arXiv subjects

Yanan Ma

Publications and source records attributed to Yanan Ma.

At least 19 recordsLinked to original sources

arXiv2026

HealthLoopQA: A Context-Aware Question Answering Benchmark for Interpreting Wearable Monitoring Data in Diabetes Care

As medical wearables become integrated into daily chronic disease care, effectively interpreting longitudinal monitoring data is essential for patients and clinicians to understand health trends, detect safety-critical events, and make informed decisions. While large language models (LLMs) show promise for transforming this streaming physiological data into personalized health insights, evaluating their reasoning capability and analytical rigor in diverse monitoring tasks remains a fundamental challenge. Existing medical wearable question answering (QA) benchmarks primarily assess short-horizon classification or statistical summaries, largely ignoring the long-term patterns, therapeutic and behavioural contexts, and potential system failures inherent in real-world deployments. To address this, we introduce HealthLoopQA, a comprehensive diagnostic benchmark for evaluating LLM reasoning over continuous diabetes monitoring data. Grounded in a novel taxonomy of eleven atomic reasoning abilities, HealthLoopQA comprises 127 tasks and over 1,500 QA instances spanning process mining, anomaly detection, and prediction over 30-day horizons. To systematically evaluate safety awareness, we complement real-world datasets with a fault-injected simulation testbed modeling diverse device malfunctions and cyber-physical attacks to generate physiologically plausible hazard scenarios. Evaluating state-of-the-art LLMs across prompting and agentic frameworks reveals severe limitations in complex temporal pattern mining. Furthermore, we identify a broader phenomenon of In-context Laziness under long-context prompting, highlighting critical open challenges in deploying LLMs for rigorous long-horizon medical reasoning.

cs.LG↗

arXiv2026

Reading Between the Frames: Interpreting Implicit and Non-literal Meaning in Social Media Videos

Social media videos often communicate meanings that go beyond their visible actions, captions, or speech. A mundane clip may become humorous, ironic, or satire only through the interaction of multimodal cues and cultural context, making such content a difficult test case for video-language models. In this paper, we introduce \textit{DrivelHub+}, a benchmark for evaluating whether models can infer the implicit, non-linear, and rhetorically layered meanings of social media videos that appear nonsensical on the surface but convey deliberate pragmatic meanings. DrivelHub+ consists of 1,000 videos collected from social media, each annotated with a human-written implicit narrative explanation. Unlike conventional video understanding tasks focused on recognition or description, we present a benchmark that targets contextual multimodal reasoning. We evaluate current video-language models from two perspectives: explanation, where models must explain the pragmatic comprehension of a video in natural language; and representation, where we adapt reasoning-as-retrieval to test whether model representations align videos with their corresponding implicit narratives in both video-to-text and text-to-video retrieval. Our benchmark provides a diagnostic setting for measuring the gap between multimodal perception and pragmatic comprehension, asking whether current models can move beyond describing what is shown to inferring what is meant.

cs.CL↗

arXiv2026

Update the Unseen Only: Minimizing AoI for Collaborative Perception through Online Learning

While collaborative perception (CP) enhances the safety of autonomous driving, limited bandwidth can cause severe shared data staleness in CP systems. Existing age-of-information (AoI) minimization policies are not well-suited for CP, as they overlook the fact that a vehicle's AoI decreases not only through updates from the source (i.e., a base station) but also through the vehicle's local sensing. To address this issue, we propose a mobility-aware AoI minimization framework for CP that explicitly accounts for vehicles' dynamic sensing ranges. We first derive a closed-form expression for the long-term time average sum AoI within a considered region, accommodating an ever-changing vehicle population and their dynamic sensed areas. Based on this characterization, we develop Local-sensing-aware Max-Weight Scheduling (LocMW), an online learning algorithm designed for sensor information broadcast from a source to vehicles under unknown environmental statistics and delayed observations. We provide performance guarantees demonstrating that LocMW achieves a sublinear cumulative excess AoI compared to the optimal stationary randomized benchmark. Extensive simulations using vehicular trajectory datasets and 3D perception tasks demonstrate that our LocMW policy substantially outperforms competing baselines, reducing the time-averaged sum AoI by up to 31.6% and improving mAP detection accuracy by up to 16.3%.

cs.NI↗

arXiv2026

Are Reasoning Vision-Language Models Robust to Semantic Visual Distractions?

Reasoning Vision-Language Models (VLMs) achieve strong performance on complex multimodal tasks, but reliable real-world application requires handling visual inputs that are messier than clean, curated benchmarks. Existing works mainly evaluate such reliability of VLMs through input corruptions, such as noise, blur and weather effects, which make visual evidence harder to perceive. This leaves a critical reliability failure mode underexplored: a model may perceive the evidence correctly, yet reason from plausible but irrelevant and distracting evidence and propagate this mistake to its final answer. To address this gap, we introduce \textbf{Distract-Bench}, a benchmark for evaluating VLM robustness to \textbf{semantic visual distractions}, defined as meaningful but task-irrelevant visual cues added to inputs while preserving the ground-truth answer. We comprehensively evaluate eight leading open-source and two closed-source VLMs across conventional vision corruptions and Distract-Bench. Our results show that Distract-Bench exposes a robustness failure distinct from vision corruptions: reasoning VLMs largely track their non-reasoning base models under perceptual degradation, but show consistently lower robustness to semantic distractions. Further analysis shows that these distractions often enter the reasoning process of VLMs, are treated as evidence, and lead to incorrect answers. Together, these findings reframe robustness evaluation for reasoning VLMs, shifting the focus from degraded perception to distractions for reliable real-world visual reasoning. Our data and code are available at https://github.com/Yizheng-Sun/Distract-Bench.

cs.CV↗

arXiv2026

V2VCrafter: Consistent Street-View Image Generation Across Vehicles

Connected and autonomous driving (CAD) systems leverage vehicle-to-vehicle (V2V) communication for multi-agent collaborative perception, yet remain constrained by scarce annotated real-world V2V datasets and limited generalization across diverse driving conditions. While image generation offers a feasible solution for data augmentation, existing single-vehicle multi-view generation frameworks face two key challenges in multi-agent settings: (1) the expanded learning objective degrades generation quality, and (2) dynamic inter-agent variation hinders consistency modeling for physical attributes (e.g., color, category) of jointly observed objects. To bridge this gap, we propose V2VCrafter, the first framework for generating controllable and realistic multi-view driving images across vehicles. For effective learning, we develop a progressive multi-agent diffusion model based on a single-agent backbone, using neighboring agents' latent states to progressively guide single-to-multi-agent generation. To address cross-vehicle inconsistency, we further propose a cross-agent attention module that leverages a collaboration view graph and learnable jointly observed object representations to model dynamic cross-vehicle camera view relationships. Experiments on real-world V2X-Real dataset show that V2VCrafter generates high-fidelity, controllable, and consistent street views across vehicles, thereby effectively enhancing downstream collaborative 3D object detection tasks.

cs.CV↗

arXiv2026

Collaborative Air-Ground Sensing, Communication, Computing, Storage, and Intelligence for Low-Altitude Economy

Low-altitude economy (LAE) is transforming low-altitude airspace into a new cyber-physical infrastructure. Although air-ground communications have been widely studied, LAE is fundamentally different in the sense that it is mission-centric with diverse requirements, such as stringent safety and compliance constraints not be effectively addressed with a communication-centric design alone, which makes air-ground collaboration indispensable: Only through effectively coordinating air-ground infrastructure and resources can LAE missions be fulfilled. Consequently, LAE calls for task-driven, closed-loop, multi-resource orchestration of Sensing, Communication, Computing, Storage, and Intelligence (SCCSI), where key decisions must be co-designed under mobility and uncertainty. In this paper, we first present a novel framework that connects (i) LAE scenarios and a requirement--resource coupling matrix, (ii) an air--ground collaborative architecture, and (iii) methodological toolboxes for SCCSI co-optimization and online decision-making. We then systematically review enabling technologies for collaborative SCCSI resources and capabilities, emphasizing their coupling and end-to-end tradeoffs. Finally, we summarize testbeds, datasets, and evaluation metrics, and provide representative use cases to illustrate how the proposed framework translates application requirements into practical task-driven optimization designs, together with open challenges and a roadmap toward scalable and trustworthy LAE deployment.

cs.NI↗

arXiv2026

CXR-ContraBench: Benchmarking Negated-Option Attraction in Medical VLMs

When a chest X-ray shows consolidation but the question asks which finding is present, a medical vision-language model may answer "No consolidation." This is more than an incorrect choice: it is a polarity reversal that emits a clinical statement contradicting the image. We study this failure as negated-option attraction, where a model is drawn to a negated answer option even when it conflicts with both the visual evidence and the question. We introduce CXR-ContraBench (Chest X-Ray Contradiction Benchmark), a diagnostic benchmark spanning internal ReXVQA slices and external OpenI and CheXpert protocols. The benchmark centers on present-finding questions, where selecting "No X" despite visible X creates the main clinical risk, and uses absent-finding questions as secondary tests of whether models copy negated wording. Across CheXpert protocols, the failure is substantial and persistent. On a strict direct presence probe, MedGemma and Qwen2.5-VL reach only 31.49% and 30.21% accuracy, respectively; on a matched 135,754-record CheXpert training-split protocol, both models select negated options on over 62% of presence questions. Chain-of-thought prompting reduces some presence-side reversals but does not eliminate them and can amplify absence-side contradictions. Finally, QCCV-Neg (Question-Conditioned Consistency Verifier for Negation) deterministically repairs the measured polarity-confused subset without retraining, raising MedGemma and Qwen2.5-VL to 96.60% and 95.32% accuracy on the direct presence probe. These results show that standard accuracy can hide a clinically meaningful inference-time polarity failure. Source code and benchmark construction scripts are available at https://github.com/fangzr/cxr-contrabench-code.

cs.CV↗

arXiv2026

Birdcast: Interest-aware BEV Multicasting for Infrastructure-assisted Collaborative Perception

Vehicle-to-infrastructure collaborative perception (V2I-CP) leverages a high-vantage node to transmit supplementary information, i.e., bird's-eye-view (BEV) feature maps, to vehicles, effectively overcoming line-of-sight limitations. However, the downlink V2I transmission introduces a significant communication bottleneck. Moreover, vehicles in V2I-CP require \textit{heterogeneous yet overlapping} information tailored to their unique occlusions and locations, rendering standard unicast/broadcast protocols inefficient. To address this limitation, we propose \textit{Birdcast}, a novel multicasting framework for V2I-CP. By accounting for individual maps of interest, we formulate a joint feature selection and multicast grouping problem to maximize network-wide utility under communication constraints. Since this formulation is a mixed-integer nonlinear program and is NP-hard, we develop an accelerated greedy algorithm with a theoretical $(1 - 1/\sqrt{e})$ approximation guarantee. While motivated by CP, Birdcast provides a general framework applicable to a wide range of multicasting systems where users possess heterogeneous interests and varying channel conditions. Extensive simulations on the V2X-Sim dataset demonstrate that Birdcast significantly outperforms state-of-the-art baselines in both system utility and perception quality, achieving up to 27\% improvement in total utility and a 3.2\% increase in mean average precision (mAP).

cs.NI↗

arXiv2026

UAV-enabled Computing Power Networks: Design and Performance Analysis under Energy Constraints

This paper presents an innovative framework that boosts computing power by utilizing ubiquitous computing power distribution and enabling higher computing node accessibility via adaptive UAV positioning, establishing a UAV-enabled Computing Power Network (UAV-CPN). In a UAV-CPN, a UAV functions as a dynamic relay, outsourcing computing tasks from the request zone to an expanded service zone with diverse computing nodes, including vehicle onboard units, edge servers, and dedicated powerful nodes. This approach has the potential to alleviate communication bottlenecks and overcome the "island effect" observed in multi-access edge computing. A significant challenge is to quantify computing power performance under complex dynamics of communication and computing. To address this challenge, we introduce task completion probability to capture the capability of UAV-CPNs for task computing. We further enhance UAV-CPN performance under a hybrid energy architecture by jointly optimizing UAV altitude and transmit power, where fuel cells and batteries collectively power both UAV propulsion and communication systems. Extensive evaluations show significant performance gains, highlighting the importance of balancing communication and computing capabilities, especially under dual-energy constraints. These findings underscore the potential of UAV-CPNs to significantly boost computing power.

cs.NI↗

arXiv2026

HFedMoE: Resource-aware Heterogeneous Federated Learning with Mixture-of-Experts

While federated learning (FL) enables fine-tuning of large language models (LLMs) without compromising data privacy, the substantial size of an LLM renders on-device training impractical for resource-constrained clients, such as mobile devices. Thus, Mixture-of-Experts (MoE) models have emerged as a computation-efficient solution, which activates only a sparse subset of experts during model training to reduce computing burden without sacrificing performance. Though integrating MoE into FL fine-tuning holds significant potential, it still encounters three key challenges: i) selecting appropriate experts for clients remains challenging due to the lack of a reliable metric to measure each expert's impact on local fine-tuning performance, ii) the heterogeneous computing resources across clients severely hinder MoE-based LLM fine-tuning, as dynamic expert activations across diverse input samples can overwhelm resource-constrained devices, and iii) client-specific expert subsets and routing preference undermine global aggregation, where misaligned expert updates and inconsistent gating networks in troduce destructive interference. To address these challenges, we propose HFedMoE, a heterogeneous MoE-based FL fine-tuning framework that customizes a subset of experts to each client for computation-efficient LLM fine-tuning. Specifically, HFedMoE identifies the expert importance based on its contributions to fine-tuning performance, and then adaptively selects a subset of experts from an information bottleneck perspective to align with each client' s computing budget. A sparsity-aware model aggregation strategy is also designed to aggregate the actively fine-tuned experts and gating parameters with importance weighted contributions. Extensive experiments demonstrate that HFedMoE outperforms state-of-the-art benchmarks in training accuracy and convergence speed.

cs.LG↗

arXiv2025

UAV-enabled Computing Power Networks: Task Completion Probability Analysis

This paper presents an innovative framework that synergistically enhances computing performance through ubiquitous computing power distribution and dynamic computing node accessibility control via adaptive unmanned aerial vehicle (UAV) positioning, establishing UAV-enabled Computing Power Networks (UAV-CPNs). In UAV-CPNs, UAVs function as dynamic aerial relays, outsourcing tasks generated in the request zone to an expanded service zone, consisting of a diverse range of computing devices, from vehicles with onboard computational capabilities and edge servers to dedicated computing nodes. This approach has the potential to alleviate communication bottlenecks in traditional computing power networks and overcome the "island effect" observed in multi-access edge computing. However, how to quantify the network performance under the complex spatio-temporal dynamics of both communication and computing power is a significant challenge, which introduces intricacies beyond those found in conventional networks. To address this, in this paper, we introduce task completion probability as the primary performance metric for evaluating the ability of UAV-CPNs to complete ground users' tasks within specified end-to-end latency requirements. Utilizing theories from stochastic processes and stochastic geometry, we derive analytical expressions that facilitate the assessment of this metric. Our numerical results emphasize that striking a delicate balance between communication and computational capabilities is essential for enhancing the performance of UAV-CPNs. Moreover, our findings show significant performance gains from the widespread distribution of computing nodes.

cs.NI↗

arXiv2025

Multi-Server FL with Overlapping Clients: A Latency-Aware Relay Framework

Multi-server Federated Learning (FL) has emerged as a promising solution to mitigate communication bottlenecks of single-server FL. In a typical multi-server FL architecture, the regions covered by different edge servers (ESs) may overlap. Under this architecture, clients located in the overlapping areas can access edge models from multiple ESs. Building on this observation, we propose a cloud-free multi-server FL framework that leverages Overlapping Clients (OCs) as relays for inter-server model exchange while uploading the local updated model to ESs. This enables ES models to be relayed across multiple hops through neighboring ESs by OCs without introducing new communication links. We derive a new convergence upper bound for non-convex objectives under non-IID data and an arbitrary number of cells, which explicitly quantifies the impact of inter-server propagation depth on convergence error. Guided by this theoretical result, we formulate an optimization problem that aims to maximize dissemination range of each ES model among all ESs within a limited latency. To solve this problem, we develop a conflict-graph-based local search algorithm optimizing the routing strategy and scheduling the transmission times of individual ESs to its neighboring ESs. This enables ES models to be relayed across multiple hops through neighboring ESs by OCs, achieving the widest possible transmission coverage for each model without introducing new communication links. Extensive experimental results show remarkable performance gains of our scheme compared to existing methods.

cs.NI↗

arXiv2025

FedOC: Multi-Server FL with Overlapping Client Relays in Wireless Edge Networks

Multi-server Federated Learning (FL) has emerged as a promising solution to mitigate communication bottlenecks of single-server FL. We focus on a typical multi-server FL architecture, where the regions covered by different edge servers (ESs) may overlap. A key observation of this architecture is that clients located in the overlapping areas can access edge models from multiple ESs. Building on this insight, we propose FedOC (Federated learning with Overlapping Clients), a novel framework designed to fully exploit the potential of these overlapping clients. In FedOC, overlapping clients could serve dual roles: (1) as Relay Overlapping Clients (ROCs), they forward edge models between neighboring ESs in real time to facilitate model sharing among different ESs; and (2) as Normal Overlapping Clients (NOCs), they dynamically select their initial model for local training based on the edge model delivery time, which enables indirect data fusion among different regions of ESs. The overall FedOC workflow proceeds as follows: in every round, each client trains local model based on the earliest received edge model and transmits to the respective ESs for model aggregation. Then each ES transmits the aggregated edge model to neighboring ESs through ROC relaying. Upon receiving the relayed models, each ES performs a second aggregation and subsequently broadcasts the updated model to covered clients. The existence of ROCs enables the model of each ES to be disseminated to the other ESs in a decentralized manner, which indirectly achieves intercell model and speeding up the training process, making it well-suited for latency-sensitive edge environments. Extensive experimental results show remarkable performance gains of our scheme compared to existing methods.

cs.NI↗

arXiv2025

NWaaS: A Non-Intrusive and Privacy-Preserving Watermarking-as-a-Service System with Adaptive Resource Scheduling

Securing intellectual property (IP) in Machine Learning as a Service is critical yet challenging. While deep neural network watermarking serves as a standard defense against model extraction, existing Watermarking-as-a-Service paradigms face a triple challenge of intrusiveness, privacy risks, and inefficiency. To address these challenges, we propose Non-intrusive Watermarking as a Service (NWaaS), a holistic framework enabling trustworthy and efficient IP protection. We first introduce $\mathtt{ShadowMark}$, a novel watermarking algorithm that establishes a side-channel for ownership verification without modifying the model. It ensures zero performance degradation and eliminates the need for parameter-heavy fine-tuning as well as access to original training data, thereby addressing the intrusiveness and inefficiency inherent in existing approaches. Leveraging this non-intrusive property, we design a collaborative partitioning mechanism that allows model owners to offload self-defined partial layers, enabling a flexible trade-off between IP privacy and service cost. Furthermore, to mitigate latency from collaborative computing under high concurrency and enhance system resource utilization, we propose proportion disparity joint scheduling, a payload-balancing resource scheduling algorithm tailored to the heterogeneous constraints of edge-cloud environments. Extensive experiments demonstrate that NWaaS provides robust ownership verification across diverse continuous X-to-Image modalities, while ensuring secure owner privacy protection and superior system performance.

cs.CR↗

arXiv2025

Task-Aware Parameter-Efficient Fine-Tuning of Large Pre-Trained Models at the Edge

Large language models (LLMs) have achieved remarkable success in various tasks, such as decision-making, reasoning, and question answering. They have been widely used in edge devices. However, fine-tuning LLMs to specific tasks at the edge is challenging due to the high computational cost and the limited storage and energy resources at the edge. To address this issue, we propose TaskEdge, a task-aware parameter-efficient fine-tuning framework at the edge, which allocates the most effective parameters to the target task and only updates the task-specific parameters. Specifically, we first design a parameter importance calculation criterion that incorporates both weights and input activations into the computation of weight importance. Then, we propose a model-agnostic task-specific parameter allocation algorithm to ensure that task-specific parameters are distributed evenly across the model, rather than being concentrated in specific regions. In doing so, TaskEdge can significantly reduce the computational cost and memory usage while maintaining performance on the target downstream tasks by updating less than 0.1\% of the parameters. In addition, TaskEdge can be easily integrated with structured sparsity to enable acceleration by NVIDIA's specialized sparse tensor cores, and it can be seamlessly integrated with LoRA to enable efficient sparse low-rank adaptation. Extensive experiments on various tasks demonstrate the effectiveness of TaskEdge.

cs.LG↗

arXiv2025

Sense4FL: Vehicular Crowdsensing Enhanced Federated Learning for Object Detection in Autonomous Driving

To accommodate constantly changing road conditions, real-time vision model training is essential for autonomous driving (AD). Federated learning (FL) serves as a promising paradigm to enable autonomous vehicles to train models collaboratively with their onboard computing resources. However, existing vehicle selection schemes for FL all assume predetermined and location-independent vehicles' datasets, neglecting the fact that vehicles collect training data along their routes, thereby resulting in suboptimal vehicle selection. In this paper, we focus on the fundamental perception problem and propose Sense4FL, a vehicular crowdsensing-enhanced FL framework featuring \textit{trajectory-dependent} vehicular \textit{training data collection} to \rev{improve the object detection quality} in AD for a region. To this end, we first derive the convergence bound of FL by considering the impact of both vehicles' uncertain trajectories and uploading probabilities, from which we discover that minimizing the training loss is equivalent to minimizing a weighted sum of local and global earth mover's distance (EMD) between vehicles' collected data distribution and global data distribution. Based on this observation, we formulate the trajectory-dependent vehicle selection and data collection problem for FL in AD. Given that the problem is NP-hard, we develop an efficient algorithm to find the solution with an approximation guarantee. Extensive simulation results have demonstrated the effectiveness of our approach in improving object detection performance compared with existing benchmarks.

cs.RO↗

arXiv2025

RAISE: Optimizing RIS Placement to Maximize Task Throughput in Multi-Server Vehicular Edge Computing

Given the limited computing capabilities on autonomous vehicles, onboard processing of large volumes of latency-sensitive tasks presents significant challenges. While vehicular edge computing (VEC) has emerged as a solution, offloading data-intensive tasks to roadside servers or other vehicles is hindered by large obstacles like trucks/buses and the surge in service demands during rush hours. To address these challenges, Reconfigurable Intelligent Surface (RIS) can be leveraged to mitigate interference from ground signals and reach more edge servers by elevating RIS adaptively. To this end, we propose RAISE, an optimization framework for RIS placement in multi-server VEC systems. Specifically, RAISE optimizes RIS altitude and tilt angle together with the optimal task assignment to maximize task throughput under deadline constraints. To find a solution, a two-layer optimization approach is proposed, where the inner layer exploits the unimodularity of the task assignment problem to derive the efficient optimal strategy while the outer layer develops a near-optimal hill climbing (HC) algorithm for RIS placement with low complexity. Extensive experiments demonstrate that the proposed RAISE framework consistently outperforms existing benchmarks.

cs.NI↗

arXiv2024

CAST: Corpus-Aware Self-similarity Enhanced Topic modelling

Topic modelling is a pivotal unsupervised machine learning technique for extracting valuable insights from large document collections. Existing neural topic modelling methods often encode contextual information of documents, while ignoring contextual details of candidate centroid words, leading to the inaccurate selection of topic words due to the contextualization gap. In parallel, it is found that functional words are frequently selected over topical words. To address these limitations, we introduce CAST: Corpus-Aware Self-similarity Enhanced Topic modelling, a novel topic modelling method that builds upon candidate centroid word embeddings contextualized on the dataset, and a novel self-similarity-based method to filter out less meaningful tokens. Inspired by findings in contrastive learning that self-similarities of functional token embeddings in different contexts are much lower than topical tokens, we find self-similarity to be an effective metric to prevent functional words from acting as candidate topic words. Our approach significantly enhances the coherence and diversity of generated topics, as well as the topic model's ability to handle noisy data. Experiments on news benchmark datasets and one Twitter dataset demonstrate the method's superiority in generating coherent, diverse topics, and handling noisy data, outperforming strong baselines.

cs.CL↗