Papers

The key-value (KV) cache is the dominant memory bottleneck of long-context large language model (LLM) inference, growing linearly with context length. We show that uniform KV quantization on a fractional-bit grid does not degrade gracefully: under a prespecified multi-seed statistical protocol, Llama-3.1-8B-Instruct with an affine quantizer is statistically indistinguishable from FP16 KV down to 2.322 code bits/value and collapses at 2.0 bits - a quality cliff in (2.0, 2.322] that reappears in generation-time quantization and multi-turn dialogue and transfers to Mistral-7B. The cliff reframes importance-aware mixed precision: above it, eight model-internal importance indicators are statistically interchangeable, so the benefit of mixing is grid interpolation, reaching average precisions uniform quantization cannot realize. SemKV preserves every token, ranks tokens by a model-internal score, and assigns two adjacent above-cliff precisions, achieving a measured 6.0x storage reduction with no statistically detectable quality difference from full KV (n=900, three seeds), and outperforming FP16 token pruning granted a 1.5x larger memory budget. Replacing the affine base with a distortion-optimized quantizer (TurboQuant-MSE) lowers the cliff in every protocol tested, raising the no-detectable-loss operating point to 7.9x. The recipe: measure the cliff for the target deployment setting, then interpolate above it.

Coded computing has emerged as a powerful paradigm for mitigating the impact of straggling workers in distributed computing systems. However, existing coded-computing schemes are predominantly designed for the exact recovery of highly structured computations, such as polynomial evaluation and matrix multiplication, and typically rely on strict recovery thresholds. These assumptions significantly limit their applicability to modern machine-learning workloads, particularly deep neural networks (DNNs), whose computations generally lack rigid algebraic structure and, in many applications, require only accurate approximations rather than exact recovery. To address this gap, we revisit coded computing from a learning-theoretic perspective and introduce General Coded Computing (GCC). Rather than adopting existing algebraic tools, GCC formulates coded computing through a natural end-to-end mean-squared error loss that directly measures the discrepancy between the desired computations and their recovered estimates. By deriving suitable upper bounds and restricting the encoder and decoder to a reproducing kernel Hilbert space (RKHS) with mild smoothness constraints, we show that both the encoder and decoder admit specific representations as linear combinations of RKHS kernel functions. This representation allows the corresponding coefficients to be computed efficiently. Moreover, this framework enables us to establish theoretical performance guarantees for GCC under two complementary straggler regimes. In the worst-case setting with $N$ worker nodes, and at most $S$ stragglers, we show that the end-to-end loss decays at least at rate $O(S^3N^{-3})$ for standard configurations. We then study a probabilistic setting in which each worker independently straggles with probability $p$. We prove that the expected loss can still converge at rate $O(\log_{1/p}^3(N)N^{-3})$.

Large-scale, publicly available datasets have driven advances in deep learning, but privacy and legal restrictions often limit data sharing in medical imaging. Synthetic data generation offers a privacy-friendly alternative to enable the training of high-performance models on health data. While most state-of-the-art generative models produce high-quality images, they remain computationally expensive, which limits their applicability on resource-constrained hardware. We propose StyleGANCA, the first lightweight general-purpose NCA-based generative adversarial network. The architecture integrates a StyleGAN-inspired mapping network and adaptive style modulation into a multi-scale NCA synthesis process, enabling latent-controlled image generation through iterative local interactions. We evaluate StyleGANCA on BloodMNIST and PathMNIST against adversarial, variational, diffusion, and NCA-based baselines. Experimental results demonstrate that StyleGANCA achieves competitive image quality with substantially fewer parameters than baseline architectures, achieving the best FID and KID scores on PathMNIST with only 617k parameters. Furthermore, downstream experiments show that the generated images preserve class-specific information and effectively support the training of multi-class classifiers. Our code is publicly available at: https://github.com/MECLabTUDA/StyleGANCA

Task handover requires communicating enough current state for a successor to resume work, yet the relevant information is often divided between system records and human observations. System records can be precise and timestamped but only partially observe the task, while human reports capture intent and task knowledge that no log contains but are vulnerable to omission and memory error. We present a provenance-aware pipeline that converts task telemetry and human-authored reports into a shared typed task-state representation, aligns and reconciles their facts, detects conflicts, and generates structured handover reports. We evaluate the approach on 13 paired task states collected in a controlled spatial multitask environment, using task-grounded metrics that estimate the state-reconstruction cost a report would spare a hypothetical recipient and the misinformation burden it would impose. Reconciling both sources preserved greater estimated task-state utility than either the user report or telemetry alone. Relative to a direct end-to-end LLM given the same inputs, structured reconciliation maintained comparable estimated utility while incurring substantially less misinformation, and task-aware rendering retained utility more efficiently (per token) than exhaustive rendering. An exploratory content analysis further shows that human reports contain substantial strategic knowledge that lies outside state-focused metrics. These results support provenance-aware state reconciliation as a design pattern for safer AI-assisted handover.

Generative recommenders increasingly emit semantic IDs (SIDs): each item is a short sequence of hierarchical discrete codes from a residual quantizer, decoded autoregressively. Before spending scarce A/B-test, a team may decide offline which decoder or reranking variants are worth testing - a job for off-policy evaluation (OPE). We ask a simple question: can the model's own SID tree serve as the action abstraction for that OPE? Our answer has three parts. (i) Under the near-argmax logging real recommenders use, per-item OPE is hopeless - as item-level effective sample size is usually small on production logs - but marginalizing items to code-prefix clusters restores estimable support and cuts error. (ii) This gain is thanks to coarsening, not to the hierarchy specifically; but the SID tree is what makes coarsening feasible in a generative system - each cluster's mass is exactly and cheaply returned by the decoder, whereas flat clustering requires enumerating item/leaf masses that a code-only decoder does not directly expose. (iii) Resolution depth is the operative knob - coarser under scarce support - and a conditional bias bound links the coarsening bias to the quantizer's worst-case reconstruction residual and the target-logging divergence.

Entanglement of purification is a fundamental measure of total correlations whose additivity remains unresolved. We study its additivity for classical states on two qubits at different Rényi orders. For every $\alpha\in[0,1)$, we prove nonadditivity within this family, witnessed by two copies of a single state. We first solve the one-copy optimization exactly for the entire family at every Rényi order. We then restrict the two-copy optimization to a natural finite set of purifications and exhibit one whose entropy is strictly below the product value. In contrast, for $\alpha\in[2,\infty]$ we prove additivity under tensor products within this family. The interval $\alpha\in[1,2)$, including the von Neumann case $\alpha=1$, remains open, and we conjecture additivity there throughout the same family.

Industrial process networks do not maintain a single effective topology while operating: streams are throttled or bypassed, and units move between idle, transition, and active regimes. Models of such systems are typically trained on measured state trajectories while the operating mechanisms that generated them remain latent, and an unconstrained graph network can fit such a trajectory without assigning stable physical meaning to the recovered routing. We address both problems with the Conservative Hybrid Graph Network (CHGN), which learns routing, regime assignment, and removal rates as data-driven surrogates and inserts them into a fixed transport equation, so that the mass balance holds by construction for any predicted routing. CHGN trained on networks of 10-20 nodes transfers zero-shot to unseen graphs of 25-40 nodes without retraining, reaching an RMSE of 2.1e-3 against 6e-2 to 9e-2 for GNN baselines under the same protocol, with a gate MAE of 7.9e-3 and regime accuracy of 94.3% (1.2e-2 and 96.4% respectively on the fixed training topology). On a fluid-mixing pilot plant, CHGN improves on a persistence baseline for held-out physical faults but does not predict manual interventions, for which the governing valve actions are unobserved. The model therefore transfers across process topologies without retraining and exposes the latent mechanisms governing plant behaviour to inspection.

We introduce ReconSplat, a feed-forward model for 3D scene reconstruction that aims to address the longstanding trade-off between plausible view generation for unobserved regions and geometric consistency, providing both geometrically aligned novel views and sharp depth estimates. Our approach builds on 3D Gaussian splatting (3DGS) as an intermediate differentiable scene representation and integrates it with a multi-view latent diffusion model (MV-LDM) trained to act simultaneously as a refiner and an inpainter for appearance and scene geometry. We enforce geometric consistency by guiding the diffusion process with variational 3D latent features for appearance and geometry, encoded by the feed-forward 3DGS representation and rasterized to 2D latent space. ReconSplat produces both photorealistic novel views and accurate depth maps on real-world benchmarks, RealEstate10K and DL3DV-10K, outperforming existing methods in challenging extrapolation setups. Notably, ReconSplat allows the extrapolation of unseen and challenging viewpoints jointly with coherent and precise scene geometry.

Capacity expansion modeling plays a critical role in optimizing the deployment of new generation, storage, and transmission, typically at national and regional levels. To support long-term planning, these models consider a large set of energy technologies and policies, along with decades of weather and demand data. Realistic capacity expansion models thus become high-dimensional optimization problems, with hundreds of millions of variables and constraints, which are challenging to solve. A common strategy to address this complexity is to omit non-linear, non-convex AC optimal power flow (ACOPF) constraints and instead use linearized power balance equations or transport formulations. While these simplifications improve tractability, they limit our understanding of how power flow and the physical properties of power networks impact investment decisions across generation, storage, and transmission infrastructure. This paper addresses this gap by extending the GenX capacity expansion model to incorporate fixed point theorem-based network constraints. These embed ACOPF-based considerations while maintaining the tractability of the planning model, nearly preserving the dimensionality of the transport formulation and incurring only modest runtime increases. This approach is much cheaper than embedding ACOPF directly, making it appropriate for large-scale capacity planning problems. We compare our approach to the original transport-based GenX model as well as a non-linear, non-convex version that incorporates the full ACOPF constraints, for a case study of the ISO New England grid.

Pixel-level cross-view geo-registration aims to align a query image (e.g., drone) to a geo-referenced satellite map so that every query pixel can be mapped to real-world GPS coordinates. Despite strong progress in cross-view geo-localization, existing benchmarks largely provide only GPS labels, limiting evaluation to a single coordinate per image and leaving dense geodetic alignment underexplored. We introduce SkyReg, a dataset and standardized benchmark for pixel-level drone-to-satellite geo-registration, providing dense per-pixel geo-location supervision across diverse settings (orthographic and perspective), scene types (urban, landmark-centric, suburban/rural), and camera configurations. Using SkyReg, we evaluate a broad set of baselines spanning retrieval, feature matching, homography-based alignment, and feed-forward 3D reconstruction. Finally, cross-view pairs from SkyReg, we train a geometry-aware reconstruction pipeline that achieves state-of-the-art results,improving performance by a significant margin.

Reconfigurable Intelligent Surfaces (RISs) are an attractive technology for Millimeter Wave (mmWave) communications due to their ability to passively reflect incident signals. However, current implementations of RIS rely on performing computationally-intensive algorithms offline to generate phase masks, which are stored as a codebook on the embedded microcontroller on the RIS. The codebook size is restricted by the embedded microcontroller's storage capacity, which limits the ability of the RIS to adapt to evolving channel conditions and deployment scenarios. In this demo, we showcase an Machine Learning (ML)-based solution for dynamically generating new phase masks during runtime. Our approach leverages a ML model deployed on the microcontroller for approximating the output of a phase mask generation algorithm, responding to new inputs while remaining smaller than a codebook.

Detecting SQL Injection (SQLi) attacks ranks among the most critical challenges in web application security. This research conducted a systematic literature review to identify the research gaps in this domain and responsively designed and optimised a DistilBERT-Stacked Ensemble pipeline to improve detection efficiency and robustness while reducing false-positive and false-negative rates. Comprehensive pre-processing and tokenisation were performed, DistilBERT embeddings were extracted, and machine-learning and ensemble classifiers were trained and ranked on accuracy, precision, recall and F1-score. The three best performers (Logistic Regression, XGBoost and SVM) were combined through a neural meta-learner to form a stacked ensemble. The ensemble was hardened with adversarial examples generated by the Fast Gradient Sign Method (FGSM) and tuned with Optuna. The optimised ensemble achieved 99.81% across all reported metrics, closely comparable to the strongest single model (DistilBERT SVM, 99.82%). On the evaluation platform used in this study (Section 3.8), the ensemble classified the full test set in 0.0136s against 1.896s for DistilBERT-SVM, an approximately 140-fold reduction in measured inference latency, while retaining 99.77% accuracy under a single-step FGSM attack. The contribution is the design and validation of a SQLi detector performing with state-of-the-art accuracy at real-time speed and with demonstrated robustness to a single-step FGSM attack, rather than a marginal gain in accuracy. Sensitivity analysis further confirmed the stability of the model. These findings highlight the value of adversarial training and stacked meta-learning in building robust Web Application Firewalls (WAFs) for SQLi detection. For open validation, the dataset, test sets and models are made available at https://github.com/mlily2024/Final-project-SQL-injection-pipeline.

What does a generation loop gain from learning on its own verified successes? In cycles of generate, verify, select and LoRA-consolidate on online bin packing, training on value-filtered candidates shifts what the model writes on held-out variants toward value (-1.7 points of excess, p=0.008; -3.1 against a random-consolidation control, p=0.004) while the best observed candidate converges to the classic heuristic's level and no further. A confirmation battery replicates the whole procedure three times, with fresh seeds and a never-consulted held-out set read exactly once: the mean was nearly identical in all three lineages (-2.0, -1.8, -1.9), and after aggregating within held-out variant all seven evaluable variants favored consolidation (p=0.008). The best observed candidate moved to the classic heuristic's level, exactly (0.021028, the lowest variant's classic level, in all three lineages and both arms); attract never went beyond its variant's classic level, while the random control did in 7 of 24 lineage-variant cells. A matched SFT-only control shows the supervised anchor, not repulsion from bad candidates, does the concentrating (96% of candidates land exactly at the classic heuristic's level). On far families the tails cut both ways: consolidation lowers the per-candidate rate of better-than-classic candidates (10% to 3.9%) while its larger production yields more such candidates absolutely (5 against 1, on few events). As motivation we report the inference-time ledger that led here: a model-written schematic recap buys judged document integration and nothing buys development; a verifier written into the stream is imitated, 16.4 fabricated verdict lines per notebook. In this arrangement (an 8-bit model in MLX, five cycles), mean quality among valid candidates can be bought and replicated; under attraction the observed best goes to the classic and, so far, never beyond it.

We introduce MineCEraft (Minecraft Construction Engineering Benchmark, pronounced mine-see-ee-raft), an easy-to-use, open-source benchmark designed to systematically evaluate the reliability and limitations of LLMs for construction tasks in Minecraft. The MineCEraft benchmark comprises 723 domain-expert hand-crafted natural-language instructions with programmatically verifiable evaluation, spanning 17 distinct task categories, providing a safe and controllable experimental environment for assessing LLMs' ability to perform realistic construction engineering tasks. With this benchmark, we conduct an in-depth evaluation of state-of-the-art LLMs and perform a detailed error analysis, revealing key failure modes and practical challenges in applying LLMs to construction engineering tasks.

Cubature rules, which approximate definite integrals as a linear combination of a set of function values, are ubiquitous and necessary for computational methods in the physical sciences. A superconvergence result for cubature rules on polytopal domains in two and three dimensions is developed, whereby a rule that is exact for all bivariate polynomials of a fixed even degree realizes an extra order of convergence under a decrease in the spacing between nodes.

Detecting sophisticated SQL Injection (SQLi) attacks remains among the most critical challenges in web applications security. This research study has resulted in an optimised hybrid BERT-GNN pipeline with improved detection accuracy and robustness while reducing false-positive and false-negative rates. SQL queries are tokenised and encoded into contextual BERT embeddings, which then initialise the node features of a Graph Neural Network (GNN) trained to classify each query, with the architecture tuned by Optuna over accuracy, precision, recall, and F1-score. The proposed model achieved 99.67% accuracy, with 99.71% precision, 99.39% recall, and 99.55% F1-score on the attack class. A sensitivity analysis, performed by perturbing graph inputs, further assessed the model robustness and yielded a low mean sensitivity score of 0.0037, indicating stable predictions under such perturbations. The results have demonstrated the potential of a novel hybrid model that couples BERT contextual understanding with the GNN structural modelling to detect sophisticated SQLi attack vectors. For open validation, the dataset, test sets and models are made available at https://github.com/mlily2024/Final-project-SQL-injection-pipeline.

Vibe-coded applications often contain silent behavioral failures in which the interface appears functional even though user-visible information does not flow to the expected state or output. We introduce FlowCheck, a constraint language to specify these user-visible information flows directly through the application interface, where constraints can also be displayed and inspected without reading code, and are structured enough for reliable LLM generation. FlowCheck translates the constraints into deterministic CodeQL analyses, and we evaluate it across four applications generated via Claude Code, and compare with three coding models as bug-finding baselines. We find that FlowCheck correctly translates and flags all 30 of our injected constraint violations with no false positives. In contrast, frontier models (Claude Opus 4.7, DeepSeek V3, and Gemini Pro) showed significantly lower accuracy when prompted to find bugs in the same code, with none achieving full accuracy. This approach lets vibe coders state intent in terms of the interface they understand, and checks it deterministically against the code they do not.

This paper develops a hybrid offline-online multi-agent reinforcement learning framework based on decision transformers. The policy is first pretrained offline via supervised sequence modeling of trajectories generated by existing policies, providing a safe and sample-efficient initialization. It is then fine-tuned online using a hybrid objective that incorporates critic-guided gradients, enabling performance improvements beyond the offline policy. To facilitate stable offline-to-online transfer and effective multi-agent coordination, the framework incorporates return-weighted sampling, a critic conditioned on neighbors' actions, and neighborhood-correlated exploration. The approach is fully distributed: both training and execution rely only on local observations and limited information exchange among neighboring agents. Evaluations with dynamic traffic arrivals in two settings: (i) joint scheduling and power allocation and (ii) coordinated beamforming, show that the proposed method achieves quality-of-service (QoS) performance comparable to centralized methods. Moreover, when pretrained on lower-quality datasets, online fine-tuning is also observed to surpass the initial offline policy. These results demonstrate a promising learning-based alternative for wireless resource management.

Language models have recently been applied to nanophotonic design, but it remains unclear whether they can reliably translate optical objectives into simulation-ready designs, execute electromagnetic analysis, and revise decisions from numerical feedback. We introduce HALO, a physics-aware framework that couples language-model planners with typed design specifications, electromagnetic simulation, diagnostic evaluation, and optional reuse of prior failure trajectories in an iterative design loop. We further introduce HALO-Bench, a 52-task benchmark spanning lab-derived, paper-derived, and open-ended nanophotonic design tasks under a shared evaluation protocol. We compare three planner configurations: a Fixed Structured Workflow, an Autonomous Structured Agent using the same simulation interface, and an Autonomous Coding Agent that directly writes and executes simulation code. The Fixed Structured Workflow is the most token-efficient and exhibits no observed code- or path-level failures, while autonomous coding can achieve higher task success with stronger models at the cost of additional operational failures. We also study reuse of prior failed trajectories. On targeted multi-round tasks, retrieved failure feedback reduces both iterations to first success and total token use. These results clarify the tradeoffs between explicit interfaces, autonomous execution, and reusable design experience in scientific agents.

In Nyström-collocation discretizations of the electric field integral equation (EFIE), the surface divergence acts on surface densities that may be discontinuous across patch boundaries, which degrades accuracy and convergence. We show that this not only affects the EFIE but every formulation in which the operator occurs, either in the equation itself or in the scattered field computation, and propose a high-order-accurate continuity-enforcing scheme for smooth surfaces as a remedy for the direct and indirect EFIEs, magnetic field integral equations (MFIEs), and regularized combined field integral equations (CFIEs) alike. The scheme comprises two ingredients: i) We show how to discretize the equations via a Chebyshev-based Nyström scheme, which admits closed quadrature rules. ii) Since unknowns and test vectors are in terms of patch-local curvilinear bases, continuity is enforced by a change of basis: we construct sparse mapping matrices assembled solely from the curvilinear geometry description. In doing so, we restore the accuracy of the EFIE such that it can be combined with the MFIEs with equal weights to form CFIEs. Numerical studies for the scattering from canonical and realistic geometries show that all considered formulations individually and combined benefit from the continuity enforcement in terms of better conditioning, reduced iterations of an iterative solver, and several more digits of accuracy in the scattered fields, despite reducing the total number of unknowns.

Supplying context at inference time to a large multimodal model is an inexpensive lever for adapting speech transcription to a domain, and earlier results on smaller models reported large gains. This work tested that mechanism where it ships, in the prompt-conditioning layer of a production oral-history transcription tool, on a sample from its own production corpus. Full prompt-level context did not detectably change side-level word error rate (WER), and none of the four preregistered hypotheses was supported. The design was a within-item paired ablation, preregistered with the analysis code frozen by hash before the confirmatory batch was scored; two disclosed gpt-4o pilot sides had been scored earlier, during scorer development. Nineteen cassette sides, about 10.6 hours of degraded 1970s-80s interview audio, were reprocessed through the production code path under three prompt arms, crossed with two deployed commercial configurations, gpt-4o-transcribe and gemini-2.5-flash, and scored against operator-corrected verbatim references. For gpt-4o-transcribe the median paired difference between the full-context and no-context arms was +0.6 WER points, with a side-resampled interval of [-1.1, +1.0]; the Gemini estimates were too unstable to support a comparable negative inference. A post-hoc rerun found run-to-run pipeline variability larger than the confirmatory differences, so effects of that size cannot be resolved from one transcription per cell. An implementation audit verified the manipulation was live, and sequence-alignment analysis found a small improvement on complete context-listed phrases, too small to materially change side-level WER, and for Gemini coexisting with worsened unlisted-token error. Evaluating context mechanisms therefore requires sequence-aligned term-level, insertion, and speaker-label measures alongside aggregate accuracy.

The automated sorting of shredded black plastics from end-of-life (EOF) industrial waste presents a significant challenge in recycling facilities, primarily due to the limitations of current sensing and analytical approaches. Existing studies predominantly rely on single-point contact-based mid-infrared spectroscopy or laboratory hyperspectral imaging (HSI) setups, which fail to provide the spatially resolved analysis necessary for fast, bulk processing. Moreover, available datasets are laboratory-controlled and focus on intact rather than shredded plastics, hindering further recycling refinement. Black industrial plastics, in particular, are underrepresented, while most classification pipelines depend on manual region selection and rule-based spectral matching, neglecting spatial information and modern deep learning (DL) methods. To address these gaps, we introduce the first publicly available HSI dataset of shredded black plastics from EOF vehicle, comprising four industrial polymers across 13 co-registered RGB, VNIR, SWIR, and MWIR scenes and their segmentation pipeline. We developed a multi-modal spectral-spatial framework that integrates foreground isolation, pixel-wise classification, and object-level majority voting. By adapting advanced hyperspectral transformers from earth observation and incorporating chemometric band selection, we achieve accurate classification of complex black plastics. The study establishes the first comprehensive benchmark using nine processing methods, including chemometric, machine learning, and DL architectures. To ensure reproducibility, the complete dataset and methodologies are publicly released, establishing a benchmark for a hyperspectral object-analysis pipeline in industrial inspection.

The ability to leverage images from co-available modalities to inform target-domain reconstruction is highly desirable in imaging algorithms. In this work, we introduce Generative Translation Priors (GTP)–a Bayesian framework that transforms diffusion-based image-to-image translation models into cross-modality image priors for ill-posed imaging inverse problems. GTP incorporates target-domain measurements through likelihood guidance, steering the translation process toward the desired posterior distribution. The framework is grounded in a theoretical analysis of the resulting posterior dynamics, which reveals an intrinsic bias introduced by likelihood guidance. We further characterize this bias and derive a ground-truth-free formulation for its estimation, enabling it to serve as a practical metric for assessing posterior sampling quality. Building on this analysis, we derive two discretized GTP algorithms based on gradient and proximal likelihood guidance, respectively. We validate GTP on computed tomography reconstruction with magnetic resonance side information, and on positron emission tomography reconstruction with computed tomography side information. Experiments demonstrate that GTP effectively incorporates complementary cross-modality information and achieves high-fidelity reconstruction even under severely undersampled measurements.

Tensor networks (TNs), originally developed for simulating many-body quantum systems, provide a systematic framework for approximating high-dimensional fields. This is achieved by factorizing the field into interconnected tensors with small bond dimensions, thereby restricting the correlations captured across field bipartitions. Belonging to the family of TNs, the matrix product state (MPS) ansatz is utilized here as a reduced-order modeling framework to construct truncated representations of isotropic turbulent flow data. Two direct numerical simulation (DNS) datasets are considered: the hydrodynamic field of an incompressible three-dimensional flow, and a conserved Fickian scalar in a similar flow. Each field is encoded as an MPS through a sequence of singular value decompositions (SVDs) in which small singular values are discarded. The truncated representation is contracted back to the full grid, and the resulting reconstructed field is compared against DNS. An interleaved ordering of the spatial tensor indices of the transport variables is applied prior to decomposition in order to localize the dominant inter-tensor correlations. Velocity reconstructions achieve $99.8\%$ fidelity using only $5\%$ of the original DNS memory, while the scalar field reaches the same fidelity at $15\%$ memory usage. A wide range of lower- and higher-order statistics, including velocity gradients, dissipation, and structure functions, are systematically examined. At these compression levels, the total kinetic energy and the scalar energy are both recovered within $0.2\%$ relative error, while the mean dissipation and mean scalar dissipation remain within approximately $10\%$ of the DNS generated values. These findings support the suitability of MPS for scalable reduced-order analysis of complex turbulent datasets and motivate further exploration of TN-based methods in computational turbulence.

Joint modulation recognition and signal-to-interference-plus-noise ratio (SINR) estimation can reduce duplicated processing in intelligent receivers, but the two tasks have different uncertainty characteristics. This letter proposes an uncertainty-aware multi-task model that transforms each short normalized in-phase/quadrature window into 36 deterministic, label-free statistics, learns a shared representation, and uses task-specific adapters for modulation classification and heteroscedastic SINR regression. A joint uncertainty score combines classification entropy and predicted regression variance to support selective inference. Simulations cover QPSK, 8PSK, 16QAM, and 64QAM under matched additive white Gaussian noise/Rayleigh channels and an unseen frequency-selective Rician channel. Over five independent seeds, the proposed model improves matched and unseen-channel accuracy over conventional multi-task learning by 14.86 and 8.61 percentage points, respectively, while reducing SINR mean absolute error by 1.60 and 1.61 dB. Confidence-based rejection further lowers modulation error under channel mismatch.

Large Language Models (LLMs) often answer the same factual question differently across languages. We study whether cross-lingual latent-space intervention can reduce this inconsistency. We train layer-specific autoencoders on parallel multilingual representations and apply inference-time corrections to factual QA prompts. We find that latent intervention improves geometric alignment between languages, and that this improvement translates into consistent gains in cross-lingual consistency with English across both open-ended and multiple-choice QA formats, without degrading factual accuracy. In open-ended QA, Spearman's rank correlation between English and non-English languages improves substantially, with gains of 0.16 for English-Arabic and 0.20 for English-Russian pairs. In multiple-choice QA, answer agreement with English improves consistently across both KLAR and mParaRel. Ablations show that AE reconstruction yields consistent gains at no accuracy cost, while PCA projection contributes marginally, and mean-shift produces substantially larger consistency gains in open-ended QA at the cost of some accuracy.

Reasoning models do not stop when they know the answer. On DeepSeek-R1-Distill-Qwen-7B the chain of thought runs about twice as long as the model's own answer probability takes to settle, and how much of that excess is removable varies from problem to problem, so a global length penalty cannot take it out. We take it out by internalizing a causal interpretability finding into the weights. The mechanism is a halt vector: a difference-of-means direction at layer 18 of this model whose steering strength controls how long it thinks, while a replicated value axis does nothing. Installing that intervention in the weights is harder than it looks. Maximizing the scalar projection onto the direction corrupts the off-axis dimensions a frozen downstream reader depends on, and generation gets longer instead of shorter; what works is reconstructing the whole steered activation with those dimensions pinned to their natural values. Fit from 24 problems and no reinforcement learning, the halt removes about a quarter of the thinking at held accuracy across five unseen benchmarks, and the cut tracks each problem's own removable slack at 0.70. It also closes a non-termination pathology that grows with difficulty and that a decoding-time confidence hook makes worse. We do not claim to beat a well-tuned length penalty or decoding-time early exit on the raw trade-off; the contribution is how the halt is obtained.

Unmanned Aerial Vehicles (UAVs) are emerging as critical enablers of next-generation wireless networking and autonomous systems. Despite their potential, deploying and testing networked UAV systems in real-world environments remains challenging, largely due to the absence of well-developed, end-to-end, ready-to-use protocol stacks. To fill this gap, we present C2Stack, a configurable protocol stack and experimental framework designed for real-time control, evaluation, and optimization of UAV networks. C2Stack incorporates a modular control plane, referred to as the~C2Stack Network Operating System (CNOS), alongside a programmable data plane that exposes APIs for cross-layer algorithm development, digital twin integration, and autonomous swarm control. In this article, we share our experience with the deployment and testing of C2Stack. We implemented C2Stack on a custom UAV swarm platform that integrates multiprocessor system-on-chip (MPSoC) radios with Intel NUC computing modules, enabling interoperability with various RF front ends. Field trials were conducted in both netted environments and large-scale outdoor test ranges, focusing on two representative use cases: (i) network utility maximization through online reinforcement learning, and (ii) collaborative interference source localization. The experiments demonstrate the feasibility of real-time, data-driven optimization in dynamic aerial environments, while also revealing practical challenges in field deployments of networked UAV systems, including power constraints, sensing limitations, and deployment logistics. We have made C2Stack source code available to the community under the MIT License, with the goal of establishing it as a foundational framework for experimental research on intelligent networked aerial systems.

Equivariant graph neural networks provide a principled way to model geometric systems, but efficient first-order architectures remain limited in how vector information can be transformed as it moves across a graph. We introduce ESNN, an Equivariant Sheaf Neural Network that enriches this interaction by learning directed, matrix-valued transport between neighboring vector features while preserving exact Euclidean equivariance. Rather than increasing the order of the representation, ESNN keeps scalar and vector features first-order and places the additional geometric flexibility in the edge transport itself. We characterize this transport theoretically, showing that when relative displacement is the only covariant geometric input, every linear $O(n)$-equivariant map decomposes into independent radial and tangential components, while learned covariant features enable richer feature-conditioned transformations. We also introduce controlled symmetry relaxation for systems with a preferred ambient direction, which may be prescribed or inferred from data while recovering full $E(n)$-equivariance when the directional pathway is inactive. Across particle dynamics, mesh-based simulation, point-cloud classification, and molecular property prediction, ESNN improves dynamics prediction, recovers the gravity axis when symmetry is broken, yields substantial gains on selected mesh tasks and long-horizon rollouts, and remains robust to unseen rotations. These results show that learning how geometric information is transported across edges offers a complementary route to expressive equivariant message passing without requiring higher-order representations.

I show how to evoke the pitch-class content of a chord from an arbitrary source sound by convolving the source with an impulse response whose grains are one windowed sinusoid per pitch-class, across each octave of hearing range; while, at the same time, minimizing artifacts. A Csound user-defined opcode, chord_convolver, mixes a dry Dirac component into that response, and applies partitioned convolution once. I contrast the effect with a linear-frequency comb filter and with a generic constant-Q resonator bank, and I demonstrate musical use on a twilight field recording alongside the ruins of Chateau de Lagarde.