Papers

Compute-optimal scaling laws guide the training of frontier language models yet remain largely unexplored for visual generation. We present a systematic scaling law study for text-to-image diffusion models using Abra, a controlled family of flow-matching transformers trained across three orders of magnitude worth of compute ($10^{19}$ to $10^{22}$ FLOPs), reaching significantly larger compute budgets than previous works. We demonstrate that diffusion models scale just as predictably as language models but require far more data to train optimally: compute optimality occurs at approximately $200$ image tokens per parameter, ten times the Chinchilla compute-optimal prescription for LLMs. We show that unlike language models, diffusion models are robust to overtraining and that practitioners should err on the side of more data rather than a larger model. Finally, we show that this predictability extends beyond training loss to generative quality metrics, optimal CFG settings, representation quality, and even the shape of the training curves, which collapse onto a universal form.

Irregular time series forecasting is crucial in many domains, such as healthcare and meteorological observation. However, due to the inherent characteristics of irregular time series, including sparse observations and non-uniform sampling, accurately predicting future dynamics remains challenging. In light of these two characteristics, many existing methods aggregate irregular observations into fixed-dimensional estimated response coefficients through predefined basis functions and use these coefficients as sequence representations. Nevertheless, this modeling paradigm still suffers from two key limitations: (i) a potential non-vanishing asymptotic bias caused by ignoring the sampling density of timestamps; and (ii) the limited adaptability of predefined basis functions to diverse temporal patterns. In this study, we propose a Debiased Neural Basis-Function Network (DNBNet) to address these challenges. Its core is a debiased neural basis-function response mechanism, which corrects asymptotic bias through importance sampling while parameterizing basis functions with neural networks to adapt to diverse temporal patterns. In addition, considering the sparsity of irregular data, we design a novel multi-scale decomposition module based on average pooling, together with a mass-aware fusion mechanism, to obtain richer representations. Finally, a dual-branch decoder is employed for forecasting. Extensive experiments on multiple real-world datasets demonstrate the effectiveness of DNBNet and its strong generalizability across diverse irregular time series scenarios. Our code can be obtained at https://github.com/hnu-vis/DNBNet.

Curriculum learning has been widely adopted in the post-training of large language models by organizing training data from easy to hard. However, its effectiveness varies substantially across reasoning tasks, suggesting that no single curriculum is universally optimal and raising a fundamental question: what determines when curriculum learning works? In this paper, we answer this question by analyzing the optimization dynamics induced by different curriculum schedules. We show that the transfer relationship between different difficulty levels characterizes the optimization dynamics induced by curriculum learning, which in turn explains the effectiveness of different curriculum schedules, and formalize this relationship as Relative Transfer, a principled measure of cross-difficulty knowledge transfer. Based on this measurement, we derive Transfer-aware Dynamic Curriculum Sampling (TDCS), which dynamically adjusts the sampling distribution according to the estimated transfer relationship throughout training. Extensive experiments on multiple reasoning benchmarks demonstrate that TDCS consistently outperforms representative scheduling strategies across different tasks, model scales, and training paradigms. More importantly, our work provides a unified optimization-based explanation of curriculum learning through cross-difficulty transfer.

Reinforcement learning (RL) has emerged as a powerful approach for improving reasoning in language and vision-language models, yet its strongest successes still depend heavily on ground-truth supervision (e.g., verifiable reward). Such annotations are costly to obtain and become increasingly scarce as reasoning capabilities advance beyond what humans can reliably evaluate. Self-rewarding RL reduces this dependence by enabling models to derive reward signals from their own completions. However, training solely on self-generated feedback can reinforce existing biases and suboptimal behaviors, reduce response diversity, and ultimately lead to homogenized responses and training collapse. In this work, we show that unsupervised reasoning can emerge through cooperative multi-agent training. We introduce Co-RL, a framework in which multiple decoupled models, sharing no parameters, are simultaneously optimized through RL using rewards derived from their peers. We further show that increasing cohort diversity, through heterogeneous model families, sizes, and rephrased training samples, reduces the correlated errors that drive self-reinforcing feedback loops. This diversity consistently improves reasoning performance, maintains behavioral diversity, and mitigates training collapse. Across text-only and multimodal domains, Co-RL consistently outperforms the base models and prior label-free approaches, while matching or surpassing supervised methods, without access to any ground-truth labels. Concretely, Co-RL yields average gains of 3.0-8.6% across seven text-only benchmarks for LLMs and 2.3-7.2% across four multimodal benchmarks for VLMs. Code is available at https://github.com/DrStranded/Co-RL.

This paper develops an adaptive surrogate modeling method for problems with very high-dimensional spatio-temporal outputs. The analysis of spatio-temporal multi-physics systems is computationally expensive and consists of a large number of inputs and outputs. Surrogate models are often constructed to replace the physics-based model to achieve computational efficiency in analyses such as uncertainty quantification and optimization that require many function calls. In order to address the challenge introduced by the high dimensionality of spatio-temporal output, a dimension reduction method is first employed to map the high-dimensional output to a low-dimensional latent space. This is followed by the construction of the surrogate model in the low-dimensional space. The prediction error in the original space, which includes both the reconstruction error and surrogate model error, is evaluated using different error metrics. Based on the prediction accuracy of the surrogate model, new training points are identified for adaptive improvement of the surrogate model. We present a novel adaptive sampling technique that combines exploration and exploitation to improve the surrogate model accuracy with the fewest possible runs of the expensive physics-based model. Thermo-mechanical analysis of a gas turbine engine blade is used to analyze the effectiveness of the proposed method.

When computational models (either physics-based or data-driven) are used for the sensitivity analysis of engineering systems, the sensitivity estimate is affected by the accuracy and uncertainty of the model. This paper considers global sensitivity analysis (GSA) for situations where both a physics-based model and experimental observations are available, and investigates physics-informed machine learning strategies to effectively combine the two sources of information in order to maximize the accuracy of the sensitivity estimate. Two representative machine learning (ML) techniques are considered, namely, deep neural networks (DNN) and Gaussian process (GP) modeling, and two strategies for incorporating physics knowledge within these techniques are investigated, namely: (i) incorporating loss functions in the ML models to enforce physics constraints, and (ii) pre-training and updating the ML model using simulation and experimental data respectively. Four different models are built for each type (DNN and GP), and the uncertainties in these models are included in the Sobol indices computation. The DNN-based models, with many degrees of freedom in terms of model parameters and training options, are found to result in smaller bounds on the sensitivity estimates when compared to the GP-based models. The proposed methods are illustrated for additive manufacturing and lake temperature modeling examples.

This article investigates several physics-informed and hybrid machine learning strategies that incorporate physics knowledge in experimental data-driven deep-learning models for predicting the bond quality and porosity of fused filament fabrication (FFF) parts. Three types of strategies are explored to incorporate physics constraints and multi-physics FFF simulation results into a deep neural network (DNN), thus ensuring consistency with physical laws: (1) incorporate physics constraints within the loss function of the DNN, (2) use physics model outputs as additional inputs to the DNN model, and (3) pre-train a DNN model with physics model input-output and then update it with experimental data. These strategies help to enforce a physically consistent relationship between bond quality and tensile strength, thus making porosity predictions physically meaningful. Eight different combinations of the above strategies are investigated. The results show how the combination of multiple strategies produces accurate machine learning models even with limited experimental data.

Low-cost, scalable screening for dementia remains an open problem. Imaging-based diagnosis is costly and hard to deploy widely. Electroencephalography (EEG) is portable and inexpensive, but its recordings are noisy, vary widely across subjects, and carry few clinical labels. We tackle this with Delta2Gamma, a self-supervised framework that learns EEG representations from unlabeled data by contrasting augmented views of each signal. Rather than treat EEG as a single stream, Delta2Gamma decomposes every recording into the five canonical neural rhythms (delta, theta, alpha, beta, gamma). Each band gets its own encoder and projection head. Each also gets a temperature that is predicted adaptively during contrastive training, so bands with different signal statistics are balanced automatically. On the ADFTD cohort under a strict leave-one-subject-out protocol, Delta2Gamma separates Alzheimer's disease from cognitively normal controls with 92.4% accuracy. This exceeds both supervised backbones and recent dedicated EEG methods.

Financial-news direction prediction has become a popular NLP benchmark, yet reported gains depend critically on whether the train-test split is chronological or random, i.e., on temporal leakage. We audit this dependence on a 49,799-article corpus across 16 feature-model combinations spanning TF-IDF, MiniLM, FinBERT, and fine-tuned RoBERTa-large / DeBERTa-v3-large, plus separate zero/few-shot and LoRA probes of Llama-3 and Qwen2.5 LLMs: random splits inflate MCC by $1.1\times$ to $6.5\times$, tracking model capacity and feature richness, and end-to-end FinBERT fine-tuning re-amplifies rather than closes the gap (size-matched ratio $1.75\times$). Conditioning on event type, mergers and acquisitions (M&A) is the only audited category with a positive locked-test signal under near-temporal chronological evaluation (TF-IDF MCC $= 0.138$ train-only, $0.068$ under train$\cup$val refit; 10,000-permutation $p < 10^{-3}$); the signal does not transfer to FNSPID's 2009-2020 U.S. corpus, localising the headline to our 2024-2025 European-tilted M&A semantics rather than a universal predictor. Three independent role labellers converge on acquirer-tagged articles as the signal locus, a power-limited qualitative convergence rather than a hypothesis-tested asymmetry. Chronological splitting plays for financial NLP the role characteristics-purging plays for asset pricing: it strips the predictable, stale component of news and leaves a residual that is small, event-localized, and lexically shallow. We advocate leakage audits as a required disclosure for financial-NLP benchmarks.

Multimodal attributed graphs combine graph structure with node text and image representations in recommendation and multimedia analysis. Graph predictors propagate these representations across connected nodes, so one input can change predictions at its own and nearby nodes. Measuring this distributed response reveals which modality-specific inputs a trained model relies on and how predictor design changes that reliance. We study influence measurement for modality-specific node representations. Given an encoded graph, a trained predictor, a training split, and fixed candidate representations, the task outputs one influence score per candidate and separate text and image rankings. We score a candidate by replacing it with its modality's training-node mean and comparing the original and changed predictions. Existing feature attribution and data valuation generally target one output, training examples, whole nodes, or graph elements rather than prediction changes across graph nodes. Our empirical study shows that nearby-node responses contain information missed by source-only scores and simple proxies, while response magnitude alone does not identify which class changes support the task. Guided by these observations, we propose MoGI (Modality-specific Graph Influence). It propagates training labels to define task direction, reads the same replacement response for the favored class and full class distribution, and averages the resulting ranks. MoGI requires no predictor retraining or learned scoring parameters. Under a shared five-dataset, eight-predictor benchmark, it achieves the largest aggregate held-out loss increase against all five external methods at every tested ranking cutoff.

Mechanistic interpretability reverse-engineers transformer circuits one input at a time, leaving observed mechanisms without guarantees over bounded input neighbourhoods. We address this gap with a framework based on constrained polynomial-zonotope (CPZ) propagation that lifts mechanistic-interpretability observations from a single input to certified statements over a bounded set of perturbations. Three internal-attention queries (top-$k$ stability, evidence mass, and attention entropy) are formulated as tractable programs over the simplex of attention weights, and CPZ propagation through transformer blocks is shown to preserve the softmax simplex and the LayerNorm zero-mean identity exactly. A recursive Jacobian zonotope construction extends the same certificates across layer depth by linearising the block stack at the input and avoids per-layer generator growth. We instantiate the framework on transformer attention; the resulting certificates offer a way to sharpen mechanistic statements that single-input inspection cannot resolve on its own, and to inform downstream decisions in regimes where empirical heuristics may be misleading.

Selective on-policy distillation trains a student only at the token positions a selector scores highest, and the literature compares selectors under a single shared learning rate–a control chosen to be neutral. We show it is not. Under LoRA on GSM8K (Qwen2.5-1.5B student, 7B teacher), across an 8x learning-rate grid, dense supervision is statistically flat (swing 1.8 pp, p=0.26) while every selective arm moves with the rate: 5.4 pp for a random 5% subset, 6.7 pp for a total-variation selector, up to 17.7 pp for a teachability selector. Consequently the dense-versus-selective verdict reads 10.1 pp at lr=1e-4 but 5.1 pp at 5e-5–a 2.0x difference decided by a parameter the protocol treats as scenery–and two of six pairwise significance calls between selectors flip between adjacent rates without any rank inversion. We call this selector-rate entanglement and trace it to selection itself rather than step size: AdamW update magnitudes track the rate to within 2.2% despite 15.5x gradient-norm differences across arms. A preregistered frozen-scoring ablation (selection scored by the initial student; criterion, budget, and on-policy rollouts unchanged; 12 seeds per cell) shows live scoring adds 3.79+/-1.69 pp of rate sensitivity (p=0.035) while the frozen arm remains significantly entangled (p=0.015): the feedback loop aggravates the phenomenon rather than causing it. Under full fine-tuning at the rates this literature actually uses (1e-6 to 1e-5) the pattern grows: dense itself swings 19.8 pp, the selective arm 49.5 pp, and the verdict ranges from a non-significant +3.6 pp at the published operating point to +34 pp (p=0.005) one notch hotter. On MATH-500 the rate dependence does not reproduce under LoRA, scoping that result, while the ~10 pp cost of selective training does. We prescribe reporting the arm x rate matrix, not a shared-rate column, as a precondition for selector comparisons.

Modern supply chain networks increasingly rely on real-time data to navigate structural uncertainties, market volatility, and operational disruptions. This manuscript bridges the gap between statistical data-driven learning and robust decision-making frameworks in logistics and operations management. We present a comprehensive, mathematically rigorous treatment of supply chain analytics, moving from empirical demand forecasting to optimal inventory and network control under uncertainty. Key topics explored include sample minimization, dynamic programming recursions for time-varying inventory replenishment, network fulfillment frameworks, and advanced distributionally robust optimization (DRO) via transport theory to hedge against rare events. By integrating predictive statistical models with prescriptive control algorithms, such as column generation for vehicle routing and non-homogeneous queueing regimes, this text provides the foundational tools necessary for designing resilient, data-driven automated systems. It serves as both a theoretical blueprint and an algorithmic guide for researchers and practitioners operating at the intersection of machine learning, mathematical optimization, and applied probability.

Customer decline early-warning systems feed account-manager action lists, and every flagged account consumes intervention capacity. In a deployed business-to-business marketplace system, one action-list slot in three went to flags that dissolve under a seasonally aligned label. The standard target in non-contractual churn prediction compares an entity's next k months of activity with its trailing k months. The two windows cover different calendar months, so for seasonal entities the threshold-ratio construction confounds seasonality with decline, and the event rate depends on the label's anchor calendar month. We formalize the mechanism and measure it on three public panels and the production panel (the public arms pre-specified). Of the adjacent-window decay events, 37–69% on the public panels and 28–50% in production have no counterpart under a seasonally aligned definition. Pooling anchors, the standard remedy, balances the training mixture but corrects no individual label. Measured alternatives repair the curve only partially or change the detection horizon. Aligning the baseline to the same k calendar months one year prior – advice practitioners already state, here formalized, measured, and costed – flattens the curve at the source. With the classifier held fixed, production holdout ROC-AUC rises from 0.767 to 0.864 for decline (different targets; the gap closes on synthetic ground truth and a production hindsight referee). The served action list shrinks by a third, 119 to 79 accounts. The measured price is extra history, a blind spot to decline-then-stabilization, and a stricter cut under sustained growth.

Looped language models have shown promising results on reasoning benchmarks, yet their potential for agentic tool use remains largely unexplored. We study this question in compositional tool-calling settings, where models must coordinate multiple API calls, maintain intermediate state, and preserve dependencies across tool interactions. We evaluate native and retrofitted looped language models on API-Bank, BFCL, and NESTful, comparing looped and non-looped models trained under matched supervised fine-tuning recipes and varying recurrent depth at inference time. In controlled experiments, recurrent computation generally benefits compositional and dependency-aware tool use, while providing smaller and more model-dependent gains on isolated API invocation. Accuracy on multi-step tool use generally increases with recurrent depth; adaptive inference, however, achieves a more favorable compute-performance trade-off by allocating additional computation only when needed. Our results suggest that looped language models are a promising architecture for agentic systems that require reliable planning, coordination, and execution of compositional tool use workflows.

This paper challenges the pessimistic meta-inductive argument against scientific realism by undermining its inductive step rather than its historical premise. Although related challenges already exist, I develop a new one. Drawing on a general epistemology of scientific inference developed in frequentist statistics, machine learning, and formal epistemology, I evaluate induction in terms of convergence to the truth. I argue that ordinary enumerative induction can achieve everywhere convergence, whereas meta-induction fails even to achieve almost everywhere convergence. Indeed, in the problem context where meta-induction arises, the failure is deeper: no inference method whatsoever achieves almost everywhere convergence.

Vision-language-action (VLA) and world-action models typically absorb unfamiliar manipulation tasks through additional robot data collection and policy optimization. This recurring retraining burden slows the acquisition of new behavior. We present Teach-and-Grow Learning (TGL), a training-free architecture that turns a few successful demonstrations into reusable robot skills. Task acquisition requires no gradient updates, fine-tuning, or reinforcement learning: pretrained model weights remain fixed as the robot expands its explicit knowledge. Teaching is an accelerator, not a precondition, because the agent can also drive the robot directly, and demonstrations mainly improve reliability. Our implementation uses OpenAI GPT-6 Astra for multimodal reasoning and Codex to connect the agent to robot tools. The agent identifies subgoals shared across demonstrations, expresses them as closed-loop Skill Blocks, and grounds each block in the current scene. Physical feedback guides the next action and any recovery. Verified behaviors enter a persistent Skill Library; Experience Memory records the conditions and repairs that inform later decisions. TGL reaches 99.9% mean success on four LIBERO suites and 92.4% on seven LIBERO-Plus perturbation categories. Controlled studies show that taught blocks persist and improve related-task execution under the same model weights and executors. We further formulate a scaling hypothesis that relates effective reusable experience to falling future-task error and teaching demand. Code and demonstration videos: https://tgl.changnie.top

Contrastive learning has become a cornerstone of modern representation learning, powering CLIP-style models that underpin text-to-image generation, vision-language models, and retrieval across a rapidly growing range of modalities. Despite this empirical success, the expressive power of these architectures remains poorly understood. To gain insight, we study expressivity by adopting a population-level, density-estimation viewpoint: each architecture comprises a parameterized set of densities whose parameters may be chosen to approximate the joint distribution of the modalities. This isolates a question of pure representational capacity: which joint distributions can a given contrastive family of parameterizations approximate to arbitrary accuracy? We show that expressivity is sharply architecture-dependent. For two modalities, the simple two-tower CLIP architecture is a universal approximator. A natural generalization of CLIP, widely used in practice when three or more modalities are present, is based on a loss found by summing over all pairwise similarities. This provably cannot represent arbitrary joint distributions, although we prove that it remains expressive enough to match all pairwise conditionals. Motivated by this gap, we propose Hadamard-CLIP, which adds a single learned weight vector on top of the existing encoders and restores universal approximation of the joint for any number of modalities while preserving CLIP's fast, precomputable-embedding retrieval.

Dimensionality reduction methods are instrumental to visualize high-dimensional data, and t-SNE stands as one of the most widely used methods due to its emphasis on local neighborhood preservation. A central component of t-SNE is the affinity matrix, which expresses pairwise similarities in the form of symmetrized probabilities, over which the optimization problem of t-SNE is defined. We study how the sharpness of this probability distribution affects neighborhood preservation at different scales. We introduce a row-wise power transform controlled by a parameter gamma that can smooth or sharpen each row of the affinity matrix while preserving sparsity and rank order. We show that this transform is equivalent to rescaling the Gaussian bandwidth and thus to changing the perplexity. However, as the sharpness of the probability distribution varies per point, a fixed gamma leads to point-dependent effective perplexities, making it distinct from changing the global perplexity. Empirically, we find that sharpening improves preservation of the very nearest neighbors, while smoothing improves preservation of broader local neighborhoods, outperforming alternative affinity constructions including multiscale methods in the mid-local range.

Reinforcement learning (RL) theory fundamentally depends on probability theory through the Markov chain. There is a deep connection between probability theory and potential theory. This paper reviews that connection and explores the potential-theoretic viewpoint for core reinforcement learning representations and algorithms under a fixed-policy assumption. This viewpoint may offer a path for improved sample efficiency and formal constraints that can be applied to RL. When the fixed-policy assumption is relaxed, the linear potential theory framework can be naturally extended to the nonlinear case.

Contextual Reinforcement Learning (CRL) seeks to generalize classical RL by maximizing task coverage across a context space of related tasks. While prior works often train from scratch and rely on either multi-task learning for a single policy or strategically training multiple policies, we advocate for a unified alternative: pretraining a single policy with good initial performance, followed by fine-tuning multiple policies for task specialization. This new paradigm, however, introduces unique challenges, such as heterogeneous marginal returns and sample inefficiency. This raises a critical research question: given a pretrained policy and a constrained budget, how much fine-tuning should each task region receive to enable sample-efficient CRL? To this end, we propose Task Specialization Fine-Tuning (TSFT), an online framework that predicts fine-tuning performance with a simple parametric model and exactly solves the resulting discrete budget allocation problem via integer linear programming. Extensive experiments across diverse decision domains, including combinatorial optimization, continuous control, and LLM fine-tuning, demonstrate that TSFT significantly outperforms baselines in task coverage and approaches oracle performance. Our work charts a new direction for model-based CRL, aligning with the modern pretrain-finetune era.

Chronic kidney disease (CKD) progresses silently and severely undermines quality of life, making early detection critical for improving patient outcomes. We present a two-part study that combines large-scale telehealth data with advanced machine learning to both classify self-reported CKD status and identify key drivers of disease. Using selected features from the Behavioral Risk Factor Surveillance System (BRFSS 2021: 438,693 samples; BRFSS 2019: 418,268 samples) and the National Health Interview Survey (NHIS 2021: 29,482 samples; NHIS 2020: 31,568 samples), we addressed missing data with nine state-of-the-art imputation methods and mitigated class imbalance via sampling strategies. Our customized stacked ensemble model achieved balanced accuracy of 72.56-76.12%, with corresponding AUROC scores of 79.59-82.29%. SHapley Additive exPlanations (SHAP) analysis, followed by clinical review, highlighted critical predictors, including regular medical check-ups, age, blood pressure, and indicators of mental health stress. These findings deliver a robust and interpretable framework for CKD risk stratification and provide actionable insights into its associated factors.

Online decision making often requires navigating a landscape shaped by both dynamic contexts and strategic interactions. In competitive pricing, for example, hotels must account for both dynamic contextual factors and rivals' strategic responses. Existing approaches address only part of this challenge: contextual bandits optimize single-agent decisions using observable features but ignore multi-player interactions, while online matrix games capture strategic behavior through Nash equilibrium but assume fixed payoffs, ignoring contextual information. How should agents act then when strategic payoffs evolve with contextual signals? We introduce online contextual matrix games to integrate contextual information into multi-player online games. We further propose OnGameLearn, an online learning algorithm that efficiently balances exploration and exploitation across both player actions and contexts. This approach comes with statistical guarantees: tail bounds for the estimated payoff matrix, the convergence of the estimated Nash equilibrium, the asymptotic normality of the parameter estimators, and the sublinear regret bound. We also develop the notion of policy value in matrix games and develop a doubly robust, $\sqrt{T}$-consistent estimator for it. Across simulated studies and a real-world hotel pricing application, we find that OnGameLearn effectively navigates the intertwined challenges of strategic and contextual decision-making.

Textual context such as news, reports, and logs can provide valuable signals for time series forecasting, especially when future dynamics are driven by external events that are not yet visible in historical values. Existing multimodal forecasting methods often either ask large language models (LLMs) to predict numerical values directly or fuse text and time series implicitly, making contextual influence difficult to interpret and control. We propose SCENARIODIFF, a hierarchical contextual reasoning framework for multimodal time series forecasting under noisy and weakly aligned documents. SCENARIODIFF organizes contextual information into three levels: a Historical Context Agent extracts stepwise evidence from raw documents, a Scenario Agent produces a qualitative scenario description for the forecast horizon, and an Anchor Guidance Agent generates sparse anchor points for event-relevant future regions. These structured signals condition a Multimodal Diffusion Transformer, while Anchor Blended Sampling locally refines generated trajectories without retraining. Experiments on the Time-MMD benchmark show that SCENARIODIFF is especially effective in event-driven domains, demonstrating the value of explicit hierarchical scenario guidance for multimodal time series forecasting. Our full implementation is available at https://anonymous.4open.science/r/ScenarioDiff_ICDM-2C4C

Off-policy reinforcement learning (RL) has become increasingly sample-efficient, enabling applications such as RL fine-tuning of Vision-Language-Action models into reliable, high-performing policies. World models offer a further lever for sample efficiency, as they predict state changes rather than actions alone, but their success has largely been confined to supervised policy learning. Prior model-based RL methods often optimize the policy or value function directly on imagined rollouts, which is prone to compounding bias and struggles to scale to large, high-dimensional problems such as real-world robotics, a problem that worsens with task horizon and visual complexity. In this work, we instead ask whether we can leverage world models directly on top of standard Q-learning to improve performance, while remaining trained and grounded in the real, online setting. We propose QWM, a framework that leverages world models to perform test-time search over imagined trajectories on top of Q-learning to select high-value actions during both online rollouts and evaluation. Since the policy and value function are trained only on real transitions, QWM avoids compounding model bias while still gaining the sample-efficiency benefits of predictive search. On challenging manipulation benchmarks Robomimic and LIBERO, QWM significantly outperforms strong prior state-of-the-art methods on both sample efficiency and performance.

What a language model internalizes from fine-tuning is usually diagnosed after the fact. We make it an experimental variable. OraclePhys is a systematic fine-tuning framework with three components: OraclePhys-Bench, an exactly-graded structural-mechanics benchmark whose finite-element oracle scores every answer and counterfactual edit – no human labels, no LLM judging; OraclePhys-30K, a supervision dataset of seven answer forms over byte-identical structure descriptions; and a controlled training study across the seven forms and three verifier roles. The study yields two findings. First, the label's answer form – not its bit count – causally determines what fine-tuning teaches: a ranking objective installs an out-of-distribution forward model where the untrained base sits at the guessing prior, a scalar objective at best a partial one, a boolean nothing detectable; the vector-scalar gulf survives a second physics domain, a second model family, and a paraphrased evaluation surface. Second, written or score-filtered answers install this capability, while advantage-weighted scores (GRPO) raise reward yet leave the model statistically equivalent to its start on held-out physics – within the recipes and budgets tested – sufficing only for routing. The trained 8B – the first LLM on spatial structural response – reaches the task's data-precision frontier: above a frontier LLM at zero- and 32-shot, at a specialist's level. What the label spells out about the target computation is what fine-tuning teaches; what you train on is what you route.

Cell mimicry arises when different cell types appear morphologically similar. Human pathologists resolve this ambiguity using surrounding tissue context, whereas current vision models either lack contextual reasoning (cell foundation models) or cannot operate at the cell level (pathology MLLMs). We present Loki-OT, which propagates region-level tissue reasoning to individual cell predictions via Unbalanced Optimal Transport, using MLLM-derived density priors as soft guidance for ambiguous cell reassignment. Loki-OT is motivated by the observation that pretrained cell foundation model features already encode discriminative information, including tissue context, but standard cell-level supervision fails to use tissue context effectively. The resulting transport plan is distilled into a lightweight student MLP classifier that learns context-aware decision boundaries within the pretrained feature space. On the independent TCGA-BRCA cohort, Loki-OT achieved lower patient-level MAE than the fully supervised in-domain PanopTILs classifier and improved F1 in epithelium-rich mimicry tissues, using 278 weak region-level MLLM estimates built on a general-domain cell foundation model. Code: https://github.com/xiangli980/Lymphocyte_Mimicry_Correction_via_Loki_OT

Several methods for auditing privacy in embedding spaces report a number called "epsilon." The common name is misleading: one number may be a heuristic score, another may come from a valid population inequality but ignore sampling uncertainty, and a third may be a confidence bound. This paper asks when such a number is evidence about differential privacy. We study four approaches based on Gaussian calibration, marginal kernel-density ratios, maximum mean discrepancy (MMD), and classifier hypothesis tests. The first two are modeling diagnostics. The MMD and classifier approaches use valid population lower bounds, but only the classifier approach is given a separate test set and a finite-sample confidence calculation. To see how these distinctions matter, we build a synthetic benchmark in which the true privacy value is known. It includes pure-DP Laplace mechanisms, approximate-DP Gaussian mechanisms, an exact privacy null, two identity geometries, and three sample sizes. At the null, the Gaussian and kernel-density diagnostics remain large. A direct conversion of an empirical ROC curve often returns infinity even though the AUC is near chance and no threshold separates the samples perfectly. The MMD value increases as the distributions become easier to distinguish, but the sample estimate is small relative to the known reference and is not a lower confidence bound. By contrast, a classifier chosen on development data and evaluated on untouched test data gives simultaneous lower confidence bounds under the stated iid model. We also apply the methods to FaceFusion and InstantID. That case study shows how the methods behave on face data but does not calibrate them because the generators have no known privacy value. The main lesson is that an epsilon-like number is meaningful only together with its assumptions and its finite-sample interpretation.

Tensor networks are powerful formats for compressing large-scale data. However, their application to general data processing has been limited by the difficulty of performing nonlinear operations. Here, we introduce iterative tensor network transformations (ITNTs), a general algorithmic framework for the element-wise evaluation of elementary and nonlinear filtering functions on data encoded as tensor trains (TTs), a class of tensor networks. Our approach operates entirely in the compressed domain, enabling efficient computation on exponentially large datasets while maintaining a controlled computational cost. We demonstrate its power in two key areas: (I) evaluating highly nonlinear elementary and filtering functions on a 3D reactive flow field, enabling high-fidelity reaction rate computation and region filtering, and (II) finding extrema in complex optimization problems, such as solving Max-SAT instances on spaces up to $2^{70}$ configurations. These results establish ITNT as a foundational tool that provides tensor network methods with the capability for general-purpose data science and large-scale optimization.

Recovering the directed acyclic graph (DAG) of a structural equation model (SEM) from observational data is a central problem in causal discovery. The iterative gradient descent and per-problem hyperparameter tuning of continuous-optimization methods are poorly suited to two practically important regimes: the sample-limited regime, where the number of samples is comparable to or smaller than the number of nodes in the DAG, and the compute-limited regime. This work proposes SURE-Ridge, a non-iterative, closed-form estimator for equal variance linear Gaussian SEM. The method performs parallel node-wise regressions with regularization parameters chosen adaptively by Stein's unbiased risk estimate (SURE), and applies an adaptive thresholding procedure to extract a DAG from the resulting soft adjacency matrix. Numerical results show that SURE-Ridge achieves the lowest structural Hamming distance in the small-sample regime and the lowest run time across all sample sizes tested, compared with NOTEARS, DAGMA, and GBNSL baselines.