Papers

Driven by ongoing standardization efforts, Wi-Fi sensing has recently emerged as a promising functionality within wireless local area networks (WLANs). However, due to the use of standard null-data packets (NDPs) to estimate the channel, conventional Wi-Fi sensing systems are susceptible to spoofing attacks. To counter this threat, we propose a lightweight tag-embedding scheme that enables physical layer authentication (PLA) of sensing signals. Specifically, a secret tag is superimposed onto the orthogonal frequency division multiplexing (OFDM) channel sounding signal, allowing legitimate WLAN receivers to verify signal authenticity and detect spoofed transmissions. A unique tag is generated for each transmission to avoid replay attacks, and the subcarrier occupancy of each tag is randomized to minimize the mean channel estimation error at each subcarrier. Simulation results demonstrate reliable authentication performance with a 95% correct authentication rate at a signal-to-noise ratio (SNR) of 10dB, while introducing an additional channel estimation error of only 0.52dB at legacy receivers that are unaware of the embedded tag. Thus, our proposed scheme provides an effective and backward-compatible countermeasure against spoofing attacks, enhancing the trustworthiness of future Wi-Fi sensing systems.

A speech neuroprosthesis decodes attempted speech from brain activity and ends by rescoring the decoder's candidate sentences with a language model of several billion parameters, the only component that needs a GPU. Replacing that model with a cheaper one is hard: general language models asked to pick one sentence from a list answer from where a label sits in the list rather than from the sentence itself. We pose rescoring as a single typed decision, one call that returns a probability for every candidate, served by Jev, a hosted model trained for calibrated decisions, and combine it with the decoder's own score. On 978 held-out sentences from a participant with ALS, where the published decoder alone reaches 8.1% word error, Jev reaches 7.5% against 7.8% for both OPT-6.7b and Qwen2.5-7B; with the decoder's weight re-tuned, 6.9% against 7.2% and 7.4%. Jev is ahead in all four comparisons and at most 0.2 points behind at the 95% bound. It costs 0.07 USD per thousand sentences and needs no GPU; a dedicated GPU running a 7B model is cheaper per sentence only above 43% utilisation, far beyond what one user generates. End-to-end latency over the internet is 262 ms, of which 62 ms is spent at the provider, the same order as a 7B model on a local GPU (27 ms) but not faster.

Perturbation-based XAI methods for audio classifiers often estimate feature importance by masking spectrogram regions and crediting output changes to the retained signal. Yet they typically assume the fill (the mask replacement) is negligible. We propose logit-space trajectory decomposition to examine this assumption. An on-axis component captures output along a line connecting the fully filled (occluded) spectrogram to the fully retained original; an off-axis component captures perpendicular displacement. We evaluate across three fills, three audio classifiers, and 1,100 AudioSet clips. We demonstrate that no fill is acoustically neutral under full occlusion: Zero fill activates silence and Gaussian Noise fill activates broadband noise. Under partial masking, 41-77% of output displacement is off-axis, with the direction of the residual stable across mask retention fraction and specific to each model-fill combination. Attribution methods are unevenly exposed to off-axis displacement through their sampling and weighting strategies, revealing apparatus-dependence. Where the off-axis residual is stable and low-dimensional, its structure affords mitigation.

Intelligent handover management is a key capability for future 6G networks. This paper investigates enhanced handover strategies in systems assisted by Simultaneously Transmitting and Reflecting Reconfigurable Intelligent Surfaces (STAR-RIS). In addition, it explores the optimal placement of multiple base stations (BSs) to further improve network performance. To eliminate coverage dead zones, a Deep Deterministic Policy Gradient (DDPG) framework is utilized to enforce a Max-Min Fairness objective, directly maximizing the worst-case Signal-to-Noise Ratio (SNR). This optimized topology is evaluated via a dynamic mobility stress test simulating 180 pedestrians executing A3-event handovers under stochastic transient blockages. Results demonstrate that the DDPG deployment outperforms random baselines by a 3.17 dB mean gap, achieving a 24 dB worst-case SNR and a 0.963 Jain's fairness index. Crucially, this optimal static placement drastically improves dynamic mobility resilience, ensuring a 100% successful handover rate and reducing post-failure outage time to a negligible 0.01%.

We present DAOCP, a dual active set solver for linear quadratic optimal control problems with stage-wise equality and inequality constraints. Active set methods are leading Model Predictive Control benchmarks for full-body robotics, but existing solvers operate on dense QPs, while typical problem dimensions favor methods that exploit the optimal control structure. DAOCP combines the warm-starting capabilities of active set algorithms with the better computational scaling of structure exploiting solvers, by relying on a generalization of the relationship between the Riccati recursion and the Cholesky factorization of the condensed Hessian. This result enables dual active set iterations to operate directly on the original optimal control problem through recursive computations, without explicitly forming the condensed quadratic program. On robotics benchmarks, DAOCP is the fastest of four solvers in four of five scenarios, cutting average solve time on a 58-state Atlas model by 9$\times$ relative to state of the art solvers DAQP and HPIPM.

Full-duplex spoken dialogue models can listen and speak simultaneously like the real-time dynamics of human conversation. For natural dialogue, the ability to search for external information in real-time is also an important capability. Many models remain trapped in parametric knowledge, leaving them unable to access real-time information and tool execution. Furthermore, even when Large Language Models (LLM) retrieve information, many duplex speech models process it within a compressed latent space rather than in its raw text form, which can lead to information loss from compression. To address this issue, we propose Context Spanning, a framework for information injection between a full-duplex speech model and an external LLM backend via real-time chunked prefill. The injected frame is encoded in a single forward pass inside the real-time frame budget. It feeds the retrieved information to the speech model as-is, enabling it to reason over the information independently and generate responses. With this approach, our model achieves high performance on Full-Duplex benchmarks and strong results on Question Answering tasks, demonstrating its conversation potential. Context Spanning shows that external information can be injected directly into a duplex speech model, introducing a new simple and powerful mechanism for duplex systems.

Text-to-Audio (T2A) retrievers are typically evaluated with caption style queries, but the same user intent can be expressed in many forms. We introduce CORA (Caption-Offset Retrieval for Audio), a caption anchored diagnostic protocol that rewrites each source caption into five intent preserving forms (Command, Question, Indirect, Key phrase, and Statement) while fixing the target audio. By tracking the same target across query forms, CORA defines RankDrop, a metric revealing failures hidden by Recall@k. Using Pearson's correlation coefficient r, we find that RankDrop is weakly associated with raw text space movement (r=0.084), but strongly associated with Target Alignment Loss and Target Boundary Margin Degradation (r=0.508 and r=0.615). The same pattern appears in OEA retrievers, where RankDrop is better explained by boundary degradation (r=0.472/0.478) than by query movement (r=0.084/0.046). Overall, these results suggest that robust T2A retrieval requires preserving the target's boundary advantage over competing audio under reformulation.

The transition from vocoder-based to neural-codec speech synthesis makes generalization more difficult for speech deepfake detectors, particularly those relying on speech-oriented representations. It remains unclear which acoustic representations retain discriminative information when the generation mechanism changes. We therefore compare 12 acoustic representations using a shared low-capacity linear classifier to identify effective evidence under codec shift. The analysis shows that hierarchical XLS-R leads on the pooled test set, while pooled no-vocals residual statistics perform best on the unseen-codec condition, revealing complementary behavior across generation conditions. Building on this finding, we propose MN-P, a dual-view detector that integrates an utterance-level pooled no-vocals representation with token-level XLS-R features through adaptive gating. The proposed MN-P reduces EER by 54.2% overall and by 60.9% on the codec-unseen condition relative to the best-performing retrained state-of-the-art system, with consistent gains across different detector backends. These results indicate that pooled no-vocals residual statistics provide effective complementary evidence for cross-generation speech deepfake detection.

Tracking speech sources remains a challenge due to ambiguous data association arising from intermittent speech, close spatial proximity, and complex acoustic conditions. To address these issues, we propose an identity-assisted association that maps unordered direction-of-arrival (DOA) estimates to speaker-consistent source trajectories for reliable speech source tracking. Specifically, speaker identity embeddings are directly integrated into the model input as a complementary cue to spatial features. This enables maintaining identity consistency by combining long-term time-invariant vocal identity characteristics with the short-term continuity of spatial cues. To effectively process these heterogeneous inputs while accommodating their distinct characteristics, we design a unified neural tracker. Within this model, time self-attention modules capture the temporal evolution of each source, while source self-attention modules distinguish between competing source tracks. Experimental results demonstrate the superiority of the proposed neural tracker in mitigating association confusion for speech source tracking.

Multi-speaker dialogue TTS requires natural speech generation, consistent speaker identity, coherent cross-turn transitions, and fine-grained control of expressive attributes such as emotion, speaking rate, and loudness. These requirements are difficult to satisfy reliably with one-shot generation, especially in long-form dialogue. We propose a controllable multi-speaker dialogue TTS framework that formulates synthesis as critique-driven iterative refinement. Its speech backbone, ControlEdit-TTS, unifies instruction-following synthesis and natural-language-guided attribute editing, enabling correction of expressive errors without full regeneration. The framework further performs hierarchical utterance-level and scene-level critique, routing detected issues to editing, resynthesis, or timing adjustment. Experiments on a bilingual Chinese–English dialogue benchmark show improved utterance-level instruction following, better dialogue-level preference than direct dialogue models and agentic baselines, and more effective refinement than regeneration-only alternatives while preserving speaker identity. Ablations further confirm the benefits of scene-level critique and edit-based correction.

Multilingual self-supervised speech models can benefit from sharing information across languages, but under a matched total pretraining data budget they still fall short of monolingual models. We show that strengthening the model's ability to discriminate languages during pretraining reduces and, on some measures, closes this multilingual gap on continuous phonetic and higher-level linguistic measures, while preserving substantial cross-language sharing. Using a controlled English/French HuBERT setting, we test two interventions which strengthen language discrimination: an auxiliary language classifier and per-language k-means targets. Across interventions, continuous-feature phone discrimination error (phone-ABX, lower is better) decreases from 11.6% in the bilingual baseline to 10.4% (monolingual: 10.8%), while lexical performance (sWUGGY, higher is better) increases from 52.1% to 56.7% (monolingual: 58.5%) and prosodic performance (ProsAudit, lexical subtask, higher is better) from 68.9% to 72.9% (monolingual: 72.6%). Across HuBERT training stages, the strongest gains on most linguistic measures occur when language discrimination is introduced in the first iteration, whereas later or repeated interventions yield smaller improvements and are accompanied by increased language-wise segregation. These results support a causal role for language discrimination in reducing the additional cost of multilingual learning.

This paper investigates joint active and passive beamforming for a multiuser downlink system assisted by a fully-connected beyond-diagonal reconfigurable intelligent surface (BD-RIS). Since the number of tunable components grows quadratically with the number of RIS elements, directly optimizing the full scattering matrix becomes increasingly computationally expensive. To address this challenge, we first derive an equivalent low-dimensional formulation that replaces the full scattering matrix with a variable whose number of columns equals the number of users. We further establish a smooth manifold structure on a dense subset of the equivalent feasible set, based on which we develop a low-dimensional Riemannian alternating optimization (LD-RAO) algorithm, where the passive variable is updated using a single Riemannian gradient ascent step at each iteration. The convergence of LD-RAO is established under mild assumptions. Numerical results demonstrate that the proposed algorithm achieves the same performance as the existing state-of-the-art (SOTA) full-dimensional methods with significantly less CPU time, particularly for large-scale BD-RIS.

Signal Temporal Logic (STL) enables rigorous verification and control of cyber-physical systems, but writing correct specifications requires expertise that most requirement holders lack. Large language models can translate natural-language (NL) requirements into STL, yet stronger translators alone approach an accuracy ceiling. We argue that this ceiling stems from how the task is posed: one-shot, open-loop translation is somewhat ill-defined. Natural language is ambiguous, and, more fundamentally, what a person writes may not always be what they intend, so the target specification is not fully contained in the input text. We therefore reformulate NL-to-STL translation as a closed-loop feedback process. Each generated formula is translated back into natural language for the user to check, and natural-language corrections drive revision until the user accepts the specification. Users never read or write formal syntax. This framework rests on an asymmetry familiar from feedback control theory. The forward path, from ambiguous language to formal logic, is hard and error-prone. The feedback path, from structured STL back to language, can be made highly precise, and a precise feedback path lets an imprecise forward path achieve precise closed-loop behavior. Experiments on 500 expert-authored requirements and seven LLMs support this view. Back-translated explanations agree with expert judgments in 99.5% of cases. Closed-loop refinement raises strong models from about 89% open-loop accuracy to 98.0–99.2%, and yields gains of over 30 percentage points for weaker models (e.g., 17.6%$\rightarrow$48.0%). Ablations show these gains come from the semantic content of the feedback rather than from repeated attempts. An expert audit and a 280-session user study further confirm the reliability of the loop. We also identify a capability threshold above which feedback no longer helps.

Stacked intelligent metasurfaces (SIMs) have emerged as a promising wave-domain processing technology for sixth-generation integrated sensing and communication networks, reducing reliance on complex radio-frequency hardware. Nevertheless, imperfect channel state information (CSI) can compromise sensing performance and communication reliability. Moreover, ensuring covert transmission introduces a further challenge, as the system must sense potential targets while concealing communication activity from unauthorized wardens. These challenges motivate the development of robust SIM-assisted integrated sensing and covert communication (ISACC) systems. In this paper, we investigate the robust transceiver design of a multi-user, multi-target ISACC system under imperfect CSI. We jointly optimize the transmit and receive beamformers, sensing covariance matrix, and SIM phase shifts to maximize the worst-case minimum sensing signal-to-interference-plus-noise ratio. The formulation enforces constraints on bounded channel uncertainties, user quality-of-service requirements, transmit-power budget, SIM phase shifts, and target detection probabilities. Since the formulated problem is highly non-convex, we develop an alternating optimization framework based on the S-procedure, successive convex approximation, and semidefinite relaxation. Furthermore, to reduce computational complexity, we derive exact lower-dimensional representations of the robust sensing linear matrix inequalities (LMIs) involved in transmit/receive-beamformer designs. We further develop a low-complexity phase-update method that avoids the large sensing LMIs. Numerical results demonstrate that the proposed design outperforms random phase shift and fully digital-beamforming benchmarks, while the low-complexity scheme achieves comparable performance to the LMI-based scheme at substantially lower computational cost.

Orchestral separation recovers instrument sections from mixtures in which shared pitches, harmonics, and timbres obscure source identity. An aligned score provides instrument labels, note pitches, and activity times. A score-informed approach appends piano rolls to audio features before mask prediction. We introduce SCISSOR (Score-Conditioned Instrument Source Separation for Orchestral Recordings), which uses the score to form a frame-wise query for each source. Each query matches a shared audio representation, and a softmax over instrument and background slots jointly assigns overlapping time-frequency evidence. The queries retain instrument identity even when notes are missing from the score. After training on SynthSOD and a small set of URMP and PHENICX-Anechoic recordings, SCISSOR achieves the highest average SDR on held-out real recordings. With SynthSOD-only training, it leads on SynthSOD and zero-shot PHENICX-Anechoic, and improves on its audio-only control on zero-shot URMP. SCISSOR also degrades less under score corruption than the evaluated score-based baselines.

Grant-free random access in massive machine-type communications requires detecting a small active set from length-L uplink pilots received at an M-antenna base station. Classical covariance-based detectors are largely built on the far-field (FF) model, where the M antenna-domain observations are treated as independent snapshots, and inference reduces to an L $\times$ L covariance description. This model becomes inadequate in mixed near-field (NF) and FF access, where NF devices induce device-specific structured spatial covariances and the aggregate observation no longer fits the FF snapshot structure. In this paper, we develop a unified covariance-aware Rician framework for activity detection that treats FF and NF devices by a single likelihood model. Within this framework, we propose a majorization-minimization projected gradient descent (MM-PGD) detector for the resulting relaxed likelihood. For scalable exact likelihood evaluation, we further derive a Kronecker-Woodbury implementation that exploits the mixed NF/FF covariance structure, and avoids factorizing the full LM $\times$ LM covariance matrix. Numerical results show that MM-PGD is on par with the strongest coordinate-wise baseline in the all-FF limit, while its advantage becomes more pronounced as the fraction of NF users increases under the tested regimes.

Speculative decoding accelerates autoregressive automatic speech recognition (ASR), but the acceptance length of alignment-aware drafters can saturate as the draft horizon increases. We propose a progress-aware speculative drafter that recurrently propagates an acoustic progress state across draft steps and feeds it back into audio cross-attention to guide token generation. We jointly train the drafter and progress predictor over variable draft horizons. On five ASR test sets, our method achieves lossless, macro-averaged end-to-end speedups of 1.657x and 1.227x over target-only autoregressive decoding with Qwen3-ASR-0.6B and Qwen3-ASR-1.7B, respectively. Relative to AnchorDraft, our method improves the macro-averaged speedup by 34.3% and 9.0%, respectively. Horizon sweeps show continued growth in acceptance length beyond the baselines' saturation. Code is available at https://github.com/yuanyuanjia71-spec/ProgDraft.

Affine frequency division multiplexing (AFDM) has emerged as a competitive waveform for integrated sensing and communication (ISAC) in high-mobility scenarios, but its data-dependent high peak-to-average power ratio (PAPR) and ambiguity function (AF) sidelobes may degrade the power-amplifier efficiency as well as the sensing performance. To mitigate the issues, one promising candidate is the phase-rotation optimization philosophy, which necessitates auxiliary side information (SI) to guarantee successful data recovery at the receiver. However, using additional signalling overhead to deliver the SI degrades the spectral efficiency. Against the background, this paper proposes a power level index modulation (PLIM)-aided phase-rotated AFDM (PLIM-PR-AFDM) scheme, which embeds the phase-rotation SI within the transmitted block. At the transmitter, the proposed scheme jointly optimizes the waveform by coordinating the PLIM power allocation, phase rotation, and embedding of SI. Specifically, subcarriers are flexibly allocated with different transmit power levels. High-power subcarriers are phase-rotated to suppress the PAPR and fast-slow-time AF sidelobes. By decomposing the fast-slow-time AF sidelobe energy into per-block periodic autocorrelation function (PACF) terms, the sensing objective can be formulated as a PACF-weighted integrated sidelobe level (WISL) minimization problem, while selected low-power subcarriers embed the phase bits as SI through constellation labels. Furthermore, the PLIM power patterns of each transmitted block can convey additional index bits, which compensates for the spectral efficiency loss caused by SI transmission. Moreover, the error performance is analyzed by deriving an upper bound of the average bit error probability (ABEP) and identifying the condition for full diversity.

Speaker verification systems achieve high accuracy but provide little account of the acoustic evidence behind their judgments. Making these systems inspectable requires exposing interpretable evidence while retaining the richer information on which their decisions depend. We present CoLMbo-SV, a speaker language model that combines strong speaker discrimination with structured, acoustically grounded comparison reports. By connecting a pretrained speaker encoder to a language model and supplying explicit acoustic measurements, CoLMbo-SV makes voice comparisons inspectable without restricting verification to the evidence verbalized in its reports. We additionally introduce VoxReason, paired recordings with measured acoustic properties and comparison reports filtered through numerical and qualitative checks, providing supervision for this combined capability. We also develop an evaluation framework that separates what acoustic information a speaker representation encodes, what influences the verification score, and what the generated report discusses. On VoxCeleb1-O, CoLMbo-SV achieves 0.99% EER, reducing verification error by approximately 80% relative to the strongest audio-language baseline fine-tuned on VoxReason, while attaining a numerical-grounding score of 0.82. Our analysis further demonstrates that acoustic correctness and decision relevance are distinct properties of an explanation, exposing a gap that numerical-grounding metrics miss. Together, these contributions substantially advance audio-language speaker verification, bring its accuracy toward that of dedicated speaker encoders while adding checkable acoustic reporting, and establish an empirical framework for connecting natural-language explanations to the decisions they explain.

We design adaptive overlapping temporal decomposition (AOTD), a parallel sequential quadratic programming (SQP) method for long-horizon nonlinear optimal control problems (OCPs). As designed, AOTD is the first overlapping temporal decomposition (OTD) algorithm that adapts the overlap size online, eliminating the need to fix a suitable overlap a priori. Specifically, at each iteration, it partitions the long horizon into overlapping nonlinear subproblems, performs one SQP step on each in parallel, and adaptively selects both the overlap size and the accuracy to which the resulting local KKT systems are solved. Two conditions govern the accepted step: an adaptive residual condition bounding the distance from the concatenated inexact direction to the exact Newton direction of the full problem, and a descent condition on the adaptive penalty parameters that certifies descent for a carefully chosen exact augmented Lagrangian. The residual condition is solver independent and accommodates both deterministic iterative solvers and randomized sketching solvers. Under standard regularity assumptions, we prove that the KKT residual converges to zero from any initialization and establish a local linear rate for sequences converging to a strict local minimizer. We validate AOTD on a power-system frequency regulation OCP and a Burgers PDE OCP, attaining a reduction in estimated FLOPs of approximately $2.5\times$ to the best fixed-overlap variant while converging across multiple horizon lengths with a single parameter setting.

In these notes, we view control as a dynamically constrained sampling problem on the state-space of a control system. With this viewpoint, we extend methods from generative modeling, such as flow matching, normalizing flows and denoising diffusions to control problems. Concepts such as controllability, optimal control and trajectory planning play an important role in guiding the extension and understanding well-posedeness of the corresponding algorithms, with application to steering systems to target states or distributions and sampling from reachable sets. The notes are intended as an accessible introduction for readers with a background in control theory and robotics.

This paper studies communication-centric symbol-level precoding (SLP) for fronthaul-limited networked integrated sensing and communication (ISAC). SLP is attractive for exploiting constructive interference, but its data-dependent nature makes fronthaul-aware waveform design difficult because the transmit covariance used in conventional linear-precoding compression models is unavailable before the symbol block is formed. To address this issue, we develop a compression-aware SLP framework that relates the fronthaul requirement to the realized block energy. We further formulate a sensing-oriented joint design. To solve the resulted high-dimensional and nonconvex problem, we propose a tractable lower-bound method with a performance bound. Simulations show that the proposed SLP scheme improves sensing performance over linear-beamforming baselines under fronthaul constraints.

Multimodal large language models (MLLMs) can now interpret a standard ten-second, twelve-lead electrocardiogram (ECG) with clinically grounded, reward-verified reasoning. Real cardiac monitoring is different. Ambulatory (Holter) and telemetry recordings span hours to days and are read as they stream in, and their clinically decisive findings are paroxysmal, brief episodes buried in an otherwise unremarkable trace. Such a recording cannot be held in one context at diagnostic resolution, and its future has not yet happened, so a reader must work online, deciding what to measure now, committing evidence to memory as it passes, and reporting events as they occur. We recast long-duration ECG interpretation as a long-horizon, online (streaming, causal) sequential decision process and introduce ECG-Scroll. As a benchmark, long ambulatory recordings are streamed to an agent chunk by chunk, and it must localize, quantify, and promptly flag paroxysmal events without access to future signal; because the underlying signal is retained, every answer is checkable against objective ground truth, giving rule-based rather than judge-based rewards, and the streaming formulation adds a metric batch evaluation cannot express, the detection latency between an event's onset and the moment the agent records it. As an agent environment, it is a fixed, gym-style interaction layer that exercises three competencies single-glance ECG models never touch: Memory, Tool use through signal-grounded measurement rather than reading pixels, and Planning of what to measure now and when to commit. We release 390 whole-recording instances spanning 2,536 hours of two-lead ambulatory ECG and evaluate a signal-threshold rule agent alongside off-the-shelf LLM agents online, characterizing how they use memory, tools, and planning and where the benchmark's head-room lies.

Gaussian process stochastic differential equations (GP-SDEs) provide a flexible Bayesian model for unknown continuous-time state dynamics with uncertainty quantification, but learning and inference from noisy and irregular observations remain computationally challenging. To address this issue, we propose GP-SDE Matching, a simulation-free variational framework for Bayesian GP drift learning and continuous-time state smoothing. We analytically marginalize the sparse GP posterior to derive a tractable drift-matching objective that accounts for both the posterior mean and uncertainty of the unknown drift. To handle irregular observations, we further introduce an irregular-time-aware variational state posterior that incorporates the actual observation times during both encoding and continuous-time marginal querying. Experiments on the stochastic Lorenz–63 system demonstrate substantially improved drift recovery and state reconstruction under irregular observations, while five system identification benchmarks show robust forecasting under increasing observation sparsity and competitive performance against existing latent-SDE and state-space methods.

Plug-and-Play (PnP) methods replace proximal operators with learned denoisers, which produce state-of-the-art reconstruction quality, but sacrifice the variational interpretation and convergence guarantees of proximal methods. Learned Proximal Networks (LPNs) address this problem by designing the denoiser architecture so that it is exactly the proximal operator of a regularizer. In this work, we clarify the theoretical foundations of LPNs and extend the framework to a broader class of activation functions. We then study two practical mechanisms for controlling the learned prior: (i) averaging the LPN with the identity, a common heuristic in PnP methods, and (ii) directly scaling the implicit regularizer induced by the proximal operator. In particular, we characterize the regularizer induced by averaging and develop a convergent method for evaluating the scaled proximal operator.

Visual perception organizes incomplete sensory evidence into coherent structures, but where do the principles governing this organization come from? We investigate whether learning to predict missing visual information can give rise to structural priors resembling classical Gestalt principles. Masked autoencoders (MAEs) trained on natural images exhibit perceptual completion consistent with good continuation, symmetry, and global form. Critically, when local evidence surrounding a missing region is held constant, manipulating distant elements systematically changes its reconstruction, demonstrating that local predictions are constrained by the global organization of the visual input. We next manipulate visual experience by adapting MAEs to either natural images or texforms that preserve local image statistics while disrupting global spatial organization. This altered experience weakens globally supported completion and shifts perceptual inference toward local continuation when local and global constraints conflict. Together, these results suggest that perceptual organization reflects structural regularities of natural scenes acquired through visual prediction: predictions integrate structural priors across multiple spatial scales, and the balance between local and global organization adapts to the statistical structure of visual experience. More broadly, our findings suggest that classical Gestalt principles may emerge as adaptive perceptual priors learned from the statistical structure of the visual world.

Small-data adaptation can improve speech detection while degrading speaker attribution. We study this discrepancy in a released streaming diarizer adapted on 7.5 h of two-party conversation and evaluated across six corpora. Adaptation substantially improves in-domain diarization performance and transfers to an independent corpus. However, this improvement is not consistent across evaluation scenarios as the additional confusion is mainly associated with impaired temporal identity consistency rather than speaker-count errors. A local-remapping diagnostic reveals different patterns of identity degradation across corpora, indicating that adaptation may alter how streaming models maintain speaker assignments over time. Rehearsal reduces the observed degradation but reduces the cross-domain transfer performance. These results highlight the need to jointly evaluate detection accuracy, identity consistency, and retention behavior when adapting streaming diarization systems.

Policy gradient methods for the linear quadratic regulator optimize feedback gains using a cost over an infinite horizon. When this cost is evaluated at one fixed initial state, it need not diverge near every part of the stability boundary. We study whether the Euclidean gradient flow can reach this boundary in finite optimization time. For controllable planar systems with one input and positive definite quadratic weights, an exact representation of the cost yields a necessary and sufficient condition for the existence of such a collision. The condition reduces to a scalar root calculation and includes the critical case, where a double direction root attracts an open set of stabilizing gains. For a triangular family, the criterion gives an explicit algebraic parameter region, and every trajectory either converges to the Riccati gain or collides with the stability boundary. A sharp threshold for compact cost sublevels provides a convergence certificate. Along every colliding trajectory, the stability margin and the smallest eigenvalue of the accumulated state Gramian vanish linearly, although the Gramian remains positive definite before collision. Numerical experiments examine the dependence on initialization, slow passage near a critical direction, and the effect of adding excitation in a second state direction.

We study the recovery of a finite three-dimensional point cloud from its spherical Fourier signal subspace at a fixed wavenumber. Two ESPRIT constructions are analyzed. The first uses finite shifts between paired small circles; the second uses angular derivatives on the whole sphere. Both recover the same commuting coordinate matrices, either through their finite exponentials or directly from a coupled linear system. We prove that the continuous generator system is injective for every distinct point cloud and that one guard harmonic degree preserves the retained equations exactly. For $s$ targets, the cutoff $K\ge s$ gives generic finite identifiability, but not uniform conditioning. We also derive a finite-cutoff perturbation bound. The accuracy of the coordinate estimates is a separate issue. A one-target perturbation calculation shows that the original generator estimate can retain a nonzero bias as the wavenumber increases. To address this bias, we use the generator eigenbasis to separate approximate atoms and recover their locations from amplitude-normalized phases. Under pointwise atom dominance, the resulting error is $O(\kappa^{-1})$; for a dominant two-atom mixture at fixed separation, it is $O(\kappa^{-2})$. Experiments on structured point clouds with smooth perturbations compare the two constructions and their use as initializers for a common MUSIC refinement.

In this work, we show how two adversaries (Eve and Mallory) can coordinate an electromagnetic side-channel attack to recon- struct the vote displayed on an e-voting machine (EVM) and link it to a specific voter (Alice). Assuming that Eve has access to a place adjacent to the e-polling room (e.g., restroom, unsupervised room), she performs vote reconstruction by intercepting un- intended electromagnetic emanations associated with the video signal. Meanwhile, Mallory observes when Alice is voting and reports this information to Eve over the Internet. To validate the most critical stage of the attack, we conduct a software-defined radio experiment using the official Brazilian e-voting interface and demonstrate through-wall vote reconstruction. Although conventional monitors are employed rather than official EVMs, our findings provide insights into information forensics and support security recommendations for government authorities responsible for e-voting systems.