Papers

Large-scale empirical studies have revealed that many widely used generalization measures correlate only weakly with generalization, suggesting that relying on a single factor is insufficient to explain it. In this work, we examine sharpness and complexity jointly, placing the reach of the two-factor view at the center: how far can they jointly explain generalization, what determines when they succeed, and where do they fall short? We investigate these questions quantitatively, using sixteen alternative metric pairs as probes and Pareto analysis and linear regression as evaluation tools. Our results show that suitably defined $(S,C)$ pairs provide strong explanatory power across a range of settings. The sharpness perturbation scale substantially affects this success, and the complexity representation influences its robustness. The remaining failures leave open whether more refined measurements would suffice or additional factors are needed.

Large language models (LLMs) increasingly summarize clinical evidence, where a claim's weight depends on how strongly it is supported. Yet these models convey confidence poorly, and properties they never state, such as truth, are often readable from their activations. Whether a clinical model registers evidence strength, distinct from truth, and states it when asked is untested, and any such signal could be lexical. We compiled 45,134 clinical claims from six public sources, harmonized 20,611 into a four-level evidence grade under three independent frameworks, and tested 22 local, open-weight LLMs from several developers (0.6-70 billion parameters; general, medical, and reasoning), with lexical, truth, and cross-framework controls. A linear estimator recovered the grade in every model (median AUROC 71.8), yet decodability did not rise with scale and was weakest in reasoning models. The grade the models stated fell to chance, 25-27 percentage points below the estimator. The recoverable signal was largely lexical and did not transfer across topics or frameworks, yet it was distinct from factual truth and still flagged weakly supported claims (AUROC 69.2). Clinical LLMs thus carry an ordered evidence-strength signal they do not express, so their stated grades fail to convey a claim's support even when it is recoverable from their representations and text.

We show that net demand for liquidity by algo strategies is identifiable from its trade and price history alone, with no knowledge of its signal or optimization problem. An exact multi-period regret decomposition implies that the sign of this statistic classifies a linear strategy as a net liquidity consumer or provider, recovering the Kyle (1985) informed-trader/market-maker dichotomy from observables alone. Under an AR(1) cost process, the same statistic equals the product of strategy size and the squared Roll (1984) implied spread, making the correction a direct proxy for prevailing illiquidity. Extending to endogenous price impact and aggregating across N correlated strategies yields a liquidity-balance condition whose violation produces welfare loss scaling as N squared, a closed-form fire-sale externality. We calibrate to CRSP equity data (2016-2025), tracking implied spreads through the COVID-19 and 2022 rate-shock episodes, with an estimator computable in O(Tnd) time.

Short-fiber thermoplastic (SFT) composites are increasingly employed in lightweight aerospace and automotive structures owing to their favorable strength-to-weight ratio, high production rates, and recyclability. Unlike continuous-fiber systems, the mechanical response of SFTs is governed by mesoscale interactions among fiber orientation, spatial clustering, and manufacturing-induced porosity. These features exhibit significant spatial variability in manufactured components and influence stiffness, damage initiation, and nonlinear deformation. Although mesoscale finite element (FE) models can resolve such heterogeneity, their application to realistic three-dimensional microstructures remains computationally intractable. A data-driven surrogate framework is proposed to predict the mechanical behavior of additively manufactured, compression-molded (AM-CM) SFTs. Microstructures reconstructed from micro-computed tomography data were discretized into Voronoi-based cells representing distinct fiber-interaction neighborhoods. Each cell was homogenized via nonlinear FE simulations incorporating matrix damage, and the resulting stress-strain responses trained a hybrid Graph Neural Network-Long Short-Term Memory (GNN-LSTM) architecture encoding microstructural topology and history-dependent mechanical evolution. The surrogate accurately predicts stiffness and stress-strain behavior of unseen microstructures, achieving $R^2\approx 0.98$ relative to high-fidelity FE simulations with over two orders-of-magnitude reduction in computational cost. Coupling the framework with experimentally calibrated damage laws demonstrates that fiber orientation, clustering, and porosity collectively govern local effective stiffness. The approach provides a physics-informed, data-efficient pathway to identify mechanically weak microstructural cells and accelerate digital-twin development for SFT components.

Ovarian cancer is frequently diagnosed at an advanced stage, making preoperative contrast-enhanced computed tomography (CT) central to staging and surgical planning; yet the scarcity of annotated imaging data, compounded by privacy regulations, limits the development of generalizable computational models in this domain. Text-conditioned 3D CT synthesis has shown promise, but existing pipelines depend on paired radiology reports and have been evaluated only on chest CT. We propose OvESyn (Ovarian Evidence-based Synthesis), a framework that constructs standardized Findings and Impression sections directly from CT-derived imaging descriptors and routine clinical metadata, without any original radiology report, and uses them to condition a latent diffusion model adapted to 493 high-grade serous ovarian carcinoma patients. This is the first text-conditioned 3D CT synthesis framework adapted to an abdomino-pelvic oncologic setting. A systematic ablation over two adaptation axes, vision-language encoder alignment and generator fine-tuning, identifies generator domain adaptation as the operative mechanism for crossing the domain gap and establishing the target anatomy: without it, synthesis remains anchored to the thoracic pretraining domain, with Precision and Recall collapsing to zero and FID2.5D exceeding 140, regardless of encoder alignment. Encoder alignment instead refines intensity and fine detail. The full OvESyn attains the best distributional and intensity fidelity (FID2.5D 29.35, Precision 0.671, Wasserstein-1 0.044), while the generator-only variant maximizes coverage (Recall 0.645), reflecting a fidelity/coverage trade-off governed by encoder adaptation. Requiring only automatic segmentations and routine preoperative metadata, OvESyn supports transferability to report-scarce settings and provides a foundation for synthetic cohort generation in abdomino-pelvic oncologic imaging.

Unsupervised tabular anomaly detection requires methods that are accurate, robust across heterogeneous datasets, and computationally efficient. Classical statistical detectors are often efficient, but they usually rely on a fixed data view and a single notion of abnormality. Deep anomaly detectors can learn more flexible scoring functions, but they are substantially slower and difficult to tune in unsupervised settings due to the lack of a reliable supervisory signal. We propose RGLD, a randomized global-local density estimator for efficient unsupervised tabular anomaly detection. RGLD combines a global random-feature density branch, which identifies samples in broadly low-density regions, with a local neighbor branch, which detects samples that are weakly supported by nearby observations. Both branches operate over feature-bagged randomized views, allowing RGLD to expose anomaly evidence that may be hidden in any single representation. We conduct experiments on 47 tabular datasets against 23 statistical and deep anomaly detection baselines under fully unsupervised setting. RGLD achieves the strongest dataset-level AUROC performance, ranking 1st in dataset wins, and ranks 2nd in AUPRC wins. RGLD is also faster than all evaluated deep detectors, achieving 50x-580x speedups, and remains competitive with statistical methods in runtime, yielding a favorable accuracy-efficiency tradeoff.

Large language models (LLMs) are increasingly used to simulate social survey responses, yet their outputs exhibit systematic biases: marginal distributions are skewed, response variance is poorly calibrated, and predictor-outcome relationships are attenuated. We ask a simple question: given a small pilot sample of human responses, can an LLM recover the statistical characteristics of a broader population? We decompose recovery along three axes: structural fidelity, marginal fidelity, and individual fidelity. Using a COVID-19 misinformation survey as a case study, we benchmark three families of approaches: prompting, rectification, and fine-tuning. The findings suggest that fine-tuning on small pilot samples offers a balanced approach for achieving multiple forms of fidelity, but the levels of such fidelity can vary across subsamples, potentially threatening pluralistic alignment.

Model quantization is essential for the efficient deployment of Large Language Models (LLMs), but introduces a critical vulnerability: Quantization-Conditioned Backdoor (QCB) attacks. In these attacks, malicious behaviors remain dormant in full-precision models and activate only after specific quantization distortions, bypassing standard security audits. To mitigate this, we introduce FlipGuard, a proactive defense framework that selectively perturbs model weights prior to quantization. By breaking the adversary's precise alignment between weight patterns and quantization boundaries, FlipGuard suppresses backdoor activation without requiring access to training data or trigger samples. We further propose the Defense Effectiveness Ratio (DER), a unified metric to jointly evaluate security gains, utility preservation, and computational cost. Extensive experiments across seven LLMs (including StarCoder and LLaMA-family models) and three quantization schemes (INT8, FP4, NF4) demonstrate that FlipGuard effectively neutralizes QCBs across three scenarios, i.e., vulnerable code generation, content injection, and over-refusal, achieving high security with negligible performance degradation.

Reinforcement learning agents can exploit misspecified reward signals to achieve high apparent returns while failing on the intended objective, a failure mode known as reward hacking. Existing practical defenses typically constrain policy updates to stay near a known safe reference, creating a tension between suppressing hacking and permitting legitimate improvement. We propose Modification-Considering Value Learning (MCVL), which operationalizes the theoretical idea of current utility optimization for standard value-based RL. MCVL wraps an off-policy learner and treats each incoming transition as a candidate modification: it forecasts two training paths, one that includes the transition and one that does not, and scores both with a frozen bootstrapped-return estimator derived from a learned reward model and value function. The transition is admitted only if inclusion does not decrease the score. We formalize conditions under which this filtering is both safe and permissive, and instantiate MCVL with DDQN and TD3. Across four safety-relevant gridworlds and three modified MuJoCo continuous-control tasks with diverse hacking mechanisms, MCVL mitigates reward hacking while continuing to improve the intended objective. Project website: ktolnos.github.io/mcvl/.

In this study we present a formal definition of large discrete sets having, informally, three properties: their elements are easily recognized, easily generated, and the latter tasks are easily learned from examples. The formalism is specialized to sets of binary strings and a definition of "machine-learnability" based on the existence of a bounded-complexity Boolean autoencoder that fixes the elements of the set. We present experiments where the autoencoders are implemented by nets of Boolean threshold functions. Machine-learnability is demonstrated for Rorschach patterns (that may have reversed contrast in the mirrored half), and considerably "wilder" sets whose elements are only approximately fixed by admissible autoencoders. In the second case we demonstrate a simple iteration that evolves wild sets to make them properly machine-learnable.

Learning to bid in repeated multi-unit auctions with bandit feedback poses a fundamental challenge. Existing methods often rely on rigid explore-then-exploit schedules, assume stationary adversaries, and optimize solely for bidder utility, thereby limiting adaptability and strategic robustness. To address these limitations, we introduce the A3M framework, which integrates adaptive deep reinforcement learning (DRL), explicit adversarial reasoning, and principled multi-objective reward design for online auction strategy optimization. A3M employs an actor-critic DRL backbone to dynamically balance exploration and exploitation, an opponent model for fictitious play against non-stationary adversaries, and a composite reward function to jointly maximize utility, auctioneer revenue, and fairness. We provide the first comprehensive empirical evaluation of this integrated approach against established baselines in both discriminatory and uniform price auctions. Results show that A3M reduces final regret by 30–40% in standard settings, maintains robust performance against adversarial strategy shifts, scales favorably with the number of units $K$, and enables tunable multi-objective trade-offs. An extensive ablation study confirms the necessity of each core component. Our work establishes A3M as a powerful and flexible framework for learning in complex auction environments.

Behavior-cloned diffusion policies are expressive but remain vulnerable to covariate shift: small deviations from demonstrated states can compound into task failure. Existing methods address this either by expanding the training distribution through expert corrections or synthetic augmentation, or by steering a frozen policy at test time with guidance from a learned model. The former can be expensive or assumption-dependent, while the latter discards the corrected trajectories after execution. We introduce ReGuide, a self-improving framework that treats guided rollouts as reusable on-policy recovery data. ReGuide first uses Phase-Conditioned Guidance (PCG) to generate corrective rollouts: it constructs phase-specific latent targets, applies guidance only in the drifted-but-recoverable regime, and guides through the estimated clean action to match the dynamics model's training distribution. Successful guided rollouts are then absorbed back into the policy through ReGuide-FT, which fine-tunes the current checkpoint, or ReGuide-FS, which retrains from scratch on the augmented dataset; the two can also be composed and iterated. On Robomimic Can, Square, Transport, and Tool Hang, ReGuide improves base-policy success by $1.3$–$7.7\times$, outperforms LPB in the test-time-only setting, and matched-data ablations show that the gains come from guided recovery data rather than additional rollouts alone.

Venture capital (VC) investment decisions face distinct challenges, such as multi-source heterogeneous data, non-stationary time series, and the demand for explainable predictions in high-stakes, low-data settings. To overcome these issues, we introduce FinInvest-GTCN, a Graph-Temporal-Causal Network that redefines the task from content recommendation to quantitative risk-return assessment. This architecture combines a relational graph encoder to capture the investment ecosystem's topology, a multi-scale temporal fusion module to handle long-term dependencies and non-stationarity, and a causal decision head that generates risk-adjusted predictions with interpretable causal attributions. A core innovation is the Meta-Causal Adaptation (MCA) strategy, which facilitates robust fine-tuning for new, data-scarce sectors by aligning updates with causally-plausible structures derived from meta-pretraining. Comprehensive experiments on proprietary VC datasets show that FinInvest-GTCN delivers state-of-the-art results, markedly lowering the primary Risk-Adjusted Mean Squared Error (RA-MSE) to 2.51 from a baseline of 3.05 and boosting the cumulative return of a simulated portfolio by 18.7%. Ablation studies underscore the essential role of each component, while additional analyses confirm the model's stability, interpretability, and enhanced adaptability. This work pioneers a data-driven, explainable framework for investment decision support.

Large language models have driven recent progress in language and multimodal AI, yet pre-training them at scale is prohibitively expensive. Low-rank pre-training, which factorizes each weight matrix into a rank-r product to reduce both parameters and FLOPs, is a promising response but typically lags full-rank training in quality. We propose Duplicated Latent Residual (DLR), a training-only, parameter-free, foldable plug-in for low-rank pre-training. DLR augments the standard low-rank output Bz with a fixed structured residual alpha/sqrt(K) * Expand_K(z) that replicates each latent coordinate K = ceil(d_out/r) times across the output. With alpha fixed, DLR adds zero learnable parameters per layer; after training, it is absorbed into the up-projection in closed form, B* = B + alpha/sqrt(K) R^T, so deployment parameter count, FLOPs and memory match the underlying low-rank backbone exactly. Across LLaMA models from 60M to 7B parameters, DLR strengthens low-rank pre-training on C4 validation perplexity in most settings, with the clearest gains at 130M and above; folded checkpoints transfer cleanly to supervised fine-tuning on standard benchmarks.

Cybersecurity is a real-life test-bed for many machine learning problems at once, especially when considering modern strides in using Large Language Models (LLMs) to automate processes as “agents.” Cybersecurity workflows require orchestrating hundreds of standard and bespoke tools through various formats. The scale of cybersecurity data is enormous; for example, a single malware sample can be viewed as a sequence of billions of tokens. The cost of labeling any file by experts is enormous and labor-intensive, in part because an adversary (possibly a well-funded nation state actor) is attempting to subvert your detection methods. Even skilled experts may disagree on the correct label, creating ambiguity in what constitutes ground truth. When deployed, models must run quickly on billions of items a day, where low-latency is critical for operational success, in a continuously changing environment. In addition, explainability is not optional: analysts demand clear reasoning for model decisions to cope with the large number of false-positive alerts they face daily, and to quickly develop remediation and understand how something went wrong. In short, the amount of complexity cybersecurity is greater than that of natural language and computer vision, and thus we posit that cybersecurity is the better test-case for general AI progress than other, well-studied fields.

In-context learning (ICL) is an emerging paradigm that employs the semantic information inherent in large language models (LLMs) for generating answers to user queries. While the remarkable performance of ICL has been widely known, a general modeling and a rigorous theoretical analysis of this paradigm are still lacking. This work presents a probabilistic model for ICL and derives the performance of ICL for both general parametric distributions and exponential families. Based on the derived results, the work explains the impact of multiple factors such as the number of demonstrations, the sensitivity of the probabilistic model to the variation of its parameters, as well as the similarity between the demonstrations and the query on the performance of ICL.

Tool and agent routing from natural-language prompts is naturally a set-valued prediction problem: a single query may require multiple agents, while over-selection increases execution cost. The benchmark introduced here is derived from WildChat and contains 3,000 prompts over a fixed 12-agent catalog, with AI-assisted heuristic labels under a fixed schema and controlled rebalancing for multi-label evaluation. The evaluation protocol combines set-level metrics (Precision, Recall, F1, Jaccard, and Exact Match), latency, an execution-oriented capability-coverage simulation, and a constrained weighted-routing setting based on ordinal agent-cost tiers. Compared methods include nearest-neighbor matching, linear multilabel classification, dependency-aware baselines, a fine-tuned encoder, deterministic weighted post-scoring via Weighted Agent Routing (WAR), and a zero-shot LLM baseline. Results show that supervised routers substantially outperform nearest-neighbor and zero-shot LLM routing. The fine-tuned encoder achieves the strongest unconstrained set accuracy, while the linear multilabel model provides the strongest practical baseline. In the constrained setting, the weighted routing layer improves utility when applied on top of strong supervised scorers, with the largest gain observed for Encoder+WAR. Overall, the benchmark and evaluation protocol support reproducible study of accuracy-cost trade-offs in fixed-catalog multi-agent routing.

Detecting security threats in an organization's cloud computing environment has become necessary due to the increased reliance on cloud infrastructure. Logging of all cloud computing events enables investigation into any incidents after they are detected. Automated detection of threats using the logs based on heuristics or anomaly detection could result in a high false positive rate due to its relatively static nature. In this article, we present an industrial case study of a self-supervised learning method using graph neural networks applied to AWS CloudTrail logs to surface suspicious events for analyst review. The model produces an anomaly score for each event and dynamically adapts to changes in the organization without requiring periodic retraining. Based on our experiments across five organizations, the proposed model produced substantially fewer alerts than a domain expert rule-based baseline in almost all cases, reducing alert volumes to approximately 1 per hour from thousands generated by traditional methods. We note that this evaluation covers only flagged events, and false negatives cannot be estimated from the current data; findings should therefore be interpreted as a practical deployment study offering insights into real-world constraints rather than a fully validated detection system. We discuss these limitations and the requirements for extending the approach to other cloud environments as future work.

Lightweight Directory Access Protocol (LDAP) is a protocol that allows users to query and modify Active Directory (AD) data. By default, all users have read access to all AD data through LDAP, making it a common initial tool for reconnaissance when a threat actor first compromises an identity. To capture threat actors early in the reconnaissance phase, we developed two machine learning frameworks to detect LDAP reconnaissance: an ML classifier to predict malicious LDAP queries and an ML-based data-mining method to extract malicious query signatures. By correlating LDAP queries with endpoint detections, the first framework uses weak supervision to label a massive dataset and classify LDAP queries as malicious or benign. For immediate deployment, a second technique was developed on top of this approach to employ a rigorous statistical hypothesis-testing framework for mining novel, malicious LDAP signatures. While this weakly supervised approach is limited compared with manual human labeling, it is more practical for this use case because it leverages large-scale automated corpus construction, reducing costs and time. Ultimately, both the LDAP classifier and the ML-based LDAP signature mining method achieved performance benchmarks, with the classifier achieving up to a 65% True Positive Rate (TPR) on the holdout set while limiting false positives, and mined signatures demonstrating 81.48% field precision with CrowdStrike's Managed Detection and Response team.

Machine-learned (ML) operator models can be trained to predict density functional theory (DFT) Hamiltonian/density matrices at significantly reduced computational cost, thus extending electronic-structure calculations to previously unfeasible scales. Here, we introduce MALOQ (Massively Accelerated Learning of Operators for Quantum Transport), an application built to train on and predict electronic-structure matrices for systems made of few to 100k atoms, described by large basis sets, and covering a wide range of atomic elements. Based on a state-of-the-art, SO(2)-equivariant backbone architecture, MALOQ provides (i) custom data-processing kernels to handle high-rank Hamiltonian matrix data and (ii) a scalable edge-wise distribution of atomic graph(s). Trained on the largest molecular Hamiltonian datasets available today, it reduces time-per-epoch by over 30% compared to a molecule-wise-distributed framework, and enables inference on material graphs of arbitrary size. We demonstrate scalable training and inference for 3,000-12,000 atoms on the Alps supercomputer, up to 192 GPUs and 256 GPUs, respectively.

Synthetic aperture radar (SAR) data augmentation is important for improving the generalization of data-driven SAR interpretation models, yet practical augmentation workflows are often hindered by heterogeneous dataset formats, task-dependent metadata requirements, diverse generation methods, and weak validation of generated samples. This paper presents the SAR Augmentation and Generation Agent (SAGA), a schema-grounded and benefit-aware agent framework for task-oriented SAR data generation and augmentation. Given a natural-language request and heterogeneous SAR inputs, SAGA extracts observable dataset facts, validates executable dataset schemas, selects feasible augmentation strategies through validator-constrained planning, and compiles the selected strategy into an auditable augmentation workflow. Generated data are further assessed by quality, distribution, SAR-artifact, duplicate, leakage, and optional downstream-task evaluators to support evidence-qualified augmentation claims. By separating semantic proposal from deterministic validation and execution, SAGA improves the reliability and reproducibility of SAR augmentation decisions. Experiments on controlled agentic benchmarks and downstream SAR interpretation tasks show that SAGA improves schema grounding, skill planning, invalid-sample rejection, and downstream augmentation utility compared with rule-based, LLM-only, ReAct-style, and fixed-augmentation baselines.

Predicting student performance and characterizing metacognitive calibration are essential for personalization in intelligent tutoring systems. Prior research treats performance prediction, calibration error calculation, and variance decomposition as separate pipelines, preventing unified interpretation. I propose the Unified Behavioral Prediction and Calibration Analysis Pipeline (UBP-CAP), an integrated framework processing student pre-execution behavioral telemetry through three linked modules: (1) a LightGBM classifier with SHAP for binary correctness prediction, (2) formal calibration metrics (ECE, MCE, and Brier score decomposition) to evaluate metacognitive alignment, and (3) a crossed Generalized Linear Mixed-Effects Model (GLMM) for decomposing calibration deviations. I introduce the Predictive-Explanatory Divergence Index (PEDI), which quantifies structural divergence between predictive and explanatory feature profiles. Evaluated on 1,195 interaction records (27 students, 45 tasks), Logistic Regression achieves AUC-ROC = 0.903, outperforming LightGBM (0.878). Student naive ECE (0.109) significantly exceeds model ECE (0.068), confirming systematic miscalibration. The crossed GLMM yields ICCStudent = 0.123, showing calibration is situational rather than dispositional. PEDIcos = 0.081 (p = 0.327) indicates structural alignment between prediction and explanation on shared behavioral features.

The adaptive moment estimation algorithm, known as Adam, is widely used in modern machine learning, owing to its low per-iteration complexity and strong empirical performance. Despite its prevalent use, the theoretical foundation of Adam remains largely unexplored for time-varying and nonstationary systems. In fact, the existing theoretical analyses of Adam-type algorithms are primarily concerned with time-invariant model parameters and explicitly or implicitly rely on independent and identically distributed (i.i.d.) data assumptions, under which the learning taskcan be formulated as minimizing a fixed expected objective with a static minimizer. However, such assumptions are often violated in time-varying and nonstationary systems, thereby calling for a theoretical investigation beyond the conventional yet idealized i.i.d. setting. The main objective of this paper is to solve this challenging problem by establishing a general theory of Adam for time-varying and nonstationary stochastic systems. We will introduce some new techniques for analyzing the products of nonstationary and dependent random matrices induced by Adam's coupled first- and second-moment recursions, and will construct a new stochastic Lyapunov function that blends these two moment dynamics. Under a stochastic excitation condition that allows nonstationary and dependent data, we will derive both parameter tracking and output prediction error bounds explicitly, quantifying the effects of stepsize, first- and second-momentum parameters, gradient noise and parameter drift. These bounds not only provide guarantees for Adam performance, but also provide guidelines for hyperparameter selection. Experiments on both synthetic and real-world data validate our theory and design guidelines.

Memory-Mediated Learning Architecture (MMLA) separates slow base parameters theta, a bounded numerical policy carrier Phi, and a bounded authoritative memory M. Predictive Dual-State Adaptation (PDSA) lets feedback update Phi while one problem remains active and lets a trusted lifecycle atomically commit one typed row or exact NULL. Later reasoning may read both states, but their writers, resets, rollback domains, and ledgers remain distinct. Realized futures supervise values only during training; deployment is causal and future-blind. We give conditional theory and falsifiable contracts for reasoning-time updates, completed-segment consolidation, predictive admission, authoritative memory, and dual-state attribution. Assumptions, counterexamples, capacity and cost ledgers, recovery duties, and identifying experiments are explicit; these are not implementation guarantees. Controlled studies show exact lifecycle execution on 300/300 held-out records for each of three seeds, calibrated retrieval gains over frozen-hidden dense and BM25 baselines, and exact typed anchor-filler transport on 240/240 held-out records per seed. These validate restricted components, not natural-language memory management or complete PDSA. Post-training studies retain positive and negative evidence. Later protocols obtain restricted readout progress, but a nine-trajectory comparison finds that matched latent readout, a full-width bridge, and bridge plus frozen text-teacher alignment all fail continuous-event qualification across both task families. A separately adapted text reference and restoration checks pass. At the September 13, 2026 evidence cutoff, no strict policy-only reasoning-time-training effect, predictive-admission oracle margin, learned future-blind admission policy, or policy-by-memory factorial advantage is established.

Predicting the aerodynamic performance (e.g. lift, drag, and moment coefficients) of an aircraft is challenging – computational models are biased and direct simulations are prohibitive. A pragmatic way to overcome this limitation is by calibrating low-fidelity computational predictions with experimental measurements. This, however, requires calibrating against sparse measurements contaminated with uncertainty in both the control inputs and the measured aerodynamic response. We develop a methodology to address this problem based on Gaussian process surrogates and the classical Kennedy-O'Hagan calibration. A surrogate model learned on abundant-but-cheap low-fidelity data is calibrated with a sparse set of measurement data. Crucialy, we develop a Bayesian latent Gaussian process based approach that marginalizes the calibrated surrogate model over the input uncertainty, while also matching the marginal mean and variance of the measured output uncertainty. Once calibrated, our surrogate model predicts the uncertainty in aerodynamic coefficients with very high accuracy, including at extrapolative input settings. We validate our calibrated surrogate model predictions against measurement data with true uncertainty intervals to demonstrate that the model places $94.2-95.8\%$ of its predictive samples inside the released $95\%$ truth intervals, with endpoint cumulative probabilities very close to the nominal 0.025 and 0.975 levels.

The common factor analytic model is related to Helmholtz and Boltzmann machines, can be conceived as a linear autoencoder, or can be thought of as a single-hidden-layer generative neural network. We thus consider it a basal generative representation learner that can be used as a minimal model for studying the foundational characteristics of (deep) generative model architectures. We focus on the fundamental problem of indeterminacy in latent factor projections. This indeterminacy implies that, even when the intrinsic dimension of the latent vector is known, regularity conditions are met, and rotational indeterminacy is resolved, an inherent indefiniteness in the retrieval of causative latent sources remains: they will be uncertain, distributionally deviant, and non-unique. This can have major implications for data representation but remains an elusive issue, even to practitioners and theorists well-versed in the factor model. Moreover, this classic psychometric problem is intricately related to the modern issue of latent variable collapse in the variational autoencoder framework for deep generative modeling. Here, we assess this indeterminacy from various perspectives and show how these are mathematically and conceptually related and we discuss subsequent implications for the Psychometrics, Statistics, and Artificial Intelligence communities. We show that one has latent factor determinacy across all its facets when the feature-dimension grows to infinity. This feeds into an essentially distribution-free estimation approach in the sample case when the number of features grows very large. We conclude, as these are emergent properties at scale, that the factor model is suited for representation learning of very-high-dimensional data.

We introduce the Contagion Tensor, a measurement framework for quantifying how large language model (LLM) output distributions couple across modalities, agents, and time steps. From the tensor we derive the Coupling Amplification Factor (CAF), a family of ratio-based metrics sharing the form CAF = E[T_condition] / E[T_baseline], providing unitless, baseline-referenced measurement with bootstrap confidence intervals. We instantiate CAF in four variants and evaluate the strongest in a complete 2x2x2 block-orthogonal simulation design with modality-specific ablation. The ablation reveals that an apparent image-condition super-linear effect (CAF = 1.40) collapses to sub-linear (CAF = 0.87) when the image perturbation module is disabled, a shift of -0.53 with zero effect on text conditions. We supplement with real-API experiments across two model families: DeepSeek-Chat (R=30) and GPT-4o-mini (R=15, real vision). Under uniform personas, text-only communication produces CAF approx 1.0 in both models. Diverse personas drive convergence (CAF = 0.88). A within-model comparison on GPT-4o-mini reveals: C3 (text) CAF = 1.02 vs. C5 (real vision, R=30) CAF = 1.72 [1.700, 1.733], delta = +0.70, validating the simulation's super-linear image-condition prediction. Of 11 conditions, 5 have been tested on real APIs and 6 remain unverified. Our contribution is two-layered: (1) a measurement instrument that makes output-distribution coupling quantitatively falsifiable; and (2) a transferable ablation protocol that any modular multi-agent simulator can adopt to distinguish genuine coupling from design artifacts.

Federated Learning (FL) emerged as a promising distributed machine learning paradigm. However, extending FL to the class incremental learning scenarios introduces unique challenges: 1) Capacity conflict and catastrophic forgetting from the shared model overloading, 2) Heterogeneity from Non-Independent and Identically Distributed (Non-IID) data, and 3) Synchronized class misalignment. In this paper, we propose Fisher-Routed MiXture of Experts for Federated Class-Incremental Learning (FedFMX), a novel framework to address these challenges via adaptive expert specialization across clients. The crucial insight is to route each sample to an expert subset that jointly optimizes knowledge acquisition and retention. Specifically, we introduce a Fisher-Routed Expert Scoring (FRES) module to estimate expert importance via Fisher-based stability cost and gradient-based plasticity gain. Then, we design an Adaptive Expert Selection (AES) module by quantifying marginal contributions for adaptive expert subset determination. Finally, by the routing-aware regularization (RAR), we achieve load balance and efficient FL training. We theoretically prove the $\mathcal{O}(T^{-1})$ convergence rate. Extensive experiments on multiple benchmarks compared with state-of-the-art methods demonstrate the superiority of FedFMX.

Quantum kernel estimation on near-term hardware is shot-budgeted: every entry of the kernel Gram matrix is a Bernoulli expectation that must be sampled with a finite number of circuit executions. Recent work on quantum kernel classification has shown that allocating shots non-uniformly across kernel entries, weighted by their downstream task sensitivity, can reduce the shot budget required to reach a target accuracy. We extend this idea to Gaussian process (GP) regression, a setting whose downstream quantities (full-spectrum posterior variance, log-determinant, marginal likelihood) couple to kernel error more tightly than the sign-only outputs of classification. We derive three closed-form pair-level sensitivities predictive coupling $|\alpha_i\alpha_j|$, leave-one-out residual, and marginal-likelihood gradient and plug them into a Neyman-style minimum-variance allocation rule. To prevent catastrophic over-concentration when the warm-up sensitivity estimate is itself noisy, we add a high uniform coverage floor justified by a Frobenius lower bound on the missing-entry perturbation. On four UCI benchmarks and two synthetic RBF + Bernoulli controlled studies, the resulting allocator delivers $10$–$21\%$ test-RMSE improvement over uniform allocation across the moderate-budget regime. The gain transfers (i) to genuine ZZ and Pauli-Z quantum kernels on quantum-natural data ($-13$–$15\%$ at low budget, $p<0.05$ paired) and (ii) to four downstream tasks (Bayesian quadrature, heteroscedastic regression, hyperparameter learning, multi-output Cokriging). On UCI features embedded into a ZZ kernel the gain disappears, consistent with the exponential-concentration regime where shot allocation has nothing to exploit.

Long-context LLM inference faces a fundamental conflict: head-adaptive compression algorithms (e.g., Top-$p$ nucleus sampling) offer superior accuracy by dynamically fluctuating memory budgets, yet modern inference engines (e.g., vLLM) demand rigid, static memory patterns to leverage CUDA Graphs and PagedAttention. We resolve this “Static-Dynamic” mismatch with HARD-KV, a unified framework that that bridges dynamic selection with rigid system constraints. HARD-KV introduces a Cascade Cache hierarchy, managing the token lifecycle across dense, sparse, and condensed tiers. Crucially, we propose a Logits Calibration mechanism that normalizes diverse importance metrics into a unified probability space, enabling consistent Top-$p$ budgeting across heterogeneous heads. To bridge the efficiency gap, we offer a system-level solution, which rewrites fragmented, dynamic indices into contiguous physical layouts compatible with high-performance inference engine. Extensive experiments on math-reasoning benchmarks (AIME, U-Math) verify that HARD-KV achieves up to 2$\times$ throughput improvement over static baselines while maintaining high-fidelity generation in 10k+ token scenarios. Code is available at https://github.com/SuDIS-ZJU/HARDInfer.