7,731 papers in this slice of arXiv.
Michael Georgiades
The Internet of Things (IoT) increasingly combines sensing, communication, artificial intelligence (AI), decision-making, and actuation. In many domains, sensor observations are processed by edge or cloud intelligence to select actions that configure or control actuators; where actuation changes the environment, later observations may also be affected. Existing explainable AI (XAI) methods can explain model predictions, but they do not by themselves explain the end-to-end path from sensed evidence to physical action. This paper introduces the Internet of Explainable Things (IoXT), a system-level paradigm that makes explainability an architectural property of intelligent IoT. Its novelty is explainability-by-design across the sensing-communication-intelligence-decision-actuation path. IoXT derives requirements and design principles for identity and addressability, temporal fidelity, cross-layer provenance, bidirectional traceability, streaming and incident-time evidence, protocol-semantic continuity, security and privacy, lifecycle continuity, and conformance. We formalize timestamped provenance graphs, sensor participation, trace completeness, cross-layer coverage, reconstruction latency, and No Orphan Actuation: a consequential action must remain traceable to the authorizing decision and source evidence, or be explicitly marked degraded or non-conformant. IoXT prescribes neither a particular XAI method nor a wire protocol. Instead, it defines the conditions under which model explanations remain connected to real sensor inputs, communication history, decisions, actuator execution, and outcomes. Explainability Telemetry Protocols (XTPs) are introduced as a protocol category for preserving these semantics across heterogeneous IoT systems, together with IoXT-ready and IoXT-conformant assurance concepts.
Vibhanshu Sharma, Alish Kanani, Miao Sun +3
Processing-in-memory (PIM)-based 2.5D multi-chiplet platforms are enablers for machine learning (ML) workloads. However, their performance is affected by the power delivery network (PDN), where varying chiplet-level current demand induces spatially and temporally varying voltage droop. These droop events lead to voltage violations, degrades system performance, and impact inference accuracy for ML workloads. In this work, we propose ReVolt, a dynamic operation unit (OU)-based framework for mitigating voltage droop in PIM-based multi-chiplet systems. ReVolt leverages an LSTM-based PDN surrogate to predict per-chiplet supply voltage trajectories at runtime, enabling proactive adjustment of OU size to mitigate droop events. By treating OU size as a control knob, ReVolt regulates chiplet-level current demand while maintaining computational accuracy. This approach prevents voltage droop violations and improves energy-delay product (EDP) while preserving ML model inference accuracy. Experimental results demonstrate that ReVolt prevents voltage droop violations while achieving an average 76x reduction in EDP compared to existing fixed and dynamic OU-based baselines, without compromising inference accuracy of ML models.
Prasanna Date, Kevin Zhu, Shruti Kulkarni +12
Spiking neural networks (SNNs) offer a promising pathway to energy-efficient AI and brain-inspired computing. However, their widespread adoption is hindered by a lack of fast, accessible, and versatile simulation frameworks. In this paper, we introduce SuperNeuroMAT, an open-source, scalable, and highly efficient Python-based SNN simulator. We devise a novel matrix-based approach to model the leaky integrate-and-fire (LIF) neuron dynamics and natively support dense and sparse execution modes. This enables fast simulation of approximately 10,000 neurons in dense mode and 100,000 neurons in sparse mode on standard laptops and desktops without requiring specialized hardware. We demonstrate that SuperNeuroMAT consistently outperforms four established SNN simulators---NEST, Brian2, BindsNET, and snnTorch---on two performance metrics (execution speed and peak resident memory) and across various network sizes and connection probabilities. Furthermore, we demonstrate SuperNeuroMAT's applicability across a diverse set of problems. SuperNeuroMAT can efficiently handle conventional machine learning benchmarks such as the Digits and citation network datasets as well as neuromorphic event-based vision tasks such as N-CARS and ASL-DVS. Moreover, it can be extended beyond machine learning workloads and facilitate general-purpose workloads. We validated this by implementing the neuromorphic shortest path algorithm and two arithmetic primitives (addition and multiplication). SuperNeuroMAT can be installed via the Python Package Index (PyPI), thereby lowering the barrier to entry into the field of neuromorphic computing and accelerating the broader development of neuromorphic algorithms.
John Sengendo, Zineddine Bettouche, Khalid Ali +2
As mobile networks transition from Beyond 5G (B5G) towards 6G, accurate traffic forecasting is a prerequisite for improving network management. However, with increasing heterogeneity and a massive surge in connected devices, combined with dynamically evolving traffic patterns, accurate forecasting is a persistent bottleneck. Existing frameworks, while generally effective, often lack efficiency and degrade under drift, thus requiring costly model retraining to restore performance. In this paper, we propose a lightweight error correction framework that improves forecasting accuracy by integrating a Proportional-Integral-Derivative (PID) controller as a correction layer enhancing Hierarchical Spatio-temporal Models (HiSTM). Unlike retraining-based model adaptation, our framework performs online error correction without modifying the model parameters. Results from the proposed framework, evaluated across drift scenarios and cell-level analysis, demonstrate reduced Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE), achieving an average drift mitigation of up to 30.18% in MAE and 26.68% in RMSE, thereby validating the robustness of the PID framework as a drift mitigation mechanism for network traffic forecasting.
John Sengendo, Fabrizio Granelli
Network Digital Twins (NDTs) enable proactive network management and optimization by predicting system behavior before control actions are applied to live infrastructures, supporting critical operations in Internet Service Provider (ISP) networks and wide-area networks (WANs). However, to anchor the superior performance NDTs promise to provide, key enabler techniques are required. Given that mobile networks are modeled as graphs, graph-based architectures such as graph neural networks (GNNs) have shown promising performance in modeling network behavior. This work proposes a novel Hybrid Spatial-Temporal Graph Neural Network (HSTGNN) architecture. Unlike single-branch GNN approaches, we propose a multi-scale design that combines three complementary message-passing paradigms: local neighborhood aggregation, spectral filtering, and learnable attention-based weighting. When benchmarked against other approaches, the proposed HSTGNN achieved superior performance delivering a coefficient of determination score of approximately 0.8816, 17.5% better than the best baseline ChebNet. Furthermore, HSTGNN achieved the lowest Mean Absolute Error (MAE) of 0.0300, and Root Mean Squared Error (RMSE) of 0.0458, significantly outperforming baseline frameworks and certifying the proposed framework's capability in enabling NDTs.
Md Tarek Hassan, Dmitry Zelenchuk, Muhammad Ali Babar Abbasi
Accurate user equipment (UE) localization is critical for beam management in reconfigurable intelligent surface (RIS)-assisted millimeter-wave (mmWave) based sixth-generation (6G) networks, especially if the direct base-station-UE links are unavailable. This paper proposes a beam-domain fingerprint framework that maps the received signal-to-noise ratio (SNR) across a small set of predefined RIS reflection states to the UE azimuth angle and range, without requiring channel state information (CSI). Crucially, we extend the framework to a realistic interference-impaired scenario in which a nearby cross-link interferer (CLI) corrupts the clean SNR fingerprint, yielding a signal-to-interference-plus-noise ratio (SINR) fingerprint; an interference-to-noise ratio (INR)-constrained calibration strategy keeps the interference level physically interpretable. Four machine-learning (ML) regressors are evaluated under both conditions. Simulation results at 28 GHz with a 20x20 RIS show that k-nearest neighbors (KNN) achieves the lowest angle MAE of 0.37 degrees and range MAE of 4 cm under clean conditions, rising to 1.4 degrees and 7.6 cm under interference. A key finding is that interference degrades angle estimation substantially more than range estimation across all models, a consequence of the asymmetric encoding of location information in the beam-domain fingerprint.
Majid Kundroo, Tinku Singh, Taehong Kim
Federated Learning (FL) enables collaborative machine learning (ML) across distributed clients while preserving privacy. However, efficient model convergence in FL remains challenging, especially in wireless networks where non-independent and identically distributed (non-IID) data and frequent client dropouts are common. Traditional FL algorithms, such as FedAvg, rely solely on dataset size to weight client updates. This introduces biases towards clients with larger datasets and makes the process sensitive to non-IID data, outliers, and client dropouts. To address these challenges, we propose Federated Learning with Loss-Based Weighting (FedLBW), a novel aggregation method that assigns each client's update a weight proportional to the inverse of its validation loss, computed using a small proxy dataset on the server, rather than its dataset size. This ensures that lower-loss models exert greater influence during aggregation, prioritizing the most reliable updates and boosting overall performance. Through extensive experiments across multiple datasets, including FashionMNIST (CNN), CIFAR-10 (ResNet-18), and CIFAR-100 (ResNet-34), we demonstrate that FedLBW achieves higher accuracy and faster convergence compared to baseline algorithms such as FedAvg, FedAvgM, FedProx, FedNova, FedLAW and FedDkw, with notable improvements of up to 7.6 % higher accuracy on CIFAR-10 in extreme non-IID cases. Moreover, FedLBW showcases exceptional resilience to increasing dropout probabilities, consistently maintaining significantly higher accuracy even in challenging conditions. These results establish FedLBW as an effective and resilient solution for FL in wireless network environments, offering marked improvements in model accuracy, convergence speed, and robustness to non-IID data and client dropouts.
Ahmet Efe, Recep B. Uludag, Chris H. Kim +1
Ising machines are emerging as promising hardware for combinatorial optimization. With recent advances in CMOS Ising technology, they are becoming attractive as low-power accelerator systems for robotics, where energy is limited and combinatorial optimization arises in multiple forms. However, a hardware-aware analysis of where such chips fit within a robotics planning stack is still missing. This paper studies the capabilities and limitations of CMOS Ising machines for low-power acceleration in multi-robot multi-target planning. We analyze three planning layers---target sharing, tour construction, and pathfinding---using real 45-spin all-to-all connected CMOS Ising chips as representative devices. We propose new Ising-based planning methods and a multi-mapping pipeline that uses spin merging, coefficient quantization, and spin-budget branching to adapt subproblems to spin- and coefficient-limited hardware. Our results show that the proposed recursive target-sharing method naturally matches the Ising hardware, achieving up to 8,000x lower energy than a classical baseline. End to end, the Ising pipeline produces routes within 9% of a strong classical baseline at 130x lower energy, showing that compact CMOS Ising machines can be effective in selected parts of the planning stack.
Yue Yang, Jie Ying Wu
Mandibular reconstruction restores facial continuity and oral function after segmental resection. Patient-specific cutting guides transfer a computed tomography (CT)-based plan to the operating room with three-dimensional information, but printed guides add cost and lead time, cannot adapt after fabrication, and may interrupt surgery if sterility is lost. We investigate a markerless augmented reality (AR) alternative that registers a virtual cutting guide to the exposed mandible from surface geometry. The method extends surface-based registration for the transoral setting, where teeth form the most distinctive visible surface. After camera calibration, a HoloLens 2 time-of-flight camera captures a partial intraoperative point cloud. The user supplies a rough head-based alignment only to crop the region of interest. A teeth-weighted global stage computes correspondences and solves a truncated least-squares rigid alignment. An asymmetric point-to-plane iterative closest point (ICP) stage refines the complete CT mandible against the partial depth cloud target. The guide-to-mandible transform places the guide in the HoloLens world frame, while pose updates and interpolation follow target motion. We define a blinded phantom protocol with 30 target registration error (TRE) points under full, intermediate, and teeth-only exposure, plus a motion-to-display latency test. Our median TRE is 4.05, 6.10, and 7.10 mm respectively, and median latency is 0.805 s. These values support the feasibility of using AR to replace physical prints. The workflow removes mounted fiducials and manual landmark selection and provides a testable path toward transoral cutting guidance.
Yicheng Guang, Neel Vora, Yilun Xu +2
As quantum computing continues to demonstrate promise and attract growing attention, there is an increasing need for more precise experiments to advance the development of quantum devices, as well as higher circuit throughput to validate more domain applications. However, this need is hindered by a memory bottleneck at the quantum control system layer, arising from limited on-chip BRAM capacity and the non-deterministic latency of DRAM. To break this bottleneck, we present Ant-Q, a memory hierarchy design that integrates DRAM with BRAM to support pipelined quantum circuit execution while ensuring deterministic inter-circuit timing. We evaluated Ant-Q using 26 real-world experimental and computing circuits. The results show that Ant-Q supports deep circuits for 1Q and 2Q Randomized Benchmarking and reduces the overhead of circuit loading and readout uplink relative to execution time from 22.90%-1417.05% to near zero. Ant-Q is being integrated into QubiC 3.0, with part of its functionalities already available.
Mutasim Fuad Sarker, Adiba Rahman Namira, Wafa Binte Alam +3
Cardiac arrest remains one of the most lethal conditions encountered in intensive care units. Despite the growing availability of electronic health record data, existing mortality prediction studies in this population largely depend on static summaries derived from early admission. Such approaches ignore the temporal progression of physiological deterioration and recovery that unfolds throughout a patient's ICU stay. To address this limitation, we introduce QuanTiMedAI, a quantum-agentic framework developed for cardiac arrest mortality prediction using agentic AI guided quantum enhancement time series model. The proposed system combines an agentic large language model (LLM) for clinically informed feature discovery with a compact quantum recurrent network for temporality aware mortality prediction. Our findings demonstrate that agentic LLM-guided feature selection consistently outperforms conventional feature selection approaches, and the proposed quantum architecture achieves competitive predictive performance through nonlinear feature enhancement while keeping the number of parameters very low. Through extensive experimentation on a MIMIC-IV cohort of cardiac arrest patients, QuanTiMedAI's quantum-enhanced architecture attains an AUROC of 0.852 using only 605 parameters, an improvement of approximately 2.9% over a current state-of-the-art baseline for this task. A structured ablation study systematically validates the contribution of each architectural design choice. These results show that quantum-enhanced sequential modeling can exceed classical recurrent networks while using substantially fewer parameters.
Samuel Punch
Mapping quantum programs to restricted physical chips requires SWAP operations, incurring depth and error penalties. In symmetric programs, this routing overhead breaks theoretical symmetry because identical logical roles experience unequal shuffling. While often attributed to hardware topology alone, we show this is a two-level phenomenon. A qubit patch's shape dictates if it can host a balanced assignment. When balance is possible, the actual imbalance is set by the logical-to-physical assignment, meaning a balanced assignment can distribute routing costs perfectly evenly at no extra depth. Through exhaustive search on a 57-qubit "heavy-hex" lattice, we prove these topological constraints. For a four-part ring, 108 of 124 connected patches admit a cost-free balanced assignment, with the 16 exceptions being star-shaped. For a six-part ring, cost-free balance is impossible on compact patches. For a fully connected four-part symmetry, balance is structurally impossible at any depth. Simulations using realistic error rates show that, relative to the worst-case concentrated assignment, balanced assignments reduce symmetry-breaking by 92.7% (95% CI [+89.8%, +95.3%]) for the raw metric and 87.0% (95% CI [+79.6%, +94.1%]) for the decoherence-corrected measure (p = 2.45 x 10^-32). Substrate error heterogeneity accounts for at most 10.8% of this effect. Notably, switching to the compiler's highest generic optimization level did not yield a statistically significant change in routing imbalance, highlighting the need for targeted symmetry-aware passes. When patch geometry permits, routing imbalance is a compiler choice rather than a hardware limitation. Thus, symmetry-aware assignment should be a primary objective for compiler optimization and chip design.
Chih-Chung Hsu
Exact QAOA simulation spans several computational representations whose useful regions differ sharply across graph structure, circuit depth, precision, and available memory. Choosing only a backend name hides these differences: an executable choice also fixes the representation, adapter, precision mode, and memory policy. We introduce RASP-QAOA, a per-instance selector over ten such actions. It first removes actions that cannot implement the requested QAOA semantics or execution requirements, then orders the remaining actions using instance features; actions outside learned support are handled by analytical work estimates. On a content-disjoint 60-request H200 evaluation, RASP-QAOA succeeds on all 31 requests for which at least one admissible action completes and validates. Within this set it reaches 27/31 top-1 and 31/31 top-2 selection, with 1.051 geometric-mean regret. Its failure-penalized PAR10 score is 0.0396 times that of development-selected CUAOA (95% interval: 0.0085-0.1644). A separate 30-request crossover shows that graph structure changes 16 decisions and improves the paired penalized score, while a depth-1 stump matches gradient boosting. The evidence supports resource-aware representation selection at n <= 35, p <= 5, with gains driven by representation features rather than classifier complexity.
Chih-Chung Hsu
QAOA training repeatedly queries an objective and all shared gradients, making exact evaluation a feasibility bottleneck even when QUBO terms have bounded causal cones. Building on established causal-cone restriction and adjoint differentiation, LC-Implicit-QAOA profiles cone structure and induced-edge counts before local-amplitude and named-workspace allocation, then jointly selects equal-size microbatches and checkpoint schedules under a named active-evaluator workspace budget. "Implicit" means omitting both global state and global cost table, not implicit differentiation; infeasible requests are rejected before those allocations. An independently implemented complex128/float64 dense adjoint agrees with LC over 1,800 graph-angle comparisons, with a worst relative gradient error of 1.56 x 10^-13. LC completes all 104 target requests in a p=2 bounded-cone grid; under a prespecified n <= 24 validation cap, the matched state-plus-cost reference is executed for 28 requests and deliberately not run on 76. Across 80 budgeted requests, measured allocated evaluator memory stays within budget, reaching at most 0.797 of it. On 3-regular n=512, p=2, the adjoint reaches the same finite-budget endpoint in 101 objective-equivalent calls and 189 s, versus 909 calls and 1,565 s for central differences. LC targets fixed-depth one- and two-local diagonal QUBO costs with a transverse-field mixer; it provides neither global states, sampling, nor a hardware-independent fastest-backend rule.
Nikhil Sreekumar, Abhishek Chandra
The proliferation of multi-sensor Internet of Things (IoT) systems, from Body Sensor Networks (BSNs) to industrial monitoring, is increasingly constrained by strict energy budgets and limited on-device storage. Continuous high-fidelity sensing leads to rapid battery depletion and data gaps that compromise application reliability. Existing strategies address this through sensor selection or adaptive sampling in isolation, or rely on computationally expensive agents for joint optimization. They lack context granularity or introduce significant overhead, and critically, they do not account for the risk that an aggressive, context-specific sensing policy applied to a misidentified context degrades accuracy. In this paper, we formulate joint sensor and sampling-rate selection as an NP-hard energy-minimization problem and propose Viveka, a lightweight, context-aware framework. Viveka couples a cheap, always-on controller that estimates context and how much to trust that estimate with a stability and confidence gated policy that applies an aggressive per-context configuration only when context is certain, and falls back safely otherwise. Per-context configurations are instantiated using permutation feature importance and spectral energy analysis. Evaluation on the MHEALTH and PAMAP2 datasets shows that Viveka achieves up to 75% energy savings and 78% data reduction over standard baselines in a best-case configuration, while maintaining classification accuracy within 3-5% of the baselines.
Pratik Patil, Bhushan Bonde, Bhaskar Choubey
Proteins occupy heterogeneous free-energy landscapes in which high-entropy ensembles converge toward compact, low-energy basins with multiple sub-states. Molecular dynamics can access these landscapes at atomic resolution, but exhaustive sampling remains computationally demanding. Meanwhile, most quantum approaches target only single optimal structures, leaving full ensemble energetic heterogeneity unexplored. We introduce a residue-level, gate-based quantum circuit framework for coarse-graining protein thermodynamics. Each amino acid is represented as a two-state qubit (stabilised vs. excited solvation state) based on residue solvation energetics. A structure-informed entanglement block then encodes covalent and non-covalent contacts using parameterised controlled gates, embedding correlations across the residue-interaction network. Sampling the circuit (∼106 measurements) yields binary thermodynamic microstates used to compute protein energy distributions, residue-level statistical couplings, energetic sensitivities, and information gains relative to total free energy. We showcase the framework on the benchmark Trp-cage miniprotein 1L2Y (TC5b) and 9GDL, a disulfide-stabilised Trp-cage-fortified exenatide chimera. For 1L2Y, the circuit reproduces a structured, folding-funnel-like energy distribution. Comparative analysis with 9GDL reveals shifts in global energy distributions and residue-level stability profiles. Coupling and information-theoretic analyses localise residues associated with ensemble reorganisation, while multi-body couplings show the circuit resolves both direct and indirect statistical correlations. This framework expands quantum protein modelling beyond single-structure optimisation toward ensemble-level characterisation, capturing key features of rugged energy landscapes to guide protein design, mutation mapping, and allosteric pathway identification.
Rakesh Jain, Thomas Griffin, Syed Zawad
Approximate nearest-neighbor (ANN) search increasingly runs alongside structured data - "find the 10 nearest documents where tenant='acme' AND lang='en'" - yet similarity and filtering are usually bolted together: a specialized vector index for one, a separate filter step for the other. We ask what happens when both live inside an open lakehouse table (Apache Iceberg over Parquet on object storage), where the engine already owns a mature file-pruning stack (partition pruning, zone-maps, a bitmap index). We embed an IVF index in place in each Parquet file's footer and make filtered vector queries fast not with a new filtering algorithm but by composing the table's existing file pruning with per-file ANN: the planner prunes data files by the predicate first, then runs IVF only over the survivors. The index is built distributed and non-destructively - a metadata-only Iceberg replace that every other engine still reads - and a rendezvous-hashed per-file cache keeps object-store read latency from swamping the algorithmic win. The payoff comes entirely from file pruning. On an 11.5M x 768 table, warm IVF search is ~32x faster than brute force at recall@10 >= 0.90, a selective predicate having pruned 355 of 444 data files before ANN runs; on 5M real IBM Granite embeddings, a filter arriving across a join prunes four of five region partitions and runs nearly two orders of magnitude (~94x: 14.7 s -> 157 ms) faster than the query-time join at identical top-k, once the reduction is materialized into a region-partitioned layout. We characterize when the composition pays off - it requires file-level locality on the filter column, and the residual predicate is only safe to push into the search over a provably pure (partitioned) column, not a merely sorted one - and report the failure modes we hit bolting ANN onto a lakehouse engine.
Fiona Jiali Fröhler, Yannick Stade, Christian Ufrecht +2
Quantum circuit cutting enables the execution of large circuits on devices with a limited number of qubits by partitioning circuits into independent subcircuits. However, this introduces a sampling overhead, which grows exponentially with the number of cuts, rendering the choice of cut placements critical for practical circuit cutting. Determining optimal cut placements remains computationally challenging, particularly as circuits grow in size. Additionally, existing circuit cutting approaches typically treat gate and wire cuts independently. Those combining both cutting approaches, however, do not take advantage of joint cutting, i.e., identifying common gate groups and cutting them jointly for a reduced overhead. This work presents a unified framework that combines gate and wire cutting within a single partitioning strategy, enabling more efficient circuit decompositions. Moreover, our approach incorporates joint cutting via a novel gate grouping technique, further reducing sampling overhead. By formulating the cut placement problem as a scalable graph partitioning task, our method efficiently identifies near-optimal cut placements for large circuits, also providing diagnostic feedback on whether circuits are suitable for cutting.
Paritosh Parmar, Landy Lan, Hong Yang +2
Can computer vision help make classrooms safer? In this pilot study, we investigate privacy-aware and computationally efficient classroom incident recognition from CCTV-style observations. This setting remains underexplored, with limited benchmarks and few methods designed for the privacy, efficiency, and generalization demands of real-world deployment. We introduce a novel hybrid benchmark combining generative CCTV-style videos with real-world classroom pose data, and propose a lightweight, but robust motion-reasoning framework motivated by the observation that many incidents differ more in motion direction, speed, acceleration, and intensity than in pose alone. To that end, our method first constructs hierarchical kinematic representations of human actions. Our method then distills hierarchical, multi-order kinematic reasoning from a large teacher into a much smaller single-order student, enabling efficient per-person inference while preserving expressive motion understanding. Experiments show that our model outperforms substantially larger baselines at less than one-tenth of their computational cost, while also demonstrating stronger out-of-domain motion reasoning and zero-shot synthetic-to-real generalization. We will publicly release the benchmark, codebase, and supporting tools to facilitate further research in privacy-aware classroom safety.
Weiqi Chi, Bo Qian, Hanlin Wu +3
The vision for 6G vehicle-to-everything (V2X) communications demands reliable, adaptive connectivity for fully autonomous driving across complex dynamic environments. Millimeter-wave (mmWave) user association (UA) in heterogeneous vehicular networks presents a particularly demanding instance of this problem, where dynamic blockages and rapid channel variations continuously undermine the stationary reward assumptions of traditional multi-armed bandit (MAB) frameworks. This paper proposes a fully distributed blockage-aware non-stationary dynamic bandit algorithm (BAND) and its semi-distributed extension S-BAND for cooperative learning across vehicles. Blockage prediction is incorporated into the change-detection (CD) mechanism to suppress false alarms, while a dynamic base station (BS) set management scheme balances exploration and exploitation across large-scale BS deployments without requiring centralized channel state information (CSI) acquisition or offline training. In S-BAND, vehicles accumulate BS reward estimates as local knowledge and periodically upload them to the macro base station (MBS), which aggregates them into cluster-based central knowledge. A trajectory-aligned knowledge (TAK) region is proposed to capture the spatial correlation of mmWave channel characteristics. A knowledge inheritance fidelity (KIF) metric is introduced to quantify knowledge transfer quality. Simulation results on a realistic urban topology show that BAND and S-BAND achieve 34.9% and 59.4% regret reduction relative to a centralized MAB baseline, with performance gains sustained across blockage rates ranging from 10% to 50%. The proposed TAK region consistently outperforms the traditional K-means clustering scheme under both fidelity criteria.