Papers

Neural Architecture Search (NAS) is naturally formulated as a bilevel optimization problem, where the upper-level optimizes the architecture using validation performance and the lower-level trains network parameters using training loss. However, NAS is computationally expensive due to discrete architectural decisions, exponentially growing search spaces, and the high cost of training candidate architectures. This work develops a general bilevel optimization framework for NAS across diverse architectures, including MLPs, CNNs, RNNs, and Transformers, to identify compact architectures with strong predictive performance. We propose three scalable formulations that replace discrete neuron- and activation-level decisions with continuous relaxations, enabling differentiable optimization over otherwise combinatorial architecture spaces. These formulations give rise to three NAS methods: NAS based on Neuron Gating (NAS-NG), NAS based on Mixed Activation (NAS-MA), and NAS based on Neuron Gating and Mixed Activation (NAS-NGMA). Experiments on MLPs and CNNs using MNIST and CIFAR-10 show that the proposed methods consistently identify compact architectures with competitive or improved predictive performance. On MNIST, NAS-NGMA achieves 98.68% test accuracy with 7.69M MLP parameters, while NAS-NG achieves 99.63% accuracy with only 0.26M CNN parameters. On CIFAR-10, the proposed methods consistently outperform vanilla DARTS. Further experiments demonstrate that NAS-NG can optimize substantially over-parameterized and literature-optimal architectures, improving accuracy while reducing parameters. These results establish relaxed bilevel optimization as a scalable alternative to discrete NAS and provide a general framework for efficient neuron- and activation-level architecture optimization.

Frozen image embeddings from models such as CLIP are increasingly used to classify paintings by art-historical style, with high reported accuracy. We ask whether this accuracy reflects an understanding of style or the recognition of individual artists. Standard evaluation uses random splits in which works by the same artist appear on both sides, so a classifier can succeed by recognising the painter rather than the movement. We re-evaluate style classification under an artist-disjoint protocol, holding out every artist in turn so that no work is ever classified using other works by its own painter. On a balanced dataset of 320 paintings across four twentieth-century movements, 5-NN style accuracy falls from 0.87 to 0.77 under this protocol, and the drop is sharply uneven. Impressionism and Cubism barely move, while Surrealism falls twenty points. The pattern holds across four image encoders, including a vision-only self-supervised model, which places the effect in visual structure rather than language. Where an encoder captures genuine shared form, individual artists are barely recognisable yet style is robust, while Surrealism shows the opposite. We argue that artist-disjoint evaluation is necessary to measure stylistic understanding in frozen embeddings.

Reinforcement learning (RL) post-training provides a direct way to align diffusion models with human preferences and task-specific rewards. However, current RL algorithms for diffusion models remain fragmented: reverse-trajectory methods rely on discretized likelihood ratios, whereas forward-matching methods train on reward-labeled noising versions of the rollout samples. This paper shows that these seemingly different losses arise from a single path-space principle. Starting from the regularized diffusion-RL objective, we use importance sampling between sampling SDEs to obtain an explicit policy-gradient estimator on trajectory space. The estimator contains the stochastic Itô integral underlying Flow-GRPO-type updates; we derive an equivalent variance-reduced value-gradient form that recovers the forward-matching structure of AWM and DiffusionNFT. This identifies the empirical gap between these method families as a variance-reduction effect rather than a difference in RL principle. The derivation yields a unified design space organized by value-gradient estimation, weight functions, and sampling choices. Within this space, we propose a multi-sample KDE value-gradient estimator that reuses rollout groups, together with scale-bounded weight families that retain stable existing recipes while excluding singular ones. Experiments on SD3.5-M and Qwen-Image models validate the variance-reduction explanation and show that the resulting recipe improves over prior diffusion-RL baselines.

Power Sampling sharpens a language model's distribution over complete generation trajectories, offering a verifier-free way to improve reasoning at inference time. It also has the potential to serve as a general-purpose front end for a broad range of downstream sampling methods. However, we uncover a striking paradox: Power Sampling can drive more probability mass toward correct trajectories while degrading the downstream inference it is intended to enhance. Using self-consistency as a representative case, we observe accuracy drops of up to 18.5 percentage points across models and reasoning benchmarks. We trace this paradox to two mismatches. Dose mismatch arises because a fixed exponent induces drastically different amounts of distributional change across problems. Coverage mismatch arises because global sharpening concentrates mass on a narrow set of dominant paths: high pass@k, often interpreted as evidence of preserved diversity, can therefore coexist with the loss of broad reasoning-path support required for downstream aggregation, search, and selection. Guided by this diagnosis, we replace uniform trajectory exponentiation with a deformation-controlled, support-preserving Power target that calibrates sharpening across problems while limiting the suppression of moderate-probability paths. In a same-budget instantiation with weighted self-consistency, the repaired sampler reverses the losses caused by global Power and outperforms standard multi-sample inference across reasoning benchmarks.

Cytometry measures the complex characteristics of single cells (e.g., counts and protein expression of immune cells) and is widely used across immunological research and clinical settings. However, cytometry data is highly heterogeneous and unstandardized due to experimental protocols and the choice of measured features. While machine learning methods hold the potential to gain deeper insights into cell biology, these challenges make them difficult to apply and transfer across studies. Recent advances in foundation models can alleviate these issues, but corresponding approaches are still scarce in this field. To address this, we provide CytoBERT, a publicly available, open-source, open-weight foundation model for single-cell cytometry data with variable marker panels. CytoBERT is pretrained in a self-supervised manner on a large-scale cytometry corpus (15 human datasets with heterogeneous marker panels and more than 50 million cells) curated through marker standardization, enabling it to learn transferable inter-marker relationships within cells. Fine-tuning CytoBERT for sample-level classification demonstrates that transfer learning across heterogeneous cytometry datasets is feasible, providing a starting point for scalable, generalizable cytometry analysis. Code is available at GitHub.

We study online statistical inference for functionals of the return distribution under a fixed policy. The return distribution is estimated by nonparametric distributional temporal-difference learning from a single Markov trajectory. For the Polyak–Ruppert averaged estimator, we prove that its root-$T$ error converges weakly to a centered Gaussian random element in Cramér space. We also prove that, conditionally on the observed trajectory, the root-$T$ difference between the bootstrap and original averages converges weakly to the same Gaussian limit. These results justify bootstrap inference for smooth statistical functionals, including variance, CVaR, expected shortfall, and expectiles. For nonsmooth statistical functionals, we develop a local asymptotic theory for the estimated return CDF over $T^{-1/2}$-neighborhoods of finitely many thresholds, together with its bootstrap analogue. This theory allows us to conduct inference for nonsmooth statistical functionals characterized by CDF equations, including return quantiles.

In offline RL, estimating the optimal action-value function $Q^*$ can be formulated as solving the optimal Bellman equation based solely on offline observations. A fundamental challenge is that the reward function and transition kernel are unknown, so the optimal Bellman operator is not directly observable from data. To address this issue, we propose a novel framework that decouples operator estimation from value function learning. In this approach, we first formulate conditional diffusion models to estimate the reward law and transition kernel, which induces a data-driven approximation of the optimal Bellman operator. We then plug these estimators into the Bellman equation and obtain a deep estimator of $Q^*$ by minimizing the empirical Bellman residual over a neural network function class. Theoretically, we first establish sharp nonasymptotic convergence rates for learning the optimal Bellman operator through an end-to-end analysis of conditional diffusion estimation in total variation distance. We then establish the oracle value-stage rate $\widetilde{\mathcal O}\bigl(n^{-\frac{2\beta}{d_x+d_a+2\beta}}\bigr)$ for the excess Bellman residual risk. Finally, under a concentrability condition, we translate this residual bound into an $L^2$ convergence rate of $\widetilde{\mathcal O}\bigl(n^{-\frac{\beta}{d_x+d_a+2\beta}}\bigr)$ for the resulting deep estimator of $Q^*$, where $d_x$ and $d_a$ denote the dimensions of the state and action spaces, respectively, and $\beta$ denotes the Hölder smoothness index of $Q^*$. Importantly, our theoretical analysis does not rely on completeness assumptions commonly used in deep RL theory. Extensive numerical experiments demonstrate the effectiveness of the proposed method and its strong empirical performance.

Mixture-of-Experts (MoE) models have been widely adopted in real-time interactive applications such as coding assistants, real-time audio-video interaction systems. To meet the extremely low response latency requirements of these scenarios, practitioners commonly employ small-batch decoding, under which MoE inference becomes memory-bound and is severely bottlenecked by expert weight loading. However, this bottleneck has received limited attention, and existing solutions such as post-training weight compression or fine-grained expert design during pre-training either degrade model accuracy or introduce additional computation and communication overhead. To tackle this issue, we propose DeaMoE, a decoding-efficient MoE architecture, in which the experts are grouped into several departments, and the experts belonging to the same department share most parameters since they come from the same professional field, and additionally each expert contains a few private parameters to reflect its uniqueness. Moreover, we design customized two-stage routing strategy for DeaMoE to avoid redundant loading, under which DeaMoE greatly improves the efficiency during LLM decoding. Compared with vanilla MoE, DeaMoE reduces per-step loaded weights by up to 50.9% and achieves up to 1.33 end-to-end TPOT speedup for the pre-trained 7B model on A40, and up to 2.00x and 1.97x peak speedup for DeepSeek-V3 on A40 and H100 in microbenchmarks.

Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which messages should shape a final answer. Such filtering assumes that a message likely to be correct is also worth keeping. Yet a wrong answer can contain a useful decomposition, constraint, or scientific principle. We test this distinction with Diverse Hypothesis Deliberation (DHD), a controlled measurement protocol that caches five independently generated messages and replays the same downstream solver, called the integrator, with each message available or hidden. The replay comparison measures a message's trajectory value: whether making the message available helps or harms subsequent reasoning. Across five mathematics and science benchmarks and two openly available model families, gpt-oss-120b and gemma-4-31B-it, wrong-helpful messages appear in every benchmark-model combination. Among wrong-answer messages that change final correctness, more than four in ten changes are helpful in each model. Controlled repeats show that the number of repeatable message effects is unlikely to arise from replay variation alone (p=0.0002). A focused intervention on repeatable wrong-helpful messages finds that the complete message works best, while retaining its reasoning preserves more success than retaining only its answer; the source of the complete-message advantage remains open. Within the same problem, repeated trajectory-value evidence also identifies a better keep-or-remove choice than answer correctness alone. Answer correctness is therefore informative but does not determine trajectory value. DHD measures this missing property and produces reusable labels for learning when agents should listen.

The symmetries of a learning task have become an important factor in designing modern deep learning solutions. Data augmentation is a straightforward and effective way of incorporating symmetries into a generic neural network. Recent results show that infinitely large deep ensembles show perfect symmetry when trained on augmented data. However, since training ensembles requires repeating the training process many times, this method is costly. In this work, we study stochastic weight averaging (SWA) applied to classification as an alternative ensembling technique that does not require repeated training runs. We analyze SWA by approximating the stochastic training trajectory at the end of training with an Ornstein–Uhlenbeck process. We show that in the infinite-width limit, SWA on augmented data provides an equivariance boost that goes beyond what could be expected from the performance increase due to SWA alone. We verify our results with extensive numerical experiments on numerous models spanning image and graph classification with both discrete and continuous symmetries.

Scientific data often describe entities whose features are jointly governed by the laws of physics, yet existing self-supervised learning (SSL) objectives largely ignore this physical coherence. We introduce imposter, a discriminative pretext task that replaces subsets of an entity's features with real observations donated by another entity and trains the encoder to identify the swapped features. Because every donated value is individually plausible, the task can only be solved by learning cross-feature physical dependencies. We evaluate the proposed objectives on global ERA5-Land reanalysis data using 21 environmental variables and assess the learned representations on seven downstream tasks spanning climate classification, carbon flux estimation, and streamflow prediction. Our study includes, to our knowledge, the first systematic comparison of self-supervised objectives for land-surface modeling under a shared architecture and pre-training budget. We find that the most effective pretext task depends on the downstream task family rather than any single objective's superiority, and that imposter provides complementary information when combined with existing SSL objectives. These results suggest that physical coherence is a valuable new source of self-supervision for scientific foundation models.

We consider the notion of shattering introduced by Ben Arous and Jagannath for spherical pure $p$-spin glasses with overlap $q$. For every $p\geq 3$ and $0<\beta\leq\beta_{\mathrm{sh}}(p)$, we rule out shattering whenever $q\leq2^{-1/2}$ or $q>\sqrt{(p-2)/(p-1)}$. The proof combines a deterministic $N+1$ bound for disjoint bands in the first range with a general-$p$ sign law showing that their total marked weight has subdominant free energy in the second. A spherical-code bound and Hölder's inequality give an additional $q$-dependent obstruction; in particular, they rule out every fixed overlap for $0<\beta\leq\sqrt{\log2}$. For $p=3$, the first two ranges already exhaust every fixed $q\in(0,1)$, so the landscape is not shattered at any $T\geq T_{\mathrm{sh}}$. For $p\geq4$, the cases not covered by our criteria are confined to $2^{-1/2}<q\leq\sqrt{(p-2)/(p-1)}$ and $\sqrt{\log2}<\beta\leq\beta_{\mathrm{sh}}(p)$. In particular, this paper partially resolves Conjecture 1 of the paper above and also suggests new methods to show non-shattering.

The early detection of delayed cases in business processes is a critical capability for organizations. Predictive process monitoring (PPM) supports this task by using historical event logs to predict the remaining time of ongoing cases, enabling timely interventions to avoid missed deadlines and service level violations. Although remaining time prediction has advanced considerably through sophisticated deep learning architectures, little is known about the intrinsic difficulty of delay detection itself. Since performance is typically assessed using aggregate metrics, prior work provides limited insight into how models perform across the target distribution, especially on the operationally most critical cases with large delays. In this paper, we address this gap by analyzing the difficulty of delay detection. Across 14 event logs, we show that remaining times are typically strongly right-skewed, with only a small fraction of cases exhibiting large delays. Existing models capture the mode of this distribution well but perform poorly on high-delay cases. We further uncover pronounced heteroscedasticity, showing that predictive uncertainty increases with delay magnitude. Based on these findings, we evaluate approaches to mitigate the imbalance problem, but find only limited benefits, suggesting that the key underlying problem may not be imbalance but higher uncertainty associated with delayed cases. We show that this correlation can be exploited to substantially improve the identification of delayed cases. Overall, our work provides new insights into the sources of difficulty in delay detection and identifies uncertainty-aware modeling as a promising direction for future PPM research.

Large Language Model (LLM)-based agents are increasingly used for complex tasks such as software testing and cybersecurity assessment. While these agents demonstrate impressive capabilities, their behavior is difficult to understand, explain, and analyze. Existing evaluations focus mainly on task success and execution traces, offering limited insight into the strategies employed by the agent. We present ATLAS (Automata Learning for Agent Trajectory Analysis and Strategy Discovery), an approach for recovering interpretable behavioral models from agent trajectories. ATLAS combines trace abstraction with automata learning to infer finite-state models that capture observed agent-environment interaction strategies. These models provide human-interpretable insights and support automated analyses of recurring behaviors, decision points, successful task-completion paths, and failure loops. As a proof of concept, we apply ATLAS to trajectories generated by an LLM-based penetration-testing agent. The resulting models expose high-level behavioral strategies for exploiting vulnerable machines that are difficult to identify from raw execution traces alone. We discuss how learned behavioral models can support explainability, model-guided exploration, auditing, and analysis of agentic systems. We further demonstrate symbolic model-based knowledge transfer from powerful frontier models to compact language models. In addition, we show how model transformations can derive concise explanations of agent behavior in a penetration-testing case study comprising 12 vulnerable machines. ATLAS highlights a new opportunity for model-driven engineering: transforming agent trajectories into explicit behavioral models that enable systematic understanding and analysis of otherwise opaque AI agents.

We present a training-free method for multi-modal trajectory prediction that achieves comparable accuracy to a 57M-parameter transformer while requiring no GPU and zero learned parameters. The method builds a transition table of historical state-to-next position pairs and retrieves neighbors using a product kernel over spatial proximity, bearing, speed, and temporal context. Two inference modes operate over this shared representation: diversity-penalized sampling produces trajectories covering distinct plausible routes, while beam search finds the highest-likelihood path. On the TrAISformer benchmark (Danish Maritime AIS), our method achieves competitive accuracy at full data availability and dramatically outperforms the transformer in data-scarce regimes—remaining stable down to 10% of training data where TrAISformer degrades catastrophically. This enables deployment in new geographic regions from an order of magnitude less historical data.

We study proactive exploration in LLM agents, i.e., the ability to explore an environment to acquire information that improves future decision-making. In this regard, we first identify two fundamental bottlenecks that hinder this capability and then propose \ours, a novel method designed to instill and refine proactive exploration. Specifically, \ours\ consists of two components: (1) Exploratory Data Construction, which synthesizes exploration-rich trajectories to mitigate the hindsight bias of standard demonstrations; and (2) RL Optimization with Contrastive Signal Guidance, which leverages contrastive trajectory pairs to distinguish productive exploration from redundant wandering. Extensive experiments demonstrate the effectiveness of \ours\ and provide insights into the characteristics of proactive exploration. Our code is available at: https://github.com/GuanZhizhao/SAFARI.

Reinforcement learning is promising for autonomous urban driving, but long-horizon goal-directed navigation asks a policy to acquire several competing behaviors at once–reaching a distant goal, tracking a route, avoiding obstacles, obeying signals–and a fixed objective gives no order in which to learn them. This paper presents CORAL, which advances two schedules together: a five-stage curriculum that progressively lengthens routes and tightens behavioral constraints, and a stage-aware reward whose component weights shift emphasis from mission progress toward route following, safety, smoothness, and rule compliance as the task hardens. The policy is a multi-stream actor-critic network trained with Proximal Policy Optimization (PPO) in CARLA on a compact 99-dimensional state pairing a polar LiDAR histogram with vehicle telemetry, ego-frame route geometry, and traffic-rule indicators–no point-cloud encoder, no bird's-eye-view rasterization. Against two PPO baselines under an identical protocol, CORAL reaches the goal in all twenty evaluation episodes on the longest routes under the full set of behavioral constraints, where the baselines reach 5% and 10%; a factorial ablation shows that neither schedule alone matches their combination: removing either lowers both success and route completion, and disabling both drops success to 55%. Trained in one town, the policy transfers zero-shot to seven unseen towns, succeeding in 68-98% of episodes on routes of the same 100-150 m length, with mean lateral deviation below 0.35 m.

Principle-based regulation, with evaluative standards such as "fair, clear, and not misleading" or "deliver good outcomes", cannot be reduced to binary predicates, and LLM-as-judge is increasingly used as the substitute. Our position is that any such judge must be evaluated on four axes: accuracy, paraphrase robustness, adversarial robustness, and calibration. We release Principle-Bench, 168 cryptoasset financial-promotion scenarios mapped to two UK FCA principles, with paraphrase, adversarial keyword-stuffing, and boundary perturbations authored under a pre-registered rubric; the first benchmark covering all four axes for principle-based regulation. We also introduce Ceca (Calibrated Exemplar-Cluster Assessment): a calibrated, auditable assessor that emits exact per-exemplar counterfactual attributions. Across keyword counting, three sentence-transformer embedders, an open-weight LLM-judge, and a calibrated cascade, no method dominates all four axes. A 120B LLM-judge, strongest on benign inputs, loses 47 accuracy points (0.74 to 0.27) on keyword-stuffed Consumer Duty inputs: "compliance theatre." A second judge from a different model family agrees only at Cohen's kappa = 0.16 on that split, localising the failure to the model rather than the corpus. Any deployment-grade LLM-judge for principle-based regulation must report per-principle adversarial deception and post-hoc calibration alongside aggregate accuracy.

We study quantum multi-armed bandits (QMAB) and quantum linear bandits (QLB), where the learner queries each arm or action through a quantum reward oracle or its inverse. Prior work gives algorithms over horizon $T$ with regret $O(K\log T)$ for QMAB with $K$ arms and $O(d^2\operatorname{polylog} T)$ for $d$-dimensional QLB. This leaves open the optimal dependence on $K$ and $T$ and whether the dependence on $d$ can be further improved. In this work, we prove the first tight minimax regret bound of $\Theta(K\log(1+T/K))$ for QMAB and the first lower bound of $\Omega(d\log(1+T/d))$ for finite-action QLB, ruling out regret independent of $T$. Our lower bounds rely on a high-confidence single-arm quantum testing lower bound for distinguishing a fixed reward mean from an interval of alternatives. A bandit-to-testing reduction then lifts it to the QMAB lower bound, while a linear embedding gives the finite-action QLB lower bound. The matching QMAB upper bound is obtained using a tail bound for the Quantum Monte Carlo (QMC) estimator. For finite-action QLB, we propose a phased elimination algorithm that combines a low-bias low-variance quantum mean estimator with a small-support $G$-optimal design through a query allocation matched to the design weights. When the action set has size $\operatorname{poly}(d)$, its regret is nearly linear in $d$ and matches our lower bound up to polylogarithmic factors.

This research developed a neural network-based model to extract various information from 2D floor plans. We detect lighting symbols, identify the appropriate type of light, and extract the associated texts with lights. The study aims to enable efficient floor designing and determining the number and type of lights needed per floor, i.e., allow efficient design and estimate the power requirement of the floor plan. The model was developed using Mask RCNN as the base. The images were annotated and converted into a Coco data format for training the model. The model achieved bbox\_mAP and segm\_mAP values of 0.7596 and 0.7111, respectively. It also performed well at different IoU thresholds, i.e., with bbox\_mAP 50 and segm\_mAP 75 values of 0.9850 and 0.9219, respectively. The developed model will help various industries, such as architecture and construction, to improve design time and create efficient workflows by automatically detecting Mechanical, Electrical, and Plumbing (MEP) objects from floor plans, and it is the first step towards building tools that will help energy-efficient building design.

We study score-matching diffusion models with a convolutional architecture. We argue that the inductive bias of locality means that the machinery of effective field theory from physics can be usefully applied to describe the denoising dynamics. We apply this formalism first to a simple toy example which permits an analytical description, and thereafter to MNIST, and show that in both cases, the mutual information between two points grows in a manner predicted by a simple effective field theory of Brownian motion.

Large language models (LLMs) are increasingly used for code generation, yet they remain vulnerable to prompts that elicit insecure implementations. Existing defenses typically rely on predefined threat models or known vulnerability patterns, limiting their effectiveness against novel attacks. We propose CodeSIFT, a threat-model-agnostic detection method that leverages influence functions to identify batches of prompts that induce anomalous model behavior. Rather than detecting specific vulnerabilities, CodeSIFT measures the parameter-space influence of generated code and uses a statistical test to determine whether a candidate prompt set deviates from a benign reference distribution. To evaluate our approach, we introduce two benchmark datasets covering a variety of vulnerabilities. We evaluate CodeSIFT on three open-weight code LLMs ranging from 3B to 7B parameters, achieving AUROC scores of up to 0.98 at moderate-to-high injection rates, while maintaining well-calibrated false positive rates and substantially outperforming static analysis baselines. These results suggest that influence-function-based detection is a promising direction for identifying malicious code-generation prompts without requiring prior knowledge of the underlying attack class.

High-content microscopy enables systematic profiling of cellular responses to chemical perturbations, but the scale of the chemical space makes exhaustive phenotypic characterization experimentally infeasible. This motivates computational models that can predict image-derived phenotypes without acquiring the corresponding treated cells. We formulate molecule-induced phenotype prediction as an inductive conditional transport problem in image representation space. Given a negative-control phenotype and the structure of a molecule, we aim to predict the phenotype induced by the corresponding molecule. We first evaluate classical optimal transport baselines and show that static couplings do not yield useful predictions on large-scale phenotypic image datasets. We then introduce a molecule-conditioned Neural Optimal Transport (NOT) model with a Monge-Gap regularization training objective that learns to transport negative-control unperturbed phenotypes toward perturbed phenotypes using molecular structure as conditioning information. NOT recovers molecule-specific phenotypic effects while reducing microscopy-associated technical variation, thereby facilitating comparisons across experimental batches. On unseen active molecules, the model outperforms baseline approaches, demonstrating that chemically conditioned transport can generalize beyond the molecules observed during training. We identified the molecular encoder as the main limitation to this generalization, while transport in a compressed representation space improves performance and scalability. These results establish NOT as a promising framework for predicting cellular phenotypes from molecular structure and negative-control phenotypes, while highlighting the development of more informative molecular representations as a key direction for improving out-of-distribution performance.

We propose multiple new convex losses for SVM and Neural Networks, applied to binary classification tasks. While there are practical limitations in exploiting them with the dual SVM models, we are able to use them with SVM primal formulation and Neural Networks. In detail, the primal SVM problem with the modified losses has been solved with the Particle Swarm Optimization algorithm. We prove that the proposed losses are a generalization of the standard loss, and we experiment them with several small data-sets. This preliminary study shows that using pattern correlations inside the loss function could in theory enhance the generalization performances on some data-sets. To evaluate the performance of each loss, we adopt a Nested Cross-Validation procedure. Results show that generalization measures are the same with or without the new losses.

We present Pairton, an iterative framework for reconstructing short-lived particles in high-energy collision events. By formulating particle reconstruction as a masked prediction process over graph structures, Pairton learns conditional distributions consistent with a factorised decomposition of decay products and iteratively predicts edges in the adjacency matrix representing particle decay relationships. Leveraging a pairformer-based architecture with dynamically updated pairwise representations, our method incorporates global event consistency. We demonstrate state-of-the-art performance on fully hadronic $t\bar{t}$ decays. Pairton provides a general, flexible paradigm for particle reconstruction and can be readily extended to other topologies, bridging ideas from modern generative modelling and high-energy physics.

Model merging combines trained models directly in weight space, offering a compute-efficient alternative to additional fine-tuning. Selecting merge parameters is nevertheless difficult because downstream evaluations are expensive, gradients are unavailable, and source capabilities can conflict. We formulate merge-parameter selection as a black-box multi-objective optimization problem and introduce MOBO-Merge, a merge-operator agnostic framework that uses multi-objective Bayesian optimization to approximate the Pareto front under a limited evaluation budget. We evaluate Qwen3-4B and Llama-3.1-8B in two-model instruction-math and three-model instruction-math-code settings using Linear, SLERP, TIES, and block-wise merge operators. On held-out benchmark partitions, MOBO-Merge obtains higher mean hypervolume than random search in 11 of 12 reported comparisons. The gain is small for one-dimensional Linear interpolation but substantially larger for several TIES, block-wise, and three-objective searches. No merge operator is uniformly best: TIES leads in three of four family-setting combinations, whereas Block-Linear 4x is strongest for the Llama three-model merge. These results show that multi-objective Bayesian optimization is valuable as a search layer for expressive merge parameterizations.

Which meteorological processes control exposure to fugitive gases downwind of a source, and on what timescales, have largely been inferred from dispersion theory and partial field evidence. Here we show that the meteorological drivers of elevated hydrogen sulphide (H$_2$S) exposure at a long-monitored European landfill, and the timescales over which each acts, can be identified directly from monitoring data. Wind direction, wind speed and atmospheric pressure form the causal core, with the share of directed information carried by pressure increasing with aggregation scale. The recovered timescales are consistent with those expected from the underlying atmospheric processes. We use these driver timescales to initialise CAIRN (Causal-Anchored Inference for Receptor Nowcasting), a machine-learning nowcaster with fast and slow memory components. Trained on past exceedances of WHO guideline levels, CAIRN nowcasts them from surface weather measurements and the calendar alone, without hand-engineered features. Combining four such nowcasters produces a site-level, tiered alert that agrees substantially with that generated by a direct sensor network and tracks an independent record of community odour reports. Meteorological variables can therefore serve as an inference-time proxy for exposure relative to WHO guideline levels, and they link atmospheric dynamics to community impact as an episode unfolds.

In social insects, mortality risk comprises distinct components that may not share the same predictors: lifespan duration, senescence trajectory, and thermal vulnerability. We tested these three axes in 18 Australian ant species using paired field-laboratory survival assays (2,363 cohort-day observations; 1,148 workers). Body size predicted duration (Cox HR = 0.67, p = 0.002), while colony size (p = 0.60) and the size x temperature interaction (p = 0.72) showed no detectable moderating effect. A weak but significant size x foraging-rate interaction was detected (LRT p = 0.014), suggesting that intrinsic physiology remains the most parsimonious explanation for the main size-longevity pattern, although ecological context may contribute. Senescence trajectory was associated with circadian niche rather than size: it was steepest in matinal species (Kruskal-Wallis p = 0.009; matinal vs. crepuscular p = 0.002) and was uncorrelated with body mass (Spearman p = 0.32). Thermal hazard plateaued above 20 degrees C (Delta AIC = -38; p < 0.001), with elevated thermal sensitivity in Rhytidoponera (Ectatomminae) above the plateau (5% per degree C, p = 0.015). Circadian regime and lineage identity, not body size, therefore emerge as the most climate-relevant axes, although they are strongly collinear (Cramer's V = 0.85). These results show that body size captures only one dimension of mortality risk and that size-based vulnerability indices may misrank taxa when senescence and thermal sensitivity are decoupled from body size.

Life science knowledge graphs make large collections of structured data available through SPARQL, but each resource uses its own schema, identifiers, and links. TogoMCP helps language model agents query these resources by providing curated Metadata Interoperability Exchange files. Creating and maintaining these files still requires language model assisted drafting, validation, and manual review. We study live schema grounding, where an agent obtains the schema evidence needed for a question directly from the current endpoints. We present autoschema, a general framework for live schema grounding that requires no training. It inspects live schemas, maps entity names in a question to graph identifiers, explores relation paths, and finds possible connections between resources during iterative query construction. We use TogoMCP as our main comparison framework. We evaluate autoschema on Resource Focused Biomedical KGQA, Multi Resource Biomedical KGQA, Longitudinal Biomedical Semantic QA over BioASQ Task B, and Chemistry Knowledge Graph Transfer to a previously undocumented RDF graph. autoschema improves mean factoid accuracy over TogoMCP in the biomedical KGQA tasks and gives consistent gains in the longitudinal BioASQ evaluation. It also reduces iteration budget exhaustion and uses fewer tool calls on average in the core evaluation. The transfer study gives preliminary evidence that live schema grounding can support irregular and previously unseen graphs without first creating a curated schema file.

A spectral foundation model should remain useful when laboratories preprocess spectra differently. The standard test trains a classifier under one pipeline and evaluates under another, taking preserved accuracy as evidence of learned invariance. However, these models normalize each input before any learned parameter is applied. When normalization maps differently preprocessed spectra to the same vector, the encoder receives identical inputs and the measured invariance cannot be attributed to learning. We propose a normalization-only attribution control: compare the encoder against its normalization before interpreting transfer as learned invariance. On six Raman datasets the encoder does not measurably improve transfer over its normalization. A controlled experiment confirms invariance develops only when variation reaches the encoder past normalization. Across three systems, no encoder improves relative retention over its normalization. An audit of eighteen configurations across five modalities confirms the issue is widespread: the normalization-only control should be reported before crediting transfer to the encoder.