Search arXiv⌕ Search

arXiv subjects

Minghui Liwang

Publications and source records attributed to Minghui Liwang.

At least 19 recordsLinked to original sources
arXiv2026

JABER: Sequential Quality Control for Human-AI Data Annotation under Shared Bias

High-quality annotations are essential for training and evaluating artificial intelligence (AI) systems. Quality control (QC) often acquires additional human or AI judgments before accepting a label. Nevertheless, shared biases can cause correlated judgments, leading conventional methods to mistake repeated agreement for independent evidence of correctness. To address this challenge, we propose JABER (Joint Alias-Preserving Belief for Evidence Routing), a bias-aware sequential QC framework that maintains a joint Bayesian posterior over label correctness and shared biases to guide evidence acquisition and termination decisions. Building on this posterior, we develop a finite-horizon algorithm that selects evidence-acquisition and termination actions to minimize expected QC loss under resource constraints. Our theoretical analysis shows that conditional-independence updating can become arbitrarily confident in an incorrect label under persistent shared bias. We further identify when repeated inspections cannot distinguish a correct label from an incorrect label supported by shared bias, when obtaining a new label can resolve this ambiguity, and why modeling the dependence between label correctness and shared bias can be necessary for QC decisions. Our experiments show that JABER reduces expected QC loss by an average of 4.65% compared with a method maintaining separate label correctness and bias probabilities when shared bias makes repeated inspections unreliable. Further, JABER's finite-horizon planning, which evaluates outcomes of successive QC actions, reduces expected QC loss by an average of 10.05% compared with a one-step lookahead method. In real-API experiments on FEVER, JABER achieves zero labeling errors while reducing QC costs by 2.67% and 16.99% compared with marginal-based belief modeling and one-step lookahead methods, respectively.

cs.AI↗
arXiv2026

Predictive Scheduling and Model Sharing for Continuous UAV Edge Inference

Continuous edge inference for unmanned aerial vehicles (UAVs) faces uncertain wireless connectivity, competition for shared computing resources, and the overhead of model loading and session-state migration. These interdependent factors complicate request admission and the continuity of successive inference services. This paper investigates joint request admission, edge-server assignment, and model selection under an admission-priority objective that strictly favors any feasible increase in admitted requests over bounded losses in delay, interruption risk, model quality, migration, and deployment. To address this problem, we propose Service-Window-Guided Admission and Model Placement (SWAP), which integrates predictive service-window information with shared model deployment and coordinated scheduling. Quantile regression and probability calibration estimate the remaining service window and interruption risk, while a bounded residence factor characterizes the potential reuse of shared model instances. We then formulate a constrained exact potential game based on marginal-contribution utilities and develop a solution procedure combining unilateral improvement, coordinated admission, and finite binary logit refinement. Theoretical analysis establishes NP-hardness, the existence of a constrained pure Nash equilibrium, and finite descent, together with feasibility and approximate unilateral equilibrium guarantees for the returned assignment. Simulation results demonstrate improved service continuity and reduced request rejection under increasing resource contention, while characterizing the accompanying tradeoffs in model-deployment traffic, inference quality, and execution delay.

cs.NI↗
arXiv2026

STEPS: Semantic Contract-Guided Scheduling for LLM-Assisted Natural Language-Driven Edge AI Services

Edge user/service scheduling governs where and how AI services are executed under limited communication and computing resources. Existing edge scheduling frameworks typically assume numerically specified service requirements, such as latency bounds and energy budgets. However, users often express ambiguous and context-dependent expectations in natural language, creating a gap between user intent and scheduling decisions. We propose semantic contract-guided edge potential scheduling (STEPS), a natural language-driven framework that introduces semantic contracts as executable interfaces between user-side semantics and edge-side decisions. A large language model (LLM)-assisted semantic parser extracts service requirements and raw confidence scores from natural language requests. Confidence calibration and interpretable mapping rules convert these outputs into preference weights, fulfillment bounds, and semantic uncertainty. STEPS formulates intended per-slot edge scheduling as an exact potential game for execution-node selection, computing-resource provisioning, and bandwidth allocation, followed by capacity-feasible resource realization. Fulfillment-driven feedback signals enable adaptive scheduling under evolving service and network conditions. We establish the existence of pure-strategy Nash equilibrium, prove finite-step convergence of uncapped strict best-response dynamics, and characterize the boundedness of projected adaptive-control parameters. Experiments under synthetic and Melbourne-based hybrid settings demonstrate improved contract fulfillment and reduced service loss relative to several adapted benchmarks. Post-drift evaluations further show that feedback adaptation improves fulfillment and admission coverage under the tested conditions.

cs.NI↗
arXiv2026

Heterogeneous Distributed Zeroth-Order Nonconvex Optimization with Communication Compression

Distributed zeroth-order optimization is increasingly applied in heterogeneous scenarios where agents possess distinct data distributions and objectives. This heterogeneity poses fundamental challenges for convergence analysis, as existing convergence analyses rely on relatively strong assumptions to ensure theoretical guarantees. Specifically, at least one of the following three assumptions is usually required: (i) data homogeneity across agents, (ii) $\mathcal{O}(pn)$ function evaluations per iteration with $p$ denoting the dimension and $n$ the number of agents, or (iii) the Polyak--Łojasiewicz (P--L) or strong convexity condition with a known corresponding constant. To overcome these limitations, we propose a Heterogeneous Distributed Zeroth-Order Compressed (HEDZOC) algorithm, which is based on a two-point zeroth-order gradient estimator and a general class of compressors. Without assuming data homogeneity, we develop the analysis covering three settings: general nonconvex functions, functions satisfying the P--L condition without knowing the P--L constant, and those with a known constant. To the best of our knowledge, the proposed HEDZOC algorithm is the first distributed zeroth-order method that establishes convergence without relying on the above three assumptions. Moreover, it achieves linear speedup convergence rate, which is comparable to state-of-the-art results attainable under data homogeneity and exact communication assumptions. Finally, experiments on heterogeneous adversarial example generation validate the theoretical results.

math.OC↗
arXiv2026

Unified Communication Compression Beyond Global Error Bounds for Distributed Nonconvex Optimization

In this paper, we propose a unified compression algorithm for distributed nonconvex opitmization with both the locally- and globally-bounded communication compressors, including 1-bit compressors, saturating quantizers, and the globally-bounded compressors with both relative and absolute compression errors, as well as additional arbitrary bounded noise. We provide a rigorous convergence analysis in nonconvex settings and establish linear convergence under the Polyak-Lojasiewicz (P-L) condition. Notably, we establish an $\mathcal{O}(1/\sqrt{T})$ convergence rate for the locally-bounded class in the distributed nonconvex setting, matching that achieved by the centralized algorithms with 1-bit compressors, where $T$ denotes the total number of iterations. Moreover, one initial uncompressed communication round further yields an order-wise improvement to $\mathcal{O}(1/T^{2/3})$. For the P-L setting and the globally-bounded class, we recover state-of-the-art convergence rates.

math.OC↗
arXiv2026

ELSA: Efficient LLM-Centric Split Aggregation for Privacy-Aware Hierarchical Federated Learning over the Network Edge

Training large language models (LLMs) in resource-constrained edge networks poses fundamental challenges in computation, communication, data heterogeneity, and privacy. To address these challenges, we propose ELSA (Efficient LLM-Centric Split Aggregation), a distributed fine-tuning framework that integrates split learning (SL) with hierarchical federated learning (HFL) to coordinate computation and model aggregation across heterogeneous clients, edge servers, and the cloud. ELSA introduces three key innovations. First, it employs a task-agnostic, behavior-aware client clustering mechanism that constructs semantic fingerprints from public probe inputs using symmetric Kullback-Leibler (KL) divergence, complemented by prediction-consistency-based trust scoring and latency-aware edge assignment to account for data heterogeneity, client reliability, and communication constraints. Second, it adopts a resource-aware dynamic model partitioning strategy that distributes the LLM across clients and edge servers in three segments, while reserving the cloud for adapter aggregation. This design coordinates computation across heterogeneous nodes while balancing on-device computational demands and global convergence behavior. Third, it integrates computational sketches with semantic subspace orthogonal perturbation (SS-OP) to reduce communication overhead and mitigate privacy leakage during model exchanges. Extensive experiments across diverse NLP tasks demonstrate that ELSA outperforms state-of-the-art baselines in model performance, convergence behavior, and robustness. Further, on-device profiling on NVIDIA RTX 4090 GPUs and Jetson AGX Orin edge devices characterizes the memory footprint, energy consumption, and execution latency of key training stages, providing empirical evidence of ELSA's practical feasibility.

cs.LG↗
arXiv2026

AEGIS: Risk-Budgeted Online Scheduling for Resilient Continuous Edge Inference

Continuous edge inference requires sustained wireless and computing support across successive service instances. Under recurring channel degradation, transient edge overload, and multi-user contention, isolated deadline misses may accumulate into persistent service degradation. Existing schedulers mainly optimize instantaneous latency or per-timeslot utility and provide limited control over such cross-time effects. To address this issue, we propose AEGIS (Adaptive Exposure-Governed Inference Scheduling), a risk-budgeted online framework for service-level operational resilience. AEGIS regulates predicted deadline-risk exposure through dynamically replenished per-user risk budgets and establishes an explicit finite-horizon bound on cumulative admitted-risk exposure. One-step state estimation supports anticipatory delay and risk assessment, while the centralized bandwidth-computing allocation is transformed into an exact-potential formulation and solved through asynchronous coordinate updates. Simulation results under varying system scales and stress conditions show that adaptive replenishment improves service continuity and recovery relative to fixed replenishment, while risk budgeting reduces predicted-risk exposure compared with more aggressive scheduling alternatives.

cs.NI↗
arXiv2026

Convergence of Practical Muon

Muon is emerging as a promising alternative to AdamW for large-scale neural network training, yet theoretical understanding of its practical implementation remains incomplete, as existing analyses often simplify or omit two key components: (i) practical Newton--Schulz iterations with empirically tuned polynomial coefficients $(3.4445,-4.7750,2.0315)$; and (ii) decoupled weight decay for regularization. In this paper, we provide an optimization interpretation and establish convergence for practical Muon, jointly accounting for both components. Specifically, we interpret practical Muon as right-preconditioned optimization of the original loss with a dynamic weighted $\ell_2$ regularizer that vanishes as stationarity is approached, so that the optimization target remains the original objective. We then establish, to our best knowledge, the first convergence guarantee for practical Muon in the stochastic nonconvex setting, with an $\mathcal{O}(T^{-1/4})$ convergence rate in terms of the expected Frobenius norm of the gradient, improving the dimension dependence of the best known AdamW's convergence rate by a factor of $\sqrt{d}$, where $T$ is the iteration horizon and $d$ is the parameter dimension. Experiments further support the theoretical convergence results.

cs.LG↗
arXiv2026

Predictive Rolling-Horizon Optimization for Commitment-Aware Model-Parallel Inference under Spatio-Temporal Edge Dynamics

Model-parallel inference over dynamic edge systems requires scheduling decisions that account for not only instantaneous resources but also future resource contention and reliable service commitments. Existing edge-inference designs, however, predominantly optimize performance metrics based on current or short-term system states, without explicitly coupling current assignments with future commitment fulfillment. To address this issue, we propose PROMISE, a predictive rolling-horizon framework for commitment-aware model-parallel inference under spatio-temporal edge dynamics. PROMISE jointly models stochastic task generation, mobility-induced communication variations, privacy-aware model partitioning, and load-dependent edge computing capability. We introduce committed completion time (CCT) as an endogenous service decision and formulate joint SD--ES mapping and CCT determination to balance commitment fulfillment and service reward. To address cross-timeslot coupling, PROMISE estimates future task arrivals and computational workloads over an adaptive horizon and embeds them into certainty-equivalent ES-state rollout. A progress-aware surrogate then evaluates feasible current-stage mappings, while the corresponding CCTs are analytically recovered from predicted completion times. Only the first-stage decisions are committed, and the optimization is repeated with newly observed states in a receding-horizon manner. Numerical experiments demonstrate robust scheduling performance under diverse system scales and workload dynamics, while Raspberry-Pi-based experiments validate the practical feasibility and key system characteristics of model-parallel edge inference.

cs.DC↗
arXiv2026

FUSION: Forecast-Embedded Agent Scheduling with Service Incentive Optimization over Distributed Air-Ground Edge Networks

This paper introduces a forecasting-driven, incentive-aware service provisioning framework for distributed air--ground integrated networks with human--machine coexistence. Agent pairs (APs), each comprising a vehicle and its carried uncrewed aerial vehicles (UAVs), are proactively dispatched to overloaded hotspots to augment the computing capacity of edge servers (ESs). This design introduces four coupled challenges: uncertain spatio-temporal workloads, coupling between vehicular mobility and UAV capacity, forecast-driven contracting risks, and heterogeneous quality-of-service (QoS) requirements of human users (HUs) and machine users (MUs). To address these challenges, we propose FUSION, a two-stage framework with offline service preparation and online task scheduling. In the offline stage, a liquid neural network forecasts multi-step ES demand, an enhanced ant colony optimization scheme constructs AP service routes, and an auction-based mechanism establishes ES--AP contracts. In the online stage, we formulate congestion-aware scheduling as an exact-potential game among service demanders (SDs) and develop a potential-guided best-response dynamics algorithm. For a fixed online state, the algorithm converges to an $\varepsilon$-Nash equilibrium (NE) under a positive improvement threshold and to a pure-strategy NE when the threshold is zero. Within the considered contracting model, we theoretically establish that the offline mechanism satisfies individual rationality, near-truthfulness, and weak budget balance. Experiments on synthetic data and real-world load traces show that FUSION achieves higher social welfare while maintaining interaction delay and signaling energy overheads comparable to the considered benchmarks.

cs.NI↗
arXiv2026

TRACER: Adaptive Multi-Robot Social Navigation via Joint Human-Response Prediction and Interaction-Aware Replanning

Multi-robot navigation in human-shared spaces is inherently interactive: coordinated robot motions influence how nearby entities respond, while those responses provide valuable information for subsequent robot decisions. However, existing methods typically address action-conditioned prediction, multi-robot planning, or online adaptation separately, and therefore lack a unified mechanism for modeling joint robot-entity interactions and adapting future decisions from executed interaction outcomes. To address this gap, we propose TRACER, a bi-directional receding-horizon framework that closes the loop between prediction and adaptation. TRACER evaluates candidate (i.e., alternative feasible future motion plans for the robot team) trajectories using a per-entity probabilistic response model that separates individual-robot effects from non-additive pairwise interactions; after executing the selected trajectory prefix, it updates persistent identity-bound beliefs over latent response modes using the synchronized observed responses. These updated beliefs then guide subsequent candidate evaluation under probabilistic safety and response-aware cost criteria. Experiments show that (i) TRACER more accurately captures non-additive multi-robot interaction effects than a capacity-matched additive predictor, (ii) persistent identity-consistent evidence improves response prediction and downstream replanning, and (iii) the complete TRACER framework improves collision-free completion over an independent-robot baseline on the SocialGym2 multi-robot social-navigation benchmark.

cs.RO↗
arXiv2026

Federated Foundation Models over Vehicular Networks

This paper presents a forward-looking vision for integrating the emerging multi-modal multi-task federated foundation models (M3T FedFMs) into vehicular networks, with the goal of unifying the expressive power of multi-modal multi-task foundation models (M3T FMs) with the privacy-preserving and distributed learning capabilities of federated learning (FL). Given the largely underexplored nature of this research direction, we first introduce the fundamental training/fine-tuning principles of M3T FedFMs. We then discuss a range of their representative use cases in vehicular networks, illustrating the significant potential of M3T FedFMs to enable next-generation vehicular intelligence. Afterwards, we identify key constraints inherent to vehicular environments that challenge the practical deployment of M3T FedFMs, and articulate a set of forward-looking research directions to address these challenges. Furthermore, through a case study conducted on a real-world vehicular dataset (i.e., Waymo Open Dataset), we demonstrate the promise of M3T FedFMs for vehicular networks and release our implementation to facilitate reproducibility and stimulate research in this emerging area (repository: https://github.com/KasraBorazjani/vehicular-fedfm)

cs.LG↗
arXiv2026

PAST: Pilot and Adaptive Orchestration for Timely and Resilient Service Delivery in Edge-Assisted UAV Networks under Spatio-Temporal Dynamics

Incentive-driven resource trading is essential for uncrewed aerial vehicle (UAV) applications with intensive, time-sensitive computing demands. Traditional spot trading suffers from negotiation delays and high energy costs, while conventional futures trading struggles to adapt to the dynamic, uncertain UAV-edge environment. To address these challenges, we propose PAST (pilot-and-adaptive stable trading), a novel framework for edge-assisted UAV networks with spatio-temporal dynamism. PAST integrates two complementary mechanisms: PilotAO (pilot trading agreements with overbooking), a risk-aware, overbooking-enabled early-stage decision-making module that establishes long-term, mutually beneficial agreements and boosts resource utilization; and AdaptAO (adaptive trading agreements with overbooking rate update), an intelligent adaptation module that dynamically updates agreements and overbooking rates based on UAV mobility, supply-demand variations, and agreement performance. Together, these mechanisms integrate stable advance agreement construction with execution-feedback-driven adaptive renewal. Under the stated modeling assumptions, PilotAO satisfies the adopted individual-rationality and strong-stability criteria, as well as the competitive equilibrium and weak Pareto properties established for the considered trading model. Comprehensive experiments further demonstrate that, by coordinating advance planning with selective agreement renewal, PAST effectively balances stability, adaptability, and decision-making efficiency under dynamic UAV-edge conditions.

cs.DC↗
arXiv2026

HermesHFL: Incentive-Compatible Hierarchical Federated Unlearning for Dynamic LLM Fine-Tuning

Hierarchical federated unlearning (HFUL) for large language model (LLM) fine-tuning faces significant challenges due to hierarchical aggregation, dynamic client participation, and strong parameter coupling in LLM adaptation. Selectively removing client contributions is particularly difficult because model updates propagate across multiple aggregation stages while unlearning requests may coincide with client departures and rejoining. To address these issues, we propose HermesHFL, a hierarchical federated learning framework that supports selective unlearning, dynamic client participation, and client reintegration for scalable LLM fine-tuning via parameter-efficient fine-tuning (PEFT) with LoRA. We formulate a unified optimization problem that jointly models client participation, edge association, incentive allocation, and unlearning under heterogeneous client behaviors. To solve this problem efficiently, we develop Neogen, a neural-guided bilevel evolutionary optimization framework that combines CMA-ES for continuous incentive optimization with a CHC-based evolutionary mechanism for discrete participation and association decisions. A neural surrogate further accelerates optimization and improves search efficiency. Extensive experiments on LLM fine-tuning tasks demonstrate that HermesHFL consistently outperforms state-of-the-art baselines in model utility, unlearning effectiveness, convergence stability, and resource efficiency.

cs.CE↗
arXiv2026

Flying over The Uncertain Nature (FORTUNE): Intelligent and Humanistic 3D Path Planning for Low-Altitude Collaboration

The proliferation of low-altitude intelligent agents is increasing the demand for timely and socially responsible collaborative sensing in dynamic urban environments. However, jointly addressing heterogeneous spatiotemporal demands, environmental uncertainty, and human-centered operational constraints remains challenging. This paper studies 3D multi-UAV path planning and task assignment under uncertain ground PoI demands. Unlike existing work assuming static and fully known PoIs, we model persistent, temporally predictable, and emergent demands within a unified framework. We further incorporate altitude-dependent societal and environmental costs, including noise exposure and public safety risks, to balance sensing performance with socially compliant operations. To solve the resulting large-scale mixed-integer nonlinear problem, we propose FORTUNE, a hierarchical offline-online framework. Offline, a Transformer predicts Type-II PoI activation windows, while an enhanced sparrow search algorithm generates coordinated flight plans through priority-aware decoding and danger-aware evolution. Online, a lightweight refinement module accommodates emerging Type-III PoIs while preserving global mission coherence. Experiments on real-world traffic data and synthetic scenarios show that FORTUNE consistently outperforms state-of-the-art methods in effectiveness, scalability, and practical applicability.

cs.RO↗
arXiv2026

Spatiotemporal Feature Alignment and Weighted Fusion in Collaborative Perception Enabled by Network Synchronization and Age of Information

Collaborative perception in Internet of Vehicles (IoV) aggregates multi-vehicle observations for broader scene coverage and improved decision-making. However, fusion quality degrades under spatiotemporal heterogeneity from unsynchronized clocks, communication delays, and motion variations across vehicles. Prior work mitigates these through spatial transformations or fixed time-offset corrections, overlooking time-varying clock drifts and delays that cause persistent feature misalignment. To address these challenges, we propose a spatiotemporal feature alignment and weighted fusion framework. Specifically, network synchronization is introduced to estimate inter-vehicle clock states and establish a common temporal reference, onto which local feature timestamps can be mapped. Based on this, we define delivery-time Age of Information (AoI) to measure the expected age of a shared feature when it becomes available for fusion, by accounting for its generation time and the Vehicle-to-Everything (V2X) communication delay. The proposed spatiotemporal feature alignment then compensates asynchronous neighbor features toward the fusion time, rather than directly aggregating delayed features. Since different spatial regions contribute unequally to perception, we further perform Region-of-Interest (RoI)-level weighted fusion, where the fusion weights are determined by delivery-time AoI, synchronization reliability, and content complementarity. As a result, timely, reliable, and complementary regions are emphasized, while stale, uncertain, or redundant regions are down-weighted. Simulation results further demonstrate consistent accuracy improvements over representative baselines under clock drift, varying communication conditions, temporal misalignment levels, and vehicle numbers.

cs.NI↗
arXiv2026

SAGE: A Socially-Aware Generative Engine for Heterogeneous Multi-Agent Navigation

Safe and socially compliant navigation in open human-robot environments requires robots to reason about heterogeneous participants with different dynamics, autonomy levels, and social roles. Existing trajectory prediction and planning methods often rely on homogeneous interaction assumptions or enforce only geometric collision constraints, making it difficult to jointly model asymmetric interactions, coupled prediction-planning, and soft social norms. This paper proposes SAGE, a socially-aware generative engine for heterogeneous multi-agent navigation. SAGE represents robots and surrounding entities as a directed heterogeneous graph and employs a Heterogeneous Graph Transformer (HGT) to encode type-specific asymmetric interactions. Conditioned on the resulting context, a diffusion-based generative module jointly models future entity trajectories and robot trajectory plans. During inference, a training-free safety-social energy guidance mechanism refines sampled robot trajectories using differentiable collision, kinematic, task-progress, and role-conditioned social-compliance terms. Extensive experiments on real-world (ETH/UCY and SDD) and synthetic datasets verify the effectiveness of SAGE in improving safety and social compliance while maintaining task performance. The proposed guidance mechanism consistently reduces collision and social-violation rates, scales to teams of up to 20 robots, and enables explicit control of the safety-accuracy-task trade-off without retraining. These findings demonstrate the potential of SAGE as a scalable framework for socially-aware multi-agent navigation in complex environments.

cs.RO↗
arXiv2026

DRIFT: Risk-Constrained Diffusion with Imitation Priors for Mixed-Autonomy Traffic Generation

Future intelligent transportation systems are envisioned to evolve toward a long-term mixed-autonomy paradigm, where human-driven vehicles (HVs) and autonomous vehicles (AVs) coexist within highly coupled traffic ecosystems. Such coexistence introduces pronounced heterogeneity, amplified uncertainty, and increasingly intricate interaction dynamics. In this context, it remains fundamentally challenging to simultaneously capture the heterogeneous behavioral distribution shifts arising from dynamic AV penetration, generate diverse yet executable trajectories under strong inter-vehicle coupling, and conduct reliable closed-loop safety and stability diagnostics for rare but high-impact events. To this end, we present Diffusion with Risk constraints, Imitation priors, and long-tail Feedback for mixed-autonomy Traffic generation (DRIFT), a mixed-autonomy traffic generation framework that unifies heterogeneity-aware conditional encoding, conditional diffusion-based executable trajectory generation, and progressive adversarial alignment enhanced by risk-aware long-tail feedback, thereby enabling traffic behaviors to be iteratively generated, filtered, selected, and validated within a closed-loop execution pipeline. In addition, a unified evaluation protocol is developed to jointly characterize safety, efficiency, and closed-loop stability across representative traffic scenarios and AV penetration regimes. Experimental results demonstrate that DRIFT achieves a strong safety-efficiency trade-off in closed-loop mixed-autonomy benchmarks, while further revealing the critical influence of candidate executability, online selection, and long-tail feedback on executable traffic evolution.

cs.DC↗