BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Yuguang Fang

Yuguang Fang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Networking and Internet ArchitectureMachine LearningArtificial IntelligenceComputer Visioneess.SPComputation and LanguageComputer Science and Game TheoryDistributed, Parallel, and Cluster ComputingInformation Theorymath.IT

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
14works
0followers
10topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

14 published item(s)

preprint2026arXiv

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.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Decoder Gradient Shields: A Family of Provable and High-Fidelity Methods Against Gradient-Based Box-Free Watermark Removal

Box-free model watermarking has gained significant attention in deep neural network (DNN) intellectual property protection due to its model-agnostic nature and its ability to flexibly manage high-entropy image outputs from generative models. Typically operating in a black-box manner, it employs an encoder-decoder framework for watermark embedding and extraction. While existing research has focused primarily on the encoders for the robustness to resist various attacks, the decoders have been largely overlooked, leading to attacks against the watermark. In this paper, we identify one such attack against the decoder, where query responses are utilized to obtain backpropagated gradients to train a watermark remover. To address this issue, we propose Decoder Gradient Shields (DGSs), a family of defense mechanisms, including DGS at the output (DGS-O), at the input (DGS-I), and in the layers (DGS-L) of the decoder, with a closed-form solution for DGS-O and provable performance for all DGS. Leveraging the joint design of reorienting and rescaling of the gradients from watermark channel gradient leaking queries, the proposed DGSs effectively prevent the watermark remover from achieving training convergence to the desired low-loss value, while preserving image quality of the decoder output. We demonstrate the effectiveness of our proposed DGSs in diverse application scenarios. Our experimental results on deraining and image generation tasks with the state-of-the-art box-free watermarking show that our DGSs achieve a defense success rate of 100% under all settings.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

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.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Inference-Time Budget Control for LLM Search Agents

LLM search agents increasingly rely on tools at inference time, but their trajectories are often constrained by hard limits on both tool calls and generated tokens. Under such dual budgets, better answers require not only stronger models, but also explicit control over which search action should receive the next budget unit and when the accumulated evidence is sufficient to commit a final answer. We study this problem in multi-hop question answering (QA) and formulate it as two-stage inference-time budget control. At search time, our controller assigns each feasible action a task-level Value-of-Information (VOI) score, defined as an operational estimate of marginal task value per unit budget under the current search state and remaining dual budget, and uses this score to choose among retrieval, decomposition, and answer commitment. After search, a selective evidence-grounded finalizer compares the trajectory answer with a refined candidate and rewrites only when the residual error appears to be a low-risk answer-form error. Across four multi-hop QA benchmarks, three LLM backbones, and four budget levels, the method yields positive aggregate gains over four audited baselines under the same hard dual-budget protocol. Ablations show that search-time budget control, especially budget-dependent penalty, provides the main performance gain, while answer-time control helps mainly when the retrieval path is already adequate. These results suggest that inference-time budget control for LLM search agents should govern both how budget is spent during search and how the final answer is committed.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers

Long-horizon LLM agents depend on intermediate information-gathering turns, yet training feedback is usually observed only at the final answer, because process-level rewards require high-quality human annotation. Existing turn-level shaping methods reward turns that increase the likelihood of a gold answer, but they require answer supervision or stable task-specific verifiers. Conversely, label-free RL methods extract self-signals from output distributions, but mainly at the answer or trajectory level and therefore cannot assign credit to intermediate turns. We propose Self-Induced Outcome Potential (SIOP), which treats semantic clusters of final answers as latent future outcome states for potential-based turn-level credit assignment. For each query, SIOP samples multiple rollouts, clusters final answers into semantic outcome modes, and builds a reliability-aware target distribution over these states. It then rewards turns for increasing posterior support for reliable future states using a tractable cluster-level approximation. The objective generalizes information-potential shaping from gold-answer supervision to settings without task-specific gold verifiers while avoiding the broadcasted rollout-level advantages used by standard GRPO. We formalize the framework, characterize its supervised gold-answer limit, and show that SIOP improves average performance over verifier-free outcome-level baselines on seven search-augmented agentic reasoning benchmarks while approaching a gold-supervised outcome baseline. Code is available at https://github.com/dl-m9/SIOP.git.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

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.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

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.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Actions at the Edge: Jointly Optimizing the Resources in Multi-access Edge Computing

Multi-access edge computing (MEC) is an emerging paradigm that pushes resources for sensing, communications, computing, storage and intelligence (SCCSI) to the premises closer to the end users, i.e., the edge, so that they could leverage the nearby rich resources to improve their quality of experience (QoE). Due to the growing emerging applications targeting at intelligentizing life-sustaining cyber-physical systems, this paradigm has become a hot research topic, particularly when MEC is utilized to provide edge intelligence and real-time processing and control. This article is to elaborate the research issues along this line, including basic concepts and performance metrics, killer applications, architectural design, modeling approaches and solutions, and future research directions. It is hoped that this article provides a quick introduction to this fruitful research area particularly for beginning researchers.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Energy Efficient Federated Learning over Heterogeneous Mobile Devices via Joint Design of Weight Quantization and Wireless Transmission

Federated learning (FL) is a popular collaborative distributed machine learning paradigm across mobile devices. However, practical FL over resource constrained mobile devices confronts multiple challenges, e.g., the local on-device training and model updates in FL are power hungry and radio resource intensive for mobile devices. To address these challenges, in this paper, we attempt to take FL into the design of future wireless networks and develop a novel joint design of wireless transmission and weight quantization for energy efficient FL over mobile devices. Specifically, we develop flexible weight quantization schemes to facilitate on-device local training over heterogeneous mobile devices. Based on the observation that the energy consumption of local computing is comparable to that of model updates, we formulate the energy efficient FL problem into a mixed-integer programming problem where the quantization and spectrum resource allocation strategies are jointly determined for heterogeneous mobile devices to minimize the overall FL energy consumption (computation + transmissions) while guaranteeing model performance and training latency. Since the optimization variables of the problem are strongly coupled, an efficient iterative algorithm is proposed, where the bandwidth allocation and weight quantization levels are derived. Extensive simulations are conducted to verify the effectiveness of the proposed scheme.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

From Resource Auction to Service Auction: An Auction Paradigm Shift in Wireless Networks

In 5G and beyond, the newly emerging services, such as edge computing/intelligence services, may demand the provision of heterogeneous communications, computing, and storage (CCS) resources on and across network entities multihop apart. In such cases, traditional resource-oriented auction schemes, where buyers place bids on resources, may not be effective in providing end-to-end (E2E) quality-of-service (QoS) guarantees. To overcome these limitations, in this article, we coin the concept of E2E service auction where the auction commodities are E2E services rather than certain resource. Under this framework, buyers simply bid for services with E2E QoS requirements without having to know the inner working (which resources are behind). To guarantee E2E QoS for winning bids while ensuring essential economic properties, E2E service auction requires addressing the joint problem of network optimization and auction design with both economical and QoS constraints. To substantiate the mechanism design, we illustrate how to devise E2E service auctions for edge computing systems under various scenarios. We also identify the research opportunities on E2E service auction mechanism design for other critical use cases, including edge intelligence.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Joint Beamforming and Reflecting Design in Reconfigurable Intelligent Surface-Aided Multi-User Communication Systems

Reconfigurable intelligent surface (RIS) provides a promising way to build the programmable wireless transmission environments in the future. Owing to the large number of reflecting elements used at the RIS, joint optimization for the active beamforming at the transmitter and the passive reflector at the RIS is usually complicated and time-consuming. To address this problem, this paper proposes a low-complexity joint beamforming and reflecting algorithm based on fractional programing (FP). Specifically, we first consider a RIS-aided multi-user communication system with perfect channel state information (CSI) and formulate an optimization problem to maximize the sum rate of all users. Since the problem is nonconvex, we decompose the original problem into three disjoint subproblems. By introducing favorable auxiliary variables, we derive the closed-form expressions of the beamforming vectors and reflecting matrix in each subproblem, leading to a joint beamforming and reflecting algorithm with low complexity. We then extend our approach to handle the case when transmitter-RIS and RIS-receiver channels are not perfect and develop corresponding low-complexity joint beamforming and reflecting algorithm with practical channel estimation. Simulation results have verified the effectiveness of the proposed algorithms as compared to various benchmark schemes.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Towards Energy Efficient Federated Learning over 5G+ Mobile Devices

The continuous convergence of machine learning algorithms, 5G and beyond (5G+) wireless communications, and artificial intelligence (AI) hardware implementation hastens the birth of federated learning (FL) over 5G+ mobile devices, which pushes AI functions to mobile devices and initiates a new era of on-device AI applications. Despite the remarkable progress made in FL, huge energy consumption is one of the most significant obstacles restricting the development of FL over battery-constrained 5G+ mobile devices. To address this issue, in this paper, we investigate how to develop energy efficient FL over 5G+ mobile devices by making a trade-off between energy consumption for "working" (i.e., local computing) and that for "talking" (i.e., wireless communications) in order to boost the overall energy efficiency. Specifically, we first examine energy consumption models for graphics processing unit (GPU) computation and wireless transmissions. Then, we overview the state of the art of integrating FL procedure with energy-efficient learning techniques (e.g., gradient sparsification, weight quantization, pruning, etc.). Finally, we present several potential future research directions for FL over 5G+ mobile devices from the perspective of energy efficiency.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Creating Efficient Blockchains for the Internet of Things by Coordinated Satellite-Terrestrial Networks

Blockchain has emerged as a promising technology that can guarantee data consistency and integrity among distributed participants. It has been used in many applications of the Internet of Things (IoT). However, since IoT applications often introduce a massive number of devices into blockchain systems, the efficiency of the blockchain becomes a serious problem. In this article, we analyze the key factors affecting the efficiency of blockchain. Unlike most existing solutions that handle this from the computing perspective, we consider the problem from the communication perspective. Particularly, we propose a coordinated satellite-terrestrial network to create efficient blockchains. We also derive a network scheduling strategy for the proposed architecture. Simulation results demonstrate that the proposed system can support blockchains for higher efficiency. Moreover, several open research issues and design challenges will be discussed.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Optimizing IoT Energy Efficiency on Edge (EEE): a Cross-layer Design in a Cognitive Mesh Network

Battery-powered wireless IoT devices are now widely seen in many critical applications. Given the limited battery capacity and inaccessibility to external power recharge, optimizing energy efficiency (EE) plays a vital role in prolonging the lifetime of these IoT devices. However, a sheer amount of existing works only focus on the EE design at the infrastructure level such as base stations (BSs) but with little attention to the EE design at the device level. In this paper, we propose a novel idea that aims to shift energy consumption to a grid-powered cognitive radio mesh network thus preserving energy of battery-powered devices. Under this line of thinking, we cast the design into a cross-layer optimization problem with an objective to maximize devices' energy efficiency. To solve this problem, we propose a parametric transformation technique to convert the original problem into a more tractable one. A baseline scheme is used to demonstrate the advantage of our design. We also carry out extensive simulations to exhibit the optimality of our proposed algorithms and the network performance under various settings.

0 citations0 reviewsNo code linkedOpen access