Uncertainty quantification is essential when deploying machine learning models in safety-critical applications. Online conformal prediction (OCP) provides theoretically principled uncertainty quantification for arbitrary black-box classifiers and non-i.i.d. data streams by constructing prediction sets that are guaranteed to contain the true label at a user-specified frequency. OCP usually updates prediction sets using feedback from previously deployed predictions. We instead study an OCP setting beyond feedback: on each round, the learner can either output a prediction set or query the correct label, but not both. Thus, no deployed prediction is ever evaluated directly. We reduce this problem to a partial monitoring game in which prediction actions return no observation and a separate query action reveals the label. The reward function is constructed in a way that encourages the learner to output small prediction sets while ensuring that the correct label is covered with a sufficiently high probability. To solve this game, we develop OCP with queries (OCPQ) by adapting the label efficient forecaster of Cesa-Bianchi, Lugosi, and Stoltz (2004) to our setting. For any black box classifier and any (non-i.i.d.) oblivious data stream of length T, OCPQ has O(T^2/3) expected regret and expected coverage at least β-O(T^-1/3) for a user-defined β, while querying only an expected T^-1/3 fraction of rounds. This provides coverage comparable to bandit-based OCP methods while requiring no feedback from deployed prediction sets. Experiments on real-world datasets further demonstrate the effectiveness of our approach.

AI is poised to revolutionize telecommunication networks by boosting efficiency, automation, and decision-making. However, the black-box nature of most AI models introduces substantial risk, possibly deterring adoption by network operators. These risks are not addressed by the current prevailing deployment strategy, which typically follows a best-effort train-and-deploy paradigm. This paper reviews conformal calibration, a general framework that moves beyond the state of the art by adopting computationally lightweight, advanced statistical tools that offer formal reliability guarantees without requiring further training or fine-tuning. Conformal calibration encompasses pre-deployment calibration via uncertainty quantification or hyperparameter selection; online monitoring to detect and mitigate failures in real time; and counterfactual post-deployment performance analysis to address "what if" diagnostic questions after deployment. By weaving conformal calibration into the AI model lifecycle, network operators can establish confidence in black-box AI models as a dependable enabling technology for wireless systems.

Reward modeling is central to alignment pipelines such as RLHF, RLAIF, and PPO-based policy optimization, yet its reliability is constrained by limited and heterogeneous human preference data that are expensive to collect at scale. While synthetic augmentation can expand preference supervision, existing methods often augment uniformly or at the representation level, without targeting examples where the reward model is uncertain or prone to mis-ranking. In this paper, we introduce MARS (Margin and Semantic-Aware Data Augmentation for Reward Modeling), an adaptive augmentation framework that prioritizes low-margin preference pairs and uses semantic distance as a second layer for refinement to enhance the contrast between the chosen and rejected responses. Across multiple preference datasets, reward-model backbones, downstream alignment settings, and benchmarks including RewardBench and AlpacaEval, MARS improves both reward-model quality and alignment performance over existing baselines. Our results show that reward-model augmentation is most effective when guided by both model margins and semantic structure.

Large language models (LLMs) are emerging as key enablers of automation in domains such as telecommunications, assisting with tasks including troubleshooting, standards interpretation, and network optimization. However, their deployment in practice must balance inference cost, latency, and reliability. In this work, we study an edge-cloud-expert cascaded LLM-based knowledge system that supports decision-making through a question-and-answer pipeline. In it, an efficient edge model handles routine queries, a more capable cloud model addresses complex cases, and human experts are involved only when necessary. We define a misalignment-cost constrained optimization problem, aiming to minimize average processing cost, while guaranteeing alignment of automated answers with expert judgments. We propose a statistically rigorous threshold selection method based on multiple hypothesis testing (MHT) for a query processing mechanism based on knowledge and confidence tests. The approach provides finite-sample guarantees on misalignment risk. Experiments on the TeleQnA dataset – a telecom-specific benchmark – demonstrate that the proposed method achieves superior cost-efficiency compared to conventional cascaded baselines, while ensuring reliability at prescribed confidence levels.

Zeroth-order (ZO) optimization estimates gradients using only forward-pass evaluations, making it suitable for fine-tuning non-differentiable, event-driven spiking neural networks (SNNs). However, its deployment on in-memory computing (IMC) accelerators is constrained by the repeated read-modify-write (RMW) operations arising from explicit weight perturbation and the prohibitive hardware footprint of random number generators (RNGs) for statistically independent per-weight perturbations. To address these challenges, we propose an implicit-perturbation ZO (IPZO) architecture in which perturbation sums computed by an event-triggered perturbation generation unit (PGU) are combined with the weighted sums produced by the IMC array, eliminating perturbation-induced RMW operations while preserving weight-stationary execution of IMC. By exploiting spike sparsity, the PGU generates and accumulates perturbation contributions only for spike-activated weight rows, reducing the required row dimension of the RNG array. An address-driven XOR recombination scheme (PGU-XOR) is further introduced to mitigate the spatial correlations caused by direct RNG reuse (PGU-Reuse). The results show that (1) PGU-XOR matches software RNGs in accuracy on Spikingformer/CIFAR-10 (76.41

We study the remote estimation of a linear Gaussian system over a channel that wears out over time and with every use. The sensor can either transmit a fresh measurement in the current time slot, restore the channel quality at the cost of downtime, or remain silent. Frequent transmissions yield accurate estimates but incur significant wear on the channel. Renewing the channel too often improves channel conditions but results in poor estimation quality. What is the optimal timing to transmit measurements and restore the channel? This problem is formulated as a semi-Markov decision process (SMDP). We establish monotonicity properties of the optimal policy and propose structure-aware solution methods.

Neuromorphic and quantum computing have recently emerged as promising paradigms for advancing artificial intelligence, each offering complementary strengths. Neuromorphic systems built on spiking neurons excel at processing time-series data efficiently through sparse, event-driven computation, consuming energy only upon input events. Quantum computing, on the other hand, leverages superposition and entanglement to explore feature spaces that are exponentially large in the number of qubits. Hybrid approaches combining these paradigms have begun to show potential, but existing quantum spiking models have important limitations. Notably, prior quantum spiking neuron implementations rely on classical memory mechanisms on single qubits, requiring repeated measurements to estimate firing probabilities, and they use conventional backpropagation on classical simulators for training. Here we propose a stochastic quantum spiking (SQS) neuron model that addresses these challenges. The SQS neuron uses multi-qubit quantum circuits to realize a spiking unit with internal quantum memory, enabling event-driven probabilistic spike generation in a single shot. Furthermore, we outline how networks of SQS neurons – dubbed SQS neural networks (SQSNNs) – can be trained via a hardware-friendly local learning rule, eliminating the need for global classical backpropagation. The proposed SQSNN model fuses the time-series efficiency of neuromorphic computing with the exponentially large inner state space of quantum computing, paving the way for quantum spiking neural networks that are modular, scalable, and trainable on quantum hardware.

Deep neural network (DNN)-based receivers offer a powerful alternative to classical model-based designs for wireless communication, especially in complex and nonlinear propagation environments. However, their adoption is challenged by the rapid variability of wireless channels, which makes pre-trained static DNN-based receivers ineffective, and by the latency and computational burden of online stochastic gradient descent (SGD)-based learning. In this work, we propose an online learning framework that enables rapid low-complexity adaptation of DNN-based receivers. Our approach is based on two main tenets. First, we cast online learning as Bayesian tracking in parameter space, enabling a single-step adaptation, which deviates from multi-epoch SGD . Second, we focus on modular DNN architectures that enable parallel, online, and localized variational Bayesian updates. Simulations with practical communication channels demonstrate that our proposed online learning framework can maintain a low error rate with markedly reduced update latency and increased robustness to channel dynamics as compared to traditional gradient descent based method.

Neuromorphic computing enables event-driven, low-power inference and is therefore an attractive technology for jointly carrying out communication, sensing, and processing at resource-constrained wireless devices. Impulse radio ultra-wideband (IR-UWB) signaling, which is standardized in the IEEE 802.15.4 family and widely deployed for ranging and short-range communication, is naturally matched to neuromorphic processing, since both operate through sparse temporal events, or spikes. In this context, this paper studies a standard-compliant neuromorphic integrated sensing and communications (N-ISAC) system in which a single spiking neural network (SNN) receiver jointly demodulates digital data and detects a passive radar target directly from a common IEEE 802.15.4z high-rate-pulse-repetition-frequency (HRP) UWB waveform. Unlike prior N-ISAC work, which assumed a basic pulse-position-modulation interface and a simplified multipath channel, we consider the full standardized physical layer together with a realistic ray-traced channel aided by a reconfigurable intelligent surface (RIS). The model accounts for the frequency-selective response of a metamaterial-based RIS, which disperses the wideband IR-UWB pulses and can degrade both communication and sensing. Numerical experiments quantify the impact of RIS frequency selectivity on UWB ISAC and characterize the trade-off between ISAC performance and receiver computation energy.

Stacked intelligent metasurfaces (SIMs) have recently emerged as a promising architecture for large-scale beamforming systems, including cell-free massive MIMO (CF-mMIMO), due to their cost-effective wave-domain signal processing capabilities. However, existing algorithms for the joint optimization of digital and SIM-enabled wave-domain beamforming typically incur prohibitive computational complexity. In this work, we propose an efficient alternating optimization (AO) algorithm for weighted sum-rate maximization in SIM-assisted CF-mMIMO systems employing hybrid digital-wave beamforming. Unlike prior approaches that rely on general-purpose optimization solvers or per-element gradient ascent methods, the proposed algorithm updates the digital and wave-domain beamforming variables on a per-access point (AP) or per-SIM-layer basis, enabling closed-form updates at each step. Numerical results demonstrate that the proposed algorithm reduces the computational complexity by more than 99% compared to existing algorithms while achieving nearly identical sum-rate performance.

Training effective artificial intelligence models for telecommunications is challenging due to the scarcity of deployment-specific data. Real data collection is expensive, and available datasets often fail to capture the unique operational conditions and contextual variability of the network environment. Digital twinning provides a potential solution to this problem, as simulators tailored to the current network deployment can generate site-specific data to augment the available training datasets. However, there is a need to develop solutions to bridge the inherent simulation- to-reality (sim-to-real) gap between synthetic and real-world data. This article reviews recent advances on two complementary strategies: 1) the calibration of digital twins (DTs) through realworld measurements, and 2) the use of sim-to-real gap-aware training strategies to robustly handle residual discrepancies between digital twin-generated and real data. For the latter, we evaluate two conceptually distinct methods that model the simto- real gap either at the level of the environment via Bayesian learning or at the level of the training loss via prediction-powered inference.

Conformal selection (CS) uses calibration data to identify test inputs whose unobserved outcomes are likely to satisfy a pre-specified minimal quality requirement, while controlling the false discovery rate (FDR). Existing methods fix the target FDR level before observing data, which prevents the user from adapting the balance between number of selected test inputs and FDR to downstream needs and constraints based on the available data. For example, in genomics or neuroimaging, researchers often inspect the distribution of test statistics, and decide how aggressively to pursue candidates based on observed evidence strength and available follow-up resources. To address this limitation, we introduce post-hoc CS (PH-CS), which generates a path of candidate selection sets, each paired with a data-driven false discovery proportion (FDP) estimate. PH-CS lets the user select any operating point on this path by maximizing a user-specified utility, arbitrarily balancing selection size and FDR. Building on conformal e-variables and the e-Benjamini-Hochberg (e-BH) procedure, PH-CS is proved to provide a finite-sample post-hoc reliability guarantee whereby the ratio between estimated FDP level and true FDP is, on average, upper bounded by 1, so that the average estimated FDP is, to first order, a valid upper bound on the true FDR. PH-CS is extended to control quality defined in terms of a general risk. Experiments on synthetic and real-world datasets demonstrate that, unlike CS, PH-CS can consistently satisfy user-imposed utility constraints while producing reliable FDP estimates and maintaining competitive FDR control.

Federated Bayesian neural networks require fixing a prior on the model parameters together with a likelihood. Eliciting meaningful priors on the weight space of modern overparameterized models is notoriously difficult, and misspecification of either component can severely degrade accuracy and calibration. Motivated by the rapid progress of predictive models such as large language models, the martingale posterior, also known as predictive Bayes, replaces the prior--likelihood pair with a predictive distribution and recovers parameter uncertainty by repeatedly drawing predictive samples and refitting the model. A direct federated implementation, however, would require clients to share the local data sets. This letter proposes {federated martingale posterior} (FMP) sampling, a one-shot embarrassingly parallel protocol in which each client uploads a small set of trainable data embeddings and the server runs the predictive sampler centrally. Experiments on MNIST, CIFAR-10, and CIFAR-100 show that FMP closely matches the centralized counterpart and significantly improves calibration over consensus-style baselines.

Deploying trustworthy AI systems requires principled uncertainty quantification. Conformal prediction (CP) is a widely used framework for constructing prediction sets with distribution-free coverage guarantees. In many practical settings, including healthcare, finance, and mobile sensing, the calibration data required for CP are distributed across multiple clients, each with its own local data distribution. In this federated setting, data can often be partitioned into, potentially overlapping, groups, which may reflect client-specific strata or cross-cutting attributes such as demographic or semantic categories. We propose group-conditional federated conformal prediction (GC-FCP), a federated extension of conditional conformal calibration for a target mixture over prespecified groups. GC-FCP constructs mergeable, atom-stratified coresets from local calibration scores, enabling compact aggregation at the server when the number of active atoms is moderate. Experiments on synthetic and real-world datasets validate the performance of GC-FCP compared to centralized calibration baselines. The code of our work can be found at https://github.com/HaifengWen/GC-FCP.

Narrowband interference can severely degrade the performance of WiFi links by concentrating significant power on a small portion of the channel. Machine learning (ML) detectors trained on baseband I/Q samples can identify the affected subcarriers with high accuracy, surpassing model-based detectors that rely on hand-crafted statistics. The predictive probabilities produced by such detectors are, however, typically poorly calibrated, and downstream mitigation modules generally operate under strict resource budgets that limit the number of candidate interference states that can be acted upon. Conformal prediction (CP) provides a distribution-free framework for constructing prediction sets that control the probability of excluding the true output, i.e., the miscoverage level, at a prescribed level. However, this target miscoverage level must be fixed in advance, while the resulting prediction-set size remains uncontrolled, which is misaligned with operationally constrained settings. To address this issue, we develop a backward conformal prediction (BCP) framework in which the prediction-set size is fixed by the operational budget and the corresponding per-input miscoverage level is estimated from calibration data with provable reliability guarantees. We instantiate the framework for narrowband interference detection in WiFi systems and show through simulations that BCP yields reliable miscoverage estimates whose accuracy approaches that of an uncalibrated baseline as the calibration set grows.

In safety-critical applications such as medical image segmentation, prediction systems must provide reliability guarantees that extend beyond conventional expected loss control. While risk-controlling prediction sets (RCPS) offer probabilistic guarantees on the expected risk, they fail to capture tail behavior and worst-case scenarios that are crucial in high-stakes settings. This paper introduces optimized certainty equivalent RCPS (OCE-RCPS), a novel framework that provides high-probability guarantees on general optimized certainty equivalent (OCE) risk measures, including conditional value-at-risk (CVaR) and entropic risk. OCE-RCPS leverages upper confidence bounds to identify prediction set parameters that satisfy user-specified risk tolerance levels with provable reliability. We establish theoretical guarantees showing that OCE-RCPS satisfies the desired probabilistic constraint for loss functions such as miscoverage and false negative rate. Experiments on image segmentation demonstrate that OCE-RCPS consistently meets target satisfaction rates across various risk measures and reliability configurations, while OCE-CRC fails to provide probabilistic guarantees.

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

Artificial intelligence (AI) research today is largely driven by ever-larger neural network models trained on graphics processing units (GPUs). This paradigm has yielded remarkable progress, but it also risks entrenching a hardware lottery in which algorithmic choices succeed primarily because they align with current hardware, rather than because they are inherently superior. In particular, the dominance of transformer architectures running on GPU clusters has led to an arms race of scaling up models, resulting in exorbitant computational costs and energy usage. At the same time, today's AI models often remain unreliable in the sense that they cannot properly quantify uncertainty in their decisions-for example, large language models (LLMs) tend to produce incorrect outputs with high confidence. This paper argues that achieving more efficient and reliable AI will require embracing a set of principles that are well aligned with the goals of neuromorphic engineering, which are in turn inspired by how the brain processes information. Specifically, we outline six key neuromorphic principles, spanning algorithms, architectures and hardware, that can inform the design of future AI systems: (i) the use of stateful, recurrent models; (ii) extreme dynamic sparsity, possibly down to spike-based processing; (iii) backpropagation-free on-device learning and fine-tuning; (iv) probabilistic decision-making; (v) in-memory computing (IMC); and (vi) hardware-software co-design via stochastic computing. We discuss each of these principles in turn, surveying relevant prior work and pointing to directions for research. This article is part of the discussion meeting issue 'Bits, neurons and qubits for sustainable AI'.

Modern artificial intelligence systems require calibrated uncertainty estimates that remain reliable in sequential and non-stationary environments. Online conformal prediction (OCP) addresses this challenge through adaptively updated prediction sets that provide deterministic long-run miscoverage guarantees. These guarantees, however, hinge on the assumption of perfect feedback about the coverage of past prediction sets. In practice, the observed miscoverage indicator may be corrupted by noise, communication failures, or adversarial manipulation, which can severely degrade OCP's calibration guarantees. In this paper, we study OCP under corrupted feedback. We first model feedback corruption as an arbitrary binary flip sequence, and analyze how feedback corruption affects and degrades the miscoverage performance of standard OCP. We then propose two robust schemes: robust OCP via filtering, which leverages the structural properties of the predicted threshold to filter corrupted feedback, and robust OCP via active compensation, which incorporates an active compensation mechanism to mitigate the effect of corrupted feedback. For both methods, we establish explicit miscoverage guarantees, which are further specialized for an independent stochastic flip model and for an arbitrary error model with memory bounds. Experiments on real-world datasets validate the proposed approach, showing markedly improved calibration and significantly smaller prediction sets compared with baseline OCP methods under corrupted feedback.