Papers

The test suites used as RLVR rewards for code have natural false positives: per-task, persistent, asymmetric errors that accept the same wrong programs every time they appear, unlike the symmetric or resampled noise assumed by existing noise-robustness analyses. We run a preregistered two-arm causal contrast on a deployed suite: GRPO on identical MBPP tasks, seeds, and compute, rewarded by the original MBPP tests (leaky) versus the MBPP+ extra tests (hardened). Two further families replicate the design under a preregistration frozen before their data existed. [C] The average held-out effect is bounded: non-inferior under a preregistered 1.5-pt margin (gap 0.20 pt, one-sided 95% upper bound 0.75 pt). [C] Rewarded false-positive mass tracks a cheap static leakiness audit computed before training (Spearman 0.80), and the registered train-side test puts the leak-stratum FP share +43.8 pt above clean tasks. [E] Auditing every rewarded FP under signed, human-adjudicated rules finds a large residual of verified genuinely wrong code: 47.57% record-weighted; both replication families reproduce a large share. The reward paid for real bugs, not merely suite artifacts. [E] Mechanism evidence is consistent with selection of pre-existing error modes rather than learned exploitation: FP incidence does not grow within our horizon, and untrained base models already produce the same wrong outputs under the leaky filter. We then turn the same instrument on the frontier judges themselves: on their own false positives they self-assess only weakly, a same-author test is unresolved, and even the highest-scoring reader we probe stays far below its score on a weaker policy's errors – two subjects on MBPP, licensing nothing about frontier models in general. A cheap static audit locates exposure before training; hardening the reward removes the measurement inflation, though here it buys little capability.

Continual learning is a long-standing capability gap between LLMs and humans. Writing new knowledge into a model's weights routinely causes it to forget old knowledge, commonly denoted as "catastrophic forgetting". Various modifications of supervised fine-tuning and distillation aim to mitigate catastrophic forgetting, but quantifying what (or how much) information was forgotten is often difficult. In this paper, we study whether current methods of writing knowledge into weights enable models to learn continually without forgetting. We introduce a framework for studying continual learning in the iterative regime, writing invented facts one at a time into a Qwen3 model already modified by previous writes, and varying the training data, method, and parameter update. Across SFT and off- and on-policy distillation, using LoRA or full fine-tuning, we compare repeated statement training (the same fact repeated in two formats) with varied example training (24 factual restatements) and find that varied examples comprehensively support more flexible use. After twenty sequential writes and merges, the model answers only 1% of questions about earlier facts correctly when every write uses repeated statements, compared with 46% when every write uses varied examples. We additionally show that this retention depends on the data used for the later writes, regardless of training method or parameter update, and that behavioral forgetting of an earlier fact does not erase its presence from the log-probabilities. Together, our framework neatly provides a comparison of performance across training data, training regimes, and parameter update schemes in an iterative learning task.

Data re-uploading parameterized quantum circuits (DRU-PQCs) are universal function approximators, yet their expressivity produces oscillatory, non-convex loss landscapes that resist gradient-based optimization. We show that the primary optimization bottleneck in DRU-PQCs is not insufficient capacity but a structural failure mode we term Fourier locking (FL): because encoding weights and entangling layers are nonlinearly coupled, random initialization on high-frequency targets collapses the encoding parameters into spurious local minima. Two Fisher diagnostics characterize FL. The input-space quantum Fisher information $F_x$ measures the effective frequency content of the encoded state; the Fisher discriminant ratio of the measured features measures their alignment with the class labels. In two independent 50-seed experiments, the locking is literal: trapped circuits hold $F_x$ frozen for the entire run, while escaping circuits migrate their frequency content (direct training: $r_{pb} = -0.48$; curriculum: $d = 1.34$; both $p < 0.001$). The replicated signature is this spectral mobility, not any endpoint value of $F_x$, and trapped circuits retain a fully non-degenerate parameter-space QFIM ($r_{pb} \approx 0$): the failure is spectral misalignment of a responsive state, not a loss of geometric sensitivity. A frequency-staged homotopy protocol that paces the target frequency ($f: 1.0 \to 3.0$) convexifies the early loss landscape; escaping circuits raise $F_x$ in step with the curriculum, and the escape rate triples (18% vs. 6%). Fourier locking is a frequency-alignment problem, and its remedy is frequency pacing.

Few-shot multimodal classification commonly attaches a lightweight head, such as $k$-nearest neighbors, logistic regression, or a linear SVM, to a frozen pretrained encoder. Although computationally efficient, these heads can produce poorly calibrated confidence scores. We ask whether TabPFN can provide reliable confidence estimates on multimodal embeddings without sacrificing predictive accuracy, and under what conditions. We systematically evaluate TabPFN as a zero-gradient head for frozen image, text, and audio encoders. Across 22{,}820 evaluation episodes spanning 14 datasets, 11 encoders, and three modalities, TabPFN achieves the best mean rank among nine classification heads on both negative log-likelihood (NLL) and expected calibration error (ECE). At a representative setting, it reduces NLL by 48–62% and ECE by 2.1–5.3$\times$ relative to the average of eight baselines while matching or exceeding their average accuracy. This calibration benefit transfers broadly, whereas the accuracy advantage is conditional: it concentrates at moderate-to-high shot counts and low-to-moderate feature dimensions ($k \ge 50$, $d \le 32$), and diminishes when labeled data are scarce, feature dimensions are high, or competing methods approach ceiling accuracy. After backbone adaptation, replacing the trained linear head with TabPFN improves calibration while preserving competitive accuracy, showing that representation adaptation and reliable head choice are complementary. Together, these results identify when TabPFN can serve as a training-free head for calibration-sensitive multimodal classification. To support transparency and reproducibility, we publicly release the source code, experiment configurations, and evaluation scripts in our GitHub repository: https://github.com/Jingxiang-Zhang/tabpfn-multimodal-embeddings.

This paper develops a model-free reinforcement learning framework for continuous–time extended mean field control problems, where both the dynamics and reward may depend on the joint distribution of states and controls. We adopt deterministic feedback policies, under which the state–action distribution is induced directly as a push–forward of the state law. This avoids optimization over stochastic kernels and bypasses key limitations of existing approaches in extended mean field settings. We first establish a model–free sensitivity formula for parameterized McKean–Vlasov dynamics and use it to derive a deterministic policy gradient formula expressed through an advantage–rate function on the Wasserstein space. We then refine this formula by introducing local value and advantage–rate representations that depend on the state, action, and joint state–action distribution, yielding a policy gradient that includes both action derivatives and measure–derivative terms with respect to the control distribution. These characterizations lead to a martingale–based learning principle and motivate a continuous–time deep deterministic policy gradient algorithm combining particle approximations, measure–dependent neural networks, temporal–difference learning, and exploration in either action or parameter space. Numerical experiments on stochastic Cucker–Smale consensus control and optimal liquidation with trade crowding demonstrate the efficiency, stability, and robustness of the proposed method, including problems with explicit dependence on the control distribution.

Zero-dimensional reduced-order models (0D ROMs) are central to multi-dimensional design workflows for high-end complex equipment. However, the planning process currently relies on manual expertise, limiting topological exploration and prolonging iterations. Even traditional optimization methods such as Genetic Algorithms (GA) are typically confined to local parameter tuning. Although Large Language Model (LLM) agents have shown promise in exploring large sample spaces, and frameworks such as Chain of Thought (CoT) and Reason and Act (ReAct) improve reasoning reliability, while Retrieval-Augmented Generation (RAG) overcomes domain knowledge barriers, a single agent still falls short for the long-horizon and highly coupled nature of complex 0D ROM planning. This paper proposes the Zero-dimensional reduced-order model CO-Planning framework (Z-COPA), a multi-agent architecture featuring a Symbolic Action Graph Engine (SAGE) and a MILP-Guided Navigation (MGN) optimizer. Its core innovation is a dedicated graph representation method that accurately encodes the 0D flow network topology, converting the empirical planning process into a rigorous graph structure optimization problem. We validate the forward and inverse design capabilities and generalization performance of Z-COPA on two real aircraft engine secondary-air systems, two IEEE power-distribution reconfiguration benchmarks, and two water-distribution network benchmarks. The results show superior task completion quality, obtaining the best performance in both forward and reverse design of air systems. Z-COPA disrupts the traditional 0D model planning paradigm, providing a new technical approach for exploring broader topological space and achieving highly automated, globally optimal air system architectures.

Existing Stochastic 3D Human Motion Prediction models are fundamentally constrained by hard-coding the skeleton kinematics, severely limiting generalization, preventing cross-dataset training, and requiring complex data retargeting. We introduce EquiFusion, the first kinematics-agnostic model to solve this bottleneck, implementing a latent diffusion model with a permutation equivariant architecture. EquiFusion treats the kinematics' connectivity as an explicit input parameter, ensuring its internal computations are inherently agnostic to joint ordering and graph structure. This novel design enables truly cross-dataset generalization to unseen kinematics and unlocks novel zero-shot directions, such as motion prediction from partial or occluded observations and targeted limb generation. EquiFusion achieves state-of-the-art results on major benchmarks, being up to 75% more compact than previous kinematics-specific methods, while achieving faster training and inference. EquiFusion thus establishes a new, flexible standard for robust human motion prediction. Model and training code are available at https://ceveloper.github.io/publications/equifusion/.

Federated learning distributes data among $n$ clients, making it vulnerable to malicious attacks and data heterogeneity, which together pose challenges for robust learning. To tackle this issue, centered clipping and Huber aggregators have been exploited for Byzantine robustness. In this paper, we first demonstrate their equivalence via convex conjugate theory, and show that they can yield biased solutions in the presence of outliers, leading to failure under high data heterogeneity and a substantial fraction of outliers. Next, we propose a new robust aggregation rule that utilizes the truncated-quadratic (TQ) loss, effectively mitigating the biases of existing methods, such as centered clipping and Huber aggregators. We show that our aggregator achieves order-optimal Byzantine-robust learning under nonconvex loss functions and heterogeneous data, ultimately enhancing the reliability of federated learning systems. Additionally, we provide a robust deviation estimation strategy for TQ, demonstrating its effectiveness. Furthermore, we show that TQ maintains robustness even when only an estimate of the number of Byzantine clients is available. Finally, experimental results on MNIST, Fashion-MNIST, and CIFAR-10, indicate that our aggregator provides better robustness performance than the competing techniques.

Given a large graph, how to generate a compact summary graph that is configurable by the user and supports multiple graph queries with either no loss or with high accuracy? The ever growing size of graph datasets makes the above question on graph summarization very pertinent. Although, there are several approaches, there does not exist a configurable graph summarization method that offers high compression along with support for multiple graph queries on the summary graph with high accuracy, and allows the user to configure the summarization based on: (1) lossless or lossy summarization, (2) amount of tolerable neighborhood loss, (3) the type of loss it can tolerate, in terms of false positive edges (i.e., extra edges), false negative edges (i.e., missing edges), or neither, in both the (a) reconstructed graph and the (b) query answers. To overcome these limitations, we propose a novel graph summarization framework CGS (Configurable Graph Summarizer) that builds upon the idea of aggregating nodes with common neighborhoods. The CGS framework consists of three summarization variants, CGS-E, CGS-I and CGS-U. While CGS-E is a lossless scheme, CGS-I and CGS-U are lossy schemes that allow reconstruction of the input graph with no false positive edges and no false negative edges, respectively. To bound the graph reconstruction loss, we introduce a user-specified parameter neighborhood loss tolerance threshold, that limits the maximum loss allowed in the neighborhood of each node. This allows graph reconstruction and neighborhood query evaluation with either no loss or with bounded loss guarantees. Empirical evaluation on several synthetic and real-world graphs shows that CGS offers superior summarization than the state-of-the-art methods, and can answer graph queries with fairly high accuracy and efficiency.

We study the problem of efficient online proportional sampling from a high-dimensional domain under a $\sigma$-smoothed adversary, where the sampling distribution is induced by a dynamically evolving weight function defined over a sequence of piecewise-structured partitions. This setting captures a broad range of applications, including principal-agent games (e.g., pricing and contract design), and algorithm configuration and parameter tuning. The central challenge is maintaining an efficient data structure as the induced partition grows increasingly complex over time – naively, the number of subregions can grow as $O(t^d)$ by round $t$ in $d$ dimensions. We design a data structure that supports efficient updates and proportional sampling while avoiding the cost of explicitly maintaining this exponential growth, where the discontinuities are structured from axis-parallel hyperplanes. Under a $\sigma$-smoothed adaptive adversary, we prove a tight $O(\sqrt{\sigma T})$ bound on the depth of our data structure, and an $O(\log T)$ bound under a random-order adversary – to our knowledge, the first such results for this class of problems. We apply this framework to online learning with piecewise-structured rewards, obtaining efficient no-regret algorithms under both full-information and bandit feedback, with provable sublinear regret guarantees.

Understanding fracture behavior is critical for assessing the structural integrity and longevity. Highly time-consuming physics-based fracture simulations motivate the development of machine-learning-based fracture evolution prediction with surrogate models. However, most existing machine-learning models for fracture prediction operate as black boxes and require large training datasets to generalize reliably. In this work, Thermodynamically Consistent Latent Dynamics Identification (tLaSDI) for parametric systems is introduced to predict fracture patterns and evolution in heterogeneous materials. The model learns the thermodynamic state variable in a lower-dimensional latent space using parametric GENERIC Formalism-Informed Neural Networks (pGFINNs) that enforce key thermodynamic principles, such as total energy conservation and entropy generation. This model embeds physics into the neural network architecture using a hard-constraint method that inherently complies with the underlying thermodynamic principles. The proposed tLaSDI-pGFINNs is further enhanced by a Geometry-Conditioned Autoencoder in learning the geometry configuration for effective geometry-guided learning. The energy and entropy evolution histories demonstrate that the model preserves the thermodynamic constraints on unseen testing samples. The results further show that tLaSDI-pGFINNs can more accurately capture both fracture patterns and the subsequent fracture evolution than the purely data-driven Autoencoder Long Short-Term Memory (AE-LSTM) model.

Large language models (LLMs) and agentic AI systems are increasingly being explored for domain-specific maintenance and prognostics tasks, raising the question of whether they can effectively support prognostics and health management (PHM). In this paper, we investigate remaining useful life (RUL) estimation with multimodal large language models (MLLMs) grounded through time-series retrieval. We propose a framework in which historically similar degradation segments are retrieved from the training set and, together with the test trajectory, transformed into a visual comparison artifact that is processed by the MLLM through a structured multimodal prompt. The approach is evaluated on the FD001 partition of the C-MAPSS benchmark under repeated experiments comparing retrieval-based inference against a non-retrieval baseline based on random reference selection. The results show that time-series retrieval consistently improves MLLM-based RUL prediction across the evaluated models, yielding lower error and more stable performance. At the same time, the magnitude of the benefit depends on model capacity, indicating that retrieval is most effective when the underlying MLLM is able to exploit the retrieved evidence. Overall, the study shows that time-series RAG is a promising mechanism for improving multimodal prognostic reasoning, while also highlighting the current limitations of MLLM-based RUL estimation in practical PHM settings.

Remaining useful life prediction for aircraft centrifugal air compressors in real commercial operations poses challenges that controlled benchmark datasets do not expose. In-flight sensor signals superimpose genuine degradation on continuously varying operating conditions, and no channel can be assumed a priori to carry a reliable degradation signature. Moreover, models trained on one subset of a fleet generalize poorly to unseen aircraft and installation positions, a cross-domain problem of underappreciated practical severity. This paper presents a framework combining physics-guided processing with adaptive temporal encoding. A population-level selection procedure identifies surge margin as the most consistent degradation indicator across the fleet. Operating regime filtering and windowed aggregation recover the health trend from operational noise, and two physically motivated features encoding current health level and cumulative degradation rate enable cross-unit comparison without absolute signal values. Sinusoidal positional encoding provides lifecycle context without data leakage, and a structured cross-domain evaluation identifies encoding period mismatch as the primary mechanism of performance loss under fleet transfer. An adaptive recalibration scheme estimates each target unit's lifecycle scale from early observations alone, requiring no future information or labeled target data. The approach yields substantial, consistent gains in cross-domain accuracy across transfer scenarios of increasing domain distance, and a Gaussian Process Regression model further provides calibrated uncertainty estimates supporting risk-informed maintenance scheduling.

Reinforcement learning with verifiable rewards (RLVR) can improve one-sample accuracy while making a model worse under repeated sampling. We study this pass@k inversion: after training, the policy may solve fewer distinct problems than its base model at large $k$. The failure concentrates on boundary prompts, where the base model contains rare correct trajectories that are recoverable by sampling but too sparse to reliably appear in finite RLVR rollout groups. We argue that a two-mode account explains this as an absence-of-evidence failure: rare correct trajectories may disappear before RLVR samples and reinforces them often enough. The main contribution is this diagnostic and mechanistic framing. Per-Problem Base Anchoring (PBA) is a deliberately simple proof-of-concept: sharpen prompts with sufficient frozen-base correct evidence, and anchor risky prompts to the base distribution. Across three training seeds on Omni-MATH-Test, with MATH500 as a secondary high-coverage validation benchmark, PBA improves both \PassK{1} and high-budget coverage over matched GRPO. A 3000-prompt regime-controlled diagnostic study is consistent across seeds with the expected signature: ordinary GRPO loses base-solvable boundary prompts, while PBA preserves rare verifier-positive trajectories. We use mathematical verifiers as a controlled testbed for verifier-guided optimization; the same pass@k inversion risk applies to ECCV-relevant vision-language agents when repeated visual, spatial, or chart-reasoning attempts are checked by external tools or verifiers. Reasoning post-training should decide not only how strongly to optimize, but which prompts are safe to optimize.

Brain-encoding foundation models predict fMRI responses to video, audio and text well enough to win the Algonauts 2025 challenge. We ask whether their predicted responses, obtained with no scanner, are a useful feature lens for a human-behavior task: forecasting short-video memorability. Each clip is projected into TRIBE v2's predicted cortical space and scored by ridge regression against a matched control, the model's own V-JEPA2 visual backbone taken before the brain projection. The answer is dataset-dependent. Within Memento10k (499 clips) the backbone wins (Spearman 0.594 vs 0.544); within VideoMem (820 clips) the brain projection wins (0.415 vs 0.368). Because the claim is that the ordering reverses, we test the reversal itself: the dataset-by-representation interaction is +0.097, 95% CI [+0.032, +0.160], two-sided bootstrap p=0.001, and over 10 cross-validation seeds the datasets separate completely (0/10 seeds favor the brain projection on Memento10k, 10/10 on VideoMem). Cross-dataset transfer inherits the split: Memento10k->VideoMem the brain projection wins (+0.076); the reverse loses heavily (-0.311). The VideoMem advantage is not a sample-size artifact (it survives matched training size and PCA-then-ridge) and not mere compression (a compressed, heavily regularized or transfer-tuned backbone stays below it). Predicted-brain features thus carry a small but real memorability signal the backbone misses on one dataset and not the other: a dataset-specific representation, not a domain-general prior. A vision-orthogonal component (partial Spearman 0.19, permutation p=2.5e-4) localizes to ventral occipito-temporal cortex, and predicted BOLD dynamics add nothing beyond the time-average because 3-4 samples per clip cannot resolve the sub-second late memorability response. Our pre-specified within-dataset hypothesis returned NO-GO; the reversal is what survived.

LLMs are now proposed for fraud detection, scam investigation, content moderation, and other trust-and-safety workflows. Much of the public literature still evaluates them as models, with less attention to their behavior as components in operational pipelines. This creates a practical evidence question: what would justify placing an LLM inside a live workflow with latency, cost, escalation, human-review, and adversarial-risk constraints? We address this question through a fraud-first survey of deployment evidence. We code 49 operationally relevant sources on LLM use in fraud detection, investigation support, content moderation, and cross-cutting robustness (18 fraud, 14 moderation, 17 cross-cutting), supplemented by 15 contextual references that establish the survey boundaries. These sources include systems, benchmarks, frameworks, and deployment-relevant surveys, not 49 production deployments. The main finding is an evidence imbalance. Fraud supplies the largest task-specific portion of the coded corpus. The moderation papers, however, include more explicit public evidence on latency, cost, governance, and fairness. Among the 18 fraud and investigation sources, none report clean per-decision latency, per-decision dollar cost, or calibration evidence; most report offline task performance, retrieval gains, or case-study accuracy instead. The survey contributes a role-and-evidence organizing frame, FORTE, for locating LLMs as classifiers, retrieval interfaces, explanation generators, reviewer assistants, agents, feature extractors, or escalation components. It also contributes a minimum deployment-evidence checklist covering latency budget, cost per decision, decision threshold, explanation integrity, and adversarial pressure. The resulting agenda identifies studies needed to support deployment claims for LLM-based fraud and trust-and-safety work.

An activation-based safety gate must distinguish harmful assistance from legitimate work on the same topic. We test whether probes trained on broad harmful-versus-harmless data provide this decision boundary. Five checkpoint-specific readouts and their source-derived thresholds are transferred unchanged to four matched-pair cohorts containing 450 pairs, manually reviewed for topic and request-frame similarity. On Twin-70, the primary cohort of 70 pairs, central harmful and harmless score intervals overlap. Area under the receiver operating characteristic curve (AUROC) falls from 0.996-0.999 on the broad source task to 0.701-0.860. Pair ranking remains 0.829-0.929, but the transferred thresholds detect 0.943-1.000 of harmful requests while falsely blocking 0.686-0.986 of matched harmless requests. False blocking remains low on XSTest. Even with thresholds refitted within pair-grouped cross-validation, balanced threshold error is 0.229-0.329. Alternative source-trained logistic, radial-basis, and shallow multilayer probes reduce false blocking but detect only 0.200-0.671 of harmful requests at their transferred thresholds. Three primary readouts meet all prespecified Wall criteria, while two yield mixed evidence. Matched-label training recovers the distinction for the three checkpoints tested, and lexical controls also exhibit transfer loss. An automated post-freeze audit finds little numerical sensitivity to arm-label disagreement. The evaluated source operating points fail to combine strong harmful-request detection with access for legitimate same-topic work. This gap between risk ranking and a usable decision boundary is the security concern captured by the Entanglement Wall.

This work studies the inverse problem of recovering the relative magnitudes of the tension, bending, and bearing loads acting on a crack from its stress-intensity-factor profile along the crack front, using the public SIFBench finite-element data. The central claim is not forensic load recovery on field cases, but a rigorous characterization of when the combined load is identifiable at all, together with an estimator that returns calibrated uncertainty precisely in the regimes where it is not. For a known geometry the forward map from loads to profile is exactly linear, and identifiability reduces to a single geometric question: whether the three elementary load profiles are linearly independent as functions along the front. When they are nearly dependent, many different load combinations produce almost the same profile and the inverse problem is illposed; the analysis shows that the degree of ill-posedness is controlled by an intrinsic stability margin, not by the conditioning number alone. A single crack-front operator serves both as a structured forward surrogate and as the differentiable map required by a simplex-constrained, set-valued inverse estimator. On the SIFBench corner-crack scenario the empirical behaviour matches the theory: the typical geometry is well posed while a sizable minority is genuinely ill-posed, so a point estimate is reliable on the majority and provably uninformative on the rest. Validation is on controlled synthetic noise; no real fracture cases are used or claimed.

Point-adjustment (PA), for years the default scoring protocol in time-series anomaly detection (TSAD), was shown by Kim et al. (2022) to award near-perfect F1 to random anomaly scores. The field adopted a suite of replacement metrics (PA%K, range-based precision/recall, affiliation precision/recall, and Volume-Under-the-Surface, VUS, ROC/PR). We ask, independently and adversarially, whether these resist no-skill detectors on real benchmarks, and find the answer turns entirely on one overlooked variable: N, the number of random attempts an adversary reports the best of. Under a single honest run (N=1), not one replacement metric is gameable on any of six benchmarks (UCR, SMD, SMAP, MSL, NAB, PSM): a random detector reaches 90% of the best real detector's score on at most 11% of series for affiliation-F1, 5% for the ROC family, and 2% for the PR-based metrics and PA%K. But under best-of-N reporting, the seed-shopping endemic to ML, the metrics split sharply. affiliation-F1 and every ROC-based metric inflate steeply, affiliation crossing gameable (25% of series) by N=3 and reaching 0.98 at the full pool (N=41), the ROC family crossing by N=9-11; the PR-based metrics and PA%K stay near-flat at every N, floored near the anomaly prevalence (the lone exception is NAB at large N). A paired test finds VUS-ROC inflated on 131 series where its sibling VUS-PR is not, and never the reverse. The ROC-vs-PR split follows from the order-statistic behaviour of AUC under extreme class imbalance (a random PR-AUC is floored at prevalence); affiliation inflates by a second route, its extreme single-run leniency (already fragile at N=1). We release a pip-installable stress-test harness, and recommend reporting single-run scores or disclosing N and preferring PR-based metrics, which resist best-of-N inflation on nearly every benchmark.

Independently trained neural networks have no shared neuron-index reference frame, so comparing them requires accounting for coordinate freedom. Neural Collapse sharpens this problem: networks converge toward a shared, low-dimensional geometry, raising the question of whether trajectory-specific functional variation remains distinguishable after convergence. We distinguish three claims - detectability, transplantability, and causal persistence - and address the first. Using five independently trained networks reconstructing Neural Collapse on MNIST, we apply a verified affine-correct alignment mapping donor heads into recipient coordinates. Donor-specific functional fingerprints remain distinguishable after recipient-level baseline correction: all 20 ordered donor-recipient pairs are correctly identified, with an exact permutation p=0.0083, robust to a leakage audit. These findings establish detectability under the test used here, but not transplantability or causal persistence. The study shows how alignment, ambiguity diagnostics, and leakage control combine to test cross-network variation in a controlled setting; whether this generalizes beyond it is open.

Autonomous driving requires long-horizon closedloop decision making in dynamic traffic environments. Latent world models offer an effective framework for this problem by enabling imagination-based decision making in compact latent spaces. However, multi-source observations contain controlirrelevant redundancy, whereas reliable driving decisions rely on risk-relevant relations, future dynamics, and continuous action adjustments. This mismatch makes observation reconstruction and absolute action modeling suboptimal for learning decisionrelevant latent dynamics. We propose LIDAR-AD, a decoderfree Latent-Interaction Dreamer with Action-Residual Chains for autonomous driving. LIDAR-AD replaces observation reconstruction with redundancy-reduced latent alignment, encouraging compact representations of risk-relevant relations in multi-source driving inputs. It further models vehicle control as residual action updates and uses residual-action sequence contrastive learning to align multi-step residual-driven rollouts with future latent states. A deterministic analysis shows that the latent-tanh residual parameterization preserves interior action reachability while representing smooth long-horizon control as compact local updates. Together, these designs improve risk-aware state abstraction, continuous-control modeling, and long-horizon dynamics prediction. Extensive experiments across diverse simulated driving scenarios demonstrate that LIDAR-AD consistently outperforms world-model baselines, achieving the highest reward and the best success rate among learning-based methods. Evaluations on nuPlan-derived log-reconstructed scenarios further demonstrate the transferability of LIDAR-AD under real-world traffic layouts.

The early detection of Chronic Kidney Disease using machine learning has attracted significant interest in healthcare-related computer science. Despite rapid advancements in this field, many reported studies remain inconsistent and potentially misleading. A significant drawback is the lack of organized evaluation regarding methodological concerns. Key issues include data leakage, limited access to temporal patient records and inconsistency in reported clinical indicators. This research offers a systematic literature review of existing CKD prediction studies using interpretable machine learning techniques, where nineteen relevant studies were selected via systematic searches across major academic databases. To assess methodological reliability, this study introduces a structured taxonomy of information leakage and a quantitative leakage scoring framework to systematically evaluate reliability across CKD prediction studies. The analysis reveals a strong relationship between leakage and inflated performance. Here, High leakage-studies report an average accuracy of 95.48%, compared to 80.2% for leakage-free studies, reflecting an increase of approximately 15.28%. Furthermore, a cross-study feature stability analysis shows that only a small subset of predictors is consistently reproducible, with over 80% lacking reliability. Overall, the findings suggest that many reported performance improvements stem from methodological limitations rather than true predictive capability.

Self-supervised learning offers a compelling approach for medical imaging, where labeled data are scarce and acquisition costs are high. We present COJEPA, a self-supervised framework for volumetric brain MRI that combines a joint-embedding predictive architecture (JEPA) with a contrastive loss (CO), targeting two complementary properties: local predictivity and global discriminability. The model is trained without labels on T1-weighted structural MRI from two cohorts (HCP-YA and AABC, $N{=}2286$, ages 22 to 90), extending I-JEPA to 3D with foreground-aware block masking, a hierarchical convolutional patch embedding, and world-space sinusoidal positional encodings. We evaluate all three objectives across zero-shot twin retrieval, brain tumor segmentation (BraTS 2024), and age regression (OpenBHB). COJEPA achieves the best monozygotic twin recall at rank@1 (0.84), the best finetuning age MAE (2.55 years on OpenBHB 3.0T), and matches CO on BraTS whole-tumor Dice, demonstrating that the combined objective yields representations that are simultaneously discriminative and locally structured.

Under the free energy principle, a predictive system does not observe reality directly; it maintains a generative model of the world and experiences that model's best current hypothesis. Can a synthetic environment be made consistent enough that a predictive system's own inference machinery adopts it as this default hypothesis, permanently displacing the environment that first shaped it? We call this state ontological inversion. Because inducing and monitoring such a transition in a nervous system is neither ethical nor technically feasible, we study the underlying computational problem through a controlled proxy: a convolutional variational autoencoder paired with a recurrent latent predictor, whose evidence lower bound objective is mathematically identical, up to sign, to variational free energy itself. The network is trained first on a baseline visual domain, then on a mixed stream in which a swept rehearsal ratio r controls how much baseline content persists during transition to a target domain. Representational capacity, what the latent space can discriminate, is tracked separately from default behavior, what the system generates when left unconstrained. Across a full sweep of 90 runs, the two diverge sharply: representational accuracy stays near ceiling, 0.97 to 0.998, regardless of r, while default behavior spans nearly the system's entire range depending on r alone, a decoupling of learning from acceptance. More strikingly, at intermediate r the system's default output rises toward the target domain, then partially reverts toward the baseline while training continues unchanged, a structural failure we term cognitive relapse. Resistance to reality-adoption is not reducible to learning speed; it is a structural property with its own distinct failure modes, established here as a computational existence proof and nothing further.

Data Shapley can be computed exactly and efficiently for unweighted K-nearest-neighbor (KNN) models, the basis of the popular KNN-Shapley. For weighted KNN, however, efficient exact algorithms are known only for hard-label classification. In regression, the prediction is a weighted average whose normalization term changes with every subset. The best exact algorithm then takes O(N^K) time for N training points. We show that this normalization term is not an obstacle. A subset affects the prediction only through two numbers: the total weight of its K nearest neighbors and their total weighted target. Once the weights are discretized, subsets with equal total weight share their normalization term and can be summed as a group. This gives an exact algorithm that is near-linear in N and polynomial in K and the number of weight levels, for real targets under the squared loss. The same idea gives exact values for soft-label classifiers in the same time, and speeds up the earlier exact algorithm for hard labels by a factor of N. For continuous weights, we give a deterministic approximation with a certified error bound, without discretizing the weights. On the downside, we prove that some exact values take exponentially many bits to write down, so the dependence on weight precision cannot be removed in general. In experiments on real datasets with up to 100,000 training points and with 10 or 100 validation points, we compare the exact values with Monte Carlo estimates computed in the same time. Monte Carlo ranks the points less and less like the exact values as the training set grows. Two of its runs also disagree on a large share of the top 10% of points.

Trader-facing dynamic fees are increasingly proposed for automated market makers (AMMs), but historical data do not identify how order flow would respond: trader-facing fees do not vary, trader types are latent, and a replayed tape is not a sequential decision environment. We therefore construct a minimal closed-loop simulator in which the missing signal exists by construction: two constant-product pools repriced by an equilibrium-inspired dynamic-fee rule, fee-sensitive noise flow, and closed-form CEX–AMM arbitrage. Equilibrium is used as a closure principle, not as an object the trader learns. Against a tuned benchmark ladder of schedule, planning, lookahead, and tabular policies, a small DQN is the only evaluated valid policy whose paired improvement over tuned one-step routing excludes zero. On a reserved final block of 1{,}000 seeds with completion forced to 1.0 for every policy, it reduces implementation shortfall under every tested intra-step ordering, by $13.3\bps$ of order notional under the pre-specified agent-last ordering, and the edge is concentrated in, and learned from, dynamic-fee environments: under constant fees the paired difference is indistinguishable from zero. The result is model-conditioned counterfactual evidence about execution control in AMMs, not evidence about historical traders, equilibrium play, or deployable profit.

Standard learning rate schedules such as cosine annealing are tied to a fixed training horizon, limiting their ability to accommodate post hoc horizon extension. Warmup-stable-decay (WSD) partially addresses this issue by maintaining a long constant-rate phase before a short linear cooldown, allowing training to resume from a pre-decay checkpoint. However, its peak learning rate is still tuned based on the original training horizon and can become suboptimal when training is extended. Motivated by stochastic convex optimization, we propose WSqD (Warmup with Square-root base and linear Decay), a learning rate schedule that replaces WSD's constant stable phase with a shifted inverse-square-root base while retaining the final linear cooldown. In the stochastic convex setting, WSqD provably attains the minimax-optimal $O(1/\sqrt{T})$ last-iterate convergence rate. Importantly, its base learning rate schedule is horizon-independent, and the training horizon is needed only to determine when to begin the final cooldown. Empirically, on language-model pretraining using the SlimPajama corpus, WSqD matches or outperforms carefully tuned WSD and other baselines across multiple training horizons while reusing a single peak learning rate.

We introduce sticky jump diffusions (SJDs), continuous-time Markov processes on $\mathbb{R}^d$ whose discrete anchors are token embeddings. In forward time, anchors release their mass at a hazard rate and the released mass diffuses in the continuous ambient space; time reversal couples a score-driven SDE with a sticky jump kernel whose rate and destination are fixed by flux balance with the forward law. We estimate the score and the per-anchor reverse hazards from a single denoising classifier via denoising hazard matching, the hazard analogue of denoising score matching, with simulation-free cross-entropy training. SJD recovers masked diffusion, continuous diffusion, and hybrid diffusion as limits. Its reversal explains features that each family treats as given: the mask of masked diffusion carries no evidence about the source token because the unsticking kernel of every anchor collapses to the same absorbing point; the terminal projection of continuous diffusion is required due to the absence of atoms in its forward marginal, without which flux balance yields no reverse jumps; and the update rules of hybrid diffusion (commit rate, destination, and drift) all follow from flux balance rather than from separate design. Beyond these limits, the unsticking kernel becomes a design space: a cross-position blending corrupts each position toward a blend of its neighbors' clean values or embeddings, turning dependency structure such as spatial locality or a constraint graph into an inductive bias of the corruption itself, and improves over the identity-kernel hybrid on CIFAR-10, Text8, and Sudoku.

We study the bandit-feedback version of online principal component analysis (Bandit PCA): in each round $t = 1,\dots,T$, the adversary selects a $d \times d$ symmetric gain matrix $G_t$ with spectrum in $[0,1]$ and rank at most $r$; the learner simultaneously selects a unit vector $w_t \in S^{d-1}$ and receives the reward $w_t^\top G_t w_t$. The learner receives no other feedback, and aims to minimize the regret against the best unit vector in hindsight. This problem was introduced by Kotlowski and Neu (2019), who gave an algorithm with regret $O(d\sqrt{rT \log T})$ and showed the lower bound of $\Omega(r\sqrt{T/\log T})$. We improve upon both of these bounds and essentially bridge the gap between them, establishing the minimax regret of order $r\sqrt{dT}$ up to polylogarithmic factors in $d$ and $T$. The upper bound is attained by a novel algorithm, which combines online mirror descent on the spectrahedron of (real) density matrices with a multiscale exploration scheme in which the eigenspaces with different spectral magnitudes are updated at different rates. For the lower bound, we construct an adaptive adversary that refines a hidden large-reward subspace based on the learner's actions, in such a way that low regret is impossible without estimating the subspace; as a result, lower-bounding the regret reduces to studying the arising subspace estimation problem. Finally, we discuss connections of Bandit PCA with adaptive-measurement quantum tomography.

Decoding brain activity is useful for characterizing brain processes and understanding the functional architecture underlying cognition. However, the inter-individual variability in brain response patterns limits the development of decoders that generalize across individuals. A solution to this challenge is functional alignment: aligning functional data across individuals before training population-level decoders. The core issue is to strike the balance between aligning functional features and preserving the anatomical structure, while maintaining computational efficiency. We introduce a new functional alignment method for fMRI, SpectralOT, that embeds cortical geometry into Laplace-Beltrami eigenmodes along functional data to regularize the alignment.