitly modeling the trade-off between index footprint and buffer capacity. We instantiate CAM for disk-based PGM-index and RMI, and further apply the same modeling principle to learned-index-based joins through a hybrid strategy that adaptively chooses point or range probes based on local key density. Extensive experiments on real benchmarks show that CAM provides \textit{accurate and efficient} I/O estimation across diverse workloads: CAM-guided tuning improves PGM throughput by \textbf{1.17$\times$} over multicriteria PGM tuning and improves RMI throughput by \textbf{1.66$\times$} over CDFShop with I/O-related considerations. For learned-index-based joins, our hybrid strategy improves end-to-end performance by up to \textbf{8.8$\times$} over disk-based index nested-loop join.

cs.DB↗

arXiv2026

Voxel-CKM: Voxelized Radio Frequency Radiance Fields for Fast and Few-Shot CKM Construction

Channel knowledge maps (CKMs) are designed to predict channel state information (CSI) from user locations, thereby enabling low-overhead CSI acquisition. However, existing CKM construction methods often require hours-to-days of training time and dense measurements, resulting in substantial deployment cost. In this paper, we propose Voxel-CKM, a novel voxelized radio frequency (RF) radiance field framework for fast and few-shot CKM construction. The core idea is to replace implicit neural representations with explicit voxel grids to efficiently capture the spatial variation of wireless channels. Building upon this, we further introduce a compact vector-matrix (VM) decomposition to parameterize these voxel grids using a small set of matrices and vectors, which significantly accelerates convergence and facilitates fast CKM construction. To enable few-shot learning, we incorporate a transmitter prior as an inductive bias to guide the learning process under sparse measurements. Additionally, a total-variation (TV) regularization loss is proposed to mitigate overfitting and stabilize optimization. Experiments show that Voxel-CKM substantially accelerates training convergence and improves performance in the few-shot regime.

eess.SP↗

arXiv2026

Efficient Banzhaf-Based Data Valuation for $k$-Nearest Neighbors Classification

Data valuation, the task of quantifying the contribution of individual data points to model performance, has emerged as a fundamental challenge in machine learning. Game-theoretic approaches, such as the Banzhaf value, offer principled frameworks for fair data valuation; however, they suffer from exponential computational complexity. We address this challenge by developing efficient algorithms specifically tailored for computing Banzhaf values in $k$-nearest neighbor ($k$NN) classifiers. We first establish the theoretical hardness of the problem by proving that it is \#P-hard. Despite this intractability, we exploit the locality properties of $k$NN classifiers to develop practical exact algorithms. Our main contribution is a dynamic programming framework that achieves significant computational improvements: we present a pseudo-polynomial algorithm with $O(Wkn^2)$ time complexity for weighted $k$NN classifiers, where $W$ is the maximum sum of top-$k$ weights, and a specialized algorithm for unweighted $k$NN that achieves $O(nk^2)$ time complexity, that is, linear in the number of data points. We also offer efficient Monte Carlo estimation methods. Extensive experiments on real-world datasets demonstrate the practical efficiency of our approach and its effectiveness in data valuation applications.

cs.LG↗

arXiv2026

FL-Sailer: Efficient and Privacy-Preserving Federated Learning for Scalable Single-Cell Epigenetic Data Analysis via Adaptive Sampling

Single-cell ATAC-seq (scATAC-seq) enables high-resolution mapping of chromatin accessibility, yet privacy regulations and data size constraints hinder multi-institutional sharing. Federated learning (FL) offers a privacy-preserving alternative, but faces three fundamental barriers in scATAC-seq analysis: ultra-high dimensionality, extreme sparsity, and severe cross-institutional heterogeneity. We propose FL-Sailer, the first FL framework designed for scATAC-seq data. FL-Sailer integrates two key innovations: (i) adaptive leverage score sampling, which selects biologically interpretable features while reducing dimensionality by 80%, and (ii) an invariant VAE architecture, which disentangles biological signals from technical confounders via mutual information minimization. We provide a convergence guarantee, showing that FL-Sailer converges to an approximate solution of the original high-dimensional problem with bounded error. Extensive experiments on synthetic and real epigenomic datasets demonstrate that FL-Sailer not only enables previously infeasible multi-institutional collaborations but also surpasses centralized methods by leveraging adaptive sampling as an implicit regularizer to suppress technical noise. Our work establishes that federated learning, when tailored to domain-specific challenges, can become a superior paradigm for collaborative epigenomic research.

cs.LG↗

arXiv2026

Location-Agnostic Channel Knowledge Map Construction for Dynamic Scenes

To alleviate the pilot and CSI-feedback burden in 6G, channel knowledge map (CKM) has emerged as a promising approach that predicts CSI solely from user locations. Nevertheless, accurate location information is rarely available in current systems. Moreover, the uncertainty inherent to highly dynamic scenes further degrades the performance of existing schemes that typically assume quasi-static scenarios. In this paper, we propose a novel framework named location-agnostic dynamic CKM (LAD-CKM). Specifically, LAD-CKM is constructed through dynamic radio frequency (RF) radiance field rendering, which takes instantaneous uplink CSI and partial downlink CSI as inputs. To enable effective rendering, a dedicated radiator representation network (RARE-Net) is designed to capture the spatial-spectral correlations within the inputs. Furthermore, an adaptive deformation module is devised to deform the uplink CSI-based queries of RARE-Net according to instantaneous channel dynamics, thereby enhancing CSI prediction accuracy under mobility. In addition, a novel synthetic channel dataset is created in outdoor dynamic scenes via ray-tracing. Simulation results demonstrate that LAD-CKM yields significant performance gains compared with existing baselines in terms of effective data rate.

eess.SP↗

arXiv2026

Prediction-Powered Risk Monitoring of Deployed Models for Detecting Harmful Distribution Shifts

We study the problem of monitoring model performance in dynamic environments where labeled data are limited. To this end, we propose prediction-powered risk monitoring (PPRM), a semi-supervised risk-monitoring approach based on prediction-powered inference (PPI). PPRM constructs anytime-valid lower bounds on the running risk by combining synthetic labels with a small set of true labels. Harmful shifts are detected via a threshold-based comparison with an upper bound on the nominal risk, satisfying assumption-free finite-sample guarantees on the type-I error. We demonstrate the effectiveness of PPRM through extensive experiments on image classification, large language model (LLM), and telecommunications monitoring tasks.

cs.LG↗

arXiv2026

F$^4$-CKM: Learning Channel Knowledge Map with Radio Frequency Radiance Field Rendering

In 6G mobile communications, acquiring accurate and timely channel state information (CSI) becomes increasingly challenging due to the growing antenna array size and bandwidth. To alleviate the CSI feedback burden, the channel knowledge map (CKM) has emerged as a promising approach by leveraging environment-aware techniques to predict CSI based solely on user locations. However, how to effectively construct a CKM remains an open issue. In this paper, we propose F$^4$-CKM, a novel CKM construction framework characterized by four distinctive features: radiance Field rendering, spatial-Frequency-awareness, location-Free usage, and Fast learning. Central to our design is the adaptation of radiance field rendering techniques from computer vision to the radio frequency (RF) domain, enabled by a novel Wireless Radiator Representation (WiRARE) network that captures the spatial-frequency characteristics of wireless channels. Additionally, a novel shaping filter module and an angular sampling strategy are introduced to facilitate CKM construction. Extensive experiments demonstrate that F$^4$-CKM significantly outperforms existing baselines in terms of wireless channel prediction accuracy and efficiency.

eess.SP↗

arXiv2025

Conformal Sparsification for Bandwidth-Efficient Edge-Cloud Speculative Decoding

Edge-cloud speculative decoding (SD) accelerates inference by having a cloud-based large language model (LLM) that verifies draft tokens generated by a resource-constrained small language model (SLM) at the edge. A central bottleneck is the limited bandwidth of the edge-cloud link, which necessitates efficient compression of draft token distributions. We first derive an information-theoretic bound that decomposes the token rejection rate into contributions from SLM-LLM distribution mismatch and from quantization distortion. Guided by this analysis, we propose the Sparse Quantize-and-Sample SD (SQS-SD) framework, which exploits distributional sparsity through structured sparsification and lattice-based quantization. Within this framework, K-SQS applies fixed top-K truncation, while C-SQS adaptively adjusts the retained token set via online conformal prediction to ensure bounded deviation from the dense distribution. Empirical results confirm that both approaches improve end-to-end latency and rejection rates in complimentary operating regimes.

cs.LG↗

arXiv2025

Rethinking Unsupervised Cross-modal Flow Estimation: Learning from Decoupled Optimization and Consistency Constraint

This work presents DCFlow, a novel unsupervised cross-modal flow estimation framework that integrates a decoupled optimization strategy and a cross-modal consistency constraint. Unlike previous approaches that implicitly learn flow estimation solely from appearance similarity, we introduce a decoupled optimization strategy with task-specific supervision to address modality discrepancy and geometric misalignment distinctly. This is achieved by collaboratively training a modality transfer network and a flow estimation network. To enable reliable motion supervision without ground-truth flow, we propose a geometry-aware data synthesis pipeline combined with an outlier-robust loss. Additionally, we introduce a cross-modal consistency constraint to jointly optimize both networks, significantly improving flow prediction accuracy. For evaluation, we construct a comprehensive cross-modal flow benchmark by repurposing public datasets. Experimental results demonstrate that DCFlow can be integrated with various flow estimation networks and achieves state-of-the-art performance among unsupervised approaches.

cs.CV↗

arXiv2025

Boosting Multi-View Indoor 3D Object Detection via Adaptive 3D Volume Construction

This work presents SGCDet, a novel multi-view indoor 3D object detection framework based on adaptive 3D volume construction. Unlike previous approaches that restrict the receptive field of voxels to fixed locations on images, we introduce a geometry and context aware aggregation module to integrate geometric and contextual information within adaptive regions in each image and dynamically adjust the contributions from different views, enhancing the representation capability of voxel features. Furthermore, we propose a sparse volume construction strategy that adaptively identifies and selects voxels with high occupancy probabilities for feature refinement, minimizing redundant computation in free space. Benefiting from the above designs, our framework achieves effective and efficient volume construction in an adaptive way. Better still, our network can be supervised using only 3D bounding boxes, eliminating the dependence on ground-truth scene geometry. Experimental results demonstrate that SGCDet achieves state-of-the-art performance on the ScanNet, ScanNet200 and ARKitScenes datasets. The source code is available at https://github.com/RM-Zhang/SGCDet.

cs.CV↗

arXiv2025

Quantize-Sample-and-Verify: LLM Acceleration via Adaptive Edge-Cloud Speculative Decoding

In edge-cloud speculative decoding (SD), edge devices equipped with small language models (SLMs) generate draft tokens that are verified by large language models (LLMs) in the cloud. A key bottleneck in such systems is the limited communication bandwidth between edge and cloud, which necessitates quantization of the information transmitted about generated tokens. In this work, we introduce a novel quantize-sample (Q-S) strategy that provably preserves the output distribution of the cloud-based model, ensuring that the verified tokens match the distribution of those that would have been generated directly by the LLM. We develop a throughput model for edge-cloud SD that explicitly accounts for communication latency. Leveraging this model, we propose an adaptive mechanism that optimizes token throughput by dynamically adjusting the draft length and quantization precision in response to both semantic uncertainty and channel conditions. Simulations demonstrate that the proposed Q-S approach significantly improves decoding efficiency in realistic edge-cloud deployment scenarios.

eess.SP↗

arXiv2025

Piecewise Linear Approximation in Learned Index Structures: Theoretical and Empirical Analysis

A growing trend in the database and system communities is to augment conventional index structures, such as B+-trees, with machine learning (ML) models. Among these, error-bounded Piecewise Linear Approximation ($\epsilon$-PLA) has emerged as a popular choice due to its simplicity and effectiveness. Despite its central role in many learned indexes, the design and analysis of $\epsilon$-PLA fitting algorithms remain underexplored. In this paper, we revisit $\epsilon$-PLA from both theoretical and empirical perspectives, with a focus on its application in learned index structures. We first establish a fundamentally improved lower bound of $\Omega(\kappa \cdot \epsilon^2)$ on the expected segment coverage for existing $\epsilon$-PLA fitting algorithms, where $\kappa$ is a data-dependent constant. We then present a comprehensive benchmark of state-of-the-art $\epsilon$-PLA algorithms when used in different learned data structures. Our results highlight key trade-offs among model accuracy, model size, and query performance, providing actionable guidelines for the principled design of future learned data structures.

cs.DB↗

arXiv2025

Dynamic Bandwidth Allocation for Hybrid Event-RGB Transmission

Event cameras asynchronously capture pixel-level intensity changes with extremely low latency. They are increasingly used in conjunction with RGB cameras for a wide range of vision-related applications. However, a major challenge in these hybrid systems lies in the transmission of the large volume of triggered events and RGB images. To address this, we propose a transmission scheme that retains efficient reconstruction performance of both sources while accomplishing real-time deblurring in parallel. Conventional RGB cameras and event cameras typically capture the same scene in different ways, often resulting in significant redundant information across their outputs. To address this, we develop a joint event and image (E-I) transmission framework to eliminate redundancy and thereby optimize channel bandwidth utilization. Our approach employs Bayesian modeling and the information bottleneck method to disentangle the shared and domain-specific information within the E-I inputs. This disentangled information bottleneck framework ensures both the compactness and informativeness of extracted shared and domain-specific information. Moreover, it adaptively allocates transmission bandwidth based on scene dynamics, i.e., more symbols are allocated to events for dynamic details or to images for static information. Simulation results demonstrate that the proposed scheme not only achieves superior reconstruction quality compared to conventional systems but also delivers enhanced deblurring performance.

cs.CV↗

arXiv2025

Efficient and Practical Approximation Algorithms for Advertising in Content Feeds

Content feeds provided by platforms such as X (formerly Twitter) and TikTok are consumed by users on a daily basis. In this paper, we revisit the native advertising problem in content feeds, initiated by Ieong et al. Given a sequence of organic items (e.g., videos or posts) relevant to a user's interests or to an information search, the goal is to place ads within the organic content so as to maximize a reward function (e.g., number of clicks), while accounting for two considerations: (1) an ad can only be inserted after a relevant content item; (2) the users' attention decays after consuming content or ads. These considerations provide a natural model for capturing both the advertisement effectiveness and the user experience. In this paper, we design fast and practical 2-approximation greedy algorithms for the associated optimization problem, improving over the best-known practical algorithm that only achieves an approximation factor of~4. Our algorithms exploit a counter-intuitive observation, namely, while top items are seemingly more important due to the decaying attention of the user, taking good care of the bottom items is key for obtaining improved approximation guarantees. We then provide the first comprehensive empirical evaluation on the problem, showing the strong empirical performance of our~methods.

cs.DS↗

arXiv2025

Joint Transmission and Deblurring: A Semantic Communication Approach Using Events

Deep learning-based joint source-channel coding (JSCC) is emerging as a promising technology for effective image transmission. However, most existing approaches focus on transmitting clear images, overlooking real-world challenges such as motion blur caused by camera shaking or fast-moving objects. Motion blur often degrades image quality, making transmission and reconstruction more challenging. Event cameras, which asynchronously record pixel intensity changes with extremely low latency, have shown great potential for motion deblurring tasks. However, the efficient transmission of the abundant data generated by event cameras remains a significant challenge. In this work, we propose a novel JSCC framework for the joint transmission of blurry images and events, aimed at achieving high-quality reconstructions under limited channel bandwidth. This approach is designed as a deblurring task-oriented JSCC system. Since RGB cameras and event cameras capture the same scene through different modalities, their outputs contain both shared and domain-specific information. To avoid repeatedly transmitting the shared information, we extract and transmit their shared information and domain-specific information, respectively. At the receiver, the received signals are processed by a deblurring decoder to generate clear images. Additionally, we introduce a multi-stage training strategy to train the proposed model. Simulation results demonstrate that our method significantly outperforms existing JSCC-based image transmission schemes, addressing motion blur effectively.

eess.IV↗