Papers

In the year $1977,$ while developing the theory of modules arising in the context of Serre's problem on projective modules in the paper “On Stably Free Modules" (see \cite{AS}), A. A. Suslin constructed matrices inductively using unimodular rows. Our aim is to connect these matrices to the current and applicable field of coding theory. To this end, we construct Suslin-Rao codes, by using looking at certain unimodular all one vectors over the finite field $\mathbb{F}_2$. Comparative analysis with standard families such as Hamming, Simplex and BCH codes shows that the Suslin-Rao codes achieve better performance than Hamming and Simplex codes in terms of code rate and error correction capability, though BCH codes may outperform them for large code lengths. Bit error rate (BER) versus signal-to-noise ratio (SNR) simulations further support the practical applicability of these codes in noisy channels. The recursive nature of the construction allows efficient encoder design, making the proposed codes attractive for real-time communication systems and hardware implementation.

Physics-informed neural networks (PINNs) often converge to inaccurate solutions for conservation laws with shocks, because uniformly distributed collocation points undersample localized features and let the residual be dominated by regions that are already well resolved. We propose a feature-tracking PINN (FT-PINN) in which the solution network is defined on a fixed reference domain and composed with a diffeomorphic deformation map from a parameterized nonlinear manifold. The deformation and solution-network parameters are trained jointly by minimizing the pulled-back conservation-law residual. This lets collocation points concentrate along features of essentially arbitrary geometry, including curved, oblique, and merging shocks, without prior knowledge of their locations. The framework is agnostic to the choice of parameterization. Boundary preservation is enforced exactly through a tangential projection of the displacement, and folding is discouraged by a one-sided penalty on the Jacobian determinant. On four test problems (space-time viscous Burgers with merging shocks, a decelerating Burgers shock, the space-time Euler shock tube, and steady 2D Euler regular shock reflection), FT-PINN resolves shocks at their correct locations with a limited collocation budget. A vanilla PINN with the same architecture, budget, and training either misplaces the shocks or fails to form them.

On Blackwell, normalization and operand movement can limit attention kernels whose matrix multiplications are already deeply pipelined. We implement an FA4-style pipeline in Triton TLX with fixed-shift dense softmax and a saved inverse denominator for backward. The fixed shift removes recurrent accumulator corrections; the saved reciprocal moves row normalization from the quadratic backward loop into linear preprocessing. The guarded causal path uses a first-block anchor with selective recovery, and fully masked diagonal contractions are skipped. A packed BF16 exponential approximation and pipelined dQ publication reduce per-element work and on-chip movement. On B200 at 1,000 W, using prepared launches and the original FA4 timer, TLX improves geometric-mean throughput by 7.3 percent across the 24 cases in FA4's BF16 variable-batch grid through 32,768 tokens at head dimension 128. Dense forward and backward improve by 13.0 and 10.4 percent, respectively. Causal backward improves by 8.0 percent, while causal forward is 1.5 percent slower. The TritonBench comparison has geometric- mean gains of 13.4 percent in forward and 24.4 percent in backward

Compression trees have been historically a key component of several arithmetic units, most notably multipliers. The latter have been for the most part standalone units and in common situations synthesis tools can generate very close to optimal solutions. With large matrix multiply structures taking more of a central role in the compute industry, the need for a better understanding of these compression trees is apparent. Furthermore, the boundary of its usage needs to be redefined: dot products, polynomial fitting of non-linear operators, are all sums of products. And since products are sums of partial products, in the end, we are just adding many things together as bit heaps; i.e. the fundamental role of a compression tree. Therefore, we must see them as more than just a component of a multiplier. This paper presents a delay-aware compression-tree methodology based on a weighted bit heap. Each bit is described by its significance and relative arrival time, and the generator uses technology-independent normalized delay units to estimate Boolean logical pressure. By exploiting the commutativity of addition within each column, the method reorders bits across reduction stages and uses a Dadda-style maximum-bandwidth topology with flexible CSA3:2 operators. For Radix-4 Booth multipliers from 11 to 64 bits, the resulting trees show lower modeled delay and estimated logic volume than the evaluated Wallace-style maximum-compression trees. Fused four-way integer dot products further demonstrate how the same representation can evaluate the cost of microarchitectural constraints, such as preserving individual product redundant formats. These results show that weighted bit-heap generation provides a practical technology-independent basis for exploring compression trees beyond standalone multiplication.

Conventional FPGA routing optimizes timing, congestion, and routability but does not distinguish routes with similar nominal performance and substantially different susceptibility to configuration-induced delay degradation. This paper presents a vulnerability-weighted routing methodology for SRAM-based field-programmable gate arrays (FPGAs) that incorporates predicted routing-fault severity directly into the routing objective. A continuous vulnerability cost relates delay perturbations caused by electrically attachable dormant routing resources to the available downstream timing slack, while a complementary configuration-concentration term discourages excessive localization of vulnerable resources. To limit implementation disruption, only the highest-risk nets are selectively ripped up and rerouted while unaffected routes remain fixed. The method is implemented on a Zynq UltraScale+ XCZU7EV using a Vivado/RapidWright-based flow and evaluated across four routed benchmarks against commercial timing-driven routing, vulnerability-agnostic rerouting, and binary vulnerable-resource avoidance. Controlled configuration-equivalent perturbations provide hardware-level validation. The proposed method reduces aggregate configuration-induced timing vulnerability by 41.7% with approximately 1.0% nominal timing degradation and captures 85.8% of the vulnerability reduction obtained at the expanded routing budget by rerouting only the highest-risk 5% of eligible nets. The results demonstrate that continuous vulnerability information can improve configuration-upset resilience with limited impact on nominal routing quality.

A world model learns to forecast how a physical system evolves from recorded trajectories, yet the systems it imitates obey physical laws that are neither fully supplied nor reliably respected. The model may create energy, drift or diverge over long rollouts, and answer a changed law query using the law observed during training. We ask how much general physical structure must be hard coded into a world model, and how much system-specific physics can then be learned from data, for four properties to hold simultaneously: second law compatible dissipation, correct responses to interventions on physical parameters, stability out to one hundred times the training horizon, and robustness to disturbances. The imposed structure is general: dynamics are generated from the gradient of a learned energy through a fixed reversible operator, the energy is restricted to a confining class, a one way port can remove energy but never inject it, the drive channel is known, and the intervened parameter enters through a separable map. The model learns the energy functional, constitutive relations, dissipation rate, and couplings. Across an electromagnetic cavity, a particle in cell grid, and a shallow-water fluid, models with roughly nine thousand parameters recover constitutive functions with unit slope, separate conserving from dissipating worlds by four orders of magnitude using a single set of weights, and transfer changes in sign, magnitude, rate, and gravity to unseen values, where equal-capacity models without the same structure perform at chance or worse. A nonlinear constitutive law is recovered with its curvature preserved and predicts a held-out intervention $2$-$17\times$ better than a converged linear model.

The segmentation of anatomical structures in medical images and particularly in MRI scans, is essential for clinical diagnosis and monitoring disease progression. While Deep Learning (DL) architectures, such as U-Net and its extensions are very effective in medical image segmentation tasks, they often struggle with preserving fine-grained details and global contextual information. This is especially challenging for MRI data segmentation, where anatomical structures are characterized by irregular boundaries and variations in shape, contrast, and scale. To address this challenge, we propose a novel DL architecture for MRI segmentation across different anatomical structures. Specifically, the architecture introduces a module, named Multi-Resolution Feature Fusion (MRFF), that can be easily integrated into any U-Net-like architecture. The MRFF is integrated in all levels of an encode-decoder structure, along with attention mechanisms and skip connections to extract features at multiple resolutions, enabling the model to capture both fine-grained details and global contextual information. We evaluate the MRFFU-Net on two publicly available benchmark MRI datasets of different anatomical targets; one for Cerebrospinal Fluid (CSF) segmentation in spinal MR scans, and one for left atrium cardiac segmentation, from the Medical Segmentation Decathlon (MSD) challenge. Experimental results indicate that MRFFU-Net outperforms state-of-the-art models across multiple evaluation metrics, demonstrating its effectiveness in MRI segmentation.

Federated multimodal graph foundation models (GFMs) aim to adapt pretrained multimodal models to decentralized graph data, where each client owns a private multimodal graph and cannot share raw information. These models typically combine a multimodal Encoder that extracts semantic evidence from heterogeneous modalities and a graph neural network (GNN) that performs relational reasoning over graph structures. However, existing federated GFM adaptation methods mainly update graph-side modules while keeping the multimodal Encoder frozen, limiting adaptation to how information is propagated while fixing what information is extracted. Through empirical studies, we reveal that Encoder and GNN adaptations are not independent: Encoder adaptation is affected by graph relations, while cross-client module swapping reveals substantial pairing sensitivity between separately parameterized Encoder and GNN updates. Motivated by this observation, we propose FedCORE, a federated adaptation framework that represents Encoder and GNN updates through a shared low-dimensional latent state. FedCORE jointly optimizes this core from multimodal and structural signals and performs federated evolution directly in the shared state space, preserving compatibility between perception and reasoning adaptations. Extensive experiments demonstrate that FedCORE reduces the Encoder–GNN pairing gap from $30.6$ to $5.9$, corresponding to an $80.7\%$ reduction over independent joint adaptation.

Native full-duplex speech models can respond before a user finishes speaking, making the behavior of the model depend on both the final utterance and when intent-defining information arrives. Existing benchmarks primarily evaluate turn-taking mechanics, whereas safety evaluations typically assume that the complete request is observed prior to response generation. We introduce LateIntent-Bench, a matched-pair benchmark for delayed intent revelation. A shared ambiguous prefix precedes either a benign or a harmful continuation, using a controlled pause to delay when the branches become distinguishable. We define the Premature Response Rate (PRR) to measure whether response onset precedes the revelation of intent. Joint evaluation of harmful and benign engagement distinguishes changes in safety selectivity from general losses in responsiveness. Across 3,136 sessions, four native full-duplex models exhibit distinct response-timing patterns under delayed intent. Three models show increased harmful engagement while maintaining benign responsiveness, whereas one loses engagement with both branches. Inserting a 1.5s silence after intent revelation keeps PRR near the no-pause baseline and substantially reduces changes in harmful engagement. These results demonstrate that evaluating fully specified requests alone fails to capture emerging timing patterns, highlighting the necessity of assessing delayed intent revelation in full-duplex models. The code will be publicly released soon.

Multimodal graph learning faces a fundamental challenge: new classes may emerge after deployment, while models are trained with a fixed label space. Existing approaches typically detect unknown nodes and use LLMs to generate candidate class descriptions, but they do not determine whether existing classes are insufficient to cover these nodes or whether a generated class is reliable enough to expand the class space. Our empirical study reveals three challenges: multimodal information beyond individual modalities is required for unknown-node identification, LLM-generated class descriptions may not fully capture multimodal class characteristics, and directly adding candidate classes can introduce redundant categories. Based on these observations, we propose MOVE, a multimodal open-world class verification and expansion framework. MOVE identifies nodes that cannot be assigned to existing classes by jointly considering visual tokens, textual attributes, and graph context, leverages a multimodal LLM to generate candidate classes, and selectively expands the class space only when candidates are consistently supported by multimodal evidence without introducing unnecessary categories. Experiments demonstrate that MOVE achieves an average improvement of 11.87% across unknown recognition, open-domain annotation, and downstream graph learning tasks.

Compact edge system-on-chip (SoC) platforms increasingly run sustained LLM inference under thermal constraints, while their CPU, GPU, and RAM share a cooling path. Prefill and decode therefore consume shared, time-varying thermal headroom, yet vendor governors react only near hardware throttling thresholds without knowledge of request state or upcoming work. A control decision that improves current performance can thus consume headroom too quickly and degrade subsequent service. In this paper, we present ThermE, a runtime system that predicts and jointly manages shared thermal headroom for sustained LLM inference on edge SoCs. Its Fast LLM-to-Heat Compiler maps the model, requests, runtime state, and candidate actions to domain heats without executing LLMs. A partial differential equation (PDE)-constrained Headroom Predictor uses ThermPINN for offline thermal identification and a Reduced Headroom Predictor (RHP) for low-overhead online uncertainty-calibrated headroom forecasts. An Uncertainty-Aware Action Scheduler then selects actions that balance serving quality and future headroom. We implement ThermE atop vLLM and evaluate it across four LLM inference workloads. The results show that ThermE reduces TTFT and TPOT by 40.55% and 12.17%, respectively, relative to vLLM. It achieves a 5.70% SLO violation rate, compared with 12.30% for the strongest baseline, while its predictor obtains a 1.94 $^\circ$C MAE with 11.50 ms overhead.

Large Language Bayes (LLB) answers an informal modelling question by sampling candidate probabilistic programs from a language model, running approximate inference on each, and averaging them with weights proportional to an exponentiated evidence bound. We show that this weighting depends on how a model is written. The log marginal likelihood is invariant to reparameterisation; the evidence bound is not. On eight schools the centered and non-centered programs are the same measure to $5.7\times10^{-14}$, yet their weights differ by $6.1\times$; importance weighting reduces this only to $2.2\times$, and reproducing the inference LLB actually runs, a full-covariance Gaussian matched to the posterior moments, still leaves $1.9\times$ on eight schools and $8.9\times$ in $64$ dimensions. Across likelihood families, dimensions and funnel severities the discrepancy reaches $31.9\times$ and reverses sign, so no single writing is uniformly preferable. It inverts Bayes factors against eight natural competitors, and the induced error in the model posterior, and in any downstream target, is controlled by the spread $\Delta$ of the bound shortfalls through a known sharp Hilbert-distance bound. Across $360$ programs from six language models the parameterisation written ranges from $0\%$ to $100\%$ centered and is stable within a model. Detecting equivalent programs statistically can falsely merge genuinely different models at practical sample budgets; verifying reparameterisations we generate ourselves cannot, and closes the window.

Energy imbalance remains a key challenge in Wireless Sensor Networks (WSNs), as nodes near the base station deplete their energy faster due to heavy forwarding loads. While mobile agents (MAs) have been employed for either data collection or sensor charging, existing approaches lack adaptability and fail to integrate both functions under realistic hardware constraints. This paper introduces a unified mobile agent framework that performs both data collection and wireless charging sequentially under single-antenna limitations. The agent's decision-making is formulated as a two-layer Hierarchical Reinforcement Learning (HRL) problem, where the upper layer optimizes movement planning and the lower layer determines the appropriate service based on real-time network states. This hierarchical structure enables the agent to learn adaptive task scheduling policies without predefined rules. Extensive simulations demonstrate that the proposed method achieves up to 15% longer network lifetime and more balanced energy distribution compared with state-of-the-art mobile agent and deep RL approaches.

Selective intent routing allows an assistant to act on reliable predictions while deferring uncertain requests. Standard confidence scores primarily reflect the base model's representation, leaving an opportunity to incorporate complementary evidence without changing its decisions. We introduce a signed lexical gate that combines a sentence classifier's logit margin with a sparse lexical model's support for the classifier's predicted intent. By assigning positive evidence to lexical agreement and negative evidence to a lexically favored competing intent, the gate retains more information than either unsigned lexical confidence or a hard agreement rule. An independent binomial calibration stage selects an operating threshold for a specified risk target. Across ten runs on BANKING77, CLINC150, and HWU64, the proposed score reduces area under the risk-coverage curve by 15.8%, 15.1%, and 11.8% relative to a learned semantic-only gate. At a nominal 5% error target, it increases accepted coverage by 1.83 and 5.14 percentage points on BANKING77 and HWU64, while CLINC150 is already near full coverage. At a stricter 2% target, the simultaneous binomial procedure yields a nonempty policy in all 30 dataset-run combinations at the available calibration budgets. Matched controls show that the proposed feature improves average error ranking over the tested unsigned lexical-confidence feature, with dataset-dependent gains over binary agreement. The resulting two-feature gate provides a compact, interpretable confidence enhancement for risk-calibrated intent routing while preserving the base classifier's predictions.

Smart manufacturing needs to move sensor data off the plant floor, react to it, and feed decisions back to actuators within bounded time. Programmable logic controllers (PLCs) handle fast, deterministic, safety-critical actuation, but they are not designed for the higher-level functions required by Industry 4.0, such as predictive maintenance, machine learning inference, and cross-facility analytics. These functions need a scalable, durable, and observable communication substrate. We present the communication architecture of a production system that provides this substrate and closes the loop back to the plant in near real time. The design is built from industry-standard components: Apache Kafka as the streaming backbone, OPC-UA for PLC connectivity, a relational time-series database for persistence, and JSON for serialization. The novelty is architectural. We show how these standards are integrated for closed-loop industrial control through four design choices: a single event stream per production line serves control, monitoring, machine learning, and durable recording, allowing one producer to serve many independent consumers; a protocol bridge converts polled OPC-UA traffic into publish/subscribe streams, aligns per-signal timestamps to a common time base to remove cross-signal jitter, and provides a symmetric actuation path; a transport technique carries sub-second process dynamics at a coarser publication cadence by packing timestamped samples into fixed-order arrays; and an edge-to-cloud replication scheme keeps the edge authoritative, so local control continues during wide-area network outages while cloud analytics operate on replicated data. We describe the loop latency budget, report measured broker transport latency, and discuss operational experience. The system provides soft, near-real-time behavior rather than hard real-time guarantees.

In standard transformer attention, a source token sends the same value vector to every receiver. The query determines how much to attend but not what to extract. This work introduces attention manifolds: learned 2D B-spline surfaces $S_d(q_d, k_d)$ that modulate each value dimension based on the query-key interaction. Each surface is a tensor-product cubic B-spline initialized to zero, preserving pretrained behavior. Applied to LLaMA 3.2-1B-Instruct and 3B-Instruct, attention manifolds reduce WikiText-2 validation perplexity by 2–2.5 points with 0.3% parameter overhead. Across 112 diverse prompts, surfaces change greedy-decoded output for 69% (1B) to 83% (3B) of cases, with the strongest effects on ambiguous and polysemous inputs (94–100% change rate). The surfaces improve output quality: correcting factual errors (“the CAP theorem has three main components” $\to$ “it is impossible to guarantee all three”), increasing precision (“impossible to know certain properties” $\to$ “impossible to know both position and momentum”), and adding specificity (a generic quote $\to$ an attributed Saint Augustine citation, consistently at both scales). The learned surfaces are also mechanically editable: inverting a layer's coefficients changes greedy output for 9/10 prompts (KL~0.010), providing a geometric mechanism for model steering. Setting surface coefficients to $-1$ creates “attention walls” that block value flow through specific dimensions. In a preliminary experiment, a layer-wide wall redirects an explosive-device prompt from specific instructions to general educational content, suggesting a path toward safety-oriented manifold shaping.

External verification can correct individual outputs while leaving a self-reinforcing population in the basin of a wrong consensus. We study how the timing and addressing of a fixed verification budget affect recovery in an asynchronous binary register. For a general nonlinear response, we derive the minimum fuel required to cross a basin boundary under a peak verification constraint. For a finite population, an exact birth–death calculation gives the probability of subsequent wrong consensus after a pulse. Our main asymptotic result identifies the critical budget window: a leading term $N\log(x_0/b)$ and a correction of order $\sqrt N$, with separate variance contributions from repeated verification targets and autonomous amplification after verification stops. The distinction is substantial: with 16 majority-updated slots and 14 initially wrong, 9 random checks cross the mean-field budget threshold, whereas 23 are required for 95% eventual recovery in the exact model. A prospectively specified experiment records 13,392 language-model responses, including calibration and 108 held-out trajectories. Calibration produces different fitted response regimes, but all four adjusted schedule-comparison intervals include zero. A distributional audit also finds that modest mean-prediction error can conceal a large underestimate of terminal consensus occupancy. The results support risk-calibrated reset scheduling under a specified update contract, while explicitly separating it from distinct-target checking and unrestricted evidence broadcast.

Quantum compiler assurance requires a semantic relation that matches the intended use and observations that can expose violations at the delivered interface. This critical integrative survey compares verified transformations, equivalence checking, differential and metamorphic testing, property-based testing, and evidence for assurance across revisions. A source catalogue and focused extraction matrix distinguish formal guarantees, reported empirical findings, analytical deductions, and proposed practice. A recorded coverage update and source-level selection decisions make the review auditable within its declared scope. Four documented failure cases connect conditional applicability, parameter association, termination, and phase conventions to method selection. A worked example involving layout metadata, parameter bindings, and ancillary qubits demonstrates why validating a circuit under a reconstructed interpretation can leave the delivered interface unchecked. An illustrative revision scenario then separates fault detection from change attribution. The resulting guidance specifies applicability, complementary observations, and treatment of inconclusive outcomes. Published bug counts, mutation results, and processing benchmarks support different claims and do not establish a common effectiveness ranking. The proposed regression architecture remains unevaluated as a complete system; its practical value requires controlled comparisons on independently adjudicated compiler-change events.

Smoothed particle hydrodynamics (SPH) is well suited to large-deformation fluid problems, and the growing use of automatic differentiation in engineering applications has motivated interest in differentiable SPH solvers. In this study, a composable differentiable SPH framework, CraftSPH, has been developed. In CraftSPH, major computational operations are implemented as independent modules that users can combine to construct solvers for different purposes. This design supports high-accuracy discretization and both explicit and implicit computation within a common framework, while allowing individual components to be maintained and extended. Selected numerical operations also support automatic differentiation (AD) for physical-parameter estimation and potential coupling with deep learning models. These capabilities were demonstrated through forward and inverse analyses. Forward analyses using an implicit SPH scheme with high-accuracy discretization showed good agreement with analytical and reference solutions for Poiseuille flow and a rising bubble, while capturing the key experimental trends in two- and three-dimensional dam-break problems. In inverse analyses, explicit and implicit SPH schemes were used to estimate kinematic viscosity in Taylor-Green vortex flow and Reynolds number in lid-driven cavity flow. The results also showed that the choice of operations included in the computational graph affects the computed gradients. Together, these findings demonstrate that CraftSPH enables users to assemble problem-specific solvers for forward and inverse analyses within a common framework.

The representation number of a graph is the least positive integer $k$ for which its vertices can be arranged in a word, each occurring $k$ times, so that two distinct letters alternate precisely when the corresponding vertices are adjacent. We prove that every bipartite graph on $N\ge9$ vertices has representation number at most $\lceil N/4\rceil$. Together with the known representation number of crown graphs, this settles the conjecture that crowns maximise the representation number among bipartite graphs of the same order. The proof develops a construction of Mozhui and Krishna by reducing the choice of a representing word to an ordering problem for neighbourhoods. We characterise the obstructions to this ordering and use probability estimates to exclude them for all sufficiently large balanced bipartitions. Two finite assertions complete the argument, each established by a checked Boolean unsatisfiability certificate. A refinement of the ordering argument treats the remaining odd part sizes directly. The main theorem and the crown-extremality corollary, including the finite certificate arguments, have also been formalised and verified in Lean 4.

Mutation testing evaluates test-suite adequacy by injecting synthetic faults into program code. However, traditional rule-based tools often generate large numbers of trivial, redundant, or equivalent mutants that limit their practical use for identifying gaps in a test suite. While recent large language model (LLM)-based approaches generate more realistic faults, most remain test-blind: The model sees only the source code and cannot reason about what existing tests already cover. We propose test-aware mutant generation, in which an LLM receives the problem statement, canonical solution and base tests in a single prompt, and must generate a nontrivial mutant that passes the base unit tests. We evaluate this approach across a set of five LLMs – Gemini 3.1 Pro, Gemini 3 Flash, GPT 5.1 Codex Mini, GPT 4.1 Mini, Qwen3-32B – on the HumanEval and MBPP benchmarks. The extended EvalPlus test suites serve as an automated oracle to verify whether surviving mutants represent genuine bugs. Test-aware prompting yields verified fault rates of 87.7% (HumanEval) and 79.1% (MBPP), meaning these mutants pass all base tests but are caught by the oracle. This vastly outperforms the matched test-blind prompting (which yields only 12.2% and 23.0%, respectively) and the traditional rule-based tool mutmut (4.4% and 5.7%). While fault subtlety (the fraction of extended tests a mutant fails) remains comparable across all three methods, test-awareness minimizes the computational cost per verified fault, compared to test-blind prompting. Exposing an LLM to existing unit tests shifts mutant generation from untargeted bug injection toward effective discovery of weaknesses in an existing test suite. Our work establishes a concrete foundation for future research to scale test-aware mutant generation to production-level environments.

We establish matching polynomial query bounds for low-rank approximation from exact matrix–vector products. Given an unknown matrix $A\in\mathbb{R}^{m\times n}$, at each step a randomized algorithm chooses either $v\in\mathbb{R}^n$ and receives $Av$, or $u\in\mathbb{R}^m$ and receives $A^\top u$. The choice may depend measurably on all previous queries and replies and on the algorithm's private randomness; each vector product costs one query. The output is a rank-$k$ right projector with Schatten-$p$ residual at most $1+\varepsilon$ times optimal. Write $N=\min\{m,n\}$ and let $Q_p^*$ denote the worst-case query budget for success probability $2/3$ on every input. For every $1\le k<N$ and sufficiently small $\varepsilon$, our lower bounds, combined with existing Krylov upper bounds, give $Q_p^*=\widetilde{\Theta}\!\left(\min\{N,k\min\{p^{1/6}\varepsilon^{-1/3},\varepsilon^{-1/2}\}\}\right)$ $(2\le p<\infty)$, $Q_\infty^*=\widetilde{\Theta}\!\left(\min\{N,k\varepsilon^{-1/2}\}\right)$. These bounds have universal constants and allow $p$ to vary with the problem parameters, identifying the transition at $p\varepsilon\asymp1$. A complementary result for each fixed $1\le p<2$ gives $\widetilde{\Theta}_p(\min\{N,k\varepsilon^{-1/3}\})$, with constants and an accuracy threshold that may depend on $p$. Together, the results recover this fixed-norm rate for every fixed finite $p$, supplying the multiplicative rank dependence missing from previous lower bounds. Tildes suppress logarithmic factors. The proof extends adaptive Wishart deferred decisions to a rectangular factor with a $k$-dimensional nullspace. Posterior overlap gives a short fixed-norm argument, while persistence of small compression eigenvalues controls growing $p$ and the spectral endpoint. Exact range recovery handles target costs of order $k$; the Wishart family covers the remaining regimes.

Handclaps provide an equipment-free excitation for room acoustics, but their unknown and variable source waveform makes room impulse response (RIR) estimation challenging. In this work, we investigate whether RIRs can be estimated directly from handclaps. To this end, we introduce an anechoic handclap dataset containing 2,540 claps from 17 participants, designed to capture variability across natural claps and different hand configurations. We first establish the performance attainable when the excitation clap is known using regularized deconvolution, and show that approximating the unknown excitation by windowing the direct sound from the reverberant recording is insufficient. To estimate the RIR without a known excitation, we propose using the anechoic handclap recordings to train a deep neural network with a supervised regression objective. Evaluated on a controlled synthetic benchmark, the proposed neural regressor significantly outperforms windowing-based baselines across all instrumental metrics. Furthermore, we test the proposed method on handclap recordings measured in real acoustic spaces, showing that the inferred RIR spectra are consistent across different handclap measurements taken in the same room location. These results showcase the feasibility of directly estimating RIRs from natural handclaps without requiring knowledge of the excitation signal.

With the constant advancements in AI, one possibility is to model agents after humans and, in turn, use these agents to carry out synthetic interactions. Such models could be used to predict interactions between their real counterparts, or potentially interactions at larger scales. In this paper, we test a more controlled version of this question through chess. We use 8 elite chess players, seal their direct pairwise games, learn each player independently using different methods, and then compose the resulting models on the withheld dyads. To evaluate the generated interactions, we use two measurements: opening-family total variation distance and win-draw-loss (WDL) total variation distance. M1 primarily improves WDL fidelity while producing smaller opening-family improvements, whereas M2 produces much larger opening-family improvements while having little effect on WDL-TV. For opening-family behaviour under M2, the correct assignment of the eight learned player identities also gives the closest match among all $8! = 40{,}320$ possible assignments. These results show that at least some properties of previously unseen interactions can be recovered from independently learned individuals. The partial recovery observed here may reflect limitations of the current individual modelling methods rather than a fundamental limit on compositional interaction recovery. An additional post-hoc method that combines the two mechanisms improves both measurements, suggesting that recovery across these behavioural properties is not necessarily mutually exclusive.

Quantum SDKs such as Qiskit are revised continually, and a single transpiler-pass change can introduce a software regression, so continuous integration (CI) must select and prioritize tests from a large, cost-heterogeneous suite under a fixed budget. We present a leakage-safe, cost-aware regression-test-selection methodology for the Qiskit quantum transpiler, with a pre-registered, budget binding evaluation that avoids data leakage. The evaluation uses a cost-heterogeneous corpus (116 units, per-unit cost spread 9,945X, T_full = 69.17 s) whose budgets were fixed from measured cost before any test-oracle label was read. A transparent risk_score selector does not beat simple test case-prioritization baselines: mean detection-vs-budget AUC is 0.721 [95% CI 0.44, 0.94] versus 0.874 [0.65, 1.00] for diversity-only (Cliff's {\delta} = -0.64, large), with cost/history/change-stage baselines at 0.840 and random at 0.821. A component ablation shows the composite underperforms its own best signal: diversity and novelty, not severity or cost, are the effective signal. A second, independently pre-registered evaluation (19 mutation-testing events: nine original plus ten new, verified operators) tests the decomposed, diversity-first selector this mechanism implies: it closes the gap to the strongest baseline to a negligible effect size (0.880 vs 0.880, {\delta} = -0.08) while decisively beating the original composite (0.880 vs 0.768, {\delta} = +0.57). Two verified forward-regression events from real Qiskit CI history corroborate it, reported per event, not pooled, under a pre-declared claim-scope rule. We report the negative result as an honest, pre-registered finding with its mechanism. All code, data, and artifacts from this empirical software engineering study are released for reproducibility.

Running a language model on edge hardware provides private and low-latency reasoning without a network connection, and yet the small models that fit on such devices are unreliable on the tasks computers are expected to handle well, such as arithmetic, algebra, and formal logic problems. We argue that much of this unreliability is avoidable. Many queries appearing to demand reasoning are in fact structurally deterministic and permit fast and exact symbolic solutions. Therefore, forcing a probabilistic model to approximate them sacrifices accuracy and energy for little benefit. We present a neurosymbolic router that classifies each incoming query and dispatches it to the cheapest correct solver, sending structured tasks to deterministic engines and reserving the small language model (SLM) for open-ended word problems. Instead of hand-coding the routing logic, we learn a deterministic finite automaton (DFA) with the L* grammatical inference algorithm, using the SLM as a membership oracle and labeled data as an equivalence oracle. On a Raspberry Pi 4B (8 GB RAM, no GPU), evaluated on 100 untested prompts from DeepMind Mathematics, GSM8K, and RuleTaker, learned routing attains 100% routing accuracy and 98.3% overall accuracy with a 512-token reasoning budget (93.3% on word problems), compared with 72.0% for the strongest agent baseline, Program-of-Thought, and 58.7% for a tool-calling agent given the same solvers. Since formatted queries never reach the model, the router answers them in 1-11 ms and, in its 30-token configuration, runs 8.8x faster and 2.8x more energy-efficient than Program-of-Thought.

Optimal Transport (OT) provides a principled framework for comparing and transforming probability distributions while preserving geometric structure. Recently, OT has gained significant attention in machine learning due to its ability to measure discrepancies between distributions, even when their supports do not overlap, making it effective for tasks such as generative modeling, domain adaptation, and transfer learning. Despite its success in fields such as computer vision and natural language processing, OT remains relatively underexplored in speech research. Speech signals present unique challenges, including temporal dynamics, speaker variability, noise, reverberation, and heterogeneous multimodal representations involving audio, text, and visual information. These factors often lead to distribution mismatches, where OT offers a natural framework for alignment and interpretation. This work aims to promote broader adoption of OT in speech processing by: (1) reviewing OT foundations through intuitive physical interpretations and highlighting connections to modern generative models; (2) presenting computational algorithms suitable for deep learning frameworks; and (3) demonstrating OT applications in cross-domain and cross-modal speech tasks, including speech enhancement, automatic speech recognition, language and speaker recognition, and audio spoof detection. We highlight OT's strong potential for addressing distributional variations in real-world speech applications.

Maximum likelihood estimation of Markov deterioration hazard models for infrastructure asset management is sensitive to the numerical conditioning of explanatory covariates, yet production pipelines often adopt a single scaling convention without systematic justification. We study four covariate scaling transformations—baseline max scaling, min-max scaling, z-score scaling, and Box-Cox transformation with a training-derived positivity shift—applied to an Exponential Hazard Markov (EHM) model estimated via L-BFGS-B on bridge inspection transition data.

Audio-only pedestrian detection is attractive for urban sensing but limited by weak acoustic cues. An appealing strategy is cross-modal knowledge distillation, in which a video teacher supervises the audio student during training so that the deployed model runs on audio alone. Under this task's severe class imbalance and wide video-audio modality gap, however, what such distillation contributes is unclear. We introduce Trust-Filtered Distillation (TFD), which selectively suppresses teacher supervision on pedestrian samples, and interpret its logit formulation as conditional label smoothing under a shared temperature. Across ten distillation configurations under five-fold cross-session validation on ASPED, most methods yield modest gains in macro accuracy accompanied by small changes in PR-AUC. The main effect is higher no-pedestrian accuracy at the cost of lower pedestrian recall. Adding TFD to logit distillation strengthens this trade-off without improving mean PR-AUC. These findings clarify the benefits and limitations of selective cross-modal supervision by distinguishing operating-point shifts from discrimination gains in imbalanced acoustic detection.

Open-weight models are often released, fine-tuned, aligned, merged, and re-released, making provenance audits ask not only whether checkpoints are related, but also which checkpoint came first. Many existing model-provenance methods are designed for a base-known audit setting: given a victim or source model, they test whether a suspect model is related to it. Although these audits are framed as source-to-suspect tests, their underlying evidence is often symmetric, relying on representation similarity, weight similarity, behavioral fingerprints, or correlation statistics. Symmetric pairwise comparisons can detect relatedness, but they cannot by themselves orient relationship between checkpoints A and B. We therefore introduce a local geometric comparison: instead of comparing two checkpoints directly, we add a third same-family checkpoint as a witness and compare the geometry around each candidate endpoint. Direction is inferred by asking which candidate behaves more like a branching parent. Motivated by this idea, and by the empirically observed asymmetry between parent-anchored and child-anchored witness-overlap distributions, we propose Witness Overlap, a prompt-free, training-free white-box test for directional provenance. On 176 LLM checkpoints from 16 families, our one-witness test orients 95.3% of parent-child decisions using Frobenius cosine. We further evaluate root identification, sibling discrimination, generalizations to VLM and diffusion families, and chain-structured ordering. The signal is robust to weight noise and sparse pruning, with a proposed SVD weight reduction variant showing greater robustness than Frobenius cosine.