Peer Revenue Equity in science

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Machine Learning

cs.LG Watch Machine Learning (sign in to use)

Wednesday 24 December

Machine Learning · Cross-listed from cs.AI

A multi-algorithm approach for operational human resources workload balancing in a last mile urban delivery system

Efficient workload assignment to the workforce is critical in last-mile package delivery systems. In this context, traditional methods of assigning package deliveries to workers based on geographical proximity can be inefficient and surely guide to an unbalanced workload distribution among delivery workers. In this paper, we look at the problem of operational human resources workload balancing in last-mile urban package delivery systems. The idea is to consider the effort workload to optimize the system, i.e., the optimization process is now focused on improving the delivery time, so that the workload balancing is complete among all the staff. This process should correct significant decompensations in workload among delivery workers in a given zone. Specifically, we propose a multi-algorithm approach to tackle this problem. The proposed approach takes as input a set of delivery points and a defined number of workers, and then assigns packages to workers, in such a way that it ensures that each worker completes a similar amount of work per day. The proposed algorithms use a combination of distance and workload considerations to optimize the allocation of packages to workers. In this sense, the distance between the delivery points and the location of each worker is also taken into account. The proposed multi-algorithm methodology includes different versions of k-means, evolutionary approaches, recursive assignments based on k-means initialization with different problem encodings, and a hybrid evolutionary ensemble algorithm. We have illustrated the performance of the proposed approach in a real-world problem in an urban last-mile package delivery workforce operating at Azuqueca de Henares, Spain.
Read the full abstract

All authors Luis M. Moreno-Saavedra, Silvia Jimenez-Fernandez, Antonio Portilla-Figueras, David Casillas-Perez, Sancho Salcedo-Sanz

Machine Learning · Cross-listed from cs.DC

Governing Cloud Data Pipelines with Agentic AI

Cloud data pipelines increasingly operate under dynamic workloads, evolving schemas, cost constraints, and strict governance requirements. Despite advances in cloud-native orchestration frameworks, most production pipelines rely on static configurations and reactive operational practices, resulting in prolonged recovery times, inefficient resource utilization, and high manual overhead. This paper presents Agentic Cloud Data Engineering, a policy-aware control architecture that integrates bounded AI agents into the governance and control plane of cloud data pipelines. In Agentic Cloud Data Engineering platform, specialized agents analyze pipeline telemetry and metadata, reason over declarative cost and compliance policies, and propose constrained operational actions such as adaptive resource reconfiguration, schema reconciliation, and automated failure recovery. All agent actions are validated against governance policies to ensure predictable and auditable behavior. We evaluate Agentic Cloud Data Engineering platform using representative batch and streaming analytics workloads constructed from public enterprise-style datasets. Experimental results show that Agentic Cloud Data Engineering platform reduces mean pipeline recovery time by up to 45%, lowers operational cost by approximately 25%, and decreases manual intervention events by over 70% compared to static orchestration, while maintaining data freshness and policy compliance. These results demonstrate that policy-bounded agentic control provides an effective and practical approach for governing cloud data pipelines in enterprise environments.
Read the full abstract

All authors Aswathnarayan Muthukrishnan Kirubakaran, Adithya Parthasarathy, Nitin Saksena, Ram Sekhar Bodala, Akshay Deshpande, Suhas Malempati, Shiva Carimireddy, Abhirup Mazumder

Machine Learning

LLMTM: Benchmarking and Optimizing LLMs for Temporal Motif Analysis in Dynamic Graphs

The widespread application of Large Language Models (LLMs) has motivated a growing interest in their capacity for processing dynamic graphs. Temporal motifs, as an elementary unit and important local property of dynamic graphs which can directly reflect anomalies and unique phenomena, are essential for understanding their evolutionary dynamics and structural features. However, leveraging LLMs for temporal motif analysis on dynamic graphs remains relatively unexplored. In this paper, we systematically study LLM performance on temporal motif-related tasks. Specifically, we propose a comprehensive benchmark, LLMTM (Large Language Models in Temporal Motifs), which includes six tailored tasks across nine temporal motif types. We then conduct extensive experiments to analyze the impacts of different prompting techniques and LLMs (including nine models: openPangu-7B, the DeepSeek-R1-Distill-Qwen series, Qwen2.5-32B-Instruct, GPT-4o-mini, DeepSeek-R1, and o3) on model performance. Informed by our benchmark findings, we develop a tool-augmented LLM agent that leverages precisely engineered prompts to solve these tasks with high accuracy. Nevertheless, the high accuracy of the agent incurs a substantial cost. To address this trade-off, we propose a simple yet effective structure-aware dispatcher that considers both the dynamic graph's structural properties and the LLM's cognitive load to intelligently dispatch queries between the standard LLM prompting and the more powerful agent. Our experiments demonstrate that the structure-aware dispatcher effectively maintains high accuracy while reducing cost.
Read the full abstract

All authors Bing Hao, Minglai Shao, Zengyi Wo, Yunlong Chu, Yuhang Liu, Ruijie Wang

Machine Learning

LuxIA: A Lightweight Unitary matriX-based Framework Built on an Iterative Algorithm for Photonic Neural Network Training

PNNs present promising opportunities for accelerating machine learning by leveraging the unique benefits of photonic circuits. However, current state of the art PNN simulation tools face significant scalability challenges when training large-scale PNNs, due to the computational demands of transfer matrix calculations, resulting in high memory and time consumption. To overcome these limitations, we introduce the Slicing method, an efficient transfer matrix computation approach compatible with back-propagation. We integrate this method into LuxIA, a unified simulation and training framework. The Slicing method substantially reduces memory usage and execution time, enabling scalable simulation and training of large PNNs. Experimental evaluations across various photonic architectures and standard datasets, including MNIST, Digits, and Olivetti Faces, show that LuxIA consistently surpasses existing tools in speed and scalability. Our results advance the state of the art in PNN simulation, making it feasible to explore and optimize larger, more complex architectures. By addressing key computational bottlenecks, LuxIA facilitates broader adoption and accelerates innovation in AI hardware through photonic technologies. This work paves the way for more efficient and scalable photonic neural network research and development.
Read the full abstract

All authors Tzamn Melendez Carmona, Federico Marchesin, Marco P. Abrate, Peter Bienstman, Stefano Di Carlo, Alessandro Savino Senior

Machine Learning · Cross-listed from cs.CV

Evaluating an Adaptive Multispectral Turret System for Autonomous Tracking Across Variable Illumination Conditions

Autonomous robotic platforms are playing a growing role across the emergency services sector, supporting missions such as search and rescue operations in disaster zones and reconnaissance. However, traditional red-green-blue (RGB) detection pipelines struggle in low-light environments, and thermal-based systems lack color and texture information. To overcome these limitations, we present an adaptive framework that fuses RGB and long-wave infrared (LWIR) video streams at multiple fusion ratios and dynamically selects the optimal detection model for each illumination condition. We trained 33 You Only Look Once (YOLO) models on over 22,000 annotated images spanning three light levels: no-light (<10 lux), dim-light (10-1000 lux), and full-light (>1000 lux). To integrate both modalities, fusion was performed by blending aligned RGB and LWIR frames at eleven ratios, from full RGB (100/0) to full LWIR (0/100) in 10% increments. Evaluation showed that the best full-light model (80/20 RGB-LWIR) and dim-light model (90/10 fusion) achieved 92.8% and 92.0% mean confidence; both significantly outperformed the YOLOv5 nano (YOLOv5n) and YOLOv11 nano (YOLOv11n) baselines. Under no-light conditions, the top 40/60 fusion reached 71.0%, exceeding baselines though not statistically significant. Adaptive RGB-LWIR fusion improved detection confidence and reliability across all illumination conditions, enhancing autonomous robotic vision performance.
Read the full abstract

All authors Aahan Sachdeva, Dhanvinkumar Ganeshkumar, James E. Gallagher, Tyler Treat, Edward J. Oughton

Machine Learning · Cross-listed from q-bio.QM

INSIGHT: Spatially resolved survival modelling from routine histology crosslinked with molecular profiling reveals prognostic epithelial-immune axes in stage II/III colorectal cancer

Routine histology contains rich prognostic information in stage II/III colorectal cancer, much of which is embedded in complex spatial tissue organisation. We present INSIGHT, a graph neural network that predicts survival directly from routine histology images. Trained and cross-validated on TCGA (n=342) and SURGEN (n=336), INSIGHT produces patient-level spatially resolved risk scores. Large independent validation showed superior prognostic performance compared with pTNM staging (C-index 0.68-0.69 vs 0.44-0.58). INSIGHT spatial risk maps recapitulated canonical prognostic histopathology and identified nuclear solidity and circularity as quantitative risk correlates. Integrating spatial risk with data-driven spatial transcriptomic signatures, spatial proteomics, bulk RNA-seq, and single-cell references revealed an epithelium-immune risk manifold capturing epithelial dedifferentiation and fetal programs, myeloid-driven stromal states including $\mathrm{SPP1}^{+}$ macrophages and $\mathrm{LAMP3}^{+}$ dendritic cells, and adaptive immune dysfunction. This analysis exposed patient-specific epithelial heterogeneity, stratification within MSI-High tumours, and high-risk routes of CDX2/HNF4A loss and CEACAM5/6-associated proliferative programs, highlighting coordinated therapeutic vulnerabilities.
Read the full abstract

All authors Piotr Keller, Mark Eastwood, Zedong Hu, Aimée Selten, Ruqayya Awan, Gertjan Rasschaert, Sara Verbandt, Vlad Popovici, Hubert Piessevaux, Hayley T Morris, Petros Tsantoulis, Thomas Alexander McKee, André D'Hoore, Cédric Schraepen, Xavier Sagaert, Gert De Hertogh, Sabine Tejpar, Fayyaz Minhas

Machine Learning

The Physics Constraint Paradox: When Removing Explicit Constraints Improves Physics-Informed Data for Machine Learning

Physics-constrained data generation is essential for machine learning in scientific domains where real data are scarce; however, existing approaches often over-constrain models without identifying which physical components are necessary. We present a systematic ablation study of a physics-informed grating coupler spectrum generator that maps five geometric parameters to 100-point spectral responses. By selectively removing explicit energy conservation enforcement, Fabry-Perot oscillations, bandwidth variation, and noise, we uncover a physics constraint paradox: explicit energy conservation enforcement is mathematically redundant when the underlying equations are physically consistent, with constrained and unconstrained variants achieving identical conservation accuracy (mean error approximately 7 x 10^-9). In contrast, Fabry-Perot oscillations dominate threshold-based bandwidth variability, accounting for a 72 percent reduction in half-maximum bandwidth spread when removed (with bandwidth spread reduced from 132.3 nm to 37.4 nm). We further identify a subtle pitfall: standard noise-addition-plus-renormalization pipelines introduce 0.5 percent unphysical negative absorption values. The generator operates at 200 samples per second, enabling high-throughput data generation and remaining orders of magnitude faster than typical full-wave solvers reported in the literature. Finally, downstream machine learning evaluation reveals a clear physics-learnability trade-off: while central wavelength prediction remains unaffected, removing Fabry-Perot oscillations improves bandwidth prediction accuracy by 31.3 percent in R-squared and reduces RMSE by 73.8 percent. These findings provide actionable guidance for physics-informed dataset design and highlight machine learning performance as a diagnostic tool for assessing constraint relevance.
Read the full abstract

Machine Learning

Cardiac mortality prediction in patients undergoing PCI based on real and synthetic data

Patient status, angiographic and procedural characteristics encode crucial signals for predicting long-term outcomes after percutaneous coronary intervention (PCI). The aim of the study was to develop a predictive model for assessing the risk of cardiac death based on the real and synthetic data of patients undergoing PCI and to identify the factors that have the greatest impact on mortality. We analyzed 2,044 patients, who underwent a PCI for bifurcation lesions. The primary outcome was cardiac death at 3-year follow-up. Several machine learning models were applied to predict three-year mortality after PCI. To address class imbalance and improve the representation of the minority class, an additional 500 synthetic samples were generated and added to the training set. To evaluate the contribution of individual features to model performance, we applied permutation feature importance. An additional experiment was conducted to evaluate how the model's predictions would change after removing non-informative features from the training and test datasets. Without oversampling, all models achieve high overall accuracy (0.92-0.93), yet they almost completely ignore the minority class. Across models, augmentation consistently increases minority-class recall with minimal loss of AUROC, improves probability quality, and yields more clinically reasonable risk estimates on the constructed severe profiles. According to feature importance analysis, four features emerged as the most influential: Age, Ejection Fraction, Peripheral Artery Disease, and Cerebrovascular Disease. These results show that straightforward augmentation with realistic and extreme cases can expose, quantify, and reduce brittleness in imbalanced clinical prediction using only tabular records, and motivate routine reporting of probability quality and stress tests alongside headline metrics.
Read the full abstract

All authors Daniil Burakov, Ivan Petrov, Dmitrii Khelimskii, Ivan Bessonov, Mikhail Lazarev

Machine Learning · Cross-listed from cs.AI

Logic Sketch Prompting (LSP): A Deterministic and Interpretable Prompting Method

Large language models (LLMs) excel at natural language reasoning but remain unreliable on tasks requiring strict rule adherence, determinism, and auditability. Logic Sketch Prompting (LSP) is a lightweight prompting framework that introduces typed variables, deterministic condition evaluators, and a rule based validator that produces traceable and repeatable outputs. Using two pharmacologic logic compliance tasks, we benchmark LSP against zero shot prompting, chain of thought prompting, and concise prompting across three open weight models: Gemma 2, Mistral, and Llama 3. Across both tasks and all models, LSP consistently achieves the highest accuracy (0.83 to 0.89) and F1 score (0.83 to 0.89), substantially outperforming zero shot prompting (0.24 to 0.60), concise prompts (0.16 to 0.30), and chain of thought prompting (0.56 to 0.75). McNemar tests show statistically significant gains for LSP across nearly all comparisons (p < 0.01). These results demonstrate that LSP improves determinism, interpretability, and consistency without sacrificing performance, supporting its use in clinical, regulated, and safety critical decision support systems.
Read the full abstract

Machine Learning · Cross-listed from cs.AI

Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks

We present the surprising finding that a language model's reasoning capabilities can be improved by training on synthetic datasets of chain-of-thought (CoT) traces from more capable models, even when all of those traces lead to an incorrect final answer. Our experiments show this approach can yield better performance on reasoning tasks than training on human-annotated datasets. We hypothesize that two key factors explain this phenomenon: first, the distribution of synthetic data is inherently closer to the language model's own distribution, making it more amenable to learning. Second, these `incorrect' traces are often only partially flawed and contain valid reasoning steps from which the model can learn. To further test the first hypothesis, we use a language model to paraphrase human-annotated traces – shifting their distribution closer to the model's own distribution – and show that this improves performance. For the second hypothesis, we introduce increasingly flawed CoT traces and study to what extent models are tolerant to these flaws. We demonstrate our findings across various reasoning domains like math, algorithmic reasoning and code generation using MATH, GSM8K, Countdown and MBPP datasets on various language models ranging from 1.5B to 9B across Qwen, Llama, and Gemma models. Our study shows that curating datasets that are closer to the model's distribution is a critical aspect to consider. We also show that a correct final answer is not always a reliable indicator of a faithful reasoning process.
Read the full abstract

All authors Abhranil Chandra, Ayush Agrawal, Arian Hosseini, Sebastian Fischmeister, Rishabh Agarwal, Navin Goyal, Aaron Courville

Machine Learning · Cross-listed from cs.GT

Analyzing Skill Element in Online Fantasy Cricket

Online fantasy cricket has emerged as large-scale competitive systems in which participants construct virtual teams and compete based on real-world player performances. This massive growth has been accompanied by important questions about whether outcomes are primarily driven by skill or chance. We develop a statistical framework to assess the role of skill in determining success on these platforms. We construct and analyze a range of deterministic and stochastic team selection strategies, based on recent form, historical statistics, statistical optimization, and multi-criteria decision making. Strategy performance is evaluated based on points, ranks, and payoff under two contest structures Mega and 4x or Nothing. An extensive comparison between different strategies is made to find an optimal set of strategies. To capture adaptive behavior, we further introduce a dynamic tournament model in which agent populations evolve through a softmax reweighting mechanism proportional to positive payoff realizations. We demonstrate our work by running extensive numerical experiments on the IPL 2024 dataset. The results provide quantitative evidence in favor of the skill element present in online fantasy cricket platforms.
Read the full abstract

All authors Sarthak Sarkar, Supratim Das, Purushottam Saha, Diganta Mukherjee, Tridib Mukherjee

Machine Learning

Graph Attention-based Adaptive Transfer Learning for Link Prediction

Graph neural networks (GNNs) have brought revolutionary advancements to the field of link prediction (LP), providing powerful tools for mining potential relationships in graphs. However, existing methods face challenges when dealing with large-scale sparse graphs and the need for a high degree of alignment between different datasets in transfer learning. Besides, although self-supervised methods have achieved remarkable success in many graph tasks, prior research has overlooked the potential of transfer learning to generalize across different graph datasets. To address these limitations, we propose a novel Graph Attention Adaptive Transfer Network (GAATNet). It combines the advantages of pre-training and fine-tuning to capture global node embedding information across datasets of different scales, ensuring efficient knowledge transfer and improved LP performance. To enhance the model's generalization ability and accelerate training, we design two key strategies: 1) Incorporate distant neighbor embeddings as biases in the self-attention module to capture global features. 2) Introduce a lightweight self-adapter module during fine-tuning to improve training efficiency. Comprehensive experiments on seven public datasets demonstrate that GAATNet achieves state-of-the-art performance in LP tasks. This study provides a general and scalable solution for LP tasks to effectively integrate GNNs with transfer learning. The source code and datasets are publicly available at https://github.com/DSI-Lab1/GAATNet
Read the full abstract

All authors Huashen Lu, Wensheng Gan, Guoting Chen, Zhichao Huang, Philip S. Yu

Machine Learning

Interpretable Perturbation Modeling Through Biomedical Knowledge Graphs

Understanding how small molecules perturb gene expression is essential for uncovering drug mechanisms, predicting off-target effects, and identifying repurposing opportunities. While prior deep learning frameworks have integrated multimodal embeddings into biomedical knowledge graphs (BKGs) and further improved these representations through graph neural network message-passing paradigms, these models have been applied to tasks such as link prediction and binary drug-disease association, rather than the task of gene perturbation, which may unveil more about mechanistic transcriptomic effects. To address this gap, we construct a merged biomedical graph that integrates (i) PrimeKG++, an augmentation of PrimeKG containing semantically rich embeddings for nodes with (ii) LINCS L1000 drug and cell line nodes, initialized with multimodal embeddings from foundation models such as MolFormerXL and BioBERT. Using this heterogeneous graph, we train a graph attention network (GAT) with a downstream prediction head that learns the delta expression profile of over 978 landmark genes for a given drug-cell pair. Our results show that our framework outperforms MLP baselines for differentially expressed genes (DEG) – which predict the delta expression given a concatenated embedding of drug features, target features, and baseline cell expression – under the scaffold and random splits. Ablation experiments with edge shuffling and node feature randomization further demonstrate that the edges provided by biomedical KGs enhance perturbation-level prediction. More broadly, our framework provides a path toward mechanistic drug modeling: moving beyond binary drug-disease association tasks to granular transcriptional effects of therapeutic intervention.
Read the full abstract

Machine Learning

Temporal Visual Semantics-Induced Human Motion Understanding with Large Language Models

Unsupervised human motion segmentation (HMS) can be effectively achieved using subspace clustering techniques. However, traditional methods overlook the role of temporal semantic exploration in HMS. This paper explores the use of temporal vision semantics (TVS) derived from human motion sequences, leveraging the image-to-text capabilities of a large language model (LLM) to enhance subspace clustering performance. The core idea is to extract textual motion information from consecutive frames via LLM and incorporate this learned information into the subspace clustering framework. The primary challenge lies in learning TVS from human motion sequences using LLM and integrating this information into subspace clustering. To address this, we determine whether consecutive frames depict the same motion by querying the LLM and subsequently learn temporal neighboring information based on its response. We then develop a TVS-integrated subspace clustering approach, incorporating subspace embedding with a temporal regularizer that induces each frame to share similar subspace embeddings with its temporal neighbors. Additionally, segmentation is performed based on subspace embedding with a temporal constraint that induces the grouping of each frame with its temporal neighbors. We also introduce a feedback-enabled framework that continuously optimizes subspace embedding based on the segmentation output. Experimental results demonstrate that the proposed method outperforms existing state-of-the-art approaches on four benchmark human motion datasets.
Read the full abstract

Machine Learning

Amortized Inference for Model Rocket Aerodynamics: Learning to Estimate Physical Parameters from Simulation

Accurate prediction of model rocket flight performance requires estimating aerodynamic parameters that are difficult to measure directly. Traditional approaches rely on computational fluid dynamics or empirical correlations, while data-driven methods require extensive real flight data that is expensive and time-consuming to collect. We present a simulation-based amortized inference approach that trains a neural network on synthetic flight data generated from a physics simulator, then applies the learned model to real flights without any fine-tuning. Our method learns to invert the forward physics model, directly predicting drag coefficient and thrust correction factor from a single apogee measurement combined with motor and configuration features. In this proof-of-concept study, we train on 10,000 synthetic flights and evaluate on 8 real flights, achieving a mean absolute error of 12.3 m in apogee prediction - demonstrating promising sim-to-real transfer with zero real training examples. Analysis reveals a systematic positive bias in predictions, providing quantitative insight into the gap between idealized physics and real-world flight conditions. We additionally compare against OpenRocket baseline predictions, showing that our learned approach reduces apogee prediction error. Our implementation is publicly available to support reproducibility and adoption in the amateur rocketry community.
Read the full abstract

Machine Learning

The Affine Divergence: Aligning Activation Updates Beyond Normalisation

A systematic mismatch exists between mathematically ideal and effective activation updates during gradient descent. As intended, parameters update in their direction of steepest descent. However, activations are argued to constitute a more directly impactful quantity to prioritise in optimisation, as they are closer to the loss in the computational graph and carry sample-dependent information through the network. Yet their propagated updates do not take the optimal steepest-descent step. These quantities exhibit non-ideal sample-wise scaling across affine, convolutional, and attention layers.Solutions to correct for this are trivial and, incidentally, derive normalisation from first principles despite motivational independence. Consequently, such considerations offer a fresh, conceptual reframe of normalisation's action, with auxiliary experiments bolstering this mechanistic interpretation. Moreover, this analysis makes clear a second possibility: a solution that is functionally distinct from modern normalisations, without scale invariance, yet remains empirically successful – an alternative to the affine map. This outperforms conventional normalisers across several tests. This generalises to convolution via a new functional form, “PatchNorm”, a compositionally inseparable normaliser. Together, these provide an alternative mechanistic framework that both adds to and counters some of the discussion of normalisation. Further, it is argued that normalisers are better decomposed into activation-function-like maps with parameterised scaling. Overall, this constitutes a theoretically principled approach that yields new functions with empirical validation and raises questions about the affine + nonlinear approach.
Read the full abstract

Machine Learning

An Equivariance Toolbox for Learning Dynamics

Many theoretical results in deep learning can be traced to symmetry or equivariance of neural networks under parameter transformations. However, existing analyses are typically problem-specific and focus on first-order consequences such as conservation laws, while the implications for second-order structure remain less understood. We develop a general equivariance toolbox that yields coupled first- and second-order constraints on learning dynamics. The framework extends classical Noether-type analyses in three directions: from gradient constraints to Hessian constraints, from symmetry to general equivariance, and from continuous to discrete transformations. At the first order, our framework unifies conservation laws and implicit-bias relations as special cases of a single identity. At the second order, it provides structural predictions about curvature: which directions are flat or sharp, how the gradient aligns with Hessian eigenspaces, and how the loss landscape geometry reflects the underlying transformation structure. We illustrate the framework through several applications, recovering known results while also deriving new characterizations that connect transformation structure to modern empirical observations about optimization geometry.
Read the full abstract

Machine Learning

dUltra: Ultra-Fast Diffusion Language Models via Reinforcement Learning

Masked diffusion language models (MDLMs) offer the potential for parallel token generation, but most open-source MDLMs decode fewer than 5 tokens per model forward pass even with sophisticated sampling strategies, limiting their parallel generation potential. Existing acceleration methods either rely on fixed confidence-based heuristics or use distillation-based approaches that finetune MDLMs on trajectories generated by a base model, which can become off-policy during finetuning and restrict performance to the quality of the base model's samples. We propose dUltra, an on-policy reinforcement learning framework based on Group Relative Policy Optimization (GRPO) that learns unmasking strategies for efficient parallel decoding. dUltra introduces an unmasking planner head that predicts per-token unmasking likelihoods under independent Bernoulli distributions. We jointly optimize the base diffusion LLM and the unmasking order planner using reward signals combining verifiable reward, distillation reward, and the number of unmasking steps. Across mathematical reasoning and code generation tasks, dUltra achieves superior accuracy-efficiency trade-offs compared to state-of-the-art heuristic (Fast-dLLM) and distillation baselines (d3LLM, dParallel), demonstrating that learned unmasking trajectories through on-policy RL enable better exploitation of parallel generation in MDLMs. Code and checkpoints are released at https://github.com/chinsengi/dUltra-os.
Read the full abstract

All authors Shirui Chen, Jiantao Jiao, Lillian J. Ratliff, Banghua Zhu

Machine Learning · Cross-listed from cs.SE

Fuzzwise: Intelligent Initial Corpus Generation for Fuzzing

In mutation-based greybox fuzzing, generating high-quality input seeds for the initial corpus is essential for effective fuzzing. Rather than conducting separate phases for generating a large corpus and subsequently minimizing it, we propose FuzzWise which integrates them into one process to generate the optimal initial corpus of seeds (ICS). FuzzWise leverages a multi-agent framework based on Large Language Models (LLMs). The first LLM agent generates test cases for the target program. The second LLM agent, which functions as a predictive code coverage module, assesses whether each generated test case will enhance the overall coverage of the current corpus. The streamlined process allows each newly generated test seed to be immediately evaluated for its contribution to the overall coverage. FuzzWise employs a predictive approach using an LLM and eliminates the need for actual execution, saving computational resources and time, particularly in scenarios where the execution is not desirable or even impossible. Our empirical evaluation demonstrates that FuzzWise generates significantly fewer test cases than baseline methods. Despite the lower number of test cases, FuzzWise achieves high code coverage and triggers more runtime errors compared to the baselines. Moreover, it is more time-efficient and coverage-efficient in producing an initial corpus catching more errors.
Read the full abstract

All authors Hridya Dhulipala, Xiaokai Rong, Aashish Yadavally, Tien N. Nguyen

Machine Learning · Cross-listed from cs.CL

Morality is Contextual: Learning Interpretable Moral Contexts from Human Data with Probabilistic Clustering and Large Language Models

A key question in current AI alignment research is how to make AI algorithms learn moral values. Because human morality is highly context-dependent, actions are judged not only by their outcomes but by the context in which they occur. We present COMETH (Contextual Organization of Moral Evaluation from Textual Human inputs), a framework that integrates a probabilistic context learner with LLM-based semantic abstraction and human moral evaluations to model how context shapes the acceptability of ambiguous actions. We curate an empirically grounded dataset of 300 scenarios across six core actions relative to three moral rules (violating "Do not kill", "Do not deceive", and "Do not break the law") and collect ternary judgments (Blame/Neutral/Support) from N=101 participants. A preprocessing pipeline standardizes actions via an LLM filter and MiniLM embeddings with K-means, producing robust, reproducible core-action clusters. COMETH then learns action-specific moral contexts by clustering scenarios online from human judgment distributions using principled divergence criteria. To generalize and explain predictions, a Generalization module extracts concise, non-evaluative binary contextual features and learns feature weights in a transparent likelihood-based model. Empirically, COMETH roughly doubles alignment score with most human judgments relative to end-to-end LLM prompting (60% vs. 30% on average), while revealing which contextual features drive its predictions. The contributions are: (i) an empirically grounded moral-context dataset, (ii) a reproducible pipeline combining human judgments with model-based context learning and LLM semantics, and (iii) a more interpretable alternative than end-to-end LLMs for context-sensitive moral prediction and explanation.
Read the full abstract

All authors Geoffroy Morlat, Marceau Nahon, Augustin Chartouny, Raja Chatila, Ismael T. Freire, Mehdi Khamassi

Machine Learning · Cross-listed from stat.AP

Dynamic Attention (DynAttn): Interpretable High-Dimensional Spatio-Temporal Forecasting (with Application to Conflict Fatalities)

Forecasting conflict-related fatalities remains a central challenge in political science and policy analysis due to the sparse, bursty, and highly non-stationary nature of violence data. We introduce DynAttn, an interpretable dynamic-attention forecasting framework for high-dimensional spatio-temporal count processes. DynAttn combines rolling-window estimation, shared elastic-net feature gating, a compact weight-tied self-attention encoder, and a zero-inflated negative binomial (ZINB) likelihood. This architecture produces calibrated multi-horizon forecasts of expected casualties and exceedance probabilities, while retaining transparent diagnostics through feature gates, ablation analysis, and elasticity measures. We evaluate DynAttn using global country-level and high-resolution PRIO-grid-level conflict data from the VIEWS forecasting system, benchmarking it against established statistical and machine-learning approaches, including DynENet, LSTM, Prophet, PatchTST, and the official VIEWS baseline. Across forecast horizons from one to twelve months, DynAttn consistently achieves substantially higher predictive accuracy, with particularly large gains in sparse grid-level settings where competing models often become unstable or degrade sharply. Beyond predictive performance, DynAttn enables structured interpretation of regional conflict dynamics. In our application, cross-regional analyses show that short-run conflict persistence and spatial diffusion form the core predictive backbone, while climate stress acts either as a conditional amplifier or a primary driver depending on the conflict theater.
Read the full abstract

All authors Stefano M. Iacus, Haodong Qi, Marcello Carammia, Thomas Juneau

Machine Learning · Cross-listed from cs.CV

Scalable Deep Subspace Clustering Network

Subspace clustering methods face inherent scalability limits due to the $O(n^3)$ cost (with $n$ denoting the number of data samples) of constructing full $n\times n$ affinities and performing spectral decomposition. While deep learning-based approaches improve feature extraction, they maintain this computational bottleneck through exhaustive pairwise similarity computations. We propose SDSNet (Scalable Deep Subspace Network), a deep subspace clustering framework that achieves $\mathcal{O}(n)$ complexity through (1) landmark-based approximation, avoiding full affinity matrices, (2) joint optimization of auto-encoder reconstruction with self-expression objectives, and (3) direct spectral clustering on factorized representations. The framework combines convolutional auto-encoders with subspace-preserving constraints. Experimental results demonstrate that SDSNet achieves comparable clustering quality to state-of-the-art methods with significantly improved computational efficiency.
Read the full abstract

Machine Learning

DeepCQ: General-Purpose Deep-Surrogate Framework for Lossy Compression Quality Prediction

Error-bounded lossy compression techniques have become vital for scientific data management and analytics, given the ever-increasing volume of data generated by modern scientific simulations and instruments. Nevertheless, assessing data quality post-compression remains computationally expensive due to the intensive nature of metric calculations. In this work, we present a general-purpose deep-surrogate framework for lossy compression quality prediction (DeepCQ), with the following key contributions: 1) We develop a surrogate model for compression quality prediction that is generalizable to different error-bounded lossy compressors, quality metrics, and input datasets; 2) We adopt a novel two-stage design that decouples the computationally expensive feature-extraction stage from the light-weight metrics prediction, enabling efficient training and modular inference; 3) We optimize the model performance on time-evolving data using a mixture-of-experts design. Such a design enhances the robustness when predicting across simulation timesteps, especially when the training and test data exhibit significant variation. We validate the effectiveness of DeepCQ on four real-world scientific applications. Our results highlight the framework's exceptional predictive accuracy, with prediction errors generally under 10% across most settings, significantly outperforming existing methods. Our framework empowers scientific users to make informed decisions about data compression based on their preferred data quality, thereby significantly reducing I/O and computational overhead in scientific data analysis.
Read the full abstract

All authors Khondoker Mirazul Mumenin, Robert Underwood, Dong Dai, Jinzhen Wang, Sheng Di, Zarija Lukić, Franck Cappello

Machine Learning · Cross-listed from cs.SE

Cerberus: Multi-Agent Reasoning and Coverage-Guided Exploration for Static Detection of Runtime Errors

In several software development scenarios, it is desirable to detect runtime errors and exceptions in code snippets without actual execution. A typical example is to detect runtime exceptions in online code snippets before integrating them into a codebase. In this paper, we propose Cerberus, a novel predictive, execution-free coverage-guided testing framework. Cerberus uses LLMs to generate the inputs that trigger runtime errors and to perform code coverage prediction and error detection without code execution. With a two-phase feedback loop, Cerberus first aims to both increasing code coverage and detecting runtime errors, then shifts to focus only detecting runtime errors when the coverage reaches 100% or its maximum, enabling it to perform better than prompting the LLMs for both purposes. Our empirical evaluation demonstrates that Cerberus performs better than conventional and learning-based testing frameworks for (in)complete code snippets by generating high-coverage test cases more efficiently, leading to the discovery of more runtime errors.
Read the full abstract

Machine Learning · Cross-listed from cs.CV

A Tool Bottleneck Framework for Clinically-Informed and Interpretable Medical Image Understanding

Recent tool-use frameworks powered by vision-language models (VLMs) improve image understanding by grounding model predictions with specialized tools. Broadly, these frameworks leverage VLMs and a pre-specified toolbox to decompose the prediction task into multiple tool calls (often deep learning models) which are composed to make a prediction. The dominant approach to composing tools is using text, via function calls embedded in VLM-generated code or natural language. However, these methods often perform poorly on medical image understanding, where salient information is encoded as spatially-localized features that are difficult to compose or fuse via text alone. To address this, we propose a tool-use framework for medical image understanding called the Tool Bottleneck Framework (TBF), which composes VLM-selected tools using a learned Tool Bottleneck Model (TBM). For a given image and task, TBF leverages an off-the-shelf medical VLM to select tools from a toolbox that each extract clinically-relevant features. Instead of text-based composition, these tools are composed by the TBM, which computes and fuses the tool outputs using a neural network before outputting the final prediction. We propose a simple and effective strategy for TBMs to make predictions with any arbitrary VLM tool selection. Overall, our framework not only improves tool-use in medical imaging contexts, but also yields more interpretable, clinically-grounded predictors. We evaluate TBF on tasks in histopathology and dermatology and find that these advantages enable our framework to perform on par with or better than deep learning-based classifiers, VLMs, and state-of-the-art tool-use frameworks, with particular gains in data-limited regimes. The project details and the code are available at https://christinaliu2020.github.io/tbm/.
Read the full abstract

All authors Christina Liu, Alan Q. Wang, Joy Hsu, Jiajun Wu, Ehsan Adeli

Machine Learning

A Survey of Freshness-Aware Wireless Networking with Reinforcement Learning

The age of information (AoI) has become a central measure of data freshness in modern wireless systems. Reinforcement learning (RL) has emerged as a promising approach to AoI optimization, enabling adaptive decision-making in dynamic and stochastic wireless environments without requiring precise system models. Yet existing surveys either focus on classical AoI formulations or provide broad discussions of RL in wireless networks without addressing freshness as a unified learning problem. Motivated by this gap, this survey examines RL specifically through the lens of AoI and generalized freshness optimization. Motivated by this gap, this survey examines RL specifically through the lens of AoI and generalized freshness optimization. We organize AoI and its variants into native, function-based, and application-oriented families, providing a clearer view of how freshness should be modeled in B5G and 6G systems. Building on this foundation, we introduce a policy-centric taxonomy that reflects the decisions most relevant to freshness, consisting of update-control RL, medium-access RL, risk-sensitive RL, and multi-agent RL. This structure provides a coherent framework for understanding how learning can support important wireless networking problems, including sampling, scheduling, UAV trajectory planning, medium access, and distributed coordination. We further synthesize recent progress in RL-driven freshness control and highlight open challenges. The goal is to establish a unified foundation for learning-based freshness optimization in next-generation wireless networks.
Read the full abstract

All authors Alimu Alibotaiken, Suyang Wang, Oluwaseun T. Ajayi, Mushu Li, Yu Cheng

Machine Learning

kooplearn: A Scikit-Learn Compatible Library of Algorithms for Evolution Operator Learning

kooplearn is a machine-learning library that implements linear, kernel, and deep-learning estimators of dynamical operators and their spectral decompositions. kooplearn can model both discrete-time evolution operators (Koopman/Transfer) and continuous-time infinitesimal generators. By learning these operators, users can analyze dynamical systems via spectral methods, derive data-driven reduced-order models, and forecast future states and observables. kooplearn's interface is compliant with the scikit-learn API, facilitating its integration into existing machine learning and data science workflows. Additionally, kooplearn includes curated benchmark datasets to support experimentation, reproducibility, and the fair comparison of learning algorithms. The software is available at https://github.com/Machine-Learning-Dynamical-Systems/kooplearn.
Read the full abstract

All authors Giacomo Turri, Grégoire Pacreau, Giacomo Meanti, Timothée Devergne, Daniel Ordonez, Erfan Mirzaei, Bruno Belucci, Karim Lounici, Vladimir Kostic, Massimiliano Pontil, Pietro Novelli

Machine Learning · Cross-listed from cs.IT

Learning to Reconfigure: Using Device Status to Select the Right Constrained Coding Scheme

In the age of data revolution, a modern storage~or transmission system typically requires different levels of protection. For example, the coding technique used to fortify data in a modern storage system when the device is fresh cannot be the same as that used when the device ages. Therefore, providing reconfigurable coding schemes and devising an effective way to perform this reconfiguration are key to extending the device lifetime. We focus on constrained coding schemes for the emerging two-dimensional magnetic recording (TDMR) technology. Recently, we have designed efficient lexicographically-ordered constrained (LOCO) coding schemes for various stages of the TDMR device lifetime, focusing on the elimination of isolation patterns, and demonstrated remarkable gains by using them. LOCO codes are naturally reconfigurable, and we exploit this feature in our work. Reconfiguration based on predetermined time stamps, which is what the industry adopts, neglects the actual device status. Instead, we propose offline and online learning methods to perform this task based on the device status. In offline learning, training data is assumed to be available throughout the time span of interest, while in online learning, we only use training data at specific time intervals to make consequential decisions. We fit the training data to polynomial equations that give the bit error rate in terms of TD density, then design an optimization problem in order to reach the optimal reconfiguration decisions to switch from a coding scheme to another. The objective is to maximize the storage capacity and/or minimize the decoding complexity. The problem reduces to a linear programming problem. We show that our solution is the global optimal based on problem characteristics, and we offer various experimental results that demonstrate the effectiveness of our approach in TDMR systems.
Read the full abstract

Machine Learning

A Reinforcement Learning Approach to Synthetic Data Generation

Synthetic data generation (SDG) is a promising approach for enabling data sharing in biomedical studies while preserving patient privacy. Yet, state-of-the-art generative models often require large datasets and complex training procedures, limiting their applicability in small-sample settings common in biomedical research. This study aims to develop a more principled and efficient approach to SDG and evaluate its efficacy for biomedical applications. In this work, we reframe SDG as a reinforcement learning (RL) problem and introduce RLSyn, a novel framework that models the data generator as a stochastic policy over patient records and optimizes it using Proximal Policy Optimization with discriminator-derived rewards. We evaluate RLSyn on two biomedical datasets–AI-READI and MIMIC-IV–and benchmark it against state-of-the-art generative adversarial networks (GANs) and diffusion-based methods across extensive privacy, utility, and fidelity evaluations. On MIMIC-IV, RLSyn achieves predictive utility comparable to diffusion models (S2R AUC 0.902 vs 0.906 respectively) while slightly outperforming them in fidelity (NMI 0.001 vs. 0.003; DWD 2.073 vs. 2.797) and achieving comparable, low privacy risk (~0.50 membership inference risk AUC). On the smaller AI-READI dataset, RLSyn again matches diffusion-based utility (S2R AUC 0.873 vs. 0.871), while achieving higher fidelity (NMI 0.001 vs. 0.002; DWD 13.352 vs. 16.441) and significantly lower vulnerability to membership inference attacks (AUC 0.544 vs. 0.601). Both RLSyn and diffusion-based models substantially outperform GANs across utility and fidelity on both datasets. Our results suggest that reinforcement learning provides a principled and effective approach for synthetic biomedical data generation, particularly in data-scarce regimes.
Read the full abstract

All authors Natalia Espinosa-Dice, Nicholas J. Jackson, Chao Yan, Aaron Lee, Bradley A. Malin

Machine Learning · Cross-listed from physics.med-ph

Deep learning-enhanced dual-mode multiplexed optical sensor for point-of-care diagnostics of cardiovascular diseases

Rapid and accessible cardiac biomarker testing is essential for the timely diagnosis and risk assessment of myocardial infarction (MI) and heart failure (HF), two interrelated conditions that frequently coexist and drive recurrent hospitalizations with high mortality. However, current laboratory and point-of-care testing systems are limited by long turnaround times, narrow dynamic ranges for the tested biomarkers, and single-analyte formats that fail to capture the complexity of cardiovascular disease. Here, we present a deep learning-enhanced dual-mode multiplexed vertical flow assay (xVFA) with a portable optical reader and a neural network-based quantification pipeline. This optical sensor integrates colorimetric and chemiluminescent detection within a single paper-based cartridge to complementarily cover a large dynamic range (spanning ~6 orders of magnitude) for both low- and high-abundance biomarkers, while maintaining quantitative accuracy. Using 50 uL of serum, the optical sensor simultaneously quantifies cardiac troponin I (cTnI), creatine kinase-MB (CK-MB), and N-terminal pro-B-type natriuretic peptide (NT-proBNP) within 23 min. The xVFA achieves sub-pg/mL sensitivity for cTnI and sub-ng/mL sensitivity for CK-MB and NT-proBNP, spanning the clinically relevant ranges for these biomarkers. Neural network models trained and blindly tested on 92 patient serum samples yielded a robust quantification performance (Pearson's r > 0.96 vs. reference assays). By combining high sensitivity, multiplexing, and automation in a compact and cost-effective optical sensor format, the dual-mode xVFA enables rapid and quantitative cardiovascular diagnostics at the point of care.
Read the full abstract

All authors Gyeo-Re Han, Merve Eryilmaz, Artem Goncharov, Yuzhu Li, Shun Ye, Aoi Tomoeda, Emily Ngo, Margherita Scussat, Xiao Wang, Zixiang Ji, Max Zhang, Jeffrey J. Hsu, Omai B. Garner, Dino Di Carlo, Aydogan Ozcan