Papers

We propose to finetune vision-language models to generate more pragmatically optimal referring expressions by transforming observations of incremental listener comprehension, in the form of gaze scanpaths, into learning signals. During training, referring expressions are sampled from the speaker policy being optimized, conditioned on images and target referents; then, a neural listener estimating human gaze behavior maps from images and sampled referring expressions to scanpaths, each represented by a sequence of fixations, with each fixation corresponding to a word in the referring expression. We experiment with several approaches to convert fixation sequences and target referents into token- and sequence-level rewards, which are used to optimize policy parameters. Through evaluation with human listeners, we find that speaker policies trained with gaze-estimating listeners result in significantly more pragmatically-optimal references than base models, reducing sequence length from 15.4 down to 4.0 words while increasing referential success from 75.2 up to 80.0%. Our work demonstrates a promising opportunity for learning to generate utterances through language-based interaction, not only from the explicit signal of communicative success, but also from implicitly-available observations of a listener's process of comprehension.

Managing drawdown, the peak-to-trough decline in an investment portfolio's value, is a precondition for long-term survival in practical investment management. However, mainstream stock forecasting methods predominantly optimize returns or Sharpe ratios under the independent and identically distributed (i.i.d.) assumption. Real markets do not follow this assumption, triggering catastrophic drawdowns. We propose a cross-asset state-space trading system (CAST), consisting of two components: The predictor, Cross-Asset Collaborative Kalman Filter (CoKF), estimates each asset's latent state online, coupling all assets through their correlations and adaptively fusing multiple integrated-random-walk orders. The controller, Model Predictive Control (MPC), converts the predictor's forecast into trades, using forecast uncertainty as an explicit risk penalty that controls drawdown. We evaluate CAST on four real-world stock markets over a 15-year test window and show that it consistently occupies the return-drawdown Pareto frontier, achieving strong risk-adjusted performance while maintaining substantially lower maximum drawdown than competitive baselines. A stress test across crisis periods further demonstrates robust behavior under market shocks and distribution shift. Because the predictor and controller interact only through the predicted price path, both are plug-and-play, making CAST a modular, interpretable trading system. The code is available at https://github.com/FanBroWell/CAST

Surgical tissue manipulation demands precision; however, tool-tissue manipulation force magnitudes under realistic conditions are rarely quantified. To address this gap, we proposed and validated a portable ex-vivo force-sensing platform that measures tool-tissue interaction forces across the skull-brain interface during simulated neurosurgery. The system involves fresh calf brain tissue, used as a biological surrogate for brain parenchyma, placed in a 3D-printed human skull model equipped with a 6 degree-of-freedom force/torque sensor and a real-time data acquisition system. Five validation protocols assessed the accuracy and dynamic fidelity of the platform against ground-truth measurement, static accuracy and linearity using calibrated weights (0.5-50 g), minimum detectable force, spatial consistency across different anatomical regions, effect of surgical draping, and long-duration stability. Across protocols, measured forces showed excellent agreement with reference loads (correlation R = 0.9997), with RMSE < 0.005 N and mean relative error under 2%. The platform reliably detected low-magnitude forces down to 1 g (9.8 mN), while surgical drapes introduced no meaningful signal distortion and prolonged recordings exhibited minimal drift. Overall, the proposed framework provides objective, high-fidelity force quantification for skill training and performance assessment using fresh calf brain tissue and may serve as a foundation for force-based evaluation across other surgical procedures. Future work will integrate clinically used surgical instruments to increase procedural realism and will progress toward clinical trials to evaluate usability, educational impact, and translational relevance in practice-adjacent settings.

We develop controlled B-series and controlled Runge-Kutta methods as extensions of classical B-series and Runge-Kutta theory to controlled-driven rough differential equations. The driving signal is a path controlled by an underlying $\alpha$-Hölder step-$2$ rough path, with $\alpha\in(1/3,1/2]$, as arises when the output of one rough system drives another. Controlled B-series retain the classical rooted-tree and elementary-differential structure, while incorporating driver-dependent coefficients defined recursively through controlled rough integration. We establish finite-order expansions of the exact solution and its controlled Runge-Kutta approximation, and derive corresponding tree-based order conditions. Under suitable smoothness, solvability, stability, and boundedness assumptions, matching through tree order $p$ yields local error $O(|t-s|^{(p+1)\alpha})$ and global error $O(h^{(p+1)\alpha-1})$, provided $(p+1)\alpha>1$. The standard rough differential equation formulation is recovered when the controlled driver is the reference path itself, and the classical time-driven case recovers the usual B-series and Runge-Kutta methods. We further construct a simplified method using only increments of the controlled driver. Segmentwise canonical lifting of its piecewise linear interpolation gives explicit tree coefficients and reduces the third-order conditions to the classical ones. Assuming a Wong-Zakai solution-approximation rate $r_0>0$, the simplified method has global error $O(h^{\min\{r_0,(p+1)\alpha-1\}})$. Numerical experiments with fractional Brownian controlled drivers illustrate the resulting convergence behaviour.

Multi-agent language-model systems often add a reviewer to improve an upstream agent's decision. Yet a reviewer can both repair errors and replace decisions that were already correct. We study this as a problem of institutional jurisdiction: conditional on the same proposal, task information, model, and review output, when is the reviewer authorized to make its recommendation binding? We compare broad override authority with an evidence gate that permits replacement only after the reviewer produces a mechanically valid record of a binding-constraint violation and a compliant repair. Across two locally run open-weight models, 96 spatial-policy tasks, and a 96-task portfolio-transfer benchmark, the gate sharply reduces corruption of correct proposals while retaining most repairs of violations. The directions of this tradeoff are partly implied by the rule; its magnitude depends on reviewer transitions and upstream proposal states. A prospective validation then gives the reviewer an explicit choice to retain, replace, or escalate. This eliminates correct-proposal corruption for Qwen, but Mistral still replaces all 48 correct proposals; Qwen also declines every welfare-only repair that Mistral frequently attempts. Thus interface design changes reviewer behavior but is not a model-independent safeguard. The result is not that restricted review is universally better. It is that reviewer competence, action interface, and binding jurisdiction jointly determine both the correction domain and the corruption surface.

This study proposes and validates a methodology for reconstructing the Human Development Index (HDI) from individual-level survey microdata, enabling disaggregated estimates for demographic subpopulations while maintaining coherence with the official HDI. Data from 40,185 respondents in 21 countries from the European Social Survey (ESS7, 2014) were analysed, combined with World Bank indicators for life expectancy, gross national income per capita, and expected years of schooling. The health dimension was estimated from national life expectancy, adjusted by self-rated health; income, by a lognormal multiplier calibrated by the Gini coefficient; and education, by combining observed and expected years of schooling. The dimensions were aggregated by geometric mean, weighted by sampling weights, with confidence intervals estimated via the delta method. Among the 39,706 individuals with valid data (98.8%), the reconstructed HDI showed high agreement with the official 2014 HDI, with a mean absolute error of 0.0099 and a Pearson correlation of 0.917. Consistent differences across subgroups evidenced the methodology's convergent validity and its capacity to produce disaggregated estimates of human development, expanding the HDI's potential for analyses of socioeconomic and demographic inequalities.

Physical Activity (PA) is consistently associated with lower risk of dementia, yet the mechanism linking PA to dementia prevention remain incomopletely understood. Here, we integrate large language model (LLM)-guided causal discovery with mediation analysis in 42,293 older adults aged 60 years or older from the UK Biobank to systematically identify pathways connecting objectively measured moderate-to-vigorous physical activity (MVPA) to dementia risk. Across behavioral, psychological, functional, and clinical domains, causal discovery consistently identified interconnected pathways linking higher MVPA to lower dementia risk through depression, functional capacity, smoking behavior, hypertension, cardiovascular disease, chronic kidney disease, and brain injury. Chain mediation analyses further identified depression as a central pathway, accounting for 15.1% of the overall association between MVPA and dementia risk. Sex-stratified analyses revealed distinct mechanistic patterns, with females exhibiting predominantly metabolic and functional pathways, while males showed behavioral and cardiometabolic cascades involving smoking and cardiovascular disease. Together, these findings suggest that the protective association between PA and dementia is mediated through interconnected behavioral, psychological, and cardiometabolic processes rather than a single pathway. Depression emerged as a prominent and potentially modifiable pathway, highlighting opportunities for integrating dementia prevention strategies that combine PA promotion with mental health and cardiovascular risk management.

We study the fair division of indivisible goods among agents with nonnegative additive valuations. An agent's maximin share (MMS) is the value she can guarantee by partitioning the goods into as many bundles as there are agents and receiving a least-valued bundle. We prove the existence of exact MMS allocations for a valuation domain that generalizes several few-valued domains as well as weakly lexicographic valuations. For each agent, the lower-valued goods, after a positive rescaling, may take values in $\{0,1,d,d+1\}$, $\{0,1,2,2e\}$, or $\{0,1,2,3,4\}$, where $d,e\ge 2$ are integers. Above these goods, the valuation may contain arbitrarily many value classes, subject to the condition that a single good in each class is worth at least the total value of all strictly lower-valued goods. The value classes, scaling factors, and parameters may vary across agents. We give an algorithm that computes an MMS allocation in $O(nm\log^2(2+m))$ time, where $n$ is the number of agents and $m$ is the number of goods.

Open-source video-game quality depends on inter-actions among code, assets, configuration, tests, contributors, and issue workflows, yet conventional defect predictors usually flatten or omit these relations. We investigate release-level forecasting of a quality incident within thirty days using GAMEQUALGRAPH-Pilot, a typed temporal feature pipeline with calibrated risk estimates and effort-aware ranking. Because the accessible OS-SGameBench materials do not provide manually audited release dates and outbreak labels, the executed evaluation is explicitly simulation-backed rather than an empirical claim about real games. Five seeded worlds each contain 120 projects and 24 releases, with project-disjoint validation and future cross-project testing. The pilot obtains an AUPRC of 0.520, AUROC of 0.673, Brier score of 0.207, and 29.68% effort-aware recall at a twenty-percent testing budget. Its closest local comparator, Static-Hetero-Reimpl, reaches 0.522 AUPRC; the -0.002 difference is not statistically significant after Holm correction. Inference requires 0.023 milliseconds per release in the measured environment. Ablations and controlled missingness, drift, engine, project-size, alert-threshold, and attribution analyses expose where typed interactions help and where they fail. Results support the reproducibility of the proposed protocol, not deployment effectiveness. Real OSSGameBench release reconstruction, stratified label audits, and official graph-model comparisons remain mandatory before journal submission or operational use in practice. This boundary protects research integrity and supports credible evaluation.

Low-cost indoor air-quality sensors could support personalized asthma prevention, but their nonlinear measurement error, delayed exposure effects, time-varying confounding, and heterogeneous lower-tail responses limit risk estimation. We present CAUSALQUANT-ASTHMA, a measurement-error-aware causal quantile distributed-lag framework for short-horizon peak expiratory flow analysis. Sparse reference measurements train a nonlinear calibration model; stabilized sequential generalized-propensity weights address measured exposure assignment; and a susceptibility-modulated, smooth, noncrossing quantile model estimates lag-specific and sustained-exposure contrasts. Because no authorized cohort simultaneously provided dense indoor sensing, reference co-location, and outcome-compatible longitudinal data, evaluation used five semi-synthetic panels with known counterfactual truth, 150 patients and 12,600 patient-days per realization. Across eight methods, CAUSALQUANT achieved a dose-response integrated absolute error of 0.304 plus or minus 0.094, improving 24.2 percent over the strongest measurement-error and propensity-weighted baseline. It also obtained the lowest overall pinball loss, 1.065, while maintaining zero quantile crossings and 78.1 percent coverage for the nominal 80 percent interval. Sensor calibration reduced held-out exposure RMSE by 33.7 percent. Stress tests quantified degradation under sensor noise, missing personal measurements, and hidden confounding. These findings establish methodological feasibility and reproducibility, not clinical effectiveness; prospective, governance-approved external validation is required before patient-level interpretation or deployment.

Automated incident management in large-scale microservice systems relies on learning robust representations from multimodal observability data, including metrics, logs, and traces. Although recent self-supervised frameworks enable unified modeling for anomaly detection (AD), failure triage (FT), and root cause localization (RCL), they often struggle with non-stationary temporal dynamics and heterogeneous service dependency structures. In this paper, we propose STAR, a Spatial-Temporal Adaptive Representation learning framework that explicitly addresses these challenges through adaptive normalizations. STAR introduces two tightly coupled mechanisms: Temporal Adaptive Normalization (TAN), which dynamically normalizes multivariate time series using multi-scale temporal context, and Spatial Adaptive Normalization (SAN), which performs structure-aware normalization over service dependency graphs. Unlike prior methods that treat normalization as static or task-agnostic, STAR formulates it as a learnable, context-conditioned transformation aligned with the intrinsic properties of microservice systems. The resulting adaptive representations are integrated into a unified self-supervised framework, enabling end-to-end unsupervised support for AD, FT, and RCL tasks. Extensive experiments on two real-world microservice benchmarks demonstrate that STAR consistently outperforms all state-of-the-art baselines, yielding significant and stable improvements across all three tasks. Our results highlight adaptive normalization as a principled and effective mechanism for robust multimodal representation learning in complex software systems.

Reinforcement learning (RL) is widely used in language-model post-training to maximize rewards assigned to individual model outputs, such as scores from binary verifiers or reward models trained on human feedback. However, applications such as synthetic-data generation, fairness-related constraint satisfaction, and policy exploration require controlling the distribution of outputs across model generations rather than only maximizing expected reward. We propose a general RL-based framework for Distribution Matching allowing matching the distribution of a latent categorical attribute of model outputs to a specified target distribution. Empirically, we demonstrate that dominant post-training recipes such as Group Relative Policy Optimization (GRPO) reduce output diversity by concentrating policy probability towards a single mode. Entropy regularization and sampling temperature can improve the spread of the distribution but have constrained effectiveness, limited to apply only in token space and toward uniform distributions. We show that prior work in this area is a specific case of Distribution Matching involving the $L_2$ divergence. We then propose reward functions for other divergences such as KL and Jensen-Shannon and motivate them with theoretical justification. Finally, we demonstrate the effectiveness of our approach on a set of experiments involving mathematical reasoning and programming.

A principal who deploys a binary classifier with an abstention option must decide which queries the mechanism abstains on. The right choice depends on the adversary. A gaming adversary already knows the classifier and tries to manipulate features across the boundary, so the principal does best by abstaining on queries close to that boundary. The same boundary-localizing rule is the worst possible choice against a learning adversary who does not know the classifier: each abstention now tells the adversary that the boundary is nearby, which is enough to drive a binary search. We analyze this tension. The two natural defenses, abstaining at a fixed rate and abstaining near the boundary, are Blackwell-incomparable: neither can be simulated by post-processing the other's responses. The number of queries needed to reconstruct the boundary to error $\eps$ is $\tilde\Theta(d/\eps)$ under the first defense and $\Theta(d \log(1/\eps))$ under the second, where $d$ is the VC dimension of the classifier family and $\tilde\Theta$ suppresses factors polylogarithmic in $d$ and $1/\eps$. The first rate is a worst case over query distributions; no reconstruction algorithm can close the gap at the distributions that attain it. We characterize the Pareto frontier between the two defense objectives, and confirm both rates on seven binary-classification tasks spanning tabular, image, and language-model-feature inputs: label-plus-counterfactual access extracts the boundary with up to $200\times$ fewer queries than a published label-only baseline.

Online reviews shape consumer decisions, platform governance, and corporate reputation.Fake reviews compromise this information channel by injecting deceptive evidence into rating systems, recommendation pipelines, and public trust mechanisms.The rise of large language models, or LLMs, has changed the problem in two directions.LLMs can generate fluent and context-aware deceptive reviews, while pre-trained language models, or PLMs, and LLMs also provide stronger semantic representations for detection.This survey reviews fake review detection from an information fusion perspective, covering 211 studies published from 2018 to early 2026.We organize existing work by evidence source and fusion level, covering review text, sentiment, rating behavior, temporal metadata, user-product graphs, multimodal content, external knowledge, and LLM-generated signals.We trace the development from traditional machine learning and deep learning to PLM-based and LLM-based methods, and examine how different approaches combine textual, behavioral, structural, and multimodal evidence.We also analyze reported performance trends on widely used Amazon, Yelp, and OpSpam benchmark families, while noting the limitations caused by different label construction procedures, data splits, and evaluation protocols.Finally, we identify open problems in adversarial generation, cross-domain transfer, uncertainty-aware fusion, missing-source robustness, interpretability, and trustworthy evaluation for AI-generated deceptive content.

Artificial intelligence helps education most where an essential provision has been rationed by cost. For language learners that provision is a teacher's voice, which binds listening, reading, speaking, and writing into one act. Published evidence shows why most learners lack it, from a global shortage of 44 million teachers to heavy household tutoring bills, and why technology has not substituted for it: computer-assisted language learning proved effective but narrow, applications presuppose connectivity 2.6 billion people lack, and One Laptop per Child's randomized evaluation found that hardware without capable software teaches nothing. We distill eight difficulties and four binding constraints, and argue that small open-weight models dissolve the last: a complete four-skill stack now fits a \$200-class laptop and, on community measurements, generates at the pace speech is consumed, for about one US cent of electricity per study hour. We therefore propose LLMersion, a scheme for AI for education that runs entirely at home, over the learner's own documents, with an AI-written, AI-understood, AI-updated codebase anyone can customize; present LLMersion-1, a released open-source prototype (https://github.com/QM378/LLMersion ); and outline the vision of a private learning agent.

Quadruped manipulators enable mobile grasping in complex environments, yet their whole-body control policies remain vulnerable to unreliable onboard visual perception. Existing methods are typically developed under relatively reliable observations and have not systematically examined how occlusion, segmentation-mask dropout, depth noise, and target-localization jitter affect grasp reasoning and target tracking. To address this gap, we introduce DeViGrasp-Bench, a benchmark for mobile grasping under degraded vision that incorporates controlled visual degradations, seen and unseen objects, multiple difficulty levels, and complex terrains, and evaluates task success, execution efficiency, and action smoothness. We further propose DeViGrasp-Net, a teacher–student framework that combines state-conditioned grasp reasoning with reliability-aware temporal target estimation. The privileged teacher attends to offline grasp candidates conditioned on object, robot, end-effector, and task states, while the deployable student fuses dual-view segmented-depth observations with current, memory, and recovery target hypotheses through Target Hold Memory and Temporal Memory Attention. DeViGrasp-Net outperforms VBC across degradation levels, unseen objects, and complex terrains, and surpasses an adapted DQ-Net across all evaluated degradation levels. Under the Difficult setting, it achieves a success rate of 62.3%, improving upon VBC and DQ-Net by 16.1 and 4.3 percentage points, respectively; under the Hard setting, its margin over DQ-Net increases to 10.5 percentage points. Ablation studies confirm the complementary benefits of grasp-aware supervision and reliability-aware temporal memory.

Visual impairment affects over 2.2 billion people worldwide, yet conventional white canes cannot detect elevated hazards or provide semantic environmental context. Existing AI-assisted navigation systems typically rely on expensive hardware or cloud connectivity, limiting accessibility in resource-constrained settings. This paper presents an affordable (\$88 USD), fully offline AI-integrated smart cane designed for multimodal mobility assistance on an ultra-low-power Raspberry Pi Zero 2W. The system fuses RGB vision sensing with Time-of-Flight (ToF) distance estimation, pairing an INT8-quantized SSD MobileNet V1 model with distance-aware vibrotactile feedback and real-time audio alerts. To ensure operational robustness on constrained hardware, a multiprocessing architecture isolates sensor acquisition, neural inference, and haptic feedback into independent processes with fail-safe sensing support. Experimental evaluation across indoor mobility scenarios demonstrates a macro-averaged F1-score of 0.82 (precision: 0.85, recall: 0.81), a mean end-to-end latency of 330\,ms, and a peak power draw of 2.8\,W. A preliminary usability study with 12 participants (SUS: 78.5, NASA-TLX) demonstrated positive user perception and enhanced obstacle awareness. The proposed prototype validates the feasibility of deploying privacy-preserving, edge-native assistive intelligence for cost-sensitive mobility assistance.

Concurrent local LLM serving on unified-memory desktops must preserve memory headroom and output fidelity, which speed-only rankings overlook. We introduce SiliconBench, which evaluates nine Apple Silicon serving engines through three lenses: speed, memory, and fidelity. We evaluate chat and agent serving on Qwen3, Qwen3.5, and Gemma 4. We use a classification task to check for quality regressions against an NVIDIA reference. DGX Spark provides a complementary serving-performance reference. Three desiderata guide interpretation: serving architecture readiness, memory discipline, and multi-node scaling. On Qwen3-0.6B, vllm-metal alone more than doubles throughput on both workloads from concurrency 1 to 16. CUDA vLLM and SGLang show stronger concurrency scaling on the same prompts. Explicit memory budgets do not guarantee memory headroom: two stacks complete every request while memory use approaches physical capacity and throughput declines. The newer model architectures have narrower engine support. Their evaluated implementations match the fidelity reference. Only three stacks satisfy the completion, fidelity, and model-coverage gates. Comparisons on larger dense and MoE models reinforce the importance of scheduling prompt processing alongside ongoing generation: vllm-metal's packed prefill-decode path maintains lower first-token latency than omlx under concurrent load. In the tested two-machine configurations, tensor parallelism over Thunderbolt RDMA scales while pipeline parallelism over TCP regresses. We release benchmark code, per-run results, and maintenance journals, supported by a workflow combining bounded agent fixes with human review.

Autonomous coding agents now open pull requests in public repositories at a scale that was out of reach two years ago, yet little is known about what happens to that code after it lands. This paper studies 37,623 provenance-labeled pull requests (PRs) from five commercial agents (OpenAI Codex, Devin, GitHub Copilot, Cursor, and Claude Code) and a matched human baseline, drawn from 2,807 GitHub repositories between December 2024 and July 2025. We combine the AIDev dataset with 58,792 cached GitHub API responses to measure security smells in added code, structural maintainability, post-merge churn, revert rates, and human review behavior. Three results stand out. First, quality differences are vendor-specific rather than uniform: Codex-authored PRs were reverted about half as often as human PRs (6.1% vs. 11.5%, odds ratio 0.50), while Devin PRs were reverted more often (14.5%, odds ratio 1.31). Second, agent code pooled across vendors was less likely than human code to contain a security smell (odds ratio 0.63), driven by fewer hardcoded credentials and eval-style constructs. Third, review effort concentrates unevenly: Copilot PRs drew the most human reviews and change requests, and Claude Code PRs waited the longest for a first human review (median 12.6 hours). All pipeline code, statistical reports, and figures are released for replication.

In the improving multi-armed bandits problem, each of $k$ arms has an unknown nondecreasing, discretely concave reward curve $f_i$, and pulling arm $i$ for the $t$-th time yields $f_i(t)$. For sufficiently long horizons, Blum and Ravichandran (ALT 2025) proved that randomized algorithms achieve an $O(\sqrt k)$ approximation to the best single arm when the scale $m=f^*(T)$ of the optimal arm is known ($T\ge2k$), and $O(\sqrt k\log k)$ when it is not ($T>4k$), against an $\Omega(\sqrt k)$ lower bound. The logarithmic factor is unnecessary: a one-page probe-and-commit algorithm achieves competitive ratio $4\sqrt3\,\sqrt k$ for $T\ge2\lfloor\sqrt k\rfloor$, without any knowledge of the scale, and we determine the optimal ratio for every horizon, $\Theta(\sqrt k+k/T)$, also for unknown horizons. Without noise, no prior is needed at all: a random-marginal probing algorithm reading neither the scale $m$, nor the concavity-envelope exponent $\beta$ of Blum, Garicano, Ravichandran and Sharma (UAI 2026), nor the horizon $T$, achieves the optimal $\Theta(k^{\beta/(1+\beta)}+k/T)$ simultaneously for every $\beta$ and every horizon. Under the multiplicative noise model of Blum and Ravichandran, probe-and-commit keeps the same all-horizon order $\Theta(\sqrt k+k/T)$ without knowing the noise level (and $\Theta(\sqrt k)$ on the same range), but the price of priors jumps: for any fixed noise level $\varepsilon\in(0,1/2]$, the uniform price of adaptation $\phi_\varepsilon(k)$ — the worst case over horizons $T\ge16k$ of the loss relative to $k^{\beta/(1+\beta)}$ for algorithms knowing neither $m$ nor $\beta$ — is $\Theta_\varepsilon(\sqrt{\log k/\log\log k})$, the lower bound asymptotic in $k$ at fixed positive $\varepsilon$ and matched by a nested random-permutation probing algorithm, whereas knowing either $m$ or $\beta$ alone restores a constant price.

Can gradient-based training learn the rank needed to store and compose associations in a matrix memory? In our earlier study, we used a matrix-augmented reasoner on a task that admits a rank-1 solution, leaving this question open. We train matrix memories on $K$ fresh key-value bindings whose exact linear recovery requires $\mathrm{rank}(Z) \geq K$. A fixed linear readout queries a single matrix state without access to the original bindings. Experiments measure recovery by cosine similarity greater than 0.9, a threshold distinct from mathematical equality. Learned effective rank increases with $K$ across the tested grid (Spearman $\rho = 1.0$ at $d = 16$). Training-time rank caps produce a recovery transition near $k = K$: at $d = 8$, $K = 4$, rank 3 gives at most 0.0004 recovery and rank 4 gives 0.97. Four of five seeds retain at least 0.9996 recovery through 21-fold self-application of the trained operator. On the entity subspace, the learned operator has effective rank close to $K$ and approximates the ideal cycle. For the single converged seed capped below $K$, a calculation using the entity-subspace operator and ideal cycle predicts the measured cosine within 0.008 through seven applications. Extending training resolves several initial failures, but recovery still declines at larger matrix dimensions with encoder width fixed.

Single-machine asymmetric weighted earliness–tardiness (AWET) scheduling asks how to sequence jobs around a common synchronization date when early and late completion incur unrelated job-dependent penalties. At the boundary nonrestrictive date $d=\sum_jp_j$, a compact V-shaped schedule reduces the continuous-time problem to a quadratic choice of a nonempty early set. We establish four complementary results for this model. First, the positive-integer problem is strongly NP-complete by a unary-polynomial reduction from Restricted Exact Cover by 3-Sets. Second, unrestricted AWET admits a polynomial-time $(3+2\sqrt2+\varepsilon)$-approximation based on an anchored semidefinite relaxation and deterministic marginal thresholding. Third, when the earliness and tardiness ratio orders are strict reversals, the problem is weakly NP-complete but has an exact two-resource pseudopolynomial dynamic program. Fourth, for fixed total refinements whose ratio permutation is separable, an exact separating-tree recurrence and coordinated geometric trimming yield an FPTAS. The proofs use different manifestations of the same canonical objective: scale-separated prefix penalties, positive-semidefinite minimum-kernel covariance, a dominant completed load square, and a bounded four-coordinate decomposition interface. Together, the results show that the decisive issue is not merely whether the two ratio orders agree, but whether their interaction can be controlled by a global certificate or compressed into a bounded constructive interface.

We give a polynomial-size linear programming bound for $q$-ary all-symbol locally recoverable codes with locality parameters $(r,\delta)$, without assuming linearity. The key idea is to keep, for every ordered pair of codewords and every selected recovery view, the joint Hamming weight on the helper set, the recovered coordinate, and the rest of the code – rather than collapsing this triple into a single distance, as earlier formulations do. Averaging this three-block distribution over recovery views of the same length yields exact identities linking it to the global distance distribution, together with nonnegative product-Krawtchouk constraints that encode locality and spectral positivity simultaneously. The resulting LP has polynomially many variables, its optimum dominates the ordinary Delsarte bound, and an earlier outside-distance formulation, the convex-hull bound of Li–Wei–Xiong, and the dual-based bound of Gruica–Jany–Ravagnani all arise from it as coarser marginals. Exact rational certificates over $q=2,3,4$ show the bound is strictly stronger than the best of these prior LPs in thirteen of fifteen tested cases, pinning down seven exact maximum code sizes and twelve exact maximum linear dimensions.

Swept surface construction is widely used in computer-aided design. We propose a novel optimization method using non-uniform B-splines to improve the approximate accuracy of swept surfaces. First, discrete points on the swept shape are computed, and geometric properties such as surface area, discrete curvature, first-order derivatives, and their rotation angles are used to derive a distribution function representing surface irregularity, with weights adjusted from samples. Then, feature points are selected based on the distribution function to determine control points for the approximate non-uniform B-spline surface via inverse calculation, producing an optimized approximation. Finally, the number of feature points is adjusted based on the estimated approximation error. Experiments on 969 randomly generated sweep samples and 1 pipe example show that the proposed algorithm achieves similar accuracy with fewer control points, reducing them by about 15.85% at a specified accuracy of 0.01. Moreover, with ample sampling points, it reduces the average error by approximately 51.35% when the feature point multiple is 10 times the path control points, outperforming comparable methods.

A secure and privacy-preserving identity verification process is essential for digital ecosys- tems. Current eKYC frameworks that rely on Zero-Knowledge Proofs (ZKPs) face high computational cost, rigid circuit design, complex integration, and expensive on-chain verification. The W3C 2021 BitString- based credential status mechanism also suffers from inefficient updates and poor scalability in large- scale deployments. We propose a transparent and cost-effective identity verification framework based on Multi-Party Computation (MPC). It enables private off-chain code execution and produces runtime proofs anchored to a blockchain. The framework introduces a multidimensional bit-matrix model with efficient compression. Using ZSTD, the credential data is reduced to 76 bytes compared to 140 bytes with GZIP, cutting storage and bandwidth costs. The system also supports fine-grained status updates and Layer-2 blockchain anchoring for tamper-evident, low-cost verification. The system employs reusable verifiable presentations (VPs) with unique access tokens, enabling cost-free verification and stronger access control. Selective disclosure preserves user control and strengthens privacy. Finally, the system integrates SHA3 hashing and Falcon post-quantum signatures. This guarantees robustness against quantum attacks, transparency, and scalability. It is a future-proof solution for national-scale identity verification, as demonstrated by experimental findings and security studies that validate its robustness and applicability.

On-policy distillation (OPD) is increasingly applied to frontier foundation model post-training. Prior work in this area has largely focused on algorithmic advances, yet it remains unclear how much OPD depends on its training questions and, in particular, how far this dependence can be reduced. Across two representative single-teacher OPD settings, we find that training on 8 real prompts yields performance comparable to training on 17k problems, while datasets differing substantially in measured difficulty and initial distillation gap yield similar outcomes. Our analyses suggest two complementary explanations: repeated sampling could allow even a few prompts to expose substantial teacher supervision, while OPD transfers generalizable reasoning capabilities beyond dataset-specific knowledge. Building on these observations, we next propose a data-free on-policy distillation (DF-OPD) setting to investigate whether the system can supply the training questions itself, eliminating the need for external data. With 64 self-generated questions obtained without seed examples, DF-OPD yields performance comparable to full-data OPD in both single-teacher settings. This finding also holds in multi-teacher OPD: across mathematics, code, and instruction following, 1k generated questions achieve performance comparable to training on approximately 7k real post-training examples. We further explore whether OPD can operate even without explicit training questions. The experiments show that this is effective only in limited cases, where the student unexpectedly generates and answers its own questions, thereby reducing the process to an implicit form of DF-OPD. Together, these findings invite a reassessment of the role of training data in on-policy distillation. Code is available at https://github.com/Ryuki661/DF-OPD

Extremum seeking control (ESC) relies on deliberately injected excitation to extract optimization information from measured outputs, making its networked implementation particularly vulnerable to denial-of-service (DoS) attacks. This paper develops a resilient discrete-time ESC architecture for cyber-physical systems subject to DoS attacks. By holding the most recently successfully transmitted signals during DoS intervals, the proposed mechanism yields averaged error dynamics with an exponentially contracting mode under successful communication and a neutral mode under attack. For deterministic DoS attacks, practical exponential convergence to the extremum is established under an average bound on the attack duration, with an explicit convergence rate depending on the fraction of time under attack. For probabilistic DoS attacks, almost-sure and in-probability convergence properties are established via stochastic averaging, with the attack success probability explicitly entering the convergence rate. A key finding is that a seemingly natural zero-input strategy can fundamentally compromise ESC: attacks synchronized with the dither generate an $\mathcal{O}(1/a)$ bias in the averaged dynamics, where $a$ is the dither amplitude, and can displace the equilibrium from the true optimizer. Thus, under the proposed hold-based architecture, increasingly severe DoS attacks primarily slow the optimization process rather than destroy its stability, provided that communication is not permanently blocked. Numerical simulations illustrate the theoretical guarantees and the failure mechanism induced by dither-synchronized attacks.

Human motion may be viewed as a combination of action content, style, and body morphology. Existing motion style transfer methods transfer a reference style onto a content motion while assuming a canonical body, whereas shape-aware motion generators adapt motion to a target shape without explicit style control. This separation of motion style and shape (morphology) makes it difficult to generate stylized motions for non-canonical bodies; naively combining a style transfer module with a shape-aware generator often leaks action content from the style reference and disrupts shape-consistent kinematics. We present MorphoStyle, a framework for shape-aware motion style transfer that is built on a shape-conditioned Finite-Scalar-Quantization Variational Auto-Encoder (FSQ-VAE). The key contribution is to pose the desired style transfer as modular latent disentanglement comprising: (i) a contrastive style encoder that extracts content-decoupled style embeddings; (ii) a text-guided style-routing mechanism that locates style-relevant joints in a text-motion feature space; and (iii) a manifold preserving style modulator that injects discriminative style embeddings in content features as a temporally-gated low-rank offset. Extensive experiments on benchmark datasets demonstrate that MorphoStyle outperforms competing baselines in terms of both shape control and motion style transfer, while simultaneously providing quantitative shape control. For more details, please see project website: https://github.com/funkdub/MorphoStyle.

Memory-efficient feature representations are increasingly important in machine learning settings where storage, transmission cost, bandwidth, or privacy constraints limit access to raw data. Bloom Filter (BF) encodings provide compact probabilistic representations of engineered features, but their behavior under structural compression and their applicability to regression tasks remain underexplored. In this work, we propose entropy-punctured Bloom Filters, a memory-aware encoding strategy that removes low-variability bit positions identified using empirical entropy. Starting from fixed-length BF encodings of quantized features, the proposed approach produces reduced representations that preserve predictive structure while improving predictive efficiency relative to encoded representation size. We evaluate the approach on diverse regression datasets, comparing raw features, Principal Component Analysis (PCA), Random Projection (RP), and Bloom Filter variants under leakage-free evaluation protocols and approximately matched representation sizes. Performance is assessed using ridge regression, XGBoost, and neural networks, with predictive efficiency measured as R2 relative to encoded representation size per sample. Results show that Bloom Filter encodings remain competitive with classical compressed representations while achieving substantial storage savings. Entropy-based puncturing further reduces representation size with minimal loss in predictive fidelity, yielding improved predictive efficiency. These findings demonstrate that entropy-punctured Bloom Filters provide an effective representation-level compression approach for memory-constrained machine learning.

Bird's Eye View (BEV)-based multi-view 3D object detection suffers from challenges of computational complexity, multi-scale feature extraction, and efficiency of dense 2D-to-BEV view transformation. To address these problems, this paper proposes an improved BEV 3D object detection algorithm Sparse-BEVNet. Firstly, a Bi-Level Routing Attention (BRA) mechanism is introduced into the image feature extraction network to reduce the computational burden of the backbone. Second, Cascaded Group Attention (CGA) is employed in the feature fusion module, which enhances deep interaction across features of different hierarchical levels without introducing additional computational overhead. Furthermore, a Sparse Spatial Cross-Attention mechanism is adopted to replace the conventional dense view projection pipeline. Experimental results on the public nuScenes dataset demonstrate that the proposed method achieves a mean Average Precision (mAP) of 45.2% and a nuScenes Detection Score (NDS) of 54.5%, corresponding to 3.6% and 2.8% improvements relative to the baseline model, respectively.