Papers

Integrated sensing and communication (ISAC) can substantially improve spectral, hardware, and energy efficiency by unifying radar sensing and data communications. In wideband and scattering-rich environments, clutter often dominates weak target reflections and becomes a fundamental bottleneck for reliable sensing. Practical ISAC clutter includes "cold" clutter arising from environmental backscatter of the probing waveform, and "hot" clutter induced by external interference and reflections from the environment whose statistics can vary rapidly over time. In this article, we develop a unified wideband multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) signal model that captures both clutter types across the space, time, and frequency domains. Building on this model, we review clutter characterization at multiple levels, including amplitude statistics, robust spherically invariant random vector (SIRV) modeling, and structured covariance representations suitable for limited-snapshot regimes. We then summarize receiver-side suppression methods in the temporal and spatial domains, together with extensions to space-time adaptive processing (STAP) and space-frequency-time adaptive processing (SFTAP), and we provide guidance on selecting techniques under different waveform and interference conditions. To move beyond reactive suppression, we discuss clutter-aware transceiver co-design that couples beamforming and waveform optimization with practical communication quality-of-service (QoS) constraints to enable proactive clutter avoidance. We conclude with open challenges and research directions toward environment-adaptive and clutter-resilient ISAC for next-generation networks.

The rapid growth of data centers driven by cloud computing and artificial intelligence is reshaping infrastructure planning and environmental governance in the United States. Georgia has emerged as a major market for data center development, particularly in the Atlanta metropolitan region, creating economic opportunity alongside significant challenges. Data centers are water-intensive, energy-intensive, and land-intensive infrastructure whose cumulative impacts strain municipal water systems, electric grids, and local land-use frameworks. Unlike single industrial projects, data centers are often proposed in clusters, amplifying community and infrastructure impacts. This report draws on insights from a Georgia-based expert convening to describe the implications of data center growth for water management, energy reliability, ratepayer equity, zoning, and community engagement, identify potential gaps in transparency and regulatory coordination, and present a policy roadmap to help Georgia balance digital infrastructure growth with sustainability, equity, and community protection.

In this paper, we investigate scale-free delta-level coherent output synchronization for multi-agent systems (MAS) operating under bounded disturbances or noises. We introduce an adaptive scale-free framework designed solely based on the knowledge of agent models and completely agnostic to both the communication topology and the size of the network. We define the level of coherency for each agent as the norm of the weighted sum of the disagreement dynamics with its neighbors. We define each agents coherency level as the norm of a weighted sum of its disagreement dynamics relative to its neighbors. The goal is to ensure that the networks coherency level remains below a prescribed threshold delta, without requiring any a priori knowledge of the disturbance.

Unmanned aerial vehicle (UAV) downlink transmission facilitates critical time-sensitive visual applications but is fundamentally constrained by bandwidth scarcity and dynamic channel impairments. The rapid fluctuation of the air-to-ground (A2G) link creates a regime where reliable transmission slots are intermittent and future channel quality can only be predicted with uncertainty. Conventional deep joint source-channel coding (DeepJSCC) methods transmit coupled feature streams, causing global reconstruction failure when specific time slots experience deep fading. Decoupling semantic content into a deterministic structure component and a stochastic texture component enables differentiated error protection strategies aligned with channel reliability. A predictive transmission framework is developed that utilizes a split-stream variational codec and a channel-aware scheduler to prioritize the delivery of structural layout over reliable slots. Experimental evaluations indicate that this approach achieves a 5.6 dB gain in peak signal-to-noise (SNR) ratio over single-stream baselines and maintains structural fidelity under significant prediction mismatch.

Large Audio Language Models (LALMs) have demonstrated strong capabilities in audio understanding and reasoning. However, their performance on fine grained auditory perception remains unreliable, and existing approaches largely rely on data intensive training to internalize perceptual abilities. We propose AudioRouter, a reinforcement learning framework that enables LALMs to improve audio understanding by learning when and how to use external audio tools. Rather than tightly coupling tool usage with audio reasoning, AudioRouter formulates tool use as an explicit decision making problem and optimizes a lightweight routing policy while keeping the underlying reasoning model frozen. Experimental results show that AudioRouter achieves substantial improvements on standard audio understanding benchmarks while requiring up to 600x less training data to learn tool usage compared with conventional training paradigms. These findings suggest that learning effective tool usage offers a data efficient and scalable alternative to internalizing perceptual abilities in LALMs.

Orthogonal time frequency space (OTFS) modulation has demonstrated significant advantages in high-mobility scenarios in future 6G networks. However, existing channel estimation methods often overlook the structured sparsity and clustering characteristics inherent in realistic clustered delay line (CDL) channels, leading to degraded performance in practical systems. To address this issue, we propose a novel nonparametric Bayesian learning (NPBL) framework for OTFS channel estimation. Specifically, a stick-breaking process is introduced to automatically infer the number of multipath components and assign each path to its corresponding cluster. The channel coefficients within each cluster are modeled by a Gaussian mixture distribution to capture complex fading statistics. Furthermore, an effective pruning criterion is designed to eliminate spurious multipath components, thereby enhancing estimation accuracy and reducing computational complexity. Simulation results demonstrate that the proposed method achieves superior performance in terms of normalized mean squared error compared to existing methods.

In recent years, unmanned aerial vehicles (UAVs) equipped with imaging sensors and automated processing algorithms have emerged as a promising tool to accelerate large-area surveys while reducing risk to human operators. Although hyperspectral imaging (HSI) enables material discrimination using spectral signatures, standardized benchmarks for UAV-based landmine detection remain scarce. In this work, we present a systematic benchmark of four classical statistical detection algorithms, including Spectral Angle Mapper (SAM), Matched Filter (MF), Adaptive Cosine Estimator (ACE), and Constrained Energy Minimization (CEM), alongside a proposed lightweight Spectral Neural Network utilizing Parametric Mish activations for PFM-1 landmine detection. We also release pixel-level binary ground truth masks (target/background) to enable standardized, reproducible evaluation. Evaluations were conducted on inert PFM-1 targets across multiple scene crops using a recently released VNIR hyperspectral dataset. Metrics such as receiver operating characteristic (ROC) curve, area under the curve (AUC), precision-recall (PR) curve, and average precision (AP) were used. While all methods achieve high ROC-AUC on an independent test set, the ACE method observes the highest AUC of 0.989. However, because target pixels are extremely sparse relative to background, ROC-AUC alone can be misleading; under precision-focused evaluation (PR and AP), the Spectral-NN outperforms classical detectors, achieving the highest AP. These results emphasize the need for precision-focused evaluation, scene-aware benchmarking, and learning-based spectral models for reliable UAV-based hyperspectral landmine detection. The code and pixel-level annotations will be released.

Recent work has popularized a practical recipe in diffusion and flow matching: predict the clean signal $x$, convert it to a velocity, and train through a velocity-space loss. The conversion contains a singular endpoint amplification and therefore appears prone to unstable optimization, yet recent systems obtain strong empirical results with this recipe. We investigate this tension through the integrability of the pre-optimizer stochastic-gradient second moment. Under stated initialization conditions, the moment diverges under Uniform sampling; boundary-suppressing sampling can restore integrability under an additional upper-growth condition. We then show that prediction–loss alignment eliminates this conversion-induced source of non-integrability. Under a uniform moment bound, alignment yields a finite second moment for every timestep density, including Uniform sampling. Controlled experiments across continuous and binary settings reproduce the predicted sampler-dependent instability and show that aligned objectives remain trainable across the tested samplers. These results reconcile pointwise amplification with sampler-dependent empirical success and support alignment as a principled route to more robust flow-matching training.

Transparent liquid manipulation in robotic pouring remains challenging for perception systems: specular/refraction effects and lighting variability degrade visual cues, undermining reliable level estimation. To address this challenge, we introduce RadarEye, a real-time mmWave radar signal processing pipeline for robust liquid level estimation and tracking during the whole pouring process. RadarEye integrates (i) a high-resolution range-angle beamforming module for liquid level sensing and (ii) a physics-informed mid-pour tracker that suppresses multipath to maintain lock on the liquid surface despite stream-induced clutter and source container reflections. The pipeline delivers sub-millisecond latency. In real-robot water-pouring experiments, RadarEye achieves a 0.35 cm median absolute height error at 0.62 ms per update, substantially outperforming vision and ultrasound baselines.

We present a novel online learning-based approach for concept drift adaptation in optical network failure detection, achieving up to a 70% improvement in performance over conventional static models while maintaining low latency.

Cloud-based battery management systems (BMSs) rely on real-time voltage measurement data to coordinate bi-directional electric vehicle (EV) charging in vehicle-to-grid (V2G) applications. Unfortunately, an adversary can corrupt the transmitted measurement data, leading to disrupted charging/discharging of EVs. To ensure reliable voltage data under such sensor attacks, this paper proposes a secure voltage estimation scheme for large-format battery packs based on a self-learning Koopman operator with two-stage error corrections. The first stage compensates for the Koopman approximation error, and the second stage aims to recover the error amassed from the lack of higher-order battery dynamics information in the self-learning feedback. The latter is obtained from two alternative methods: an adaptable heuristic correction that leverages cell-level open-circuit voltage to state-of-charge mapping, and a Gaussian process regression-based correction. We tested our proposed secure estimator using the high-fidelity battery simulation package 'PyBaMM-liionpack', and the results show high accuracy under varying pack topologies, charging settings, battery aging, and attack policies. These findings highlight the scalability and adaptability of our algorithm to diverse battery configurations and operating conditions without requiring significant modifications, excessive data, or sensor redundancy.

Atmospheric turbulence and aero-optic effects cause phase aberrations in propagating light waves, thereby reducing effectiveness in transmitting and receiving coherent light from an aircraft. Existing optical sensors can measure the resulting phase aberrations, but the physical experiments required to induce these aberrations are expensive and time-intensive. Simulation methods could provide a less expensive alternative. For example, an existing simulation algorithm called boiling flow, which generalizes the Taylor frozen-flow method, can generate synthetic phase aberration data (i.e., phase screens) induced by atmospheric turbulence. However, boiling flow depends on physical parameters, such as the Fried coherence length r0, which are not well-defined for aero-optic effects. In this paper, we introduce a method to estimate the parameters of boiling flow from measured aero-optic phase aberration data. Our algorithm estimates these parameters to fit the spatial and temporal statistics of the measured data. This method is computationally efficient and our experiments show that the temporal power spectral density of the slopes of the synthetic phase screens reasonably matches that of the measured phase aberrations from two turbulent boundary layer data sets, with errors between 8-9%. However, the Kolmogorov spatial structure function of the phase screens does not match that of the measured phase aberrations, with errors above 28%. This suggests that, while the parameters of boiling flow can reasonably fit the temporal statistics of highly convective data, they cannot fit the complex spatial statistics of aero-optic phase aberrations.

Medical image analysis requires substantial labeled data for model training, yet expert annotation is expensive and time-consuming. Active learning (AL) addresses this challenge by strategically selecting the most informative samples for the annotation purpose, but traditional methods solely rely on predictive uncertainty while ignoring whether models learn from clinically meaningful features a critical requirement for clinical deployment. We propose an explainability-guided active learning framework that integrates spatial attention alignment into a sample acquisition process. Our approach advocates for a dual-criterion selection strategy combining: (i) classification uncertainty to identify informative examples, and (ii) attention misalignment with radiologist-defined regions-of-interest (ROIs) to target samples where the model focuses on incorrect features. By measuring misalignment between Grad-CAM attention maps and expert annotations using Dice similarity, our acquisition function judiciously identifies samples that enhance both predictive performance and spatial interpretability. We evaluate the framework using three expert-annotated medical imaging datasets, namely, BraTS (MRI brain tumors), VinDr-CXR (chest X-rays), and SIIM-COVID-19 (chest X-rays). Using only 570 strategically selected samples, our explainability-guided approach consistently outperforms random sampling across all the datasets, achieving 77.22% accuracy on BraTS, 52.37% on VinDr-CXR, and 52.66% on SIIM-COVID. Grad-CAM visualizations confirm that the models trained by our dual-criterion selection focus on diagnostically relevant regions, demonstrating that incorporating explanation guidance into sample acquisition yields superior data efficiency while maintaining clinical interpretability.

Purpose: Translating foundation models into clinical practice requires evaluating their performance under compound distribution shift, where severe class imbalance coexists with heterogeneous imaging appearances. This challenge is relevant for traumatic bowel injury, a rare but high-mortality diagnosis. We investigated whether specificity deficits in foundation models are associated with heterogeneity in the negative class. Methods: This retrospective study used the multi-institutional, RSNA Abdominal Traumatic Injury CT dataset (2019-2023), comprising scans from 23 centres. Two foundation models (MedCLIP, zero-shot; RadDINO, linear probe) were compared against three task-specific approaches (CNN, Transformer, Ensemble). Models were trained on 3,147 patients (2.3% bowel injury prevalence) and evaluated on an enriched 100-patient test set. To isolate negative-class effects, specificity was assessed in patients without bowel injury who had concurrent solid organ injury (n=58) versus no abdominal pathology (n=50). Results: Foundation models achieved equivalent discrimination to task-specific models (AUC, 0.64-0.68 versus 0.58-0.64) with higher sensitivity (79-91% vs 41-74%) but lower specificity (33-50% vs 50-88%). All models demonstrated high specificity in patients without abdominal pathology (84-100%). When solid organ injuries were present, specificity declined substantially for foundation models (50-51 percentage points) compared with smaller reductions of 12-41 percentage points for task-specific models. Conclusion: Foundation models matched task-specific discrimination without task-specific training, but their specificity deficits were driven primarily by confounding negative-class heterogeneity rather than prevalence alone. Susceptibility to negative-class heterogeneity decreased progressively with labelled training, suggesting adaptation is required before clinical implementation.

Reinforcement learning (RL) has shown great potential for designing voltage control policies, but their performance often degrades under changing system conditions such as topology reconfigurations and load variations. We introduce a topology-aware online policy optimization framework that leverages data-driven estimation of voltage-reactive power sensitivities to achieve efficient policy adaptation. Exploiting the sparsity of topology-switching events, where only a few lines change at a time, our method efficiently detects topology changes and identifies the affected lines and parameters, enabling fast and accurate sensitivity updates without recomputing the full sensitivity matrix. The estimated sensitivity is subsequently used for online policy optimization of a pre-trained neural-network-based RL controller. Simulations on both the IEEE 13-bus and SCE 56-bus systems demonstrate over 90 percent line identification accuracy, using only 15 data points. The proposed method also significantly improves voltage regulation performance compared with non-adaptive policies and adaptive policies that rely on regression-based online optimization methods for sensitivity estimation.

Quantitative MRI (qMRI) involves parameter estimation governed by an explicit signal model. However, these models are often confounded and difficult to validate in vivo. A model is misspecified when the assumed signal model differs from the true data-generating process. Under misspecification, the variance of any unbiased estimator is lower-bounded by the misspecified Cramer-Rao bound (MCRB), and maximum-likelihood estimates (MLE) may exhibit bias and inconsistency. Based on these principles, we assess misspecification in qMRI using two tests: (i) examining whether empirical MCRB asymptotically approaches the CRB as repeated measurements increase; (ii) comparing MLE estimates from two equal-sized subsets and evaluating whether their empirical variance aligns with theoretical CRB predictions. We demonstrate the framework using arterial spin labeling (ASL) as an illustrative example. Our result shows the commonly used ASL signal model appears to be specified in the brain and moderately misspecified in the kidney. The proposed framework offers a general, theoretically grounded approach for assessing model validity in quantitative MRI.

Diabetes mellitus is a chronic metabolic disorder characterized by persistent hyperglycemia due to insufficient insulin production or impaired insulin utilization. One of its most severe complications is diabetic retinopathy (DR), a progressive retinal disease caused by microvascular damage, leading to hemorrhages, exudates, and potential vision loss. Early and reliable detection of DR is therefore critical for preventing irreversible blindness. In this work, we propose an uncertainty-aware deep learning framework for automated DR severity grading that explicitly models the ordinal nature of disease progression. Our approach combines a convolutional backbone with lesion-query attention pooling and an evidential Dirichlet-based ordinal regression head, enabling both accurate severity prediction and principled estimation of predictive uncertainty. The model is trained using an ordinal evidential loss with annealed regularization to encourage calibrated confidence under domain shift. We evaluate the proposed method on a multi-domain training setup combining APTOS, Messidor-2, and a subset of EyePACS fundus datasets. Experimental results demonstrate strong cross-dataset generalization, achieving competitive classification accuracy and high quadratic weighted kappa on held-out test sets, while providing meaningful uncertainty estimates for low-confidence cases. These results suggest that ordinal evidential learning is a promising direction for robust and clinically reliable diabetic retinopathy grading.

A family of ferrimagnets (CoV2O4, GdCo, TbCo) exhibits out-of-plane magnetic anisotropy when strained compressively and in-plane magnetic anisotropy when strained expansively (or vice versa). If such a ferrimagnetic thin film is placed on top of a topological insulator (TI) thin film and its magnetic anisotropy is modulated with strain, then interfacial exchange coupling between the ferrimagnet (FM) and the underlying TI will modulate the surface current flowing through the latter. If the strain is varied continuously, the current will also vary continuously and if the strain alternates in time, the current will also alternate with the frequency of the strain modulation, as long as the frequency is not so high that the period is smaller than the switching time of the FM. If the strain is generated with a gate voltage by integrating a piezoelectric underneath the FM/TI stack, then that can implement a transconductance amplifier or a synapse for neuromorphic computation.

Audio language models process input audio into rich frame-level representations, but the standard approach to temporal localization generates timestamps as sequences of text tokens, which discards the frame-level representations in favor of autoregressive decoding. However, generating timestamps as tokens is slow and not parallelizable, and tends to hallucinate when producing timestamps outside the training distribution. We propose internal frame-level reuse, a method that trains audio LMs to reuse their own internal audio representations for temporal localization directly, bypassing token generation altogether. We introduce a lightweight prediction head trained via different frame-level objectives: a binary frame classifier and a novel inhomogeneous Poisson process (IHP) loss that models temporal event intensity. Across word localization, speaker diarization, and event localization tasks, our approach can achieve a >50x inference speedup over token-based generation and demonstrates robust length generalization, maintaining high accuracy on out-of-distribution audio durations where token-based models collapse completely. We find that reusing audio frame-level representations yields localization accuracies comparable to (and often better than) finetuned token-based baselines.

Quantum operations with indefinite causal order (ICO) represent a framework in quantum information processing where the relative order between two events can be indefinite. In this paper, we investigate whether sensing and computation, two canonical tasks in quantum information processing, can be carried out within the ICO framework. We propose a scheme for integrated sensing and computation that uses the same quantum state for both tasks. The quantum state is represented as an agent that performs state observation and learns a function of the state to make predictions via a parametric model. Under an ICO operation, the agent experiences a superposition of orders, one in which it performs state observation and then executes the required computation steps, and another in which the agent carries out the computation first and then performs state observation. This is distinct from prevailing information processing and machine intelligence paradigms where information acquisition and learning follow a strict causal order, with the former always preceding the latter. We provide experimental results and we show that the proposed scheme can achieve small training and testing losses on a representative task in magnetic navigation.

Generative image steganography is a technique that conceals secret messages within generated images, without relying on pre-existing cover images. Recently, a number of diffusion model-based generative image steganography (DM-GIS) methods have been introduced, which effectively combat traditional steganalysis techniques. In this paper, we identify the key factors that influence DM-GIS security and revisit the security of existing methods. Specifically, we first provide an overview of the general pipelines of current DM-GIS methods, finding that the noise space of diffusion models serves as the primary embedding domain. Further, we analyze the relationship between DM-GIS security and noise distribution of diffusion models, theoretically demonstrating that any steganographic operation that disrupts the noise distribution compromise DM-GIS security. Building on this insight, we propose a Noise Space-based Diffusion Steganalyzer (NS-DSer)-a simple yet effective steganalysis framework allowing for detecting DM-GIS generated images in the diffusion model noise space. We reevaluate the security of existing DM-GIS methods using NS-DSer across increasingly challenging detection scenarios. Experimental results validate our theoretical analysis of DM-GIS security and show the effectiveness of NS-DSer across diverse detection scenarios.

This work presents a concept and implementation for the secure storage and transfer of quality-relevant data of milled workpieces from online-quality assurance processes enabled by real-time simulation models. It utilises Non-Fungible Tokens (NFT) to securely and interoperably store quality data in the form of an Asset Administration Shell (AAS) on a public Ethereum blockchain. Minted by a custom smart contract, the NFTs reference the metadata saved in the Interplanetary File System (IPFS), allowing new data from additional processing steps to be added in a flexible yet secure manner. The concept enables automated traceability throughout the value chain, minimising the need for time-consuming and costly repetitive manual quality checks.

The scarcity of high-quality segmentation masks remains a major bottleneck for medical image analysis, particularly in non-contrast CT (NCCT) neuroimaging, where manual annotation is costly and variable. To address this limitation, we propose an anatomy-preserving generative framework for the unconditional synthesis of multi-class brain segmentation masks, including ischemic infarcts. The proposed approach combines a variational autoencoder trained exclusively on segmentation masks to learn an anatomical latent representation, with a diffusion model operating in this latent space to generate new samples from pure noise. At inference, synthetic masks are obtained by decoding denoised latent vectors through the frozen VAE decoder, with optional coarse control over lesion presence via a binary prompt. Qualitative results show that the generated masks preserve global brain anatomy, discrete tissue semantics, and realistic variability, while avoiding the structural artifacts commonly observed in pixel-space generative models. Overall, the proposed framework offers a simple and scalable solution for anatomy-aware mask generation in data-scarce medical imaging scenarios.

Speech provenance goes beyond detecting whether a watermark is present. Real workflows involve splicing, quoting, trimming, and platform-level transforms that may preserve some regions while altering others. Neural watermarking systems have made strides in robustness and localised detection, but most deployments produce outputs with no third-party verifiable cryptographic proof tying a time segment to an issuer-signed original. Provenance standards like C2PA adopt signed manifests and Merkle-based fragment validation, yet their bindings target encoded assets and break under re-encoding or routine processing. We propose MerkleSpeech, a system for public-key verifiable, chunk-localised speech provenance offering two tiers of assurance. The first, a robust watermark attribution layer (WM-only), survives common distribution transforms and answers "was this chunk issued by a known party?". The second, a strict cryptographic integrity layer (MSv1), verifies Merkle inclusion of the chunk's fingerprint under an issuer signature. The system computes perceptual fingerprints over short speech chunks, commits them in a Merkle tree whose root is signed with an issuer key, and embeds a compact in-band watermark payload carrying a random content identifier and chunk metadata sufficient to retrieve Merkle inclusion proofs from a repository. Once the payload is extracted, all subsequent verification steps (signature check, fingerprint recomputation, Merkle inclusion) use only public information. The result is a splice-aware timeline indicating which regions pass each tier and why any given region fails. We describe the protocol, provide pseudocode, and present experiments targeting very low false positive rates under resampling, bandpass filtering, and additive noise, informed by recent audits identifying neural codecs as a major stressor for post-hoc audio watermarks.

Expressive speech synthesis requires vibrant prosody and well-timed pauses. We propose an effective strategy to augment a small dataset to train an expressive end-to-end Text-to-Speech model. We merge audios of emotionally congruent text using a text emotion recognizer, creating augmented expressive speech data. By training with two-sentence audio, our model learns natural breaks between lines. We further apply self-supervised contrastive training to improve the speaking style embedding extraction from speech. During inference, our model produces multi-sentence speech in one step, guided by the text-predicted speaking style. Evaluations showcase the effectiveness of our proposed approach when compared to a baseline model trained with consecutive two-sentence audio. Our synthesized speeches give a closer inter-sentence pause distribution to the ground truth speech. Subjective evaluations reveal our synthesized speech scored higher in naturalness and style suitability than the baseline.

False data injection attacks (FDIAs) pose a persistent challenge to AC power system state estimation. In current practice, detection relies primarily on topology-aware residual-based tests that assume malicious measurements can be distinguished from normal operation through physical inconsistency reflected in abnormal residual behavior. This paper shows that this assumption does not always hold: when FDIA scenarios produce manipulated measurements that remain on the measurement manifold induced by AC power flow relations and measurement redundancy, residual-based detectors may fail to distinguish them from nominal data. The resulting detectability limitation is a property of the measurement manifold itself and does not depend on the attacker's detailed knowledge of the physical system model. To make this limitation observable in practice, we present a data-driven constructive mechanism that incorporates the generic functional structure of AC power flow to generate physically consistent, manifold-constrained perturbations, providing a concrete witness of how residual-based detectors can be bypassed. Numerical studies on multiple AC test systems characterize the conditions under which detection becomes challenging and illustrate its failure modes. The results highlight fundamental limits of residual-based detection in AC state estimation and motivate the need for complementary defenses beyond measurement consistency tests.

Recent approaches in music generation rely on disentangled representations, often labeled as structure and timbre or local and global, to enable controllable synthesis. Yet the underlying properties of these embeddings remain underexplored. In this work, we evaluate such disentangled representations in a set of music audio models for controllable generation using a probing-based framework that goes beyond standard downstream tasks. The selected models reflect diverse unsupervised disentanglement strategies, including inductive biases, data augmentations, adversarial objectives, and staged training procedures. We further isolate specific strategies to analyze their effect. Our analysis spans four key axes: informativeness, equivariance, invariance, and disentanglement, which are assessed across datasets, tasks, and controlled transformations. Our findings reveal inconsistencies between intended and actual semantics of the embeddings, suggesting that current strategies fall short of producing truly disentangled representations, and prompting a re-examination of how controllability is approached in music generation.

Efficient exploration remains a central challenge in reinforcement learning (RL), particularly in sparse-reward environments. We introduce Optimistic World Models (OWMs), a principled and scalable framework for optimistic exploration that brings classical reward-biased maximum likelihood estimation (RBMLE) from adaptive control into deep RL. In contrast to upper confidence bound (UCB)-style exploration methods, OWMs incorporate optimism directly into model learning by augmentation with an optimistic dynamics loss that biases imagined transitions toward higher-reward outcomes. This fully gradient-based loss requires neither uncertainty estimates nor constrained optimization. Our approach is plug-and-play with existing world model frameworks, preserving scalability while requiring only minimal modifications to standard training procedures. We instantiate OWMs within two state-of-the-art world model architectures, leading to Optimistic DreamerV3 and Optimistic STORM, which demonstrate significant improvements in sample efficiency and cumulative return compared to their baseline counterparts.

Reconfigurable intelligent surfaces (RISs) are a promising enabling technology for the sixth-generation ($6$G) of wireless communications. RISs, thanks to their intelligent design, can reshape the wireless channel to provide favorable propagation conditions for information transfer. In this work, we experimentally investigate the potential of RISs to enhance the effective rank of multiple-input multiple-output (MIMO) channels, thereby improving spatial multiplexing capabilities. In our experiment, commodity WiFi transceivers are used, representing a practical MIMO system. In this context, we propose a passive beam-focusing technique to manipulate the propagation channel between each transmit-receive antenna pair and achieve a favorable propagation condition for rank improvement. The proposed algorithm is tested in two different channel scenarios: low and medium ranks. Experimental results show that, when the channel is rank-deficient, the RIS can significantly increase the rank by $112\%$ from its default value without the RIS, providing a rank increment of $1.5$. When the rank has a medium value, a maximum of $61\%$ enhancement can be achieved, corresponding to a rank increment of $1$. These results provide the first experimental evidence of RIS-driven rank manipulation with off-the-shelf WiFi hardware, offering practical insights into RIS deployment for spatial multiplexing gains.

Lane changing in dense traffic is a significant challenge for Connected and Autonomous Vehicles (CAVs). Existing lane change controllers primarily either ensure safety or collaboratively improve traffic efficiency, but do not consider these conflicting objectives together. To address this, we propose the Multi-Agent Safety Shield (MASS), designed using Control Barrier Functions (CBFs) to enable safe and collaborative lane changes. The MASS enables collaboration by capturing multi-agent interactions among CAVs through interaction topologies constructed as a graph using a simple algorithm. Further, a state-of-the-art Multi-Agent Reinforcement Learning (MARL) lane change controller is extended by integrating MASS to ensure safety and defining a customised reward function to prioritise efficiency improvements. As a result, we propose a lane change controller, known as MARL-MASS, and evaluate it in a congested on-ramp merging simulation. The results demonstrate that MASS enables collaborative lane changes with safety guarantees by strictly respecting the safety constraints. Moreover, the proposed custom reward function improves the stability of MARL policies trained with a safety shield. Overall, by encouraging the exploration of a collaborative lane change policy while respecting safety constraints, MARL-MASS effectively balances the trade-off between ensuring safety and improving traffic efficiency in congested traffic. The code for MARL-MASS is available with an open-source licence at https://github.com/hkbharath/MARL-MASS