Papers

Federated learning (FL) enables multiple intelligent devices to collaboratively train a high-accuracy model without sharing raw data. However, due to its distributed nature, FL is vulnerable to Byzantine attacks. Existing defense methods rely on strong assumptions, such as the proportion of malicious devices not exceeding 50%, or the server having an additional root dataset that matches the training task. Moreover, they show limited efficacy as they overlook $(i)$ the divergence among benign updates and $(ii)$ the curse of dimensionality involved in comparing two high-dimensional updates. To solve these concerns, we propose FL-OA, a Byzantine-robust federated learning framework utilizing outsourced auditing. In FL-OA, the server collaborates with third-party organization that holds an additional root dataset to perform outsourced auditing, thereby enabling the server to achieve robust aggregation without strong assumptions. Additionally, FL-OA introduces a gradient ascent step and a correction term during local training to mitigate the divergence among benign updates, and designs a parameter importance indicator to extract critical parameters for auditing, alleviating the curse of dimensionality. We further provide a detailed theoretical analysis of FL-OA. Extensive experiments demonstrate that FL-OA outperforms existing defense methods against Byzantine attacks.

{AdaBoost.MH} reduces multi-class classification to a collection of binary subproblems and enjoys the classical boosting-type convergence guarantee under a weak learning condition. A more structured variant, Factorized {AdaBoost.MH}, uses base classifiers of the form $\mathbf{h}(x)=\alpha \mathbf{v} \bm{\varphi}(x)$, where a single binary classifier $\bm{\varphi}$ is shared across all classes and the label dependence is carried by a vote vector $\mathbf{v} \in\{\pm1\}^K$. This factorization is algorithmically attractive and achieves better performance in practice, but its convergence depends on whether one can always choose a vote vector with sufficiently large induced binary weight mass. Previous work resolved this question with a lower bound $\max\{1/n,1/\sqrt{2K}\}$, which still leaves a dimension-dependent slowdown relative to the original {AdaBoost.MH} analysis. In this paper, we sharpen this combinatorial step. For the minimax quantity $\mathfrak{W}_{n,K}$ governing the factorized edge, we prove $\mathfrak{W}_{n,K} = C_{\min\{n+1,K\}}$, where $C_q=1$ for $q=1$, $C_q=q/(3q-4)$ for even $q\ge2$, and $C_q=(q+1)/(3q-1)$ for odd $q\ge2$. Since $C_q\downarrow 1/3$, our bounds show that $\mathfrak{W}_{n,K}=\Theta(1)$ uniformly over $n$ and $K$. Consequently, Factorized {AdaBoost.MH} achieves the same boosting-type convergence rate as {AdaBoost.MH} up to a universal constant factor, removing the previously suggested additional dependence on $n$ or $K$ in the number of boosting rounds.

Spiking Neural Networks (SNNs) are attractive for resource-constrained remote-sensing systems, but reliable out-of-distribution (OOD) detection remains challenging. Deep ensembles provide strong predictive uncertainty, yet require multiple complete models and backbone evaluations. We propose an efficient spiking pseudo-ensemble that attaches multiple lightweight classification heads to a frozen SNN backbone. Naively training these heads with cross-entropy can lead to diversity collapse, where independently parameterized heads may produce correlated predictions. To address this, we introduce an agree–disagree objective that preserves correct predictions on clean in-distribution samples while encouraging diversity on structured, uncertainty-inducing transformations of the same inputs. This provides a diversity-promoting training signal without requiring external OOD data. Experiments with Spikformer and ResNet19-SNN on EuroSAT demonstrate consistent improvements over conventionally trained pseudo-ensembles. Using three backbones with five heads each matches or improves upon a five-model deep ensemble on UCM and AID, while requiring approximately 38% fewer parameters and 40% fewer backbone evaluations. These results show that explicit diversity promotion can recover useful ensemble-style uncertainty at substantially lower deployment cost.

LLM-based multi-agent systems (MAS) extend LLM capabilities through iterative communication and shared contexts. However, this collaboration introduces a vulnerability: backdoor behavior can be activated when peer evidence reaches a hidden threshold, rather than being determined by any single message. We introduce a collective evidence-threshold backdoor paradigm for MAS and Boundary-Conditioned Backdoor Injection (BCBI), which constructs counterfactual boundary pairs to separate benign behavior before the threshold from the adversarial objective after it, and learns latent progression aligned with evidence. To mitigate this threat, we propose LAtent Transition Test-time Evaluation (LATTE), a clean-only latent-transition defense that learns benign communication dynamics and quarantines anomalous agent updates before their responses propagate. Across several benchmarks, BCBI yields selective activation with little premature activation; without knowing the attack target or trigger, LATTE limits propagation with minimal disruption.

Tabular data is used extensively in many real-world use cases. Deep learning models have been developed to deal with tabular data, but generally perform poorly when the test data distribution differs from that of the training data. Researchers have proposed test-time adaptation approaches to deal with this problem. The fully test-time adaptation (FTTA) setting involves adapting deployed classifiers to shifted target distributions using only unlabeled test data. Leading FTTA methods inherit a batch-dependent approach from computer vision literature. This paper demonstrates for the first time that such approaches degrade sharply in strict streaming regimes where examples arrive and must be classified one at a time. This occurs because at a batch size of one, batch-level statistics become unavailable or poorly estimated. We argue that singleton tabular FTTA is not merely a small-batch variant of ordinary FTTA, but a distinct identifiability problem where only the location of the model's score stream remains directly observable. To address this, we propose Prequential Logit-Origin Centering (PLOC), a lightweight approach that keeps the source model frozen and shifts the logit space at each step. PLOC stores only a single running number (the mean of past logits), requires no labels, estimates no priors, and bypasses weight updates entirely. A deferred variant applies a static shift that preserves the source ranking, and thus the AUROC, exactly. Evaluated across five tabular benchmarks, three architectures (MLP, FT-Transformer, and TabTransformer), and five independent source checkpoints, PLOC significantly outperforms strong tabular and entropy-based baselines.

Bandit algorithms generate data for downstream inference, but adaptive sampling biases post-bandit sample means. We analyze this bias for stable index algorithms, including UCB1 and its generalizations, and derive sharp leading-order expressions for the sample-mean bias and expected $Z$-statistic, in bandit experiments of fixed horizon $T$. Our characterization reveals the algorithmic origin of bias through a key index-function-dependent quantity, which we term effective exploration rate. For example, under UCB1, the effective exploration rate is of order $\sqrt{\log T}$, and the standardized bias of any arm (that is not uniquely optimal) decays at the extremely slow rate $1/\sqrt{\log T}$. We also show how the choice of the index function affects both regret and bias, which reveals a regret-bias trade-off: more exploratory algorithm reduces bias but increases regret. We further show how bias most severely distorts confidence intervals and hypothesis tests when the tested arm is one of the tied-optimal arms. Our sharp characterization for bias uses a novel empirical fluid approximation of the algorithm's sampling dynamics, which may be of independent interest.

World models have attracted significant attention for their ability to capture and predict the structure and dynamics of the physical world. In this emerging landscape, Joint Embedding Predictive Architectures (JEPA) offer a particularly compelling direction. We study a largely unexplored regime: populous, crowded, and chaotic Global South urban environments, which we call DENSEWORLD. Unlike the lower-density, lane-structured settings that dominate existing evaluations, these scenes exhibit soft spatial boundaries, extreme agent heterogeneity, persistent occlusion, and rapid social negotiation under mixed traffic. We introduce the first large-scale dataset for this regime: 1,000 hours of drive-through, walk-through, and aerial video across 22 cities. Existing JEPA formulations struggle to preserve dense interaction dynamics under heterogeneity and partial observability. We introduce FactorJEPA, which makes world structure a first-class predictive primitive. Rather than encoding the future in a monolithic latent, it composes layout, entities, and interactions, using a visibility gate and separated subspaces to preserve partially observed agents and discourage cross-factor shortcuts. FactorJEPA improves (i) future-latent accuracy (Future-frame L1), (ii) intervention-sensitive prediction (Causal L1), and (iii) robustness to reduced visual evidence (Mask-ratio slope), while exposing (iv) a reproducible motion-information trade-off (Motion cosine). Method rankings replicate across 2B and 1B V-JEPA 2.1 backbones, with rho = 0.895 to 0.978. We publicly release the DENSEWORLD-115k dataset (https://huggingface.co/datasets/anonymousML123/denseworld-115k) and the surgery-trained FactorJEPA checkpoints (https://huggingface.co/datasets/anonymousML123/factorjepa-outputs/tree/main/outputs/full/vjepa_2_1_vitg_1B/train/m09c_surgery_3stage_DI_diheavy_encoder).

Enterprise AI agents act across many apps whose data changes continuously, so an answer is correct only relative to what data existed and who could see it at the moment it was asked. Offline evaluation today grades against a single static snapshot, effectively the end of the episode. So, it can only evaluate one situation, the final one, even though every earlier moment of the episode is a different situation that invites its own realistic questions with its own correct answers. Recreating each of those moments as a separate snapshot would mean re-provisioning a whole tenant per instant, which is prohibitively costly; and even a single snapshot leaks future state hidden inside records and cannot represent the multi-app, time-ordered way real work happens. Our system closes two gaps at once: it generates a realistic, persona-driven, temporally-evolving enterprise world from real research, and replays that world at any chosen moment to evaluate any pluggable agent. A schema-inferred temporal description drives a deterministic-plus-LLM rebuild of each record's past state; because the queryable moments are finite, all rebuilds are precomputed into a compact difference cache, making evaluation a fast, reproducible lookup with no model in the path. We describe the design, an architecture spanning both flows, and early experience evaluating enterprise agents.

Machine-learning predictors estimate processor performance far faster than cycle-level simulation. For design-space exploration, however, the valuable test is not merely reproducing the usual hardware ordering, but identifying how different hardware configurations rank on individual program phases. We evaluate four ML-predictors in two design regimes: Structural Parameters (SP), varying hardware resources such as issue width, ROB size, and cache capacity; and Behavioral Policies (BP), varying prefetching and replacement algorithms. In the SP regime, aggregate ranking is strong, yet counter-intuitive windows(CIW)—where the configuration expected to be slower is faster—constitute $22.4\%$ of non-tied windows across five pairs with a clear architectural prior. CIW match across these pairs is only $23.3$–$39.9\%$; every point estimate is below the $50\%$ random strict-ordering reference. The BP regime presents a different failure: ground-truth ties cover $37.8\%$ of pair-windows, most strict pairs have margins of only a few cycles, and no model family reliably beats a feature-free majority baseline. NeuroScalar and SimNet fall below that baseline, Concorde is statistically tied with it, and the best selected OneDSE head improves by only $2.1$ percentage points. Accuracy rises mainly at large margins. We further show that this failure is not a matter of model capacity: an information-theoretic analysis reveals that when ranking outcomes depend on hidden microarchitectural state absent from the instruction stream, no trace-based predictor can exceed the Bayes accuracy determined by observable inputs alone. Thus high cycle or aggregate ranking accuracy can reflect mastery of easy, high-margin cases while missing the local reversals that carry the most architectural insight and for which cycle-level simulation remains indispensable.

Trajectory similarity learning is fundamental to efficient trajectory retrieval under complex distance measures. Existing learning-based methods typically rely on embeddings trained to approximate trajectory distances or rankings, but they often lack guarantees with respect to the original distances, exhibit unstable performance across distance measures, and incur substantial training costs. We revisit trajectory similarity learning from a lower-bound representation perspective and propose LB-TrajRep, a unified lower-bound representation framework independent of deep neural embeddings. This framework constructs single-vector representations from a set of lower-bound components, enabling admissible and interpretable lower bounds for multiple classical trajectory distances, including Dynamic Time Warping (DTW), Hausdorff distance, and Discrete Fréchet Distance (DFD). Within this framework, we instantiate point-pivot components, which naturally support both metric and non-metric distances and remain compatible with standard vector-based retrieval pipelines. To improve ranking quality, we develop two data-driven pivot selection strategies that explicitly optimize lower-bound tightness and prioritize hard near-neighbor trajectory pairs, respectively. Extensive experiments on real-world trajectory datasets show that the proposed lower-bound representations are able to consistently outperform state-of-the-art neural trajectory embeddings across diverse distance measures, improving top-$k$ ranking accuracy by up to 20%–60% on the Hausdorff distance and DFD and by 15%–40% on DTW.

Training error is what we can observe on a training set; test error is the quantity we care about. We study squared-error linear regression in a deterministic $(d+1)$-dimensional single-spike model. Each training vector has spike coordinate $\sqrt{\gamma}$, $\gamma>1$, and equal-norm, mutually orthogonal nuisance components. Training labels are $1$. Fresh test points are centered Gaussian with covariance $\operatorname{diag}(\gamma,1,\ldots,1)$ and noise-free label $x[1]/\sqrt{\gamma}$. We compute the exact train–test tradeoff for linear predictors in the training span. When the spike direction is unknown, allowing all linear predictors does not improve this tradeoff, on average or in the worst case over directions consistent with the data. There is a range of training-set sizes where every span predictor that generalizes well must fit the training data worse than the zero predictor. We call this benign misfitting, or the fourth quadrant. At its sharpest, test error tends to zero while training error diverges, with both zero-predictor errors normalized to one. The best span predictor begins to generalize when $n\gg d/\gamma^2$, while interpolation needs $n\gg d/\gamma$. In the intervening window $d/\gamma^2\ll n\ll d/\gamma$, useful span prediction lies beyond interpolation: training predictions overshoot the labels. One-pass stochastic gradient descent with a large constant learning rate attains small test error throughout this window, matching the best span predictor up to a logarithmic factor, while leaving large empirical training error. Finally, the nuisance component responsible for the training misfit also controls adversarial sensitivity.

We present Caliber, an output-perturbation defense against model extraction that formulates noise selection as a calibration problem: how much the defense degrades the supervision signal used to train a surrogate, and the provable per-input query cost of recovering the clean logits. To defend against an attacker that uses returned scores for knowledge distillation, Caliber adds independent and identically distributed Gaussian noise to the internal logits. We establish two properties of the resulting perturbed predictions. Monotone agreement degradation: When the clean logits have a unique maximizer, agreement with the clean prediction decreases strictly with the noise scale, so every target in $(1/K,1)$ corresponds to a unique positive scale; task accuracy is bounded by computable lower and upper envelopes. Per-input recovery cost: We derive a closed-form minimax lower bound on the repeated queries needed to recover the clean logits for a fixed input. Caliber normalizes noise variance by the squared median top-two logit margin and fits the resulting noise-utility relationship with a logistic curve, either per model or shared within a task. Across more than thirty model-dataset combinations, per-model calibration achieves mean absolute relative errors of 0.6-1.4%. End-to-end experiments show that surrogate performance generally tracks the configured degradation, while fixed-input averaging follows the expected variance reduction.

Dual-target drug design aims to generate 3D molecules that can simultaneously interact with two target proteins, offering a promising route for discovering polypharmacological compounds against complex diseases. While recent generative models have shown encouraging performance in single-target drug design, existing dual-target approaches either focus on sequence generation or introduce an additional predictive drift term into the diffusion-based generative trajectory, which limits their ability to fully integrate feature information from both targets. We propose FusedBFN, a fused Bayesian flow network (BFN) for dual-target molecular design. FusedBFN formulates dual-target generation as distribution fusion in a unified continuous parameter space and employs a product-of-experts formulation to incorporate dual-target information throughout the generative process. To address the scarcity of dual-target structural data, we leverage a pretrained target-aware BFN model as the shared backbone. We further introduce a chemically aware prior-based alignment method and a prior-free pocket alignment strategy to construct aligned dual-target contexts. Extensive experiments demonstrate that FusedBFN generates molecules with strong binding affinity toward dual targets while maintaining favorable molecular properties.

Solomonoff Induction, or SolInd, provides an ideal unbounded model of a priori sequence prediction but cannot naturally describe extrapolation from a given training dataset, as performed by Large Language Models. We apply de Finetti's theorem on exchangeable distributions to SolInd to produce what we call Hierarchical Solomonoff Induction, or HSI, which maintains a hyperprior over all Solomonoff priors that can be conditioned on previously observed sequences. We extend Wood et al.'s proof that universal mixtures of semimeasures are equivalent to SolInd to show that universal mixtures of these mixtures are also equivalent, proving that HSI=SolInd. We also prove that HSI's excess error on any distribution, compared to its true generator, is bounded by that generator's complexity in the hyperprior. This result is directly comparable to SolInd's prediction error being bounded by the Kolmogorov complexity of the sequence being predicted, and forces HSI's average excess error to converge to 0 as a dataset grows, leading to optimal prediction in the limit. We claim that HSI is an ideal unbounded model of sequence prediction given a dataset in the same way that SolInd is ideal over individual sequences.

Platform teams hosting agent-extensibility surfaces face a regression-economics paradox: every onboarding customer ships an evaluation set tuned to their domain, but the platform's regression set must live under a hard query-count ceiling bounded by release cadence. To our knowledge, no published industrial pipeline addresses this platform-side curation problem: existing evaluation frameworks are customer-side, and benchmark-compression work treats benchmarks as fixed pools rather than streams of incoming sets. We describe a capability-taxonomy-driven curation pipeline applied to declarative agents with custom actions in Microsoft 365 Copilot. It takes an agent specification and a customer's eval set as input, projects each query into a platform-owned capability taxonomy, and outputs per-query decisions (admit, drop, swap, or human review), under the philosophy that a healthy regression set is the minimal set of queries capturing the maximal spread of capability signatures – distinct combinations of capabilities a query exercises together. Three components instantiate this: a classifier producing per-(query, capability) verdicts via a hybrid of deterministic specification-based extraction and large-language-model (LLM) semantic inference; an Invocation Quality (IQ) rater scoring how thoroughly a query exercises each capability, so a new query sharing a signature with an existing entry can still be recognized as a better test and displace it; and a consolidator comparing incoming queries against the regression set on coverage and quality through a rule-based decision cascade, backed by a conservative curator that only suggests evictions. The mechanism is taxonomy-agnostic and applies to any regression eval-set curation problem with a typed capability taxonomy, including taxonomies that evolve in response to the very evidence the pipeline surfaces.

Most FDR-controlled feature selection methods are designed for coordinate-wise hypotheses, where each feature has a single weight or importance score. This abstraction fails in sequential and grouped models, where one original feature is represented by a block of sub-features, such as lags, recurrent states, or attention-based interactions. We propose a grouped-feature FDR control framework for such settings. For grouped linear models, we construct null-symmetric block-level mirror statistics with matrix-valued perturbations. For neural sequential models, we combine Permutation SHAP derivatives as model-agnostic block-level importance scores with kernel-based dependence measure. The framework is model-agnostic across network architectures, does not require specifying the covariate distribution, and reduces to Gaussian Mirror or Neural Gaussian Mirror when the block size is one. We prove FDR control for low- and high-dimensional grouped linear models and asymptotic symmetry of smoothed Permutation SHAP derivatives under fixed fitted nonlinear models. Experiments on simulated and real-world datasets show reliable FDR control and improved power under correlated grouped-feature signals.

The rapid growth of single-cell transcriptomic data has enabled the development of foundation models pretrained primarily by reconstructing masked expression values. This objective encourages these models to learn gene dependencies but does not directly optimize whole-cell representations, which are essential for many downstream tasks. To bridge this gap, we propose a contrastive pretraining framework that learns cell representations through complementary transcriptomic views. Since standard contrastive learning is not readily applicable to single-cell pretraining, we introduce specific adaptations along three dimensions — co-expression-guided gene partitioning, expression-aware contrast-set construction, and competence-gated contrastive onset. Specifically, we first construct two complementary views of each cell by partitioning its genes according to their co-expression structure. Then, to prevent the model from using gene-set identity as a shortcut, we construct hard negatives by permuting expression values while keeping gene identities unchanged. Finally, we introduce a competence-aware controller to determine how the contrastive objective is applied. Experiments on cell-type annotation and gene regulatory network inference demonstrate competitive transfer under the evaluated protocols. In the six-network GRN evaluation, our method records the highest mean AUROC and AUPRC point estimates among the compared variants, while the highest-scoring variant differs across individual networks. These results establish complementary-view contrastive learning as an effective direction for single-cell pretraining beyond gene reconstruction.

Flow Matching trains continuous-time generative models by regressing the velocity field of a probability path between a simple source distribution and a target data distribution. The coupling that pairs source and target samples strongly affects optimization and sample quality, but structured couplings typically rely on mini-batch transport or assignment procedures whose cost grows at least quadratically in batch size. We propose Quantile Coupling Flow Matching (QC-FM), a lightweight one-sided coupling: rather than matching two pre-sampled batches, it samples only the data batch and constructs each paired source directly. Data ranks projected along a small number of random orthogonal directions are mapped to Gaussian quantiles, and the latent code is completed in the orthogonal complement by conditional Gaussian sampling. The construction is one-dimensional per slice, so the coupling requires no pairwise cost matrix and no assignment to solve. We show that, for each drawn frame, this coupling eliminates the irreducible regression variance along every selected slice and makes the ideal flow exactly straight there, while leaving the sampling prior unchanged: generation still starts from the standard Gaussian, and the training source deviates from it only through the copula of the slice codes, whose transport cost we bound. For training, we apply QC to an anchor subset and complete the remaining source slots with exact Gaussian samples, retaining the QC bias while preserving an explicit signal from the Baseline coupling. Across CIFAR-10, CelebA, FFHQ, and ImageNet-64, QC-FM improves over the Baseline under matched training budgets, reducing FID by up to 12.9%, and outperforms OT-CFM on all four datasets. These results suggest that preserving projected rank structure is a simple and scalable way to inject useful geometric bias into FM couplings without solving a mini-batch transport problem.

This paper presents an interpretable machine-learning framework for predicting the splitting strength (ST) of asphalt concrete and supporting data-driven mixture design. A database consisting of 296 samples was established, and 14 input variables related to asphalt properties, aggregate gradation, and fiber characteristics were selected for modeling. Six machine-learning models, namely TabPFN, ANN, SVR, RF, XGBoost, and LightGBM, were developed and compared. Hyperparameter optimization was performed for five models using NSGA-II, while TabPFN was directly applied with its default configuration. The results show that all six models achieved satisfactory predictive capability, whereas TabPFN delivered the best overall performance on the testing set, with the lowest RMSE of 0.28, MAE of 0.21, MAPE of 18.01%, MAD of 0.14, the highest R^2 of 0.88, and the highest composite score of 0.91. SHAP analysis further revealed that nine dominant variables accounted for 92.0% of the total average contribution, among which Ag9.5, FT, Ag4.75, AC, and Du were the most influential. In addition, favorable parameter ranges for improving ST were quantified, such as Ag9.5 < 66.8%, Ag4.75 < 45.0%, AC < 5.4 wt.%, AV < 3.6%, and Du > 134.7 cm. Finally, a GUI platform integrating prediction and SHAP-based explanation was developed to improve the accessibility and practical applicability of the proposed framework.

The pinball-loss support vector machine is robust, but its asymmetry parameter is usually fixed in advance. We propose a data-driven elastic-net support vector machine that learns simplex-constrained weights over candidate pinball losses while retaining one classifier. The weighted loss is equivalent to a pinball loss with a data-dependent effective parameter. An empirical oracle inequality shows that, when weight regularization and simplex truncation vanish, the classifier objective at a global minimizer does not exceed that of the best fixed candidate; otherwise, the excess is explicitly bounded. For high-dimensional data, we develop a column-partitioned variable-splitting solver. It converges with a best-iterate $O(1/T)$ squared-step residual rate. Under common initialization and global parameters, any column partition produces, in exact arithmetic, the same iterates and solution as centralized training. Experiments assess predictive behavior, numerical equivalence, and multi-process scalability.

Existing 6-DoF grasp detectors typically rank grasp candidates by detector confidence. However, our analysis on GraspNet-1Billion shows that detector confidence is often poorly aligned with grasp quality, leaving successful grasp candidates at low ranks. Motivated by this observation, we study whether learned re-ranking can improve candidate ordering while keeping detector parameters and grasp candidates unchanged. We propose GraRe, which estimates grasp quality from candidate attributes, shell-stratified local geometry, and object context. Candidate attributes condition the local geometric and object-context representations, and a Transformer fuses all three feature types. The predicted quality is combined with detector confidence to produce the final ranking. Experiments on GraspNet-1Billion with five frozen detectors show consistent improvements, with gains of up to 13.56 points in Average AP. Real-robot experiments further demonstrate robust grasping in cluttered scenes. These results show that improving candidate ranking provides a practical way to enhance frozen 6-DoF grasp detectors. Project code is available at https://minakanmi-yuki.github.io/grare/.

Automated sleep staging assigns discrete stage labels to successive time epochs throughout an overnight recording; conventionally each window spans at least 30 seconds, reflecting the minimum temporal resolution of the clinical scoring standard. Wearable photoplethysmography (PPG) has attracted sustained interest as an ambulatory alternative to laboratory-based polysomnography, which relies on electroencephalography (EEG) and other recording modalities that are impractical outside clinical environments. Yet PPG-based staging trails EEG-based methods by a substantial margin, and we argue this gap largely reflects a mismatch between signal and task. Within a stable stage, PPG's inter-stage feature differences are more subtle than those in EEG; yet at stage boundaries, PPG's principal cardiovascular features, heart rate variability and pulse morphology, shift sharply within seconds. The conventional practice of assigning one label to each 30-second epoch therefore suppresses feature that is concentrated near boundaries. We address this gap in two steps. First, we develop a label expansion pipeline based on Hidden Semi-Markov Models that converts coarse epoch labels into sec-level annotations. To assess whether these expanded labels are reliable enough for downstream supervision, we validate them on a separate expert-reviewed dataset and through an auxiliary sleep-wake task whose labels are independent of the expansion pipeline. Second, we use the resulting sec-level supervision on MESA to improve conventional four-class epoch-level staging across four architecturally diverse baselines by 3.7–5.7\,pp in accuracy against the original epoch labels, with supplementary zero-shot evaluation on CFS showing that the transfer benefit persists under cohort and annotation-protocol shift.

Electronic Health Records (EHRs) are widely used for clinical risk prediction using machine learning. International Classification of Diseases (ICD) codes provide structured information about patient diagnoses, but representing them effectively remains challenging. Existing approaches often face a trade-off between predictive performance and interpretability: grouping-based representations are interpretable but may lose information, while embedding-based representations achieve strong predictive performance but are difficult to interpret. We propose Explainable Representation of Multiple ICD Codes (xMICD), a method for constructing low-dimensional patient representations from sets of ICD codes. xMICD combines clinically meaningful diagnostic groupings with similarity in a pre-trained ICD embedding space. Instead of using binary group membership, the method assigns codes to groups via similarity-based relative assignments, yielding features that reflect how closely a patient's diagnoses align with each clinical group. Experiments on large-scale EHR datasets demonstrate that xMICD achieves predictive performance comparable to embedding-based representations such as ICD2Vec across multiple clinical prediction tasks. At the same time, the resulting features remain clinically interpretable because each dimension corresponds to a recognizable diagnostic group. xMICD therefore provides a practical way to integrate embedding-based semantic relationships into interpretable clinical feature spaces for machine learning models.

Subtype robustness asks whether a model keeps the correct coarse prediction when test examples come from fine-grained subtypes absent from training but still inside a known coarse category. Prior work studies this almost entirely through accuracy. We ask whether the model also stays calibrated. We present the first systematic study of the question across ImageNet, BREEDS, iNaturalist and CIFAR-100 with five architectures. Calibration breaks down on unseen subtypes, where accuracy drops while confidence barely follows, leaving the model systematically overconfident exactly where it has become less accurate. At matched accuracy loss, generic image corruption causes a much larger drop in confidence, so the effect is not a general consequence of losing accuracy. The model reacts to visible degradation but not to in-taxonomy novelty. Recalibration tuned on seen subtypes narrows the gap but does not close it, and out-of-distribution scores flag the affected inputs only weakly. Subtype robustness should therefore be evaluated through calibration, not accuracy alone.

Modern reranking recipes—billion-scale cross-encoders, mixture-of-experts (MoE) backbones, and distillation against strong teachers—have outpaced the training infrastructure available to most academic groups. Existing Tevatron reranker training relies on the Hugging Face Trainer with DeepSpeed or PyTorch FSDP1, but these backends lack efficient support for large-scale MoE training. We present Tevatron 3.0, which integrates a Megatron-Core training backend into Tevatron while preserving its data pipeline, evaluation workflow, and Hugging Face-compatible checkpoints. We benchmark existing distributed training configurations against the new backend, showing that Megatron matches FSDP reranker quality and training efficiency under comparable data-parallel settings, is up to 22% faster in the recommended single-node configuration, and supports both LoRA and full-parameter fine-tuning. Crucially, expert parallelism enables training a 30B-parameter Qwen3-30B-A3B MoE reranker, which is infeasible with PyTorch FSDP1. Using this framework, we conduct a controlled comparison of MoE versus dense models, LoRA versus full-parameter tuning, and distillation versus contrastive training on BEIR-15 with three first-stage retrievers, and report serving throughput for Hugging Face and vLLM. We find that the MoE reranker matches dense 8B quality while activating less than half as many parameters and achieving substantially higher inference throughput. We will release the framework and trained checkpoints.

Uplift modeling (conditional-average-treatment-effect estimation) drives personalized targeting, yet published uplift benchmarks frequently disagree on which estimator performs best; we show the disagreement is substantially about metrics, not models. UpliftBench evaluates 12 uplift estimators under an outer-test-isolated, multi-objective protocol across seven dataset families; its two findings are identified where a reference objective exists – F1 on the standard continuous benchmark (IHDP), F2 in a within-sample case study on Jobs. On that benchmark, Qini shows no detectable alignment with effect accuracy – across all 100 IHDP realizations its mean rank correlation with effect accuracy is +0.07, 95% CI [-0.03, +0.16] – while AUUC is consistently more aligned (paired prefix-mean-AUUC-over-Qini gap +0.49 [+0.40, +0.59]; the shipped cumulative-gain AUUC aligns better still, +0.73). On Jobs, ranking metrics are structurally insufficient for a sign-threshold policy because they discard the score level; empirically, within the released split-rotation analysis direct policy-risk selection yields lower benchmark regret than random model selection while Qini, AUUC, and uplift-at-$k$ do not (14-15% regret). Calibrating the decision threshold removes 81% of the Qini-selection regret. Both findings are bounded, not universal: F1 is not detected on either validation family (the ACIC and Revenue-Synthetic gaps are both indistinguishable from zero), and F2 vanishes under a budgeted-value objective where rank suffices. UpliftBench releases versioned loaders, fixed protocols, result artifacts, and a reproducible living leaderboard; the public repository accompanies the paper.

Modern network policy control maps intent to sequential placement-control decisions. Bellman-style policy optimization primarily asks which action to optimize, while constraints are commonly handled through penalty, barrier, or Lagrangian mechanisms. We observe that before a value function can certify the best deployment, intermediate signals may already identify many candidates that should be excluded from further optimization. This motivates a complementary direction: Learning Not to Optimize. Before a value function is accurate enough to select the best placement-control decision, intermediate signals may already show that candidates are equivalent under state–intent relabeling (quotienting), lead to a uniformly worse future state (dominance), or violate executable network laws (residual screening). \LNOQRD{} uses these computed or learned signals as a shadow process to reshape the domain on which primal policy optimization is performed, thereby reducing the action space. We prove lossless quotienting and dominance under explicit equivariance and monotonicity conditions, bound frontier size and ranking cost, and quantify losses from approximate certificates and primal estimates. Experiments show that \LNOQRD{} reduces small-instance candidates by $75.9\%$ while retaining $90.8\%$ near-oracle coverage and, on large instances, achieves the highest utility and intent satisfaction, the lowest hard-law violation and post-generation latency, and a $73.0\%$ average reduction among candidate-based baselines.

Federated graph learning (FGL) enables multiple clients to collaboratively train graph models without sharing their private graph data, providing a promising paradigm for mining knowledge from distributed graph repositories. While most existing FGL methods focus on supervised tasks, real-world graphs are often massive and unlabeled, making federated graph clustering an important yet still immature research direction. Notably, this task is particularly challenging due to the inherent subgraph heterogeneity across clients, which leads to client-specific community structures. In this work, we identify two critical limitations in existing federated graph clustering methods: (1) unrealistic pre-defined cluster cardinality assumptions and (2) incomplete inter-community separation. To address these challenges, we propose AdaFGC, an Adaptive Federated graph clustering framework based on Global community-aware Contrastive learning. AdaFGC introduces an over-complete set of global community anchors to model the global community structure and adaptively estimate clustering cardinality via cross-client anchor refinement. In addition, it employs a global community-aware contrastive learning scheme that uses the shared anchors as contrastive prototypes to explicitly enforce community-level attraction and repulsion across clients, complemented by node-level and topology-level objectives that stabilize local representations. Extensive experiments on eight benchmark datasets demonstrate that AdaFGC consistently outperforms existing supervised and unsupervised FGL baselines across multiple clustering metrics.

The temperature that maximizes pass@$k$ is often low for a small sampling budget and higher for a large budget. This pattern has been reported from Codex through recent multi-sample inference studies. It is not an algebraic property of pass@$k$: as Slocum et al. (ICLR 2025) observe, for one fixed task the maximizing temperature is independent of $k$. Building on that fixed-task observation and the hard/easy-task explanation, we give a formal population-level sufficient condition for the aggregate pattern. For task $X$, let $p_t(X)$ be one-sample success probability at temperature $t$, and define the conditional log-success response $m_t(u)=\mathbb{E}[\dot p_t(X)\mid p_t(X)=u]/u$. If $m_t(u)$ is nonincreasing in current success probability, then the normalized temperature derivative of aggregate pass@$k$ is nondecreasing in $k$. Consequently, derivative signs are nested across budgets; if each temperature-performance curve is strictly single-peaked, its unique maximizer is nondecreasing in $k$. The proof identifies the mechanism as a monotone-likelihood-ratio power tilt toward lower-success tasks. We derive a closed-form two-stratum phase diagram, including upward and downward regimes, and show that the marginal temperature derivative admits an exact $\mathrm{Beta}(2,k)$ kernel representation whose kernel concentrates at one-sample success of order $1/k$. Interpreting that scale as task-level localization additionally requires a regular, nonvanishing density-response factor near zero. A signed-moment representation yields diagnostic shape restrictions, while a short appendix records exact discrete refinements of the existing multi-configuration allocation formulation. No language model is trained, and no model query is used as an experimental measurement: the contribution is a conditional theory of an established empirical phenomenon, with assumptions that can be tested in future work.

How can we determine whether a trained neural network is already deep enough? We study this under a fixed function-preserving residual-growth protocol specifying insertion locations, residual families, zero-output initializations, and zero-state first-order updates. We define first-order residual depth saturation as the absence of a strict local decrease from every admissible insertion. We prove residual non-degeneracy is necessary and sufficient: additional depth has first-order value exactly when conditional activation gradients have a nonzero projection onto at least one admissible residual tangent space. This boundary is shared by descent-compatible zero-state updates and invariant under regular local reparameterizations preserving that tangent space. Under residual-signal realizability, raw activation-gradient vanishing exactly certifies saturation. Across ResNets, GPT-2-style models, and continued-pretrained Pythia checkpoints, the maximum activation-gradient norm decreases toward a low-signal regime with depth. Function-preserving growth also achieves converged performance competitive with training from scratch. These results support activation-gradient magnitude as a conservative diagnostic of the remaining empirical first-order value of residual depth.