Authors: Long Lian, Sida Wang, Felix Juefei-Xu, Tsu-Jui Fu, Xiuyu Li, Adam Yala, Trevor Darrell, Alane Suhr, Yuandong Tian, Xi Victoria Lin
Abstract: Scaling inference-time computation has enabled Large Language Models (LLMs) to achieve strong reasoning performance, but inherently sequential decoding leads to substantial latency, especially on complex tasks. Recent work on adaptive parallel reasoning aims to improve inference efficiency by decomposing the problem-solving process into concurrent reasoning threads when beneficial. However, existing methods on realistic tasks are either limited to supervised behavior cloning or exhibit significant accuracy drops compared to widely-used sequential long chain-of-thought (CoT) baselines. Moreover, many require customized inference engines, complicating deployment. We introduce ThreadWeaver, a framework for adaptive parallel reasoning that achieves accuracy on par with popular sequential reasoning models of comparable size while significantly reducing inference latency. ThreadWeaver's performance stems from three key innovations: 1) a two-stage parallel trajectory generator that produces large-scale, high-quality CoT data with parallel annotations for supervised fine-tuning; 2) a trie-based training-inference co-design that enables parallel reasoning on any off-the-shelf autoregressive inference engine without modifying position embeddings or KV caches; and 3) a parallelization-aware reinforcement learning framework that teaches the model to balance accuracy with effective parallelization. Across six challenging mathematical reasoning benchmarks, ThreadWeaver trained atop Qwen3-8B achieves accuracy comparable to cutting-edge sequential reasoning models (71.9% on average and 79.9% on AIME24) while delivering up to 1.53x average speedup in token latency, establishing a new Pareto frontier between accuracy and efficiency.
Authors: Jinping Wang, Zhiqiang Gao, Zhiwu Xie
Abstract: Recent studies on Neural Collapse (NC) reveal that, under class-balanced conditions, the class feature means and classifier weights spontaneously align into a simplex equiangular tight frame (ETF). In long-tailed regimes, however, severe sample imbalance tends to prevent the emergence of the NC phenomenon, resulting in poor generalization performance. Current efforts predominantly seek to recover the ETF geometry by imposing constraints on features or classifier weights, yet overlook a critical problem: There is a pronounced misalignment between the feature and the classifier weight spaces. In this paper, we theoretically quantify the harm of such misalignment through an optimal error exponent analysis. Built on this insight, we propose three explicit alignment strategies that plug-and-play into existing long-tail methods without architectural change. Extensive experiments on the CIFAR-10-LT, CIFAR-100-LT, and ImageNet-LT datasets consistently boost examined baselines and achieve the state-of-the-art performances.
Authors: Mohamed Elrefaie, Dule Shu, Matt Klenk, Faez Ahmed
Abstract: Benchmarking has been the cornerstone of progress in computer vision, natural language processing, and the broader deep learning domain, driving algorithmic innovation through standardized datasets and reproducible evaluation protocols. The growing availability of large-scale Computational Fluid Dynamics (CFD) datasets has opened new opportunities for applying machine learning to aerodynamic and engineering design. Yet, despite this progress, there exists no standardized benchmark for large-scale numerical simulations in engineering design. In this work, we introduce CarBench, the first comprehensive benchmark dedicated to large-scale 3D car aerodynamics, performing a large-scale evaluation of state-of-the-art models on DrivAerNet++, the largest public dataset for automotive aerodynamics, containing over 8,000 high-fidelity car simulations. We assess eleven architectures spanning neural operator methods (e.g., Fourier Neural Operator), geometric deep learning (PointNet, RegDGCNN, PointMAE, PointTransformer), transformer-based neural solvers (Transolver, Transolver++, AB-UPT), and implicit field networks (TripNet). Beyond standard interpolation tasks, we perform cross-category experiments in which transformer-based solvers trained on a single car archetype are evaluated on unseen categories. Our analysis covers predictive accuracy, physical consistency, computational efficiency, and statistical uncertainty. To accelerate progress in data-driven engineering, we open-source the benchmark framework, including training pipelines, uncertainty estimation routines based on bootstrap resampling, and pretrained model weights, establishing the first reproducible foundation for large-scale learning from high-fidelity CFD simulations, available at https://github.com/Mohamedelrefaie/CarBench.
Authors: Di Zhu, Chen Xie, Ziwei Wang, Haoyun Zhang
Abstract: New York City reports over one hundred thousand motor vehicle collisions each year, creating substantial injury and public health burden. We present RaX-Crash, a resource efficient and explainable small model pipeline for structured injury severity prediction on the official NYC Motor Vehicle Collisions dataset. RaX-Crash integrates three linked tables with tens of millions of records, builds a unified feature schema in partitioned storage, and trains compact tree based ensembles (Random Forest and XGBoost) on engineered tabular features, which are compared against locally deployed small language models (SLMs) prompted with textual summaries. On a temporally held out test set, XGBoost and Random Forest achieve accuracies of 0.7828 and 0.7794, clearly outperforming SLMs (0.594 and 0.496); class imbalance analysis shows that simple class weighting improves fatal recall with modest accuracy trade offs, and SHAP attribution highlights human vulnerability factors, timing, and location as dominant drivers of predicted severity. Overall, RaX-Crash indicates that interpretable small model ensembles remain strong baselines for city scale injury analytics, while hybrid pipelines that pair tabular predictors with SLM generated narratives improve communication without sacrificing scalability.
Authors: Alejandro Cuadron, Pengfei Yu, Yang Liu, Arpit Gupta
Abstract: Despite rapid progress in LLM agents, performance on long-horizon, tool-using tasks remains fragile. To better understand this fragility, we ask a simple question: \emph{do all actions contribute equally to failure?} Analyzing execution traces on $\tau$-Bench (Airline/Retail) and SWE-Bench Verified, we decompose trajectories into \emph{mutating} (environment-changing) vs.\ non-mutating steps and formalize \emph{decisive deviations}, earliest action, level divergences that flip success to failure. A logistic regression reveals that each additional deviation in a mutating action reduces the odds of success by upto $92\%$ on Airline and upto $96\%$ on Retail for SoTA models. In contrast, deviations in non-mutating actions have little to no effect. Errors also grow with context length as agents drift from role and act on stale constraints. Motivated by these observations, we introduce \cm{}, a model-agnostic, gradient-free, test-time safeguard that (i) adds mutation-gated verification, (ii) injects \emph{Targeted Reflection} before mutating steps, and (iii) performs block-based context cleaning. \cm{} delivers consistent gains, e.g., Qwen3-Thinking: +28\% \emph{relative} on Airline, +11\% on Retail, and +7\% on SWE-Bench Verified; Claude: +9\%/+7\%. We further identify ceiling effects in $\tau$-Bench, where annotation errors and underspecified tasks artificially cap model performance. To address this, we release $\tau$-Bench Verified, which restores benchmark headroom through targeted revisions. Our results argue for action-level analysis, targeted safeguards, and reliable evaluations as prerequisites for robust multi-turn agents.
Authors: Jinwoo Jeong, Minchul Kang, Younghun Go, Changyong Shin, Hyunho Lee, Junho Yoon, Gyeongsik Yang, Chuck Yoo
Abstract: As deep learning models in agentic AI systems grow in scale and complexity, GPU memory requirements increase and often exceed the available GPU memory capacity, so that out-of-memory (OoM) errors occur. It is well known that OoM interrupts the whole training itself and wastes substantial computational resources. Therefore, to prevent OoM, accurate prediction of GPU memory usage is essential. However, previous studies focus only on unimodal architectures and fail to generalize to multimodal models, even though the multimodal models are a common choice in agentic AI systems. To address this limitation, we propose a framework that predicts the peak GPU memory usage by analyzing the model architecture and training behavior of multimodal models. Specifically, the framework decomposes the multimodal model into its constituent layers and applies factorization to estimate the memory usage of each layer. Our evaluation shows that our framework achieves high prediction accuracy of ~8.7% average MAPE.
Authors: Yongyao Wang, Jingyuan Wang, Xie Yu, Jiahao Ji, Chao Li
Abstract: Traffic forecasting task is significant to modern urban management. Recently, there is growing attention on large-scale forecasting, as it better reflects the complexity of real-world traffic networks. However, existing models often exhibit quadratic computational complexity, making them impractical for large-scale real-world scenarios. In this paper, we propose a novel framework, Hierarchical Spatio-Temporal Mixer (HSTMixer), which leverages an all-MLP architecture for efficient and effective large-scale traffic forecasting. HSTMixer employs a hierarchical spatiotemporal mixing block to extract multi-resolution features through bottom-up aggregation and top-down propagation. Furthermore, an adaptive region mixer generates transformation matrices based on regional semantics, enabling our model to dynamically capture evolving spatiotemporal patterns for different regions. Extensive experiments conducted on four large-scale real-world datasets demonstrate that the proposed method not only achieves state-of-the-art performance but also exhibits competitive computational efficiency.
Authors: Huizheng Wang, Hongbin Wang, Shaojun Wei, Yang Hu, Shouyi Yin
Abstract: Attention-based Transformers have revolutionized natural language processing (NLP) and shown strong performance in computer vision (CV) tasks. However, as the input sequence varies, the computational bottlenecks in Transformer models exhibit dynamic behavior across stages, which calls for a cross-stage sparse acceleration strategy. Unfortunately, most existing sparse Transformer approaches are single-stage based, and their sparsity prediction mechanisms lead to significant power overhead when applied across multiple stages. To this end, this paper proposes a log-domain attention prediction algorithm-architecture co-design, named LAPA. First, an asymmetric leading one computing (ALOC) scheme is designed to eliminate expensive multiplications. Next, a mixed-precision multi-round shifting accumulation (MRSA) mechanism is further proposed to mitigate the accumulation overhead. A data-feature dependent filter (DDF) strategy is designed to work in concert with the MRSA process. Finally, an elaborate accelerator is designed to translate the theoretical enhancement into practical hardware improvement. Experimental results show that LAPA achieves 3.52x, 3.24x and 2.79x higher energy efficiency than the state-of-the-art (SOTA) works Spatten, Sanger and FACT, respectively.
Authors: Haokun Zhao, Yingzhe Bai, Qingyang Xu, Lixin Zhou, Jianxin Chen, Jicong Fan
Abstract: Accurate disease detection is of paramount importance for effective medical treatment and patient care. However, the process of disease detection is often associated with extensive medical testing and considerable costs, making it impractical to perform all possible medical tests on a patient to diagnose or predict hundreds or thousands of diseases. In this work, we propose Collaborative Learning for Disease Detection (CLDD), a novel graph-based deep learning model that formulates disease detection as a collaborative learning task by exploiting associations among diseases and similarities among patients adaptively. CLDD integrates patient-disease interactions and demographic features from electronic health records to detect hundreds or thousands of diseases for every patient, with little to no reliance on the corresponding medical tests. Extensive experiments on a processed version of the MIMIC-IV dataset comprising 61,191 patients and 2,000 diseases demonstrate that CLDD consistently outperforms representative baselines across multiple metrics, achieving a 6.33\% improvement in recall and 7.63\% improvement in precision. Furthermore, case studies on individual patients illustrate that CLDD can successfully recover masked diseases within its top-ranked predictions, demonstrating both interpretability and reliability in disease prediction. By reducing diagnostic costs and improving accessibility, CLDD holds promise for large-scale disease screening and social health security.
Authors: Junhua Shi, Qingyun Sun, Haonan Yuan, Xingcheng Fu
Abstract: We present Graph Foundation Models (GFMs) which have made significant progress in various tasks, but their robustness against domain noise, structural perturbations, and adversarial attacks remains underexplored. A key limitation is the insufficient modeling of hierarchical structural semantics, which are crucial for generalization. In this paper, we propose SA^2GFM, a robust GFM framework that improves domain-adaptive representations through Structure-Aware Semantic Augmentation. First, we encode hierarchical structural priors by transforming entropy-based encoding trees into structure-aware textual prompts for feature augmentation. The enhanced inputs are processed by a self-supervised Information Bottleneck mechanism that distills robust, transferable representations via structure-guided compression. To address negative transfer in cross-domain adaptation, we introduce an expert adaptive routing mechanism, combining a mixture-of-experts architecture with a null expert design. For efficient downstream adaptation, we propose a fine-tuning module that optimizes hierarchical structures through joint intra- and inter-community structure learning. Extensive experiments demonstrate that SA^2GFM outperforms 9 state-of-the-art baselines in terms of effectiveness and robustness against random noise and adversarial perturbations for node and graph classification.
Authors: Da Zhang, Bingyu Li, Zhiyuan Zhao, Yanhan Zhang, Junyu Gao, Feiping Nie, Xuelong Li
Abstract: Time series classification (TSC) is crucial in numerous real-world applications, such as environmental monitoring, medical diagnosis, and posture recognition. TSC tasks require models to effectively capture discriminative information for accurate class identification. Although deep learning architectures excel at capturing temporal dependencies, they often suffer from high computational cost, sensitivity to noise perturbations, and susceptibility to overfitting on small-scale datasets. To address these challenges, we propose FAIM, a lightweight Frequency-Aware Interactive Mamba model. Specifically, we introduce an Adaptive Filtering Block (AFB) that leverages Fourier Transform to extract frequency-domain features from time series data. The AFB incorporates learnable adaptive thresholds to dynamically suppress noise and employs element-wise coupling of global and local semantic adaptive filtering, enabling in-depth modeling of the synergy among different frequency components. Furthermore, we design an Interactive Mamba Block (IMB) to facilitate efficient multi-granularity information interaction, balancing the extraction of fine-grained discriminative features and comprehensive global contextual information, thereby endowing FAIM with powerful and expressive representations for TSC tasks. Additionally, we incorporate a self-supervised pre-training mechanism to enhance FAIM's understanding of complex temporal patterns and improve its robustness across various domains and high-noise scenarios. Extensive experiments on multiple benchmarks demonstrate that FAIM consistently outperforms existing state-of-the-art (SOTA) methods, achieving a superior trade-off between accuracy and efficiency and exhibits outstanding performance.
Authors: Jianling Gao, Chongyang Tao, Xuelian Lin, Junfeng Liu, Shuai Ma
Abstract: Semi-supervised anomaly detection (AD) has shown great promise by effectively leveraging limited labeled data. However, existing methods are typically structured around scoring individual points or simple pairs. Such {point- or pair-centric} view not only overlooks the contextual nature of anomalies, which are defined by their deviation from a collective group, but also fails to exploit the rich supervisory signals that can be generated from the combinatorial composition of sets. Consequently, such models struggle to exploit the high-order interactions within the data, which are critical for learning discriminative representations. To address these limitations, we propose SetAD, a novel framework that reframes semi-supervised AD as a Set-level Anomaly Detection task. SetAD employs an attention-based set encoder trained via a graded learning objective, where the model learns to quantify the degree of anomalousness within an entire set. This approach directly models the complex group-level interactions that define anomalies. Furthermore, to enhance robustness and score calibration, we propose a context-calibrated anomaly scoring mechanism, which assesses a point's anomaly score by aggregating its normalized deviations from peer behavior across multiple, diverse contextual sets. Extensive experiments on 10 real-world datasets demonstrate that SetAD significantly outperforms state-of-the-art models. Notably, we show that our model's performance consistently improves with increasing set size, providing strong empirical support for the set-based formulation of anomaly detection.
Authors: Muhammad Sukri Bin Ramli
Abstract: New methods are needed to monitor environmental treaties, like the Montreal Protocol, by reviewing large, complex customs datasets. This paper introduces a framework using unsupervised machine learning to systematically detect suspicious trade patterns and highlight activities for review. Our methodology, applied to 100,000 trade records, combines several ML techniques. Unsupervised Clustering (K-Means) discovers natural trade archetypes based on shipment value and weight. Anomaly Detection (Isolation Forest and IQR) identifies rare "mega-trades" and shipments with commercially unusual price-per-kilogram values. This is supplemented by Heuristic Flagging to find tactics like vague shipment descriptions. These layers are combined into a priority score, which successfully identified 1,351 price outliers and 1,288 high-priority shipments for customs review. A key finding is that high-priority commodities show a different and more valuable value-to-weight ratio than general goods. This was validated using Explainable AI (SHAP), which confirmed vague descriptions and high value as the most significant risk predictors. The model's sensitivity was validated by its detection of a massive spike in "mega-trades" in early 2021, correlating directly with the real-world regulatory impact of the US AIM Act. This work presents a repeatable unsupervised learning pipeline to turn raw trade data into prioritized, usable intelligence for regulatory groups.
Authors: Philipp Stark, Alexandros Sopasakis, Ola Hall, Markus Grillitsch
Abstract: We transform large-scale Swedish register data into textual life trajectories to address two long-standing challenges in data analysis: high cardinality of categorical variables and inconsistencies in coding schemes over time. Leveraging this uniquely comprehensive population register, we convert register data from 6.9 million individuals (2001-2013) into semantically rich texts and predict individuals' residential mobility in later years (2013-2017). These life trajectories combine demographic information with annual changes in residence, work, education, income, and family circumstances, allowing us to assess how effectively such sequences support longitudinal prediction. We compare multiple NLP architectures (including LSTM, DistilBERT, BERT, and Qwen) and find that sequential and transformer-based models capture temporal and semantic structure more effectively than baseline models. The results show that textualized register data preserves meaningful information about individual pathways and supports complex, scalable modeling. Because few countries maintain longitudinal microdata with comparable coverage and precision, this dataset enables analyses and methodological tests that would be difficult or impossible elsewhere, offering a rigorous testbed for developing and evaluating new sequence-modeling approaches. Overall, our findings demonstrate that combining semantically rich register data with modern language models can substantially advance longitudinal analysis in social sciences.
Authors: Maria Milena Araujo Felix
Abstract: The sophistication of modern malware, specifically regarding communication with Command and Control (C2) servers, has rendered static blacklist-based defenses obsolete. The use of Domain Generation Algorithms (DGA) allows attackers to generate thousands of dynamic addresses daily, hindering blocking by traditional firewalls. This paper aims to propose and evaluate a method for detecting DGA domains using Deep Learning and Natural Language Processing (NLP) techniques. The methodology consisted of collecting a hybrid database containing 50,000 legitimate and 50,000 malicious domains, followed by the extraction of lexical features and the training of a Recurrent Neural Network (LSTM). Results demonstrated that while statistical entropy analysis is effective for simple DGAs, the Neural Network approach presents superiority in detecting complex patterns, reaching 97.2% accuracy and reducing the false positive rate in ambiguous lawful traffic scenarios.
Authors: Pouya Ahadi, Reza Marzban, Ali Adibi, Kamran Paynabar
Abstract: Bayesian optimization is widely used for optimizing expensive black box functions, but most existing approaches focus on scalar responses. In many scientific and engineering settings the response is functional, varying smoothly over an index such as time or wavelength, which makes classical formulations inadequate. Existing methods often minimize integrated error, which captures average performance but neglects worst case deviations. To address this limitation we propose min-max Functional Bayesian Optimization (MM-FBO), a framework that directly minimizes the maximum error across the functional domain. Functional responses are represented using functional principal component analysis, and Gaussian process surrogates are constructed for the principal component scores. Building on this representation, MM-FBO introduces an integrated uncertainty acquisition function that balances exploitation of worst case expected error with exploration across the functional domain. We provide two theoretical guarantees: a discretization bound for the worst case objective, and a consistency result showing that as the surrogate becomes accurate and uncertainty vanishes, the acquisition converges to the true min-max objective. We validate the method through experiments on synthetic benchmarks and physics inspired case studies involving electromagnetic scattering by metaphotonic devices and vapor phase infiltration. Results show that MM-FBO consistently outperforms existing baselines and highlights the importance of explicitly modeling functional uncertainty in Bayesian optimization.
Authors: Ci Zhang, Huayu Li, Changdi Yang, Jiangnan Xia, Yanzhi Wang, Xiaolong Ma, Jin Lu, Geng Yuan
Abstract: Recent studies show that using diffusion models for time series signal reconstruc- tion holds great promise. However, such approaches remain largely unexplored in the domain of medical time series. The unique characteristics of the physiological time series signals, such as multivariate, high temporal variability, highly noisy, and artifact-prone, make deep learning-based approaches still challenging for tasks such as imputation. Hence, we propose a novel Mixture of Experts (MoE)-based noise estimator within a score-based diffusion framework. Specifically, the Receptive Field Adaptive MoE (RFAMoE) module is designed to enable each channel to adap- tively select desired receptive fields throughout the diffusion process. Moreover, recent literature has found that when generating a physiological signal, performing multiple inferences and averaging the reconstructed signals can effectively reduce reconstruction errors, but at the cost of significant computational and latency over- head. We design a Fusion MoE module and innovatively leverage the nature of MoE module to generate K noise signals in parallel, fuse them using a routing mechanism, and complete signal reconstruction in a single inference step. This design not only improves performance over previous methods but also eliminates the substantial computational cost and latency associated with multiple inference processes. Extensive results demonstrate that our proposed framework consistently outperforms diffusion-based SOTA works on different tasks and datasets.
Authors: Qiujing Lu, Xuanhan Wang, Runze Yuan, Wei Lu, Xinyi Gong, Shuo Feng
Abstract: Ensuring the safety of autonomous vehicles (AV) requires rigorous testing under both everyday driving and rare, safety-critical conditions. A key challenge lies in simulating environment agents, including background vehicles (BVs) and vulnerable road users (VRUs), that behave realistically in nominal traffic while also exhibiting risk-prone behaviors consistent with real-world accidents. We introduce Controllable Risk Agent Generation (CRAG), a framework designed to unify the modeling of dominant nominal behaviors and rare safety-critical behaviors. CRAG constructs a structured latent space that disentangles normal and risk-related behaviors, enabling efficient use of limited crash data. By combining risk-aware latent representations with optimization-based mode-transition mechanisms, the framework allows agents to shift smoothly and plausibly from safe to risk states over extended horizons, while maintaining high fidelity in both regimes. Extensive experiments show that CRAG improves diversity compared to existing baselines, while also enabling controllable generation of risk scenarios for targeted and efficient evaluation of AV robustness.
Authors: James Bagrow, Josh Bongard
Abstract: Kolmogorov-Arnold Networks (KANs) offer a promising path toward interpretable machine learning: their learnable activations can be studied individually, while collectively fitting complex data accurately. In practice, however, trained activations often lack symbolic fidelity, learning pathological decompositions with no meaningful correspondence to interpretable forms. We propose Softly Symbolified Kolmogorov-Arnold Networks (S2KAN), which integrate symbolic primitives directly into training. Each activation draws from a dictionary of symbolic and dense terms, with learnable gates that sparsify the representation. Crucially, this sparsification is differentiable, enabling end-to-end optimization, and is guided by a principled Minimum Description Length objective. When symbolic terms suffice, S2KAN discovers interpretable forms; when they do not, it gracefully degrades to dense splines. We demonstrate competitive or superior accuracy with substantially smaller models across symbolic benchmarks, dynamical systems forecasting, and real-world prediction tasks, and observe evidence of emergent self-sparsification even without regularization pressure.
Authors: Qi Chen, Mihai Anitescu
Abstract: We present a Fourier-enhanced recurrent neural network (RNN) for downscaling electrical loads. The model combines (i) a recurrent backbone driven by low-resolution inputs, (ii) explicit Fourier seasonal embeddings fused in latent space, and (iii) a self-attention layer that captures dependencies among high-resolution components within each period. Across four PJM territories, the approach yields RMSE lower and flatter horizon-wise than classical Prophet baselines (with and without seasonality/LAA) and than RNN ablations without attention or Fourier features.
Authors: Amogh Anshu N, Harish BP
Abstract: Network-on-Chip (NoC) design requires exploring a high-dimensional configuration space to satisfy stringent throughput requirements and latency constraints.Traditional design space exploration techniques are often slow and struggle to handle complex, non-linear parameter interactions.This work presents a machine learning-driven framework that automates NoC design space exploration using BookSim simulations and reverse neural network models.Specifically, we compare three architectures - a Multi-Layer Perceptron (MLP),a Conditional Diffusion Model, and a Conditional Variational Autoencoder (CVAE) to predict optimal NoC parameters given target performance metrics.Our pipeline generates over 150,000 simulation data points across varied mesh topologies.The Conditional Diffusion Model achieved the highest predictive accuracy, attaining a mean squared error (MSE) of 0.463 on unseen data.Furthermore, the proposed framework reduces design exploration time by several orders of magnitude, making it a practical solution for rapid and scalable NoC co-design.
Authors: Manh Nguyen (Department of Statistics, University of Wisconsin-Madison), Joshua Cape (Department of Statistics, University of Wisconsin-Madison)
Abstract: Given augmented views of each input graph, contrastive learning methods (e.g., InfoNCE) optimize pairwise alignment of graph embeddings across views while providing no mechanism to control the global structure of the view specific graph-of-graphs built from these embeddings. We introduce SpecMatch-CL, a novel loss function that aligns the view specific graph-of-graphs by minimizing the difference between their normalized Laplacians. Theoretically, we show that under certain assumptions, the difference between normalized Laplacians provides an upper bound not only for the difference between the ideal Perfect Alignment contrastive loss and the current loss, but also for the Uniformly loss. Empirically, SpecMatch-CL establishes new state of the art on eight TU benchmarks under unsupervised learning and semi-supervised learning at low label rates, and yields consistent gains in transfer learning on PPI-306K and ZINC 2M datasets.
Authors: Manh Nguyen (Department of Statistics), Daniel Pimentel-Alarc\'on (Department of Biostatistics and Medical Informatics, Wisconsin Institute of Discovery, University of Wisconsin-Madison)
Abstract: Nonnegative matrix factorization (NMF) is a widely used tool for learning parts-based, low-dimensional representations of nonnegative data, with applications in vision, text, and bioinformatics. In clustering applications, orthogonal NMF (ONMF) variants further impose (approximate) orthogonality on the representation matrix so that its rows behave like soft cluster indicators. Existing algorithms, however, are typically derived from optimization viewpoints and do not explicitly exploit the conic geometry induced by NMF: data points lie in a convex cone whose extreme rays encode fundamental directions or "topics". In this work we revisit NMF from this geometric perspective and propose Cone Collapse, an algorithm that starts from the full nonnegative orthant and iteratively shrinks it toward the minimal cone generated by the data. We prove that, under mild assumptions on the data, Cone Collapse terminates in finitely many steps and recovers the minimal generating cone of $\mathbf{X}^\top$ . Building on this basis, we then derive a cone-aware orthogonal NMF model (CC-NMF) by applying uni-orthogonal NMF to the recovered extreme rays. Across 16 benchmark gene-expression, text, and image datasets, CC-NMF consistently matches or outperforms strong NMF baselines-including multiplicative updates, ANLS, projective NMF, ONMF, and sparse NMF-in terms of clustering purity. These results demonstrate that explicitly recovering the data cone can yield both theoretically grounded and empirically strong NMF-based clustering methods.
Authors: Huanran Li (Department of Electrical Engineering), Manh Nguyen (Statistics), Daniel Pimentel-Alarc\'on (Biostatistics, Wisconsin Institute of Discovery, University of Wisconsin-Madison)
Abstract: Contrastive learning has emerged as a powerful method in deep learning, excelling at learning effective representations through contrasting samples from different distributions. However, dimensional collapse, where embeddings converge into a lower-dimensional space, poses a significant challenge, especially in semi-supervised and self-supervised setups. In this paper, we first identify a critical learning-rate threshold, beyond which standard contrastive losses converge to collapsed solutions. Building on these insights, we propose CLOP, a novel semi-supervised loss function designed to prevent dimensional collapse by promoting the formation of orthogonal linear subspaces among class embeddings. Through extensive experiments on real and synthetic datasets, we demonstrate that CLOP improves performance in image classification and object detection tasks while also exhibiting greater stability across different learning rates and batch sizes.
Authors: Hongjun Wang, Yitong Jiang, Collin McCarthy, David Wehr, Hanrong Ye, Xinhao Li, Ka Chun Cheung, Wonmin Byeon, Jinwei Gu, Ke Chen, Kai Han, Hongxu Yin, Pavlo Molchanov, Jan Kautz, Sifei Liu
Abstract: Efficient vision transformer remains a bottleneck for high-resolution images and long-video related real-world applications. Generalized Spatial Propagation Network (GSPN) addresses this by replacing quadratic self-attention with a line-scan propagation scheme, bringing the cost close to linear in the number of rows or columns, while retaining accuracy. Despite this advancement, the existing GSPN implementation still suffers from (i) heavy overhead due to repeatedly launching GPU kernels, (ii) excessive data transfers from global GPU memory, and (iii) redundant computations caused by maintaining separate propagation weights for each channel. We introduce GSPN-2, a joint algorithm-system redesign. In particular, we eliminate thousands of micro-launches from the previous implementation into one single 2D kernel, explicitly pin one warp to each channel slice, and stage the previous column's activations in shared memory. On the model side, we introduce a compact channel propagation strategy that replaces per-channel matrices, trimming parameters, and align naturally with the affinity map used in transformer attention. Experiments demonstrate GSPN-2's effectiveness across image classification and text-to-image synthesis tasks, matching transformer-level accuracy with significantly lower computational cost. GSPN-2 establishes a new efficiency frontier for modeling global spatial context in vision applications through its unique combination of structured matrix transformations and GPU-optimized implementation. Project page: https://whj363636.github.io/GSPN2/
Authors: Davide Donno, Donatello Elia, Gabriele Accarino, Marco De Carlo, Enrico Scoccimarro, Silvio Gualdi
Abstract: Accurate tropical cyclones (TCs) tracking represents a critical challenge in the context of weather and climate science. Traditional tracking schemes mainly rely on subjective thresholds, which may introduce biases in their skills on the geographical region of application. We present ByteStorm, an efficient data-driven framework for reconstructing TC tracks without threshold tuning. It leverages deep learning networks to detect TC centers (via classification and localization), using only relative vorticity (850 mb) and mean sea-level pressure. Then, detected centers are linked into TC tracks through the BYTE algorithm. ByteStorm is evaluated against state-of-the-art deterministic trackers in the East- and West-North Pacific basins (ENP and WNP). The proposed framework achieves superior performance in terms of Probability of Detection ($85.05\%$ ENP, $79.48\%$ WNP), False Alarm Rate ($23.26\%$ ENP, $16.14\%$ WNP), and high Inter-Annual Variability correlations ($0.75$ ENP and $0.69$ WNP). These results highlight the potential of integrating deep learning and computer vision for fast and accurate TC tracking, offering a robust alternative to traditional approaches.
Authors: Guilherme Seidyo Imai Aldeia, Joseph D. Romano, Fabricio Olivetti de Franca, Daniel S. Herman, William G. La Cava
Abstract: Medical decision-making makes frequent use of algorithms that combine risk equations with rules, providing clear and standardized treatment pathways. Symbolic regression (SR) traditionally limits its search space to continuous function forms and their parameters, making it difficult to model this decision-making. However, due to its ability to derive data-driven, interpretable models, SR holds promise for developing data-driven clinical risk scores. To that end we introduce Brush, an SR algorithm that combines decision-tree-like splitting algorithms with non-linear constant optimization, allowing for seamless integration of rule-based logic into symbolic regression and classification models. Brush achieves Pareto-optimal performance on SRBench, and was applied to recapitulate two widely used clinical scoring systems, achieving high accuracy and interpretable models. Compared to decision trees, random forests, and other SR methods, Brush achieves comparable or superior predictive performance while producing simpler models.
Authors: Federico Di Valerio, Michela Proietti, Alessio Ragno, Roberto Capobianco
Abstract: Continual learning constrains models to learn new tasks over time without forgetting what they have already learned. A key challenge in this setting is catastrophic forgetting, where learning new information causes the model to lose its performance on previous tasks. Recently, explainable AI has been proposed as a promising way to better understand and reduce forgetting. In particular, self-explainable models are useful because they generate explanations during prediction, which can help preserve knowledge. However, most existing explainable approaches use post-hoc explanations or require additional memory for each new task, resulting in limited scalability. In this work, we introduce CIP-Net, an exemplar-free self-explainable prototype-based model designed for continual learning. CIP-Net avoids storing past examples and maintains a simple architecture, while still providing useful explanations and strong performance. We demonstrate that CIPNet achieves state-of-the-art performances compared to previous exemplar-free and self-explainable methods in both task- and class-incremental settings, while bearing significantly lower memory-related overhead. This makes it a practical and interpretable solution for continual learning.
Authors: Sudhanva Manjunath Athreya, Paul Rosen
Abstract: Deep learning models have achieved remarkable success across various domains, yet their learned representations and decision-making processes remain largely opaque and hard to interpret. This work introduces HOLE (Homological Observation of Latent Embeddings), a method for analyzing and interpreting deep neural networks through persistent homology. HOLE extracts topological features from neural activations and presents them using a suite of visualization techniques, including Sankey diagrams, heatmaps, dendrograms, and blob graphs. These tools facilitate the examination of representation structure and quality across layers. We evaluate HOLE on standard datasets using a range of discriminative models, focusing on representation quality, interpretability across layers, and robustness to input perturbations and model compression. The results indicate that topological analysis reveals patterns associated with class separation, feature disentanglement, and model robustness, providing a complementary perspective for understanding and improving deep learning systems.
Authors: Aaron D. Mullen, Daniel R. Harris, Svetla Slavova, V. K. Cody Bumgardner
Abstract: Time series forecasting has applications across domains and industries, especially in healthcare, but the technical expertise required to analyze data, build models, and interpret results can be a barrier to using these techniques. This article presents a web platform that makes the process of analyzing and plotting data, training forecasting models, and interpreting and viewing results accessible to researchers and clinicians. Users can upload data and generate plots to showcase their variables and the relationships between them. The platform supports multiple forecasting models and training techniques which are highly customizable according to the user's needs. Additionally, recommendations and explanations can be generated from a large language model that can help the user choose appropriate parameters for their data and understand the results for each model. The goal is to integrate this platform into learning health systems for continuous data collection and inference from clinical pipelines.
Authors: Aryaman Bansal, Divya Sharma
Abstract: In critical care settings such as the Intensive Care Unit, clinicians face the complex challenge of balancing conflicting objectives, primarily maximizing patient survival while minimizing resource utilization (e.g., length of stay). Single-objective Reinforcement Learning approaches typically address this by optimizing a fixed scalarized reward function, resulting in rigid policies that fail to adapt to varying clinical priorities. Multi-objective Reinforcement Learning (MORL) offers a solution by learning a set of optimal policies along the Pareto Frontier, allowing for dynamic preference selection at test time. However, applying MORL in healthcare necessitates strict offline learning from historical data. In this paper, we benchmark three offline MORL algorithms, Conditioned Conservative Pareto Q-Learning (CPQL), Adaptive CPQL, and a modified Pareto Efficient Decision Agent (PEDA) Decision Transformer (PEDA DT), against three scalarized single-objective baselines (BC, CQL, and DDQN) on the MIMIC-IV dataset. Using Off-Policy Evaluation (OPE) metrics, we demonstrate that PEDA DT algorithm offers superior flexibility compared to static scalarized baselines. Notably, our results extend previous findings on single-objective Decision Transformers in healthcare, confirming that sequence modeling architectures remain robust and effective when scaled to multi-objective conditioned generation. These findings suggest that offline MORL is a promising framework for enabling personalized, adjustable decision-making in critical care without the need for retraining.
Authors: Tianxingjian Ding, Yuanhao Zou, Chen Chen, Mubarak Shah, Yu Tian
Abstract: Clinical decision-making in oncology requires predicting dynamic disease evolution, a task current static AI predictors cannot perform. While world models (WMs) offer a paradigm for generative prediction, existing medical applications remain limited. Existing methods often rely on stochastic diffusion models, focusing on visual reconstruction rather than causal, physiological transitions. Furthermore, in medical domain, models like MeWM typically ignore patient-specific temporal and clinical contexts and lack a feedback mechanism to link predictions to treatment decisions. To address these gaps, we introduce CLARITY, a medical world model that forecasts disease evolution directly within a structured latent space. It explicitly integrates time intervals (temporal context) and patient-specific data (clinical context) to model treatment-conditioned progression as a smooth, interpretable trajectory, and thus generate physiologically faithful, individualized treatment plans. Finally, CLARITY introduces a novel prediction-to-decision framework, translating latent rollouts into transparent, actionable recommendations. CLARITY demonstrates state-of-the-art performance in treatment planning. On the MU-Glioma-Post dataset, our approach outperforms recent MeWM by 12\%, and significantly surpasses all other medical-specific large language models.
Authors: Ashkan Shahbazi, Ping He, Ali Abbasi, Yikun Bai, Xinran Liu, Elaheh Akbari, Darian Salehi, Navid NaderiAlizadeh, Soheil Kolouri
Abstract: Scaling attention faces a critical bottleneck: the $\mathcal{O}(n^2)$ quadratic computational cost of softmax attention, which limits its application in long-sequence domains. While linear attention mechanisms reduce this cost to $\mathcal{O}(n)$, they typically rely on fixed random feature maps, such as random Fourier features or hand-crafted functions. This reliance on static, data-agnostic kernels creates a fundamental trade-off, forcing practitioners to sacrifice significant model accuracy for computational efficiency. We introduce \textsc{LUNA}, a kernelized linear attention mechanism that eliminates this trade-off, retaining linear cost while matching and surpassing the accuracy of quadratic attention. \textsc{LUNA} is built on the key insight that the kernel feature map itself should be learned rather than fixed a priori. By parameterizing the kernel, \textsc{LUNA} learns a feature basis tailored to the specific data and task, overcoming the expressive limitations of fixed-feature methods. \textsc{Luna} implements this with a learnable feature map that induces a positive-definite kernel and admits a streaming form, yielding linear time and memory scaling in the sequence length. Empirical evaluations validate our approach across diverse settings. On the Long Range Arena (LRA), \textsc{Luna} achieves state-of-the-art average accuracy among efficient Transformers under compute parity, using the same parameter count, training steps, and approximate FLOPs. \textsc{Luna} also excels at post-hoc conversion: replacing softmax in fine-tuned BERT and ViT-B/16 checkpoints and briefly fine-tuning recovers most of the original performance, substantially outperforming fixed linearizations.
Authors: Xiaobin Shen, George H. Chen
Abstract: We propose an interpretable deep competing risks model called the Deep Kernel Aalen-Johansen (DKAJ) estimator, which generalizes the classical Aalen-Johansen nonparametric estimate of cumulative incidence functions (CIFs). Each data point (e.g., patient) is represented as a weighted combination of clusters. If a data point has nonzero weight only for one cluster, then its predicted CIFs correspond to those of the classical Aalen-Johansen estimator restricted to data points from that cluster. These weights come from an automatically learned kernel function that measures how similar any two data points are. On four standard competing risks datasets, we show that DKAJ is competitive with state-of-the-art baselines while being able to provide visualizations to assist model interpretation.
Authors: Pingchuan Ma, Chengshuai Zhao, Bohan Jiang, Saketh Vishnubhatla, Ujun Jeong, Alimohammad Beigi, Adrienne Raglin, Huan Liu
Abstract: Crisis classification in social media aims to extract actionable disaster-related information from multimodal posts, which is a crucial task for enhancing situational awareness and facilitating timely emergency responses. However, the wide variation in crisis types makes achieving generalizable performance across unseen disasters a persistent challenge. Existing approaches primarily leverage deep learning to fuse textual and visual cues for crisis classification, achieving numerically plausible results under in-domain settings. However, they exhibit poor generalization across unseen crisis types because they 1. do not disentangle spurious and causal features, resulting in performance degradation under domain shift, and 2. fail to align heterogeneous modality representations within a shared space, which hinders the direct adaptation of established single-modality domain generalization (DG) techniques to the multimodal setting. To address these issues, we introduce a causality-guided multimodal domain generalization (MMDG) framework that combines adversarial disentanglement with unified representation learning for crisis classification. The adversarial objective encourages the model to disentangle and focus on domain-invariant causal features, leading to more generalizable classifications grounded in stable causal mechanisms. The unified representation aligns features from different modalities within a shared latent space, enabling single-modality DG strategies to be seamlessly extended to multimodal learning. Experiments on the different datasets demonstrate that our approach achieves the best performance in unseen disaster scenarios.
Authors: Jaron Cohen, Alexander G. Hasson, Sara Tanovic
Abstract: Since the advent of machine learning, interpretability has remained a persistent challenge, becoming increasingly urgent as generative models support high-stakes applications in drug and material discovery. Recent advances in large language model (LLM) architectures have yielded chemistry language models (CLMs) with impressive capabilities in molecular property prediction and molecular generation. However, how these models internally represent chemical knowledge remains poorly understood. In this work, we extend sparse autoencoder techniques to uncover and examine interpretable features within CLMs. Applying our methodology to the Foundation Models for Materials (FM4M) SMI-TED chemistry foundation model, we extract semantically meaningful latent features and analyse their activation patterns across diverse molecular datasets. Our findings reveal that these models encode a rich landscape of chemical concepts. We identify correlations between specific latent features and distinct domains of chemical knowledge, including structural motifs, physicochemical properties, and pharmacological drug classes. Our approach provides a generalisable framework for uncovering latent knowledge in chemistry-focused AI systems. This work has implications for both foundational understanding and practical deployment; with the potential to accelerate computational chemistry research.
Authors: Jonathan Kogan, Hayden Jananthan, Jeremy Kepner
Abstract: We study the expressivity of one-dimensional (1D) ReLU deep neural networks through the lens of their linear regions. For randomly initialized, fully connected 1D ReLU networks (He scaling with nonzero bias) in the infinite-width limit, we prove that the expected number of linear regions grows as $\sum_{i = 1}^L n_i + \mathop{{o}}\left(\sum_{i = 1}^L{n_i}\right) + 1$, where $n_\ell$ denotes the number of neurons in the $\ell$-th hidden layer. We also propose a function-adaptive notion of sparsity that compares the expected regions used by the network to the minimal number needed to approximate a target within a fixed tolerance.
Authors: Manas Joglekar, Jeremy Chen, Gabriel Wu, Jason Yosinski, Jasmine Wang, Boaz Barak, Amelia Glaese
Abstract: Large language models (LLMs) can be dishonest when reporting on their actions and beliefs -- for example, they may overstate their confidence in factual claims or cover up evidence of covert actions. Such dishonesty may arise due to the effects of reinforcement learning (RL), where challenges with reward shaping can result in a training process that inadvertently incentivizes the model to lie or misrepresent its actions. In this work we propose a method for eliciting an honest expression of an LLM's shortcomings via a self-reported *confession*. A confession is an output, provided upon request after a model's original answer, that is meant to serve as a full account of the model's compliance with the letter and spirit of its policies and instructions. The reward assigned to a confession during training is solely based on its honesty, and does not impact positively or negatively the main answer's reward. As long as the "path of least resistance" for maximizing confession reward is to surface misbehavior rather than covering it up, this incentivizes models to be honest in their confessions. Our findings provide some justification this empirical assumption, especially in the case of egregious model misbehavior. To demonstrate the viability of our approach, we train GPT-5-Thinking to produce confessions, and we evaluate its honesty in out-of-distribution scenarios measuring hallucination, instruction following, scheming, and reward hacking. We find that when the model lies or omits shortcomings in its "main" answer, it often confesses to these behaviors honestly, and this confession honesty modestly improves with training. Confessions can enable a number of inference-time interventions including monitoring, rejection sampling, and surfacing issues to the user.
Authors: Kwanyoung Park, Seohong Park, Youngwoon Lee, Sergey Levine
Abstract: In this paper, we study whether model-based reinforcement learning (RL), in particular model-based value expansion, can provide a scalable recipe for tackling complex, long-horizon tasks in offline RL. Model-based value expansion fits an on-policy value function using length-n imaginary rollouts generated by the current policy and a learned dynamics model. While larger n reduces bias in value bootstrapping, it amplifies accumulated model errors over long horizons, degrading future predictions. We address this trade-off with an \emph{action-chunk} model that predicts a future state from a sequence of actions (an "action chunk") instead of a single action, which reduces compounding errors. In addition, instead of directly training a policy to maximize rewards, we employ rejection sampling from an expressive behavioral action-chunk policy, which prevents model exploitation from out-of-distribution actions. We call this recipe \textbf{Model-Based RL with Action Chunks (MAC)}. Through experiments on highly challenging tasks with large-scale datasets of up to 100M transitions, we show that MAC achieves the best performance among offline model-based RL algorithms, especially on challenging long-horizon tasks.
Authors: Stephane Collot, Colin Fraser, Justin Zhao, William F. Shen, Timon Willi, Ilias Leontiadis
Abstract: Rigorous evaluation of large language models (LLMs) relies on comparing models by the prevalence of desirable or undesirable behaviors, such as task pass rates or policy violations. These prevalence estimates are produced by a classifier, either an LLM-as-a-judge or human annotators, making the choice of classifier central to trustworthy evaluation. Common metrics used for this choice, such as Accuracy, Precision, and F1, are sensitive to class imbalance and to arbitrary choices of positive class, and can favor judges that distort prevalence estimates. We show that Youden's $J$ statistic is theoretically aligned with choosing the best judge to compare models, and that Balanced Accuracy is an equivalent linear transformation of $J$. Through both analytical arguments and empirical examples and simulations, we demonstrate how selecting judges using Balanced Accuracy leads to better, more robust classifier selection.
Authors: Zijiang Yang
Abstract: This paper will propose a novel machine learning based portfolio management method in the context of the cryptocurrency market. Previous researchers mainly focus on the prediction of the movement for specific cryptocurrency such as the bitcoin(BTC) and then trade according to the prediction. In contrast to the previous work that treats the cryptocurrencies independently, this paper manages a group of cryptocurrencies by analyzing the relative relationship. Specifically, in each time step, we utilize the neural network to predict the rank of the future return of the managed cryptocurrencies and place weights accordingly. By incorporating such cross-sectional information, the proposed methods is shown to profitable based on the backtesting experiments on the real daily cryptocurrency market data from May, 2020 to Nov, 2023. During this 3.5 years, the market experiences the full cycle of bullish, bearish and stagnant market conditions. Despite under such complex market conditions, the proposed method outperforms the existing methods and achieves a Sharpe ratio of 1.01 and annualized return of 64.26%. Additionally, the proposed method is shown to be robust to the increase of transaction fee.
Authors: Guangmingmei Yang, David J. Miller, George Kesidis
Abstract: Most post-training backdoor detection methods rely on attacked models exhibiting extreme outlier detection statistics for the target class of an attack, compared to non-target classes. However, these approaches may fail: (1) when some (non-target) classes are easily discriminable from all others, in which case they may naturally achieve extreme detection statistics (e.g., decision confidence); and (2) when the backdoor is subtle, i.e., with its features weak relative to intrinsic class-discriminative features. A key observation is that the backdoor target class has contributions to its detection statistic from both the backdoor trigger and from its intrinsic features, whereas non-target classes only have contributions from their intrinsic features. To achieve more sensitive detectors, we thus propose to suppress intrinsic features while optimizing the detection statistic for a given class. For non-target classes, such suppression will drastically reduce the achievable statistic, whereas for the target class the (significant) contribution from the backdoor trigger remains. In practice, we formulate a constrained optimization problem, leveraging a small set of clean examples from a given class, and optimizing the detection statistic while orthogonalizing with respect to the class's intrinsic features. We dub this plug-and-play approach Class Subspace Orthogonalization (CSO) and assess it against challenging mixed-label and adaptive attacks.
Authors: Gary Ackerman, Brandon Behlendorf, Zachary Kallenborn, Sheriff Almakki, Doug Clifford, Jenna LaTourette, Hayley Peterson, Noah Sheinbaum, Olivia Shoemaker, Anna Wetzel
Abstract: Both model developers and policymakers seek to quantify and mitigate the risk of rapidly-evolving frontier artificial intelligence (AI) models, especially large language models (LLMs), to facilitate bioterrorism or access to biological weapons. An important element of such efforts is the development of model benchmarks that can assess the biosecurity risk posed by a particular model. This paper describes the first component of a novel Biothreat Benchmark Generation (BBG) Framework. The BBG approach is designed to help model developers and evaluators reliably measure and assess the biosecurity risk uplift and general harm potential of existing and future AI models, while accounting for key aspects of the threat itself that are often overlooked in other benchmarking efforts, including different actor capability levels, and operational (in addition to purely technical) risk factors. As a pilot, the BBG is first being developed to address bacterial biological threats only. The BBG is built upon a hierarchical structure of biothreat categories, elements and tasks, which then serves as the basis for the development of task-aligned queries. This paper outlines the development of this biothreat task-query architecture, which we have named the Bacterial Biothreat Schema, while future papers will describe follow-on efforts to turn queries into model prompts, as well as how the resulting benchmarks can be implemented for model evaluation. Overall, the BBG Framework, including the Bacterial Biothreat Schema, seeks to offer a robust, re-usable structure for evaluating bacterial biological risks arising from LLMs across multiple levels of aggregation, which captures the full scope of technical and operational requirements for biological adversaries, and which accounts for a wide spectrum of biological adversary capabilities.
Authors: Mikayel Samvelyan
Abstract: The growing prevalence of artificial intelligence (AI) in various applications underscores the need for agents that can successfully navigate and adapt to an ever-changing, open-ended world. A key challenge is ensuring these AI agents are robust, excelling not only in familiar settings observed during training but also effectively generalising to previously unseen and varied scenarios. In this thesis, we harness methodologies from open-endedness and multi-agent learning to train and evaluate robust AI agents capable of generalising to novel environments, out-of-distribution inputs, and interactions with other co-player agents. We begin by introducing MiniHack, a sandbox framework for creating diverse environments through procedural content generation. Based on the game of NetHack, MiniHack enables the construction of new tasks for reinforcement learning (RL) agents with a focus on generalisation. We then present Maestro, a novel approach for generating adversarial curricula that progressively enhance the robustness and generality of RL agents in two-player zero-sum games. We further probe robustness in multi-agent domains, utilising quality-diversity methods to systematically identify vulnerabilities in state-of-the-art, pre-trained RL policies within the complex video game football domain, characterised by intertwined cooperative and competitive dynamics. Finally, we extend our exploration of robustness to the domain of LLMs. Here, our focus is on diagnosing and enhancing the robustness of LLMs against adversarial prompts, employing evolutionary search to generate a diverse range of effective inputs that aim to elicit undesirable outputs from an LLM. This work collectively paves the way for future advancements in AI robustness, enabling the development of agents that not only adapt to an ever-evolving world but also thrive in the face of unforeseen challenges and interactions.
Authors: Ali Lotfi Rezaabad, Bikram Khanal, Shashwat Chaurasia, Lu Zeng, Dezhi Hong, Hossein Beshashati, Thomas Butler, Megan Ganji
Abstract: Language identification is a crucial first step in multilingual systems such as chatbots and virtual assistants, enabling linguistically and culturally accurate user experiences. Errors at this stage can cascade into downstream failures, setting a high bar for accuracy. Yet, existing language identification tools struggle with key cases--such as music requests where the song title and user language differ. Open-source tools like LangDetect, FastText are fast but less accurate, while large language models, though effective, are often too costly for low-latency or low-resource settings. We introduce PolyLingua, a lightweight Transformer-based model for in-domain language detection and fine-grained language classification. It employs a two-level contrastive learning framework combining instance-level separation and class-level alignment with adaptive margins, yielding compact and well-separated embeddings even for closely related languages. Evaluated on two challenging datasets--Amazon Massive (multilingual digital assistant utterances) and a Song dataset (music requests with frequent code-switching)--PolyLingua achieves 99.25% F1 and 98.15% F1, respectively, surpassing Sonnet 3.5 while using 10x fewer parameters, making it ideal for compute- and latency-constrained environments.
Authors: Zheng Ding, Weirui Ye
Abstract: Reinforcement learning (RL) post-training is crucial for aligning generative models with human preferences, but its prohibitive computational cost remains a major barrier to widespread adoption. We introduce \textbf{TreeGRPO}, a novel RL framework that dramatically improves training efficiency by recasting the denoising process as a search tree. From shared initial noise samples, TreeGRPO strategically branches to generate multiple candidate trajectories while efficiently reusing their common prefixes. This tree-structured approach delivers three key advantages: (1) \emph{High sample efficiency}, achieving better performance under same training samples (2) \emph{Fine-grained credit assignment} via reward backpropagation that computes step-specific advantages, overcoming the uniform credit assignment limitation of trajectory-based methods, and (3) \emph{Amortized computation} where multi-child branching enables multiple policy updates per forward pass. Extensive experiments on both diffusion and flow-based models demonstrate that TreeGRPO achieves \textbf{2.4$\times$ faster training} while establishing a superior Pareto frontier in the efficiency-reward trade-off space. Our method consistently outperforms GRPO baselines across multiple benchmarks and reward models, providing a scalable and effective pathway for RL-based visual generative model alignment. The project website is available at treegrpo.github.io.
Authors: Nanda K. Unnikrishnan, Keshab K. Parhi
Abstract: In our prior work, LayerPipe, we had introduced an approach to accelerate training of convolutional, fully connected, and spiking neural networks by overlapping forward and backward computation. However, despite empirical success, a principled understanding of how much gradient delay needs to be introduced at each layer to achieve desired level of pipelining was not addressed. This paper, LayerPipe2, fills that gap by formally deriving LayerPipe using variable delayed gradient adaptation and retiming. We identify where delays may be legally inserted and show that the required amount of delay follows directly from the network structure where inner layers require fewer delays and outer layers require longer delays. When pipelining is applied at every layer, the amount of delay depends only on the number of remaining downstream stages. When layers are pipelined in groups, all layers in the group share the same assignment of delays. These insights not only explain previously observed scheduling patterns but also expose an often overlooked challenge that pipelining implicitly requires storage of historical weights. We overcome this storage bottleneck by developing a pipeline--aware moving average that reconstructs the required past states rather than storing them explicitly. This reduces memory cost without sacrificing the accuracy guarantees that makes pipelined learning viable. The result is a principled framework that illustrates how to construct LayerPipe architectures, predicts their delay requirements, and mitigates their storage burden, thereby enabling scalable pipelined training with controlled communication computation tradeoffs.
Authors: Jiaxiang Geng, Lunyu Zhao, Yiyi Lu, Bing Luo
Abstract: Mobile phones are the most ubiquitous end devices, generating vast amounts of human-authored data and serving as the primary platform for end-side applications. As high-quality public data for large language models (LLMs) approaches exhaustion, on-device fine-tuning provides an opportunity to leverage private user data while preserving privacy. However, existing approaches are predominantly simulation-based or rely on IoT devices and PCs, leaving commodity mobile phones largely unexplored. A key gap is the absence of an open-source framework that enables practical LLM fine-tuning on mobile phones. We present MobileFineTuner, a unified open-source framework that enables end-to-end LLM fine-tuning directly on commodity mobile phones. MobileFineTuner is designed for efficiency, scalability, and usability, supporting full-parameters fine-tuning (Full-FT) and parameter-efficient fine-tuning (PEFT). To address the memory and energy limitations inherent to mobile phones, we introduce system-level optimizations including parameter sharding, gradient accumulation, and energy-aware computation scheduling. We demonstrate the practicality of MobileFineTuner by fine-tuning GPT-2, Gemma 3, and Qwen 2.5 on real mobile phones. Extensive experiments and ablation studies validate the effectiveness of the proposed optimizations and establish MobileFineTuner as a viable foundation for future research on on-device LLM training.
Authors: Jason Chuan-Chih Chou
Abstract: Decoupled weight decay, solely responsible for the performance advantage of AdamW over Adam, has long been set to proportional to learning rate $\gamma$ without questioning. Some researchers have recently challenged such assumption and argued that decoupled weight decay should be set $\propto \gamma^2$ instead based on orthogonality arguments at steady state. To the contrary, we find that eliminating the contribution of the perpendicular component of the update to the weight norm leads to little change to the training dynamics. Instead, we derive that decoupled weight decay $\propto \gamma^2$ results in stable weight norm based on the simple assumption that updates become independent of the weights at steady state, regardless of the nature of the optimizer. Based on the same assumption, we derive and empirically verify that the Total Update Contribution (TUC) of a minibatch under the Scion optimizer is better characterized by the momentum-dependent effective learning rate whose optimal value transfers and we show that decoupled weight decay $\propto \gamma^2$ leads to stable weight and gradient norms and allows us to better control the training dynamics and improve the model performance.
Authors: Ye Qin, Jingchao Wang, Yang Shi, Haiying Huang, Junxu Li, Weijian Liu, Tinghui Chen, Jinghui Qin
Abstract: Capsule Networks (CapsNets) show exceptional graph representation capacity via dynamic routing and vectorized hierarchical representations, but they model the complex geometries of real\-world graphs poorly by fixed\-curvature space due to the inherent geodesical disconnectedness issues, leading to suboptimal performance. Recent works find that non\-Euclidean pseudo\-Riemannian manifolds provide specific inductive biases for embedding graph data, but how to leverage them to improve CapsNets is still underexplored. Here, we extend the Euclidean capsule routing into geodesically disconnected pseudo\-Riemannian manifolds and derive a Pseudo\-Riemannian Capsule Network (PR\-CapsNet), which models data in pseudo\-Riemannian manifolds of adaptive curvature, for graph representation learning. Specifically, PR\-CapsNet enhances the CapsNet with Adaptive Pseudo\-Riemannian Tangent Space Routing by utilizing pseudo\-Riemannian geometry. Unlike single\-curvature or subspace\-partitioning methods, PR\-CapsNet concurrently models hierarchical and cluster or cyclic graph structures via its versatile pseudo\-Riemannian metric. It first deploys Pseudo\-Riemannian Tangent Space Routing to decompose capsule states into spherical\-temporal and Euclidean\-spatial subspaces with diffeomorphic transformations. Then, an Adaptive Curvature Routing is developed to adaptively fuse features from different curvature spaces for complex graphs via a learnable curvature tensor with geometric attention from local manifold properties. Finally, a geometric properties\-preserved Pseudo\-Riemannian Capsule Classifier is developed to project capsule embeddings to tangent spaces and use curvature\-weighted softmax for classification. Extensive experiments on node and graph classification benchmarks show PR\-CapsNet outperforms SOTA models, validating PR\-CapsNet's strong representation power for complex graph structures.
Authors: Preksha Girish, Rachana Mysore, Mahanthesha U, Shrey Kumar, Shipra Prashant
Abstract: This paper presents a mathematically rigorous framework for brain-inspired representation learning founded on the interplay between persistent topological structures and cohomological flows. Neural computation is reformulated as the evolution of cochain maps over dynamic simplicial complexes, enabling representations that capture invariants across temporal, spatial, and functional brain states. The proposed architecture integrates algebraic topology with differential geometry to construct cohomological operators that generalize gradient-based learning within a homological landscape. Synthetic data with controlled topological signatures and real neural datasets are jointly analyzed using persistent homology, sheaf cohomology, and spectral Laplacians to quantify stability, continuity, and structural preservation. Empirical results demonstrate that the model achieves superior manifold consistency and noise resilience compared to graph neural and manifold-based deep architectures, establishing a coherent mathematical foundation for topology-driven representation learning.
Authors: Nicholas Harner
Abstract: Classical Time Series Classification algorithms are dominated by feature engineering strategies. One of the most prominent of these transforms is ROCKET, which achieves strong performance through random kernel features. We introduce SPROCKET (Selected Prototype Random Convolutional Kernel Transform), which implements a new feature engineering strategy based on prototypes. On a majority of the UCR and UEA Time Series Classification archives, SPROCKET achieves performance comparable to existing convolutional algorithms and the new MR-HY-SP ( MultiROCKET-HYDRA-SPROCKET) ensemble's average accuracy ranking exceeds HYDRA-MR, the previous best convolutional ensemble's performance. These experimental results demonstrate that prototype-based feature transformation can enhance both accuracy and robustness in time series classification.
Authors: Deepak Gupta, Himanshu Pandey, Ratikanta Behera
Abstract: This work proposes a wavelet-based physics-informed quantum neural network framework to efficiently address multiscale partial differential equations that involve sharp gradients, stiffness, rapid local variations, and highly oscillatory behavior. Traditional physics-informed neural networks (PINNs) have demonstrated substantial potential in solving differential equations, and their quantum counterparts, quantum-PINNs, exhibit enhanced representational capacity with fewer trainable parameters. However, both approaches face notable challenges in accurately solving multiscale features. Furthermore, their reliance on automatic differentiation for constructing loss functions introduces considerable computational overhead, resulting in longer training times. To overcome these challenges, we developed a wavelet-accelerated physics-informed quantum neural network that eliminates the need for automatic differentiation, significantly reducing computational complexity. The proposed framework incorporates the multiresolution property of wavelets within the quantum neural network architecture, thereby enhancing the network's ability to effectively capture both local and global features of multiscale problems. Numerical experiments demonstrate that our proposed method achieves superior accuracy while requiring less than five percent of the trainable parameters compared to classical wavelet-based PINNs, resulting in faster convergence. Moreover, it offers a speedup of three to five times compared to existing quantum PINNs, highlighting the potential of the proposed approach for efficiently solving challenging multiscale and oscillatory problems.
Authors: Preksha Girish, Rachana Mysore, Mahanthesha U, Shrey Kumar, Misbah Fatimah Annigeri, Tanish Jain
Abstract: Sudden Unexpected Death in Epilepsy (SUDEP) and acute ischemic stroke are life-threatening conditions involving complex interactions across cortical, brainstem, and autonomic systems. We present a unified geometric-stochastic multimodal deep learning framework that integrates EEG, ECG, respiration, SpO2, EMG, and fMRI signals to model SUDEP and stroke vulnerability. The approach combines Riemannian manifold embeddings, Lie-group invariant feature representations, fractional stochastic dynamics, Hamiltonian energy-flow modeling, and cross-modal attention mechanisms. Stroke propagation is modeled using fractional epidemic diffusion over structural brain graphs. Experiments on the MULTI-CLARID dataset demonstrate improved predictive accuracy and interpretable biomarkers derived from manifold curvature, fractional memory indices, attention entropy, and diffusion centrality. The proposed framework provides a mathematically principled foundation for early detection, risk stratification, and interpretable multimodal modeling in neural-autonomic disorders.
Authors: Rachana Mysore, Preksha Girish, Kavitha Jayaram, Shrey Kumar, Preksha Girish, Shravan Sanjeev Bagal, Kavitha Jayaram, Shreya Aravind Shastry
Abstract: We investigate the mathematical foundations of neural networks in the infinite-width regime through the Neural Tangent Kernel (NTK). We propose the NTK-Eigenvalue-Controlled Residual Network (NTK-ECRN), an architecture integrating Fourier feature embeddings, residual connections with layerwise scaling, and stochastic depth to enable rigorous analysis of kernel evolution during training. Our theoretical contributions include deriving bounds on NTK dynamics, characterizing eigenvalue evolution, and linking spectral properties to generalization and optimization stability. Empirical results on synthetic and benchmark datasets validate the predicted kernel behavior and demonstrate improved training stability and generalization. This work provides a comprehensive framework bridging infinite-width theory and practical deep-learning architectures.
Authors: Yi Ni, Xinkun Wang, Han Zhang
Abstract: Federated Learning (FL) faces significant challenges in evolving environments, particularly regarding data heterogeneity and the rigidity of fixed network topologies. To address these issues, this paper proposes \textbf{SOFA-FL} (Self-Organizing Hierarchical Federated Learning with Adaptive Clustered Data Sharing), a novel framework that enables hierarchical federated systems to self-organize and adapt over time. The framework is built upon three core mechanisms: (1) \textbf{Dynamic Multi-branch Agglomerative Clustering (DMAC)}, which constructs an initial efficient hierarchical structure; (2) \textbf{Self-organizing Hierarchical Adaptive Propagation and Evolution (SHAPE)}, which allows the system to dynamically restructure its topology through atomic operations -- grafting, pruning, consolidation, and purification -- to adapt to changes in data distribution; and (3) \textbf{Adaptive Clustered Data Sharing}, which mitigates data heterogeneity by enabling controlled partial data exchange between clients and cluster nodes. By integrating these mechanisms, SOFA-FL effectively captures dynamic relationships among clients and enhances personalization capabilities without relying on predetermined cluster structures.
Authors: Humera Sabir, Fatima Farooq, Ashraf Aboulnaga
Abstract: Knowledge Graphs (KGs) are a rich source of structured, heterogeneous data, powering a wide range of applications. A common approach to leverage this data is to train a graph neural network (GNN) on the KG. However, existing message-passing GNNs struggle to scale to large KGs because they rely on the iterative message passing process to learn the graph structure, which is inefficient, especially under mini-batch training, where a node sees only a partial view of its neighborhood. In this paper, we address this problem and present gHAWK, a novel and scalable GNN training framework for large KGs. The key idea is to precompute structural features for each node that capture its local and global structure before GNN training even begins. Specifically, gHAWK introduces a preprocessing step that computes: (a)~Bloom filters to compactly encode local neighborhood structure, and (b)~TransE embeddings to represent each node's global position in the graph. These features are then fused with any domain-specific features (e.g., text embeddings), producing a node feature vector that can be incorporated into any GNN technique. By augmenting message-passing training with structural priors, gHAWK significantly reduces memory usage, accelerates convergence, and improves model accuracy. Extensive experiments on large datasets from the Open Graph Benchmark (OGB) demonstrate that gHAWK achieves state-of-the-art accuracy and lower training time on both node property prediction and link prediction tasks, topping the OGB leaderboard for three graphs.
Authors: Sarwesh Rauniyar
Abstract: Axis-aligned decision trees are fast and stable but struggle on datasets with rotated or interaction-dependent decision boundaries, where informative splits require linear combinations of features rather than single-feature thresholds. Oblique forests address this with per-node hyperplane splits, but at added computational cost and implementation complexity. We propose a simple alternative: JARF, Jacobian-Aligned Random Forests. Concretely, we first fit an axis-aligned forest to estimate class probabilities or regression outputs, compute finite-difference gradients of these predictions with respect to each feature, aggregate them into an expected Jacobian outer product that generalizes the expected gradient outer product (EGOP), and use it as a single global linear preconditioner for all inputs. This supervised preconditioner applies a single global rotation of the feature space, then hands the transformed data back to a standard axis-aligned forest, preserving off-the-shelf training pipelines while capturing oblique boundaries and feature interactions that would otherwise require many axis-aligned splits to approximate. The same construction applies to any model that provides gradients, though we focus on random forests and gradient-boosted trees in this work. On tabular classification and regression benchmarks, this preconditioning consistently improves axis-aligned forests and often matches or surpasses oblique baselines while improving training time. Our experimental results and theoretical analysis together indicate that supervised preconditioning can recover much of the accuracy of oblique forests while retaining the simplicity and robustness of axis-aligned trees.
Authors: M Yashwanth, Gaurav Kumar Nayak, Harsh Rangwani, Arya Singh, R. Venkatesh Babu, Anirban Chakraborty
Abstract: Federated Learning (FL) is an emerging machine learning framework that enables multiple clients (coordinated by a server) to collaboratively train a global model by aggregating the locally trained models without sharing any client's training data. It has been observed in recent works that learning in a federated manner may lead the aggregated global model to converge to a 'sharp minimum' thereby adversely affecting the generalizability of this FL-trained model. Therefore, in this work, we aim to improve the generalization performance of models trained in a federated setup by introducing a 'flatness' constrained FL optimization problem. This flatness constraint is imposed on the top eigenvalue of the Hessian computed from the training loss. As each client trains a model on its local data, we further re-formulate this complex problem utilizing the client loss functions and propose a new computationally efficient regularization technique, dubbed 'MAN,' which Minimizes Activation's Norm of each layer on client-side models. We also theoretically show that minimizing the activation norm reduces the top eigenvalue of the layer-wise Hessian of the client's loss, which in turn decreases the overall Hessian's top eigenvalue, ensuring convergence to a flat minimum. We apply our proposed flatness-constrained optimization to the existing FL techniques and obtain significant improvements, thereby establishing new state-of-the-art.
Authors: Simon Chung, Colby J. Vorland, Donna L. Maney, Andrew W. Brown
Abstract: Datasets may contain observations with multiple labels. If the labels are not mutually exclusive, and if the labels vary greatly in frequency, obtaining a sample that includes sufficient observations with scarcer labels to make inferences about those labels, and which deviates from the population frequencies in a known manner, creates challenges. In this paper, we consider a multivariate Bernoulli distribution as our underlying distribution of a multi-label problem. We present a novel sampling algorithm that takes label dependencies into account. It uses observed label frequencies to estimate multivariate Bernoulli distribution parameters and calculate weights for each label combination. This approach ensures the weighted sampling acquires target distribution characteristics while accounting for label dependencies. We applied this approach to a sample of research articles from Web of Science labeled with 64 biomedical topic categories. We aimed to preserve category frequency order, reduce frequency differences between most and least common categories, and account for category dependencies. This approach produced a more balanced sub-sample, enhancing the representation of minority categories.
Authors: Hithem Lamri, Michail Maniatakos
Abstract: Machine unlearning (MU) seeks to remove the influence of specified data from a trained model in response to privacy requests or data poisoning. While certified unlearning has been analyzed in centralized and server-orchestrated federated settings (via guarantees analogous to differential privacy, DP), the decentralized setting -- where peers communicate without a coordinator remains underexplored. We study certified unlearning in decentralized networks with fixed topologies and propose RR-DU, a random-walk procedure that performs one projected gradient ascent step on the forget set at the unlearning client and a geometrically distributed number of projected descent steps on the retained data elsewhere, combined with subsampled Gaussian noise and projection onto a trust region around the original model. We provide (i) convergence guarantees in the convex case and stationarity guarantees in the nonconvex case, (ii) $(\varepsilon,\delta)$ network-unlearning certificates on client views via subsampled Gaussian $R\'enyi$ DP (RDP) with segment-level subsampling, and (iii) deletion-capacity bounds that scale with the forget-to-local data ratio and quantify the effect of decentralization (network mixing and randomized subsampling) on the privacy--utility trade-off. Empirically, on image benchmarks (MNIST, CIFAR-10), RR-DU matches a given $(\varepsilon,\delta)$ while achieving higher test accuracy than decentralized DP baselines and reducing forget accuracy to random guessing ($\approx 10\%$).
Authors: Gary Ackerman, Zachary Kallenborn, Anna Wetzel, Hayley Peterson, Jenna LaTourette, Olivia Shoemaker, Brandon Behlendorf, Sheriff Almakki, Doug Clifford, Noah Sheinbaum
Abstract: The potential for rapidly-evolving frontier artificial intelligence (AI) models, especially large language models (LLMs), to facilitate bioterrorism or access to biological weapons has generated significant policy, academic, and public concern. Both model developers and policymakers seek to quantify and mitigate any risk, with an important element of such efforts being the development of model benchmarks that can assess the biosecurity risk posed by a particular model. This paper, the second in a series of three, describes the second component of a novel Biothreat Benchmark Generation (BBG) framework: the generation of the Bacterial Biothreat Benchmark (B3) dataset. The development process involved three complementary approaches: 1) web-based prompt generation, 2) red teaming, and 3) mining existing benchmark corpora, to generate over 7,000 potential benchmarks linked to the Task-Query Architecture that was developed during the first component of the project. A process of de-duplication, followed by an assessment of uplift diagnosticity, and general quality control measures, reduced the candidates to a set of 1,010 final benchmarks. This procedure ensured that these benchmarks are a) diagnostic in terms of providing uplift; b) directly relevant to biosecurity threats; and c) are aligned with a larger biosecurity architecture permitting nuanced analysis at different levels of analysis.
Authors: Gary Ackerman, Theodore Wilson, Zachary Kallenborn, Olivia Shoemaker, Anna Wetzel, Hayley Peterson, Abigail Danfora, Jenna LaTourette, Brandon Behlendorf, Douglas Clifford
Abstract: The potential for rapidly-evolving frontier artificial intelligence (AI) models, especially large language models (LLMs), to facilitate bioterrorism or access to biological weapons has generated significant policy, academic, and public concern. Both model developers and policymakers seek to quantify and mitigate any risk, with an important element of such efforts being the development of model benchmarks that can assess the biosecurity risk posed by a particular model. This paper discusses the pilot implementation of the Bacterial Biothreat Benchmark (B3) dataset. It is the third in a series of three papers describing an overall Biothreat Benchmark Generation (BBG) framework, with previous papers detailing the development of the B3 dataset. The pilot involved running the benchmarks through a sample frontier AI model, followed by human evaluation of model responses, and an applied risk analysis of the results along several dimensions. Overall, the pilot demonstrated that the B3 dataset offers a viable, nuanced method for rapidly assessing the biosecurity risk posed by a LLM, identifying the key sources of that risk and providing guidance for priority areas of mitigation priority.
Authors: Danial Jafarzadeh Jazi, Maryam Hajiesmaeili
Abstract: Decoding brain states from functional magnetic resonance imaging (fMRI) data is vital for advancing neuroscience and clinical applications. While traditional machine learning and deep learning approaches have made strides in leveraging the high-dimensional and complex nature of fMRI data, they often fail to utilize the contextual richness provided by Digital Imaging and Communications in Medicine (DICOM) metadata. This paper presents a novel framework integrating transformer-based architectures with multimodal inputs, including fMRI data and DICOM metadata. By employing attention mechanisms, the proposed method captures intricate spatial-temporal patterns and contextual relationships, enhancing model accuracy, interpretability, and robustness. The potential of this framework spans applications in clinical diagnostics, cognitive neuroscience, and personalized medicine. Limitations, such as metadata variability and computational demands, are addressed, and future directions for optimizing scalability and generalizability are discussed.
Authors: Weiqi Guan, Junlin He
Abstract: The relationship between Layer Normalization (LN) placement and the over-smoothing phenomenon remains underexplored. We identify a critical dilemma: Pre-LN architectures avoid over-smoothing but suffer from the curse of depth, while Post-LN architectures bypass the curse of depth but experience over-smoothing. To resolve this, we propose a new method based on Post-LN that induces algebraic smoothing, preventing over-smoothing without the curse of depth. Empirical results across five benchmarks demonstrate that our approach supports deeper networks (up to 256 layers) and improves performance, requiring no additional parameters. Key contributions: Theoretical Characterization: Analysis of LN dynamics and their impact on over-smoothing and the curse of depth. A Principled Solution: A parameter-efficient method that induces algebraic smoothing and avoids over-smoothing and the curse of depth. Empirical Validation: Extensive experiments showing the effectiveness of the method in deeper GNNs.
Authors: Junnan Qiu, Jie Li
Abstract: Offline Reinforcement Learning (RL) enables policy optimization from static datasets but is inherently vulnerable to data poisoning attacks. Existing attack strategies typically rely on locally uniform perturbations, which treat all samples indiscriminately. This approach is inefficient, as it wastes the perturbation budget on low-impact samples, and lacks stealthiness due to significant statistical deviations. In this paper, we propose a novel Global Budget Allocation attack strategy. Leveraging the theoretical insight that a sample's influence on value function convergence is proportional to its Temporal Difference (TD) error, we formulate the attack as a global resource allocation problem. We derive a closed-form solution where perturbation magnitudes are assigned proportional to the TD-error sensitivity under a global L2 constraint. Empirical results on D4RL benchmarks demonstrate that our method significantly outperforms baseline strategies, achieving up to 80% performance degradation with minimal perturbations that evade detection by state-of-the-art statistical and spectral defenses.
Authors: Waleed Razzaq, Yun-Bo Zhao
Abstract: Accurate and uncertainty-aware degradation estimation is essential for predictive maintenance in safety-critical systems like rotating machinery with rolling-element bearings. Many existing uncertainty methods lack confidence calibration, are costly to run, are not distance-aware, and fail to generalize under out-of-distribution data. We introduce two distance-aware uncertainty methods for deterministic physics-guided neural networks: PG-SNGP, based on Spectral Normalization Gaussian Process, and PG-SNER, based on Deep Evidential Regression. We apply spectral normalization to the hidden layers so the network preserves distances from input to latent space. PG-SNGP replaces the final dense layer with a Gaussian Process layer for distance-sensitive uncertainty, while PG-SNER outputs Normal Inverse Gamma parameters to model uncertainty in a coherent probabilistic form. We assess performance using standard accuracy metrics and a new distance-aware metric based on the Pearson Correlation Coefficient, which measures how well predicted uncertainty tracks the distance between test and training samples. We also design a dynamic weighting scheme in the loss to balance data fidelity and physical consistency. We test our methods on rolling-element bearing degradation using the PRONOSTIA dataset and compare them with Monte Carlo and Deep Ensemble PGNNs. Results show that PG-SNGP and PG-SNER improve prediction accuracy, generalize reliably under OOD conditions, and remain robust to adversarial attacks and noise.
Authors: Nader Sadek, Mirette Moawad, Christina Naguib, Mariam Elzahaby
Abstract: Stock market prediction is a long-standing challenge in finance, as accurate forecasts support informed investment decisions. Traditional models rely mainly on historical prices, but recent work shows that financial news can provide useful external signals. This paper investigates a multimodal approach that integrates companies' news articles with their historical stock data to improve prediction performance. We compare a Graph Neural Network (GNN) model with a baseline LSTM model. Historical data for each company is encoded using an LSTM, while news titles are embedded with a language model. These embeddings form nodes in a heterogeneous graph, and GraphSAGE is used to capture interactions between articles, companies, and industries. We evaluate two targets: a binary direction-of-change label and a significance-based label. Experiments on the US equities and Bloomberg datasets show that the GNN outperforms the LSTM baseline, achieving 53% accuracy on the first target and a 4% precision gain on the second. Results also indicate that companies with more associated news yield higher prediction accuracy. Moreover, headlines contain stronger predictive signals than full articles, suggesting that concise news summaries play an important role in short-term market reactions.
Authors: Charles Rios, Longzhen Han, Almas Baimagambetov, Nikolaos Polatidis
Abstract: Predicting the outcomes of professional basketball games, particularly in the National Basketball Association (NBA), has become increasingly important for coaching strategy, fan engagement, and sports betting. However, many existing prediction models struggle with concept drift, limited temporal context, and instability across seasons. To advance forecasting in this domain, we introduce a newly constructed longitudinal NBA dataset covering the 2004-05 to 2024-25 seasons and present a deep learning framework designed to model long-term performance trends. Our primary contribution is a Long Short-Term Memory (LSTM) architecture that leverages an extended sequence length of 9,840 games equivalent to eight full NBA seasons to capture evolving team dynamics and season-over-season dependencies. We compare this model against several traditional Machine Learning (ML) and Deep Learning (DL) baselines, including Logistic Regression, Random Forest, Multi-Layer Perceptron (MLP), and Convolutional Neural Network (CNN). The LSTM achieves the best performance across all metrics, with 72.35 accuracy, 73.15 precision and 76.13 AUC-ROC. These results demonstrate the importance of long-sequence temporal modeling in basketball outcome prediction and highlight the value of our new multi-season dataset for developing robust, generalizable NBA forecasting systems.
Authors: Huzaifa Arif
Abstract: Recent work \cite{arifgroup} introduced Federated Proximal Gradient \textbf{(\texttt{FedProxGrad})} for solving non-convex composite optimization problems in group fair federated learning. However, the original analysis established convergence only to a \textit{noise-dominated neighborhood of stationarity}, with explicit dependence on a variance-induced noise floor. In this work, we provide an improved asymptotic convergence analysis for a generalized \texttt{FedProxGrad}-type analytical framework with inexact local proximal solutions and explicit fairness regularization. We call this extended analytical framework \textbf{DS \texttt{FedProxGrad}} (Decay Step Size \texttt{FedProxGrad}). Under a Robbins-Monro step-size schedule \cite{robbins1951stochastic} and a mild decay condition on local inexactness, we prove that $\liminf_{r\to\infty} \mathbb{E}[\|\nabla F(\mathbf{x}^r)\|^2] = 0$, i.e., the algorithm is asymptotically stationary and the convergence rate does not depend on a variance-induced noise floor.
Authors: Chenglong Duan, Dazhong Wu
Abstract: Part qualification is crucial in additive manufacturing (AM) because it ensures that additively manufactured parts can be consistently produced and reliably used in critical applications. Part qualification aims at verifying that an additively manufactured part meets performance requirements; therefore, predicting the complex stress-strain behaviors of additively manufactured parts is critical. We develop a dynamic time warping (DTW)-transfer learning (TL) framework for additive manufacturing part qualification by transferring knowledge of the stress-strain behaviors of additively manufactured low-cost polymers to metals. Specifically, the framework employs DTW to select a polymer dataset as the source domain that is the most relevant to the target metal dataset. Using a long short-term memory (LSTM) model, four source polymers (i.e., Nylon, PLA, CF-ABS, and Resin) and three target metals (i.e., AlSi10Mg, Ti6Al4V, and carbon steel) that are fabricated by different AM techniques are utilized to demonstrate the effectiveness of the DTW-TL framework. Experimental results show that the DTW-TL framework identifies the closest match between polymers and metals to select one single polymer dataset as the source domain. The DTW-TL model achieves the lowest mean absolute percentage error of 12.41% and highest coefficient of determination of 0.96 when three metals are used as the target domain, respectively, outperforming the vanilla LSTM model without TL as well as the TL model pre-trained on four polymer datasets as the source domain.
Authors: Manos Plitsis, Giorgos Bouritsas, Vassilis Katsouros, Yannis Panagakis
Abstract: Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gender, race and age. To mitigate these biases, existing approaches frequently depend on curated prompt datasets - either manually constructed or generated with large language models (LLMs) - as part of their training and/or evaluation procedures. Beside the curation cost, this also risks overlooking unanticipated, less obvious prompts that trigger biased generation, even in models that have undergone debiasing. In this work, we introduce Bias-Guided Prompt Search (BGPS), a framework that automatically generates prompts that aim to maximize the presence of biases in the resulting images. BGPS comprises two components: (1) an LLM instructed to produce attribute-neutral prompts and (2) attribute classifiers acting on the TTI's internal representations that steer the decoding process of the LLM toward regions of the prompt space that amplify the image attributes of interest. We conduct extensive experiments on Stable Diffusion 1.5 and a state-of-the-art debiased model and discover an array of subtle and previously undocumented biases that severely deteriorate fairness metrics. Crucially, the discovered prompts are interpretable, i.e they may be entered by a typical user, quantitatively improving the perplexity metric compared to a prominent hard prompt optimization counterpart. Our findings uncover TTI vulnerabilities, while BGPS expands the bias search space and can act as a new evaluation tool for bias mitigation.
Authors: Udesh Habaraduwa, Andrei Lixandru
Abstract: The advancement of human healthspan and bioengineering relies heavily on predicting the behavior of complex biological systems. While high-throughput multiomics data is becoming increasingly abundant, converting this data into actionable predictive models remains a bottleneck. High-capacity, datadriven simulation systems are critical in this landscape; unlike classical mechanistic models restricted by prior knowledge, these architectures can infer latent interactions directly from observational data, allowing for the simulation of temporal trajectories and the anticipation of downstream intervention effects in personalized medicine and synthetic biology. To address this challenge, we introduce Neural Ordinary Differential Equations (NODEs) as a dynamic framework for learning the complex interplay between the proteome and metabolome. We applied this framework to time-series data derived from engineered Escherichia coli strains, modeling the continuous dynamics of metabolic pathways. The proposed NODE architecture demonstrates superior performance in capturing system dynamics compared to traditional machine learning pipelines. Our results show a greater than 90% improvement in root mean squared error over baselines across both Limonene (up to 94.38% improvement) and Isopentenol (up to 97.65% improvement) pathway datasets. Furthermore, the NODE models demonstrated a 1000x acceleration in inference time, establishing them as a scalable, high-fidelity tool for the next generation of metabolic engineering and biological discovery.
Authors: Jinfeng Xu, Zheyu Chen, Shuo Yang, Jinze Li, Hewei Wang, Yijie Li, Edith C. H. Ngai
Abstract: Early graph prompt tuning approaches relied on task-specific designs for Graph Neural Networks (GNNs), limiting their adaptability across diverse pre-training strategies. In contrast, another promising line of research has investigated universal graph prompt tuning, which operates directly in the input graph's feature space and builds a theoretical foundation that universal graph prompt tuning can theoretically achieve an equivalent effect of any prompting function, eliminating dependence on specific pre-training strategies. Recent works propose selective node-based graph prompt tuning to pursue more ideal prompts. However, we argue that selective node-based graph prompt tuning inevitably compromises the theoretical foundation of universal graph prompt tuning. In this paper, we strengthen the theoretical foundation of universal graph prompt tuning by introducing stricter constraints, demonstrating that adding prompts to all nodes is a necessary condition for achieving the universality of graph prompts. To this end, we propose a novel model and paradigm, Learning and Editing Universal GrAph Prompt Tuning (LEAP), which preserves the theoretical foundation of universal graph prompt tuning while pursuing more ideal prompts. Specifically, we first build the basic universal graph prompts to preserve the theoretical foundation and then employ actor-critic reinforcement learning to select nodes and edit prompts. Extensive experiments on graph- and node-level tasks across various pre-training strategies in both full-shot and few-shot scenarios show that LEAP consistently outperforms fine-tuning and other prompt-based approaches.
Authors: Hamsini Ramanathan, Roman Bushuiev, Matou\v{s} Sold\'at, Jir\'i Kohout, T\'eo Hebra, Joshua David Smith, Josef Sivic, Tom\'a\v{s} Pluskal
Abstract: Terpene synthases (TPS) are a key family of enzymes responsible for generating the diverse terpene scaffolds that underpin many natural products, including front-line anticancer drugs such as Taxol. However, de novo TPS design through directed evolution is costly and slow. We introduce TpsGPT, a generative model for scalable TPS protein design, built by fine-tuning the protein language model ProtGPT2 on 79k TPS sequences mined from UniProt. TpsGPT generated de novo enzyme candidates in silico and we evaluated them using multiple validation metrics, including EnzymeExplorer classification, ESMFold structural confidence (pLDDT), sequence diversity, CLEAN classification, InterPro domain detection, and Foldseek structure alignment. From an initial pool of 28k generated sequences, we identified seven putative TPS enzymes that satisfied all validation criteria. Experimental validation confirmed TPS enzymatic activity in at least two of these sequences. Our results show that fine-tuning of a protein language model on a carefully curated, enzyme-class-specific dataset, combined with rigorous filtering, can enable the de novo generation of functional, evolutionarily distant enzymes.
Authors: Jeongwhan Choi, Woosung Kang, Minseo Kim, Jongwoo Kim, Noseong Park
Abstract: Foundation models pretrained on large data have demonstrated remarkable zero-shot generalization capabilities across domains. Building on the success of TabPFN for tabular data and its recent extension to time series, we investigate whether graph node classification can be effectively reformulated as a tabular learning problem. We introduce TabPFN-GN, which transforms graph data into tabular features by extracting node attributes, structural properties, positional encodings, and optionally smoothed neighborhood features. This enables TabPFN to perform direct node classification without any graph-specific training or language model dependencies. Our experiments on 12 benchmark datasets reveal that TabPFN-GN achieves competitive performance with GNNs on homophilous graphs and consistently outperforms them on heterophilous graphs. These results demonstrate that principled feature engineering can bridge the gap between tabular and graph domains, providing a practical alternative to task-specific GNN training and LLM-dependent graph foundation models.
Authors: Th\'eo Verhelst, Gianluca Bontempi
Abstract: Uplift modeling estimates the causal effect of an intervention as the difference between potential outcomes under treatment and control, whereas counterfactual identification aims to recover the joint distribution of these potential outcomes (e.g., "Would this customer still have churned had we given them a marketing offer?"). This joint counterfactual distribution provides richer information than the uplift but is harder to estimate. However, the two approaches are synergistic: uplift models can be leveraged for counterfactual estimation. We propose a counterfactual estimator that fits a bivariate beta distribution to predicted uplift scores, yielding posterior distributions over counterfactual outcomes. Our approach requires no causal assumptions beyond those of uplift modeling. Simulations show the efficacy of the approach, which can be applied, for example, to the problem of customer churn in telecom, where it reveals insights unavailable to standard ML or uplift models alone.
Authors: Huzaifa Arif, Pin-Yu Chen, Alex Gittens, James Diffenderfer, Bhavya Kailkhura
Abstract: With the increasing reliance on AI models for weather forecasting, it is imperative to evaluate their vulnerability to adversarial perturbations. This work introduces Weather Adaptive Adversarial Perturbation Optimization (WAAPO), a novel framework for generating targeted adversarial perturbations that are both effective in manipulating forecasts and stealthy to avoid detection. WAAPO achieves this by incorporating constraints for channel sparsity, spatial localization, and smoothness, ensuring that perturbations remain physically realistic and imperceptible. Using the ERA5 dataset and FourCastNet (Pathak et al. 2022), we demonstrate WAAPO's ability to generate adversarial trajectories that align closely with predefined targets, even under constrained conditions. Our experiments highlight critical vulnerabilities in AI-driven forecasting models, where small perturbations to initial conditions can result in significant deviations in predicted weather patterns. These findings underscore the need for robust safeguards to protect against adversarial exploitation in operational forecasting systems.
Authors: Lex Weaver, Jonathan Baxter
Abstract: TD($\lambda$) with function approximation has proved empirically successful for some complex reinforcement learning problems. For linear approximation, TD($\lambda$) has been shown to minimise the squared error between the approximate value of each state and the true value. However, as far as policy is concerned, it is error in the relative ordering of states that is critical, rather than error in the state values. We illustrate this point, both in simple two-state and three-state systems in which TD($\lambda$)--starting from an optimal policy--converges to a sub-optimal policy, and also in backgammon. We then present a modified form of TD($\lambda$), called STD($\lambda$), in which function approximators are trained with respect to relative state values on binary decision problems. A theoretical analysis, including a proof of monotonic policy improvement for STD($\lambda$) in the context of the two-state system, is presented, along with a comparison with Bertsekas' differential training method [1]. This is followed by successful demonstrations of STD($\lambda$) on the two-state system and a variation on the well known acrobot problem.
Authors: Lars Ole H\"ausler, Lena Uhlenberg, G\"oran K\"ober, Diyora Salimova, Oliver Amft
Abstract: We propose a text-to-IMU (inertial measurement unit) motion-synthesis framework to obtain realistic IMU data by fine-tuning a pretrained diffusion model with an acceleration-based second-order loss (L_acc). L_acc enforces consistency in the discrete second-order temporal differences of the generated motion, thereby aligning the diffusion prior with IMU-specific acceleration patterns. We integrate L_acc into the training objective of an existing diffusion model, finetune the model to obtain an IMU-specific motion prior, and evaluate the model with an existing text-to-IMU framework that comprises surface modelling and virtual sensor simulation. We analysed acceleration signal fidelity and differences between synthetic motion representation and actual IMU recordings. As a downstream application, we evaluated Human Activity Recognition (HAR) and compared the classification performance using data of our method with the earlier diffusion model and two additional diffusion model baselines. When we augmented the earlier diffusion model objective with L_acc and continued training, L_acc decreased by 12.7% relative to the original model. The improvements were considerably larger in high-dynamic activities (i.e., running, jumping) compared to low-dynamic activities~(i.e., sitting, standing). In a low-dimensional embedding, the synthetic IMU data produced by our refined model shifts closer to the distribution of real IMU recordings. HAR classification trained exclusively on our refined synthetic IMU data improved performance by 8.7% compared to the earlier diffusion model and by 7.6% over the best-performing comparison diffusion model. We conclude that acceleration-aware diffusion refinement provides an effective approach to align motion generation and IMU synthesis and highlights how flexible deep learning pipelines are for specialising generic text-to-motion priors to sensor-specific tasks.
Authors: Anantaa Kotal, Anupam Joshi
Abstract: The widespread use of big data across sectors has raised major privacy concerns, especially when sensitive information is shared or analyzed. Regulations such as GDPR and HIPAA impose strict controls on data handling, making it difficult to balance the need for insights with privacy requirements. Synthetic data offers a promising solution by creating artificial datasets that reflect real patterns without exposing sensitive information. However, traditional synthetic data methods often fail to capture complex, implicit rules that link different elements of the data and are essential in domains like healthcare. They may reproduce explicit patterns but overlook domain-specific constraints that are not directly stated yet crucial for realism and utility. For example, prescription guidelines that restrict certain medications for specific conditions or prevent harmful drug interactions may not appear explicitly in the original data. Synthetic data generated without these implicit rules can lead to medically inappropriate or unrealistic profiles. To address this gap, we propose ContextGAN, a Context-Aware Differentially Private Generative Adversarial Network that integrates domain-specific rules through a constraint matrix encoding both explicit and implicit knowledge. The constraint-aware discriminator evaluates synthetic data against these rules to ensure adherence to domain constraints, while differential privacy protects sensitive details from the original data. We validate ContextGAN across healthcare, security, and finance, showing that it produces high-quality synthetic data that respects domain rules and preserves privacy. Our results demonstrate that ContextGAN improves realism and utility by enforcing domain constraints, making it suitable for applications that require compliance with both explicit patterns and implicit rules under strict privacy guarantees.
Authors: Xiang Chen, Yuling Shi, Qizhen Lan, Yuchao Qiu, Xiaodong Gu
Abstract: LLM agents are widely deployed in complex interactive tasks, yet privacy constraints often preclude centralized optimization and co-evolution across dynamic environments. While Federated Learning (FL) has proven effective on static datasets, its extension to the open-ended self-evolution of agents remains underexplored. Directly applying standard FL is challenging: heterogeneous tasks and sparse, trajectory-level rewards introduce severe gradient conflicts, destabilizing the global optimization process. To bridge this gap, we propose Fed-SE, a Federated Self-Evolution framework for LLM agents. Fed-SE establishes a local evolution-global aggregation paradigm. Locally, agents employ parameter-efficient fine-tuning on filtered, high-return trajectories to achieve stable gradient updates. Globally, Fed-SE aggregates updates within a low-rank subspace that disentangles environment-specific dynamics, effectively reducing negative transfer across clients. Experiments across five heterogeneous environments demonstrate that Fed-SE improves average task success rates by approximately 18% over federated baselines, validating its effectiveness in robust cross-environment knowledge transfer in privacy-constrained deployments.
Authors: Joshua Ward, Bochao Gu, Chi-Hua Wang, Guang Cheng
Abstract: Large Language Models (LLMs) have recently demonstrated remarkable performance in generating high-quality tabular synthetic data. In practice, two primary approaches have emerged for adapting LLMs to tabular data generation: (i) fine-tuning smaller models directly on tabular datasets, and (ii) prompting larger models with examples provided in context. In this work, we show that popular implementations from both regimes exhibit a tendency to compromise privacy by reproducing memorized patterns of numeric digits from their training data. To systematically analyze this risk, we introduce a simple No-box Membership Inference Attack (MIA) called LevAtt that assumes adversarial access to only the generated synthetic data and targets the string sequences of numeric digits in synthetic observations. Using this approach, our attack exposes substantial privacy leakage across a wide range of models and datasets, and in some cases, is even a perfect membership classifier on state-of-the-art models. Our findings highlight a unique privacy vulnerability of LLM-based synthetic data generation and the need for effective defenses. To this end, we propose two methods, including a novel sampling strategy that strategically perturbs digits during generation. Our evaluation demonstrates that this approach can defeat these attacks with minimal loss of fidelity and utility of the synthetic data.
Authors: Mohammad Abu-Shaira, Ajita Rattani, Weishi Shi
Abstract: Real-world datasets often exhibit temporal dynamics characterized by evolving data distributions. Disregarding this phenomenon, commonly referred to as concept drift, can significantly diminish a model's predictive accuracy. Furthermore, the presence of hyperparameters in online models exacerbates this issue. These parameters are typically fixed and cannot be dynamically adjusted by the user in response to the evolving data distribution. Gaussian Process (GP) models offer powerful non-parametric regression capabilities with uncertainty quantification, making them ideal for modeling complex data relationships in an online setting. However, conventional online GP methods face several critical limitations, including a lack of drift-awareness, reliance on fixed hyperparameters, vulnerability to data snooping, absence of a principled decay mechanism, and memory inefficiencies. In response, we propose DAO-GP (Drift-Aware Online Gaussian Process), a novel, fully adaptive, hyperparameter-free, decayed, and sparse non-linear regression model. DAO-GP features a built-in drift detection and adaptation mechanism that dynamically adjusts model behavior based on the severity of drift. Extensive empirical evaluations confirm DAO-GP's robustness across stationary conditions, diverse drift types (abrupt, incremental, gradual), and varied data characteristics. Analyses demonstrate its dynamic adaptation, efficient in-memory and decay-based management, and evolving inducing points. Compared with state-of-the-art parametric and non-parametric models, DAO-GP consistently achieves superior or competitive performance, establishing it as a drift-resilient solution for online non-linear regression.
Authors: Ana Rita Paup\'erio, Diogo Risca, Afonso Louren\c{c}o, Goreti Marreiros, Ricardo Martins
Abstract: Industrial maintenance is being transformed by the Internet of Things and edge computing, generating continuous data streams that demand real-time, adaptive decision-making under limited computational resources. While data stream mining (DSM) addresses this challenge, most methods assume fully supervised settings, yet in practice, ground-truth labels are often delayed or unavailable. This paper presents a collaborative DSM framework that integrates unsupervised anomaly detection with interactive, human-in-the-loop learning to support maintenance decisions. We employ an online Isolation Forest and enhance interpretability using incremental Partial Dependence Plots and a feature importance score, derived from deviations of Individual Conditional Expectation curves from a fading average, enabling users to dynamically reassess feature relevance and adjust anomaly thresholds. We describe the real-time implementation and provide initial results for fault detection in a Jacquard loom unit. Ongoing work targets continuous monitoring to predict and explain imminent bearing failures.
Authors: Jakub Krajewski, Amitis Shidani, Dan Busbridge, Sam Wiseman, Jason Ramapuram
Abstract: While scaling laws for Large Language Models (LLMs) traditionally focus on proxy metrics like pretraining loss, predicting downstream task performance has been considered unreliable. This paper challenges that view by proposing a direct framework to model the scaling of benchmark performance from the training budget. We find that for a fixed token-to-parameter ratio, a simple power law can accurately describe the scaling behavior of log accuracy on multiple popular downstream tasks. Our results show that the direct approach extrapolates better than the previously proposed two-stage procedure, which is prone to compounding errors. Furthermore, we introduce functional forms that predict accuracy across token-to-parameter ratios and account for inference compute under repeated sampling. We validate our findings on models with up to 17B parameters trained on up to 350B tokens across two dataset mixtures. To support reproducibility and encourage future research, we release the complete set of pretraining losses and downstream evaluation results.
Authors: Suina Tanweer, Firas A. Khasawneh
Abstract: Kernel density estimation is a key component of a wide variety of algorithms in machine learning, Bayesian inference, stochastic dynamics and signal processing. However, the unsupervised density estimation technique requires tuning a crucial hyperparameter: the kernel bandwidth. The choice of bandwidth is critical as it controls the bias-variance trade-off by over- or under-smoothing the topological features. Topological data analysis provides methods to mathematically quantify topological characteristics, such as connected components, loops, voids et cetera, even in high dimensions where visualization of density estimates is impossible. In this paper, we propose an unsupervised learning approach using a topology-based loss function for the automated and unsupervised selection of the optimal bandwidth and benchmark it against classical techniques -- demonstrating its potential across different dimensions.
Authors: Gang Liu, Sobin Alosious, Subhamoy Mahajan, Eric Inae, Yihan Zhu, Yuhan Liu, Renzheng Zhang, Jiaxin Xu, Addison Howard, Ying Li, Tengfei Luo, Meng Jiang
Abstract: Machine learning (ML) offers a powerful path toward discovering sustainable polymer materials, but progress has been limited by the lack of large, high-quality, and openly accessible polymer datasets. The Open Polymer Challenge (OPC) addresses this gap by releasing the first community-developed benchmark for polymer informatics, featuring a dataset with 10K polymers and 5 properties: thermal conductivity, radius of gyration, density, fractional free volume, and glass transition temperature. The challenge centers on multi-task polymer property prediction, a core step in virtual screening pipelines for materials discovery. Participants developed models under realistic constraints that include small data, label imbalance, and heterogeneous simulation sources, using techniques such as feature-based augmentation, transfer learning, self-supervised pretraining, and targeted ensemble strategies. The competition also revealed important lessons about data preparation, distribution shifts, and cross-group simulation consistency, informing best practices for future large-scale polymer datasets. The resulting models, analysis, and released data create a new foundation for molecular AI in polymer science and are expected to accelerate the development of sustainable and energy-efficient materials. Along with the competition, we release the test dataset at https://www.kaggle.com/datasets/alexliu99/neurips-open-polymer-prediction-2025-test-data. We also release the data generation pipeline at https://github.com/sobinalosious/ADEPT, which simulates more than 25 properties, including thermal conductivity, radius of gyration, and density.
URLs: https://www.kaggle.com/datasets/alexliu99/neurips-open-polymer-prediction-2025-test-data., https://github.com/sobinalosious/ADEPT,
Authors: Moritz Blumenthal, Tina Holliber, Jonathan I. Tamir, Martin Uecker
Abstract: Purpose: The Unadjusted Langevin Algorithm (ULA) in combination with diffusion models can generate high quality MRI reconstructions with uncertainty estimation from highly undersampled k-space data. However, sampling methods such as diffusion posterior sampling or likelihood annealing suffer from long reconstruction times and the need for parameter tuning. The purpose of this work is to develop a robust sampling algorithm with fast convergence. Theory and Methods: In the reverse diffusion process used for sampling the posterior, the exact likelihood is multiplied with the diffused prior at all noise scales. To overcome the issue of slow convergence, preconditioning is used. The method is trained on fastMRI data and tested on retrospectively undersampled brain data of a healthy volunteer. Results: For posterior sampling in Cartesian and non-Cartesian accelerated MRI the new approach outperforms annealed sampling in terms of reconstruction speed and sample quality. Conclusion: The proposed exact likelihood with preconditioning enables rapid and reliable posterior sampling across various MRI reconstruction tasks without the need for parameter tuning.
Authors: Eli Gendreau-Distler, Joshua Ho, Dongwon Kim, Luc Tomas Le Pottier, Haichen Wang, Chengxi Yang
Abstract: We present a proof-of-principle study demonstrating the use of large language model (LLM) agents to automate a representative high energy physics (HEP) analysis. Using the Higgs boson diphoton cross-section measurement as a case study with ATLAS Open Data, we design a hybrid system that combines an LLM-based supervisor-coder agent with the Snakemake workflow manager. In this architecture, the workflow manager enforces reproducibility and determinism, while the agent autonomously generates, executes, and iteratively corrects analysis code in response to user instructions. We define quantitative evaluation metrics including success rate, error distribution, costs per specific task, and average number of API calls, to assess agent performance across multi-stage workflows. To characterize variability across architectures, we benchmark a representative selection of state-of-the-art LLMs spanning the Gemini and GPT-5 series, the Claude family, and leading open-weight models. While the workflow manager ensures deterministic execution of all analysis steps, the final outputs still show stochastic variation. Although we set the temperature to zero, other sampling parameters (e.g., top-p, top-k) remained at their defaults, and some reasoning-oriented models internally adjust these settings. Consequently, the models do not produce fully deterministic results. This study establishes the first LLM-agent-driven automated data-analysis framework in HEP, enabling systematic benchmarking of model capabilities, stability, and limitations in real-world scientific computing environments. The baseline code used in this work is available at https://huggingface.co/HWresearch/LLM4HEP. This work was accepted as a poster at the Machine Learning and the Physical Sciences (ML4PS) workshop at NeurIPS 2025. The initial submission was made on August 30, 2025.
Authors: Pal Dave, Xiaohong Yuan, Madhuri Siddula, Kaushik Roy
Abstract: Cyberbullying is a well-known social issue, and it is escalating day by day. Due to the vigorous development of the internet, social media provide many different ways for the user to express their opinions and exchange information. Cyberbullying occurs on social media using text messages, comments, sharing images and GIFs or stickers, and audio and video. Much research has been done to detect cyberbullying on textual data; some are available for images. Very few studies are available to detect cyberbullying on GIFs/stickers. We collect a GIF dataset from Twitter and Applied a deep learning model to detect cyberbullying from the dataset. Firstly, we extracted hashtags related to cyberbullying using Twitter. We used these hashtags to download GIF file using publicly available API GIPHY. We collected over 4100 GIFs including cyberbullying and non cyberbullying. we applied deep learning pre-trained model VGG16 for the detection of the cyberbullying. The deep learning model achieved the accuracy of 97%. Our work provides the GIF dataset for researchers working in this area.
Authors: Guoyao Li, Ran He, Shusen Jing, Kayhan Behdin, Yubo Wang, Sundara Raman Ramachandran, Chanh Nguyen, Jian Sheng, Xiaojing Ma, Chuanrui Zhu, Sriram Vasudevan, Muchen Wu, Sayan Ghosh, Lin Su, Qingquan Song, Xiaoqing Wang, Zhipeng Wang, Qing Lan, Yanning Chen, Jingwei Wu, Luke Simon, Wenjing Zhang, Qi Guo, Fedor Borisyuk
Abstract: Large language models (LLMs) excel at capturing semantic nuances and therefore show impressive relevance ranking performance in modern recommendation and search systems. However, they suffer from high computational overhead under industrial latency and throughput requirements. In particular, cross-encoder ranking systems often create long context prefill-heavy workloads, as the model has to be presented with the user, query and item information. To this end, we propose MixLM, a novel LLM-based ranking framework, which significantly improves the system throughput via reducing the input context length, while preserving the semantic strength of cross-encoder rankers. In contrast to a standard ranking system where the context is presented to the model as pure text, we propose to use mix-interaction, a mixture of text and embedding tokens to represent the input. Specifically, MixLM encodes all items in the catalog into a few embedding tokens and stores in a nearline cache. The encoded item descriptions are used during online inference, effectively reducing the item length from a few thousand text tokens to a few embedding tokens. We share insights from deploying our MixLM framework to a real-world search application at LinkedIn, including a detailed discussion of our training pipelines, as well as a thorough analysis of our online serving infrastructure optimization. Comparing with strong baselines, MixLM increased throughput by 10.0x under the same latency budget, while maintaining relevance metrics. The efficiency gains delivered by MixLM enabled full-traffic deployment of LLM-powered search, which resulted in a significant 0.47% increase in Daily Active Users (DAU) in online A/B tests.
Authors: Mohammed Alruqimi, Luca Di Persio
Abstract: This paper investigates an optimal integration of deep learning with financial models for robust asset price forecasting. Specifically, we developed a hybrid framework combining a Long Short-Term Memory (LSTM) network with the Merton-L\'evy jump-diffusion model. To optimise this framework, we employed the Grey Wolf Optimizer (GWO) for the LSTM hyperparameter tuning, and we explored three calibration methods for the Merton-Levy model parameters: Artificial Neural Networks (ANNs), the Marine Predators Algorithm (MPA), and the PyTorch-based TorchSDE library. To evaluate the predictive performance of our hybrid model, we compared it against several benchmark models, including a standard LSTM and an LSTM combined with the Fractional Heston model. This evaluation used three real-world financial datasets: Brent oil prices, the STOXX 600 index, and the IT40 index. Performance was assessed using standard metrics, including Mean Squared Error (MSE), Mean Absolute Error(MAE), Mean Squared Percentage Error (MSPE), and the coefficient of determination (R2). Our experimental results demonstrate that the hybrid model, combining a GWO-optimized LSTM network with the Levy-Merton Jump-Diffusion model calibrated using an ANN, outperformed the base LSTM model and all other models developed in this study.
Authors: Fahad Mostafa, Hafiz Khan
Abstract: Classification of functional data where observations are curves or trajectories poses unique challenges, particularly under severe class imbalance. Traditional Random Forest algorithms, while robust for tabular data, often fail to capture the intrinsic structure of functional observations and struggle with minority class detection. This paper introduces Functional Random Forest with Adaptive Cost-Sensitive Splitting (FRF-ACS), a novel ensemble framework designed for imbalanced functional data classification. The proposed method leverages basis expansions and Functional Principal Component Analysis (FPCA) to represent curves efficiently, enabling trees to operate on low dimensional functional features. To address imbalance, we incorporate a dynamic cost sensitive splitting criterion that adjusts class weights locally at each node, combined with a hybrid sampling strategy integrating functional SMOTE and weighted bootstrapping. Additionally, curve specific similarity metrics replace traditional Euclidean measures to preserve functional characteristics during leaf assignment. Extensive experiments on synthetic and real world datasets including biomedical signals and sensor trajectories demonstrate that FRF-ACS significantly improves minority class recall and overall predictive performance compared to existing functional classifiers and imbalance handling techniques. This work provides a scalable, interpretable solution for high dimensional functional data analysis in domains where minority class detection is critical.
Authors: Ryan Feng Lin, Keyu Tian, Hanming Zheng, Congjing Zhang, Li Zeng, Shuai Huang
Abstract: The emergence of large language models (LLMs) has sparked much interest in creating LLM-based digital populations that can be applied to many applications such as social simulation, crowdsourcing, marketing, and recommendation systems. A digital population can reduce the cost of recruiting human participants and alleviate many concerns related to human subject study. However, research has found that most of the existing works rely solely on LLMs and could not sufficiently capture the accuracy and diversity of a real human population. To address this limitation, we propose CrowdLLM that integrates pretrained LLMs and generative models to enhance the diversity and fidelity of the digital population. We conduct theoretical analysis of CrowdLLM regarding its great potential in creating cost-effective, sufficiently representative, scalable digital populations that can match the quality of a real crowd. Comprehensive experiments are also conducted across multiple domains (e.g., crowdsourcing, voting, user rating) and simulation studies which demonstrate that CrowdLLM achieves promising performance in both accuracy and distributional fidelity to human data.
Authors: Arvind Agarwal, Lisa Amini, Sameep Mehta, Horst Samulowitz, Kavitha Srinivas
Abstract: Enterprise data management is a monumental task. It spans data architecture and systems, integration, quality, governance, and continuous improvement. While AI assistants can help specific persona, such as data engineers and stewards, to navigate and configure the data stack, they fall far short of full automation. However, as AI becomes increasingly capable of tackling tasks that have previously resisted automation due to inherent complexities, we believe there is an imminent opportunity to target fully autonomous data estates. Currently, AI is used in different parts of the data stack, but in this paper, we argue for a paradigm shift from the use of AI in independent data component operations towards a more holistic and autonomous handling of the entire data lifecycle. Towards that end, we explore how each stage of the modern data stack can be autonomously managed by intelligent agents to build self-sufficient systems that can be used not only by human end-users, but also by AI itself. We begin by describing the mounting forces and opportunities that demand this paradigm shift, examine how agents can streamline the data lifecycle, and highlight open questions and areas where additional research is needed. We hope this work will inspire lively debate, stimulate further research, motivate collaborative approaches, and facilitate a more autonomous future for data systems.
Authors: Pietro Capuozzo, Brandon Robinson, Benjamin Suzzoni
Abstract: Neural Network Field Theories (NN-FTs) represent a novel construction of arbitrary field theories, including those of conformal fields, through the specification of the network architecture and prior distribution for the network parameters. In this work, we present a formalism for the construction of conformally invariant defects in these NN-FTs. We demonstrate this new formalism in two toy models of NN scalar field theories. We develop an NN interpretation of an expansion akin to the defect OPE in two-point correlation functions in these models.
Authors: Soroush Baghernezhad, Elaheh Mohammadreza, Vinicius Prado da Fonseca, Ting Zou, Xianta Jiang
Abstract: Gestures are an integral part of our daily interactions with the environment. Hand gesture recognition (HGR) is the process of interpreting human intent through various input modalities, such as visual data (images and videos) and bio-signals. Bio-signals are widely used in HGR due to their ability to be captured non-invasively via sensors placed on the arm. Among these, surface electromyography (sEMG), which measures the electrical activity of muscles, is the most extensively studied modality. However, less-explored alternatives such as inertial measurement units (IMUs) can provide complementary information on subtle muscle movements, which makes them valuable for gesture recognition. In this study, we investigate the potential of using IMU signals from different muscle groups to capture user intent. Our results demonstrate that IMU signals contain sufficient information to serve as the sole input sensor for static gesture recognition. Moreover, we compare different muscle groups and check the quality of pattern recognition on individual muscle groups. We further found that tendon-induced micro-movement captured by IMUs is a major contributor to static gesture recognition. We believe that leveraging muscle micro-movement information can enhance the usability of prosthetic arms for amputees. This approach also offers new possibilities for hand gesture recognition in fields such as robotics, teleoperation, sign language interpretation, and beyond.
Authors: Robert Lefringhausen, Theodor Springer, Sandra Hirche
Abstract: Reliable optimal control is challenging when the dynamics of a nonlinear system are unknown and only infrequent, noisy output measurements are available. This work addresses this setting of limited sensing by formulating a Bayesian prior over the continuous-time dynamics and latent state trajectory in state-space form and updating it through a targeted marginal Metropolis-Hastings sampler equipped with a numerical ODE integrator. The resulting posterior samples are used to formulate a scenario-based optimal control problem that accounts for both model and measurement uncertainty and is solved using standard nonlinear programming methods. The approach is validated in a numerical case study on glucose regulation using a Type 1 diabetes model.
Authors: Jinyuan Chang, Chenguang Duan, Yuling Jiao, Ruoxuan Li, Jerry Zhijian Yang, Cheng Yuan
Abstract: This paper proposes a novel diffusion-based posterior sampling method within a plug-and-play (PnP) framework. Our approach constructs a probability transport from an easy-to-sample terminal distribution to the target posterior, using a warm-start strategy to initialize the particles. To approximate the posterior score, we develop a Monte Carlo estimator in which particles are generated using Langevin dynamics, avoiding the heuristic approximations commonly used in prior work. The score governing the Langevin dynamics is learned from data, enabling the model to capture rich structural features of the underlying prior distribution. On the theoretical side, we provide non-asymptotic error bounds, showing that the method converges even for complex, multi-modal target posterior distributions. These bounds explicitly quantify the errors arising from posterior score estimation, the warm-start initialization, and the posterior sampling procedure. Our analysis further clarifies how the prior score-matching error and the condition number of the Bayesian inverse problem influence overall performance. Finally, we present numerical experiments demonstrating the effectiveness of the proposed method across a range of inverse problems.
Authors: Pedro Santana
Abstract: Embodied agents, such as robots and virtual characters, must continuously select actions to execute tasks effectively, solving complex sequential decision-making problems. Given the difficulty of designing such controllers manually, learning-based approaches have emerged as promising alternatives, most notably Deep Reinforcement Learning (DRL) and Deep Imitation Learning (DIL). DRL leverages reward signals to optimize behavior, while DIL uses expert demonstrations to guide learning. This document introduces DRL and DIL in the context of embodied agents, adopting a concise, depth-first approach to the literature. It is self-contained, presenting all necessary mathematical and machine learning concepts as they are needed. It is not intended as a survey of the field; rather, it focuses on a small set of foundational algorithms and techniques, prioritizing in-depth understanding over broad coverage. The material ranges from Markov Decision Processes to REINFORCE and Proximal Policy Optimization (PPO) for DRL, and from Behavioral Cloning to Dataset Aggregation (DAgger) and Generative Adversarial Imitation Learning (GAIL) for DIL.
Authors: Honglian Wang, Haoyun Chen, Aristides Gionis
Abstract: Link-analysis algorithms, such as PageRank, are instrumental in understanding the structural dynamics of networks by evaluating the importance of individual vertices based on their connectivity. Recently, with the rising importance of responsible AI, the question of fairness in link-analysis algorithms has gained traction. In this paper, we present a new approach for incorporating group fairness into the PageRank algorithm by reweighting the transition probabilities in the underlying transition matrix. We formulate the problem of achieving fair PageRank by seeking to minimize the fairness loss, which is the difference between the original group-wise PageRank distribution and a target PageRank distribution. We further define a group-adapted fairness notion, which accounts for group homophily by considering random walks with group-biased restart for each group. Since the fairness loss is non-convex, we propose an efficient projected gradient-descent method for computing locally-optimal edge weights. Unlike earlier approaches, we do not recommend adding new edges to the network, nor do we adjust the restart vector. Instead, we keep the topology of the underlying network unchanged and only modify the relative importance of existing edges. We empirically compare our approach with state-of-the-art baselines and demonstrate the efficacy of our method, where very small changes in the transition matrix lead to significant improvement in the fairness of the PageRank algorithm.
Authors: Kyriakos Lotidis, Panayotis Mertikopoulos, Nicholas Bambos, Jose Blanchet
Abstract: In this paper, we examine the convergence landscape of multi-agent learning under uncertainty. Specifically, we analyze two stochastic models of regularized learning in continuous games -- one in continuous and one in discrete time with the aim of characterizing the long-run behavior of the induced sequence of play. In stark contrast to deterministic, full-information models of learning (or models with a vanishing learning rate), we show that the resulting dynamics do not converge in general. In lieu of this, we ask instead which actions are played more often in the long run, and by how much. We show that, in strongly monotone games, the dynamics of regularized learning may wander away from equilibrium infinitely often, but they always return to its vicinity in finite time (which we estimate), and their long-run distribution is sharply concentrated around a neighborhood thereof. We quantify the degree of this concentration, and we show that these favorable properties may all break down if the underlying game is not strongly monotone -- underscoring in this way the limits of regularized learning in the presence of persistent randomness and uncertainty.
Authors: Kyriakos Lotidis, Panayotis Mertikopoulos, Nicholas Bambos, Jose Blanchet
Abstract: In this paper, we examine the robustness of Nash equilibria in continuous games, under both strategic and dynamic uncertainty. Starting with the former, we introduce the notion of a robust equilibrium as those equilibria that remain invariant to small -- but otherwise arbitrary -- perturbations to the game's payoff structure, and we provide a crisp geometric characterization thereof. Subsequently, we turn to the question of dynamic robustness, and we examine which equilibria may arise as stable limit points of the dynamics of "follow the regularized leader" (FTRL) in the presence of randomness and uncertainty. Despite their very distinct origins, we establish a structural correspondence between these two notions of robustness: strategic robustness implies dynamic robustness, and, conversely, the requirement of strategic robustness cannot be relaxed if dynamic robustness is to be maintained. Finally, we examine the rate of convergence to robust equilibria as a function of the underlying regularizer, and we show that entropically regularized learning converges at a geometric rate in games with affinely constrained action spaces.
Authors: Xiuyuan Cheng, Yao Xie, Linglingzhi Zhu, Yunqin Zhu
Abstract: Worst-case generation plays a critical role in evaluating robustness and stress-testing systems under distribution shifts, in applications ranging from machine learning models to power grids and medical prediction systems. We develop a generative modeling framework for worst-case generation for a pre-specified risk, based on min-max optimization over continuous probability distributions, namely the Wasserstein space. Unlike traditional discrete distributionally robust optimization approaches, which often suffer from scalability issues, limited generalization, and costly worst-case inference, our framework exploits the Brenier theorem to characterize the least favorable (worst-case) distribution as the pushforward of a transport map from a continuous reference measure, enabling a continuous and expressive notion of risk-induced generation beyond classical discrete DRO formulations. Based on the min-max formulation, we propose a Gradient Descent Ascent (GDA)-type scheme that updates the decision model and the transport map in a single loop, establishing global convergence guarantees under mild regularity assumptions and possibly without convexity-concavity. We also propose to parameterize the transport map using a neural network that can be trained simultaneously with the GDA iterations by matching the transported training samples, thereby achieving a simulation-free approach. The efficiency of the proposed method as a risk-induced worst-case generator is validated by numerical experiments on synthetic and image data.
Authors: Aneesh Rangnekar, Harini Veeraraghavan
Abstract: Accurate segmentation of cancerous lesions from 3D computed tomography (CT) scans is essential for automated treatment planning and response assessment. However, even state-of-the-art models combining self-supervised learning (SSL) pretrained transformers with convolutional decoders are susceptible to out-of-distribution (OOD) inputs, generating confidently incorrect tumor segmentations, posing risks for safe clinical deployment. Existing logit-based methods suffer from task-specific model biases, while architectural enhancements to explicitly detect OOD increase parameters and computational costs. Hence, we introduce a plug-and-play and lightweight post-hoc random forests-based OOD detection framework called RF-Deep that leverages deep features with limited outlier exposure. RF-Deep enhances generalization to imaging variations by repurposing the hierarchical features from the pretrained-then-finetuned backbone encoder, providing task-relevant OOD detection by extracting the features from multiple regions of interest anchored to the predicted tumor segmentations. Hence, it scales to images of varying fields-of-view. We compared RF-Deep against existing OOD detection methods using 1,916 CT scans across near-OOD (pulmonary embolism, negative COVID-19) and far-OOD (kidney cancer, healthy pancreas) datasets. RF-Deep achieved AUROC > 93.50 for the challenging near-OOD datasets and near-perfect detection (AUROC > 99.00) for the far-OOD datasets, substantially outperforming logit-based and radiomics approaches. RF-Deep maintained similar performance consistency across networks of different depths and pretraining strategies, demonstrating its effectiveness as a lightweight, architecture-agnostic approach to enhance the reliability of tumor segmentation from CT volumes.
Authors: Saeeda Naz (Artificial Intelligence Lab, Department of Computer Systems Engineering, University of Engineering,Applied Sciences), Saddam Hussain Khan (Artificial Intelligence Lab, Department of Computer Systems Engineering, University of Engineering,Applied Sciences)
Abstract: A novel deep hybrid Residual-SwinCA-Net segmentation framework is proposed in the study for addressing such challenges by extracting locally correlated and robust features, incorporating residual CNN modules. Furthermore, for learning global dependencies, Swin Transformer blocks are customized using internal residual pathways, which reinforce gradient stability, refine local patterns, and facilitate global feature fusion. Formerly, for enhancing tissue continuity, ultrasound noise suppressions, and accentuating fine structural transitions Laplacian-of-Gaussian regional operator is applied, and for maintaining the morphological integrity of malignant lesion contours, a boundary-oriented operator has been incorporated. Subsequently, a contraction strategy was applied stage-wise by progressively reducing features-map progressively for capturing scale invariance and enhancing the robustness of structural variability. In addition, each decoder level prior augmentation integrates a new Multi-Scale Channel Attention and Squeezing (MSCAS) module. The MSCAS selectively emphasizes encoder salient maps, retains discriminative global context, and complementary local structures with minimal computational cost while suppressing redundant activations. Finally, the Pixel-Attention module encodes class-relevant spatial cues by adaptively weighing malignant lesion pixels while suppressing background interference. The Residual-SwinCA-Net and existing CNNs/ViTs techniques have been implemented on the publicly available BUSI dataset. The proposed Residual-SwinCA-Net framework outperformed and achieved 99.29% mean accuracy, 98.74% IoU, and 0.9041 Dice for breast lesion segmentation. The proposed Residual-SwinCA-Net framework improves the BUSI lesion diagnostic performance and strengthens timely clinical decision-making.
Authors: Srijan Dokania, Dharini Raghavan
Abstract: We introduce Zero-Splat TeleAssist, a zero-shot sensor-fusion pipeline that transforms commodity CCTV streams into a shared, 6-DoF world model for multilateral teleoperation. By integrating vision-language segmentation, monocular depth, weighted-PCA pose extraction, and 3D Gaussian Splatting (3DGS), TeleAssist provides every operator with real-time global positions and orientations of multiple robots without fiducials or depth sensors in an interaction-centric teleoperation setup.
Authors: Yihan Liao, Jacky Keung, Zhenyu Mao, Jingyu Zhang, Jialong Li
Abstract: Log-based anomaly detection (LAD) is critical for ensuring the reliability of large-scale distributed systems. However, most existing LAD approaches assume centralized training, which is often impractical due to privacy constraints and the decentralized nature of system logs. While federated learning (FL) offers a promising alternative, there is a lack of dedicated testbeds tailored to the needs of LAD in federated settings. To address this, we present FedLAD, a unified platform for training and evaluating LAD models under FL constraints. FedLAD supports plug-and-play integration of diverse LAD models, benchmark datasets, and aggregation strategies, while offering runtime support for validation logging (self-monitoring), parameter tuning (self-configuration), and adaptive strategy control (self-adaptation). By enabling reproducible and scalable experimentation, FedLAD bridges the gap between FL frameworks and LAD requirements, providing a solid foundation for future research. Project code is publicly available at: https://github.com/AA-cityu/FedLAD.
Authors: Kyungmin Kim, Seokbin Yoon, Keumjin Lee
Abstract: Accurate and reliable aircraft landing time prediction is essential for effective resource allocation in air traffic management. However, the inherent uncertainty of aircraft trajectories and traffic flows poses significant challenges to both prediction accuracy and trustworthiness. Therefore, prediction models should not only provide point estimates of aircraft landing times but also the uncertainties associated with these predictions. Furthermore, aircraft trajectories are frequently influenced by the presence of nearby aircraft through air traffic control interventions such as radar vectoring. Consequently, landing time prediction models must account for multi-agent interactions in the airspace. In this work, we propose a probabilistic multi-agent aircraft landing time prediction framework that provides the landing times of multiple aircraft as distributions. We evaluate the proposed framework using an air traffic surveillance dataset collected from the terminal airspace of the Incheon International Airport in South Korea. The results demonstrate that the proposed model achieves higher prediction accuracy than the baselines and quantifies the associated uncertainties of its outcomes. In addition, the model uncovered underlying patterns in air traffic control through its attention scores, thereby enhancing explainability.
Authors: Liao Hu, Qiteng Wu, Ruoyu Qi
Abstract: The integration of Large Language Models (LLMs) into mobile and software development workflows faces a persistent tension among three demands: semantic awareness, developer productivity, and data privacy. Traditional cloud-based tools offer strong reasoning but risk data exposure and latency, while on-device solutions lack full-context understanding across codebase and developer tooling. We introduce SolidGPT, an open-source, edge-cloud hybrid developer assistant built on GitHub, designed to enhance code and workspace semantic search. SolidGPT enables developers to: talk to your codebase: interactively query code and project structure, discovering the right methods and modules without manual searching. Automate software project workflows: generate PRDs, task breakdowns, Kanban boards, and even scaffold web app beginnings, with deep integration via VSCode and Notion. Configure private, extensible agents: onboard private code folders (up to approximately 500 files), connect Notion, customize AI agent personas via embedding and in-context training, and deploy via Docker, CLI, or VSCode extension. In practice, SolidGPT empowers developer productivity through: Semantic-rich code navigation: no more hunting through files or wondering where a feature lives. Integrated documentation and task management: seamlessly sync generated PRD content and task boards into developer workflows. Privacy-first design: running locally via Docker or VSCode, with full control over code and data, while optionally reaching out to LLM APIs as needed. By combining interactive code querying, automated project scaffolding, and human-AI collaboration, SolidGPT provides a practical, privacy-respecting edge assistant that accelerates real-world development workflows, ideal for intelligent mobile and software engineering contexts.
Authors: Yue Xiang, Shenghong Gu, Dongtao Cao
Abstract: Ultracool dwarfs consist of lowest-mass stars and brown dwarfs. Their interior is fully convective, different from that of the partly-convective Sun-like stars. Magnetic field generation process beneath the surface of ultracool dwarfs is still poorly understood and controversial. To increase samples of active ultracool dwarfs significantly, we have identified 962 ultracool dwarfs in the latest LAMOST data release, DR11. We also simulate the Chinese Space Station Survey Telescope (CSST) low-resolution slitless spectra by degrading the LAMOST spectra. A semi-supervised machine learning approach with an autoencoder model is built to identify ultracool dwarfs with the simulated CSST spectra, which demonstrates the capability of the CSST all-sky slitless spectroscopic survey on the detection of ultracool dwarfs. Magnetic activity of the ultracool dwarfs is investigated by using the H$\alpha$ line emission as a proxy. The rotational periods of 82 ultracool dwarfs are derived based on the Kepler/K2 light curves. We also derive the activity-rotation relation of the ultracool dwarfs, which is saturated around a Rossby number of 0.12.
Authors: Alexander Goslin
Abstract: For decades, procedural worlds have been built on procedural noise functions such as Perlin noise, which are fast and infinite, yet fundamentally limited in realism and large-scale coherence. We introduce Terrain Diffusion, an AI-era successor to Perlin noise that bridges the fidelity of diffusion models with the properties that made procedural noise indispensable: seamless infinite extent, seed-consistency, and constant-time random access. At its core is InfiniteDiffusion, a novel algorithm for infinite generation, enabling seamless, real-time synthesis of boundless landscapes. A hierarchical stack of diffusion models couples planetary context with local detail, while a compact Laplacian encoding stabilizes outputs across Earth-scale dynamic ranges. An open-source infinite-tensor framework supports constant-memory manipulation of unbounded tensors, and few-step consistency distillation enables efficient generation. Together, these components establish diffusion models as a practical foundation for procedural world generation, capable of synthesizing entire planets coherently, controllably, and without limits.
Authors: Wang Chen, Ziyan Luo, Shuangyue Wang
Abstract: Input features are conventionally represented as vectors, matrices, or third order tensors in the real field, for color image classification. Inspired by the success of quaternion data modeling for color images in image recovery and denoising tasks, we propose a novel classification method for color image classification, named as the Low-rank Support Quaternion Matrix Machine (LSQMM), in which the RGB channels are treated as pure quaternions to effectively preserve the intrinsic coupling relationships among channels via the quaternion algebra. For the purpose of promoting low-rank structures resulting from strongly correlated color channels, a quaternion nuclear norm regularization term, serving as a natural extension of the conventional matrix nuclear norm to the quaternion domain, is added to the hinge loss in our LSQMM model. An Alternating Direction Method of Multipliers (ADMM)-based iterative algorithm is designed to effectively resolve the proposed quaternion optimization model. Experimental results on multiple color image classification datasets demonstrate that our proposed classification approach exhibits advantages in classification accuracy, robustness and computational efficiency, compared to several state-of-the-art methods using support vector machines, support matrix machines, and support tensor machines.
Authors: Michael R. Martin, Garrick Chan, Kwan-Liu Ma
Abstract: Recent image protection mechanisms such as Glaze and Nightshade introduce imperceptible, adversarially designed perturbations intended to disrupt downstream text-to-image generative models. While their empirical effectiveness is known, the internal structure, detectability, and representational behavior of these perturbations remain poorly understood. This study provides a systematic, explainable AI analysis using a unified framework that integrates white-box feature-space inspection and black-box signal-level probing. Through latent-space clustering, feature-channel activation analysis, occlusion-based spatial sensitivity mapping, and frequency-domain characterization, we show that protection mechanisms operate as structured, low-entropy perturbations tightly coupled to underlying image content across representational, spatial, and spectral domains. Protected images preserve content-driven feature organization with protection-specific substructure rather than inducing global representational drift. Detectability is governed by interacting effects of perturbation entropy, spatial deployment, and frequency alignment, with sequential protection amplifying detectable structure rather than suppressing it. Frequency-domain analysis shows that Glaze and Nightshade redistribute energy along dominant image-aligned frequency axes rather than introducing diffuse noise. These findings indicate that contemporary image protection operates through structured feature-level deformation rather than semantic dislocation, explaining why protection signals remain visually subtle yet consistently detectable. This work advances the interpretability of adversarial image protection and informs the design of future defenses and detection strategies for generative AI systems.
Authors: Abdullah Hulusi K\"ok\c{c}am, U\u{g}ur Da\u{g}deviren, Talas Fikret Kurnaz, Alparslan Serhat Demir, Caner Erden
Abstract: The California Bearing Ratio (CBR) is a key geotechnical indicator used to assess the load-bearing capacity of subgrade soils, especially in transportation infrastructure and foundation design. Traditional CBR determination relies on laboratory penetration tests. Despite their accuracy, these tests are often time-consuming, costly, and can be impractical, particularly for large-scale or diverse soil profiles. Recent progress in artificial intelligence, especially machine learning (ML), has enabled data-driven approaches for modeling complex soil behavior with greater speed and precision. This study introduces a comprehensive ML framework for CBR prediction using a dataset of 382 soil samples collected from various geoclimatic regions in T\"urkiye. The dataset includes physicochemical soil properties relevant to bearing capacity, allowing multidimensional feature representation in a supervised learning context. Twelve ML algorithms were tested, including decision tree, random forest, extra trees, gradient boosting, xgboost, k-nearest neighbors, support vector regression, multi-layer perceptron, adaboost, bagging, voting, and stacking regressors. Each model was trained, validated, and evaluated to assess its generalization and robustness. Among them, the random forest regressor performed the best, achieving strong R2 scores of 0.95 (training), 0.76 (validation), and 0.83 (test). These outcomes highlight the model's powerful nonlinear mapping ability, making it a promising tool for predictive geotechnical tasks. The study supports the integration of intelligent, data-centric models in geotechnical engineering, offering an effective alternative to traditional methods and promoting digital transformation in infrastructure analysis and design.
Authors: Thai Duong Nguyen, Ngoc-Tan Nguyen, Thanh-Dao Nguyen, Nguyen Van Huynh, Dinh-Hieu Tran, Symeon Chatzinotas
Abstract: The deployment of Unmanned Aerial Vehicle (UAV) swarms as dynamic communication relays is critical for next-generation tactical networks. However, operating in contested environments requires solving a complex trade-off, including maximizing system throughput while ensuring collision avoidance and resilience against adversarial jamming. Existing heuristic-based approaches often struggle to find effective solutions due to the dynamic and multi-objective nature of this problem. This paper formulates this challenge as a cooperative Multi-Agent Reinforcement Learning (MARL) problem, solved using the Centralized Training with Decentralized Execution (CTDE) framework. Our approach employs a centralized critic that uses global state information to guide decentralized actors which operate using only local observations. Simulation results show that our proposed framework significantly outperforms heuristic baselines, increasing the total system throughput by approximately 50% while simultaneously achieving a near-zero collision rate. A key finding is that the agents develop an emergent anti-jamming strategy without explicit programming. They learn to intelligently position themselves to balance the trade-off between mitigating interference from jammers and maintaining effective communication links with ground users.
Authors: Tien Cuong Bui
Abstract: Graph Neural Networks (GNNs) have become a powerful tool for modeling and analyzing data with graph structures. The wide adoption in numerous applications underscores the value of these models. However, the complexity of these methods often impedes understanding their decision-making processes. Current Explainable AI (XAI) methods struggle to untangle the intricate relationships and interactions within graphs. Several methods have tried to bridge this gap via a post-hoc approach or self-interpretable design. Most of them focus on graph structure analysis to determine essential patterns that correlate with prediction outcomes. While post-hoc explanation methods are adaptable, they require extra computational resources and may be less reliable due to limited access to the model's internal workings. Conversely, Interpretable models can provide immediate explanations, but their generalizability to different scenarios remains a major concern. To address these shortcomings, this thesis seeks to develop a novel XAI framework tailored for graph-based machine learning. The proposed framework aims to offer adaptable, computationally efficient explanations for GNNs, moving beyond individual feature analysis to capture how graph structure influences predictions.
Authors: Ali Sakour
Abstract: Biological systems exhibit remarkable morphogenetic plasticity, where a single genome can encode various specialized cellular structures triggered by local chemical signals. In the domain of Deep Learning, Differentiable Neural Cellular Automata (NCA) have emerged as a paradigm to mimic this self-organization. However, existing NCA research has predominantly focused on continuous texture synthesis or single-target object recovery, leaving the challenge of class-conditional structural generation largely unexplored. In this work, we propose a novel Conditional Neural Cellular Automata (c-NCA) architecture capable of growing distinct topological structures - specifically MNIST digits - from a single generic seed, guided solely by a spatially broadcasted class vector. Unlike traditional generative models (e.g., GANs, VAEs) that rely on global reception fields, our model enforces strict locality and translation equivariance. We demonstrate that by injecting a one-hot condition into the cellular perception field, a single set of local rules can learn to break symmetry and self-assemble into ten distinct geometric attractors. Experimental results show that our c-NCA achieves stable convergence, correctly forming digit topologies from a single pixel, and exhibits robustness characteristic of biological systems. This work bridges the gap between texture-based NCAs and structural pattern formation, offering a lightweight, biologically plausible alternative for conditional generation.
Authors: Yi Pan, Wenbo Qian, Dedong Xie, Ruiyan Hu, Yigong Hu, Baris Kasikci
Abstract: The training and deployment of machine learning (ML) models have become extremely energy-intensive. While existing optimization efforts focus primarily on hardware energy efficiency, a significant but overlooked source of inefficiency is software energy waste caused by poor software design. This often includes redundant or poorly designed operations that consume more energy without improving performance. These inefficiencies arise in widely used ML frameworks and applications, yet developers often lack the visibility and tools to detect and diagnose them. We propose differential energy debugging, a novel approach that leverages the observation that competing ML systems often implement similar functionality with vastly different energy consumption. Building on this insight, we design and implement Magneton, an energy profiler that compares energy consumption between similar ML systems at the operator level and automatically pinpoints code regions and configuration choices responsible for excessive energy use. Applied to 9 popular ML systems spanning LLM inference, general ML frameworks, and image generation, Magneton detects and diagnoses 16 known cases of software energy inefficiency and further discovers 8 previously unknown cases, 7 of which have been confirmed by developers.
Authors: Nour Mitiche, Farid Ferguene, Mourad Oussalah
Abstract: Time delays in communication channels present significant challenges for bilateral teleoperation systems, affecting both transparency and stability. Although traditional wave variable-based methods for a four-channel architecture ensure stability via passivity, they remain vulnerable to wave reflections and disturbances like variable delays and environmental noise. This article presents a data-driven hybrid framework that replaces the conventional wave-variable transform with an ensemble of three advanced sequence models, each optimized separately via the state-of-the-art Optuna optimizer, and combined through a stacking meta-learner. The base predictors include an LSTM augmented with Prophet for trend correction, an LSTM-based feature extractor paired with clustering and a random forest for improved regression, and a CNN-LSTM model for localized and long-term dynamics. Experimental validation was performed in Python using data generated from the baseline system implemented in MATLAB/Simulink. The results show that our optimized ensemble achieves a transparency comparable to the baseline wave-variable system under varying delays and noise, while ensuring stability through passivity constraints.
Authors: Andreas Hauptmann, Ozan \"Oktem
Abstract: Learned image reconstruction has become a pillar in computational imaging and inverse problems. Among the most successful approaches are learned iterative networks, which are formulated by unrolling classical iterative optimisation algorithms for solving variational problems. While the underlying algorithm is usually formulated in the functional analytic setting, learned approaches are often viewed as purely discrete. In this chapter we present a unified operator view for learned iterative networks. Specifically, we formulate a learned reconstruction operator, defining how to compute, and separately the learning problem, which defines what to compute. In this setting we present common approaches and show that many approaches are closely related in their core. We review linear as well as nonlinear inverse problems in this framework and present a short numerical study to conclude.
Authors: Madhav Gupta, Vishak Prasad C, Ganesh Ramakrishnan
Abstract: Subset selection-based methods are widely used to explain deep vision models: they attribute predictions by highlighting the most influential image regions and support object-level explanations. While these methods perform well in in-distribution (ID) settings, their behavior under out-of-distribution (OOD) conditions remains poorly understood. Through extensive experiments across multiple ID-OOD sets, we find that reliability of the existing subset based methods degrades markedly, yielding redundant, unstable, and uncertainty-sensitive explanations. To address these shortcomings, we introduce a framework that combines submodular subset selection with layer-wise, gradient-based uncertainty estimation to improve robustness and fidelity without requiring additional training or auxiliary models. Our approach estimates uncertainty via adaptive weight perturbations and uses these estimates to guide submodular optimization, ensuring diverse and informative subset selection. Empirical evaluations show that, beyond mitigating the weaknesses of existing methods under OOD scenarios, our framework also yields improvements in ID settings. These findings highlight limitations of current subset-based approaches and demonstrate how uncertainty-driven optimization can enhance attribution and object-level interpretability, paving the way for more transparent and trustworthy AI in real-world vision applications.
Authors: Antonio Terpin, Raffaello D'Andrea
Abstract: Many high-performance human activities are executed with little or no external feedback: think of a figure skater landing a triple jump, a pitcher throwing a curveball for a strike, or a barista pouring latte art. To study the process of skill acquisition under fully controlled conditions, we bypass human subjects. Instead, we directly interface a generalist reinforcement learning agent with a spinning cylinder in a tabletop circulating water channel to maximize or minimize drag. This setup has several desirable properties. First, it is a physical system, with the rich interactions and complex dynamics that only the physical world has: the flow is highly chaotic and extremely difficult, if not impossible, to model or simulate accurately. Second, the objective -- drag minimization or maximization -- is easy to state and can be captured directly in the reward, yet good strategies are not obvious beforehand. Third, decades-old experimental studies provide recipes for simple, high-performance open-loop policies. Finally, the setup is inexpensive and far easier to reproduce than human studies. In our experiments we find that high-dimensional flow feedback lets the agent discover high-performance drag-control strategies with only minutes of real-world interaction. When we later replay the same action sequences without any feedback, we obtain almost identical performance. This shows that feedback, and in particular flow feedback, is not needed to execute the learned policy. Surprisingly, without flow feedback during training the agent fails to discover any well-performing policy in drag maximization, but still succeeds in drag minimization, albeit more slowly and less reliably. Our studies show that learning a high-performance skill can require richer information than executing it, and learning conditions can be kind or wicked depending solely on the goal, not on dynamics or policy complexity.
Authors: Gengmo Zhou, Feng Yu, Wenda Wang, Zhifeng Gao, Guolin Ke, Zhewei Wei, Zhen Wang
Abstract: Enzymes are crucial catalysts that enable a wide range of biochemical reactions. Efficiently identifying specific enzymes from vast protein libraries is essential for advancing biocatalysis. Traditional computational methods for enzyme screening and retrieval are time-consuming and resource-intensive. Recently, deep learning approaches have shown promise. However, these methods focus solely on the interaction between enzymes and reactions, overlooking the inherent hierarchical relationships within each domain. To address these limitations, we introduce FGW-CLIP, a novel contrastive learning framework based on optimizing the fused Gromov-Wasserstein distance. FGW-CLIP incorporates multiple alignments, including inter-domain alignment between reactions and enzymes and intra-domain alignment within enzymes and reactions. By introducing a tailored regularization term, our method minimizes the Gromov-Wasserstein distance between enzyme and reaction spaces, which enhances information integration across these domains. Extensive evaluations demonstrate the superiority of FGW-CLIP in challenging enzyme-reaction tasks. On the widely-used EnzymeMap benchmark, FGW-CLIP achieves state-of-the-art performance in enzyme virtual screening, as measured by BEDROC and EF metrics. Moreover, FGW-CLIP consistently outperforms across all three splits of ReactZyme, the largest enzyme-reaction benchmark, demonstrating robust generalization to novel enzymes and reactions. These results position FGW-CLIP as a promising framework for enzyme discovery in complex biochemical settings, with strong adaptability across diverse screening scenarios.
Authors: Gongyi Wang, Yu Zhang, Zihan Huang
Abstract: Machine learning (ML) has become a versatile tool for analyzing anomalous diffusion trajectories, yet most existing pipelines are trained on large collections of simulated data. In contrast, experimental trajectories, such as those from single-particle tracking (SPT), are typically scarce and may differ substantially from the idealized models used for simulation, leading to degradation or even breakdown of performance when ML methods are applied to real data. To address this mismatch, we introduce a wavelet-based representation of anomalous diffusion that enables data-efficient learning directly from experimental recordings. This representation is constructed by applying six complementary wavelet families to each trajectory and combining the resulting wavelet modulus scalograms. We first evaluate the wavelet representation on simulated trajectories from the andi-datasets benchmark, where it clearly outperforms both feature-based and trajectory-based methods with as few as 1000 training trajectories and still retains an advantage on large training sets. We then use this representation to learn directly from experimental SPT trajectories of fluorescent beads diffusing in F-actin networks, where the wavelet representation remains superior to existing alternatives for both diffusion-exponent regression and mesh-size classification. In particular, when predicting the diffusion exponents of experimental trajectories, a model trained on 1200 experimental tracks using the wavelet representation achieves significantly lower errors than state-of-the-art deep learning models trained purely on $10^6$ simulated trajectories. We associate this data efficiency with the emergence of distinct scale fingerprints disentangling underlying diffusion mechanisms in the wavelet spectra.
Authors: Masahiro Kato
Abstract: We consider an adaptive experiment for treatment choice and design a minimax and Bayes optimal adaptive experiment with respect to regret. Given binary treatments, the experimenter's goal is to choose the treatment with the highest expected outcome through an adaptive experiment, in order to maximize welfare. We consider adaptive experiments that consist of two phases, the treatment allocation phase and the treatment choice phase. The experiment starts with the treatment allocation phase, where the experimenter allocates treatments to experimental subjects to gather observations. During this phase, the experimenter can adaptively update the allocation probabilities using the observations obtained in the experiment. After the allocation phase, the experimenter proceeds to the treatment choice phase, where one of the treatments is selected as the best. For this adaptive experimental procedure, we propose an adaptive experiment that splits the treatment allocation phase into two stages, where we first estimate the standard deviations and then allocate each treatment proportionally to its standard deviation. We show that this experiment, often referred to as Neyman allocation, is minimax and Bayes optimal in the sense that its regret upper bounds exactly match the lower bounds that we derive. To show this optimality, we derive minimax and Bayes lower bounds for the regret using change-of-measure arguments. Then, we evaluate the corresponding upper bounds using the central limit theorem and large deviation bounds.
Authors: Yuna Kato, Shohei Mori, Hideo Saito, Yoshifumi Takatsume, Hiroki Kajita, Mariko Isogawa
Abstract: Video recordings of open surgeries are greatly required for education and research purposes. However, capturing unobstructed videos is challenging since surgeons frequently block the camera field of view. To avoid occlusion, the positions and angles of the camera must be frequently adjusted, which is highly labor-intensive. Prior work has addressed this issue by installing multiple cameras on a shadowless lamp and arranging them to fully surround the surgical area. This setup increases the chances of some cameras capturing an unobstructed view. However, manual image alignment is needed in post-processing since camera configurations change every time surgeons move the lamp for optimal lighting. This paper aims to fully automate this alignment task. The proposed method identifies frames in which the lighting system moves, realigns them, and selects the camera with the least occlusion to generate a video that consistently presents the surgical field from a fixed perspective. A user study involving surgeons demonstrated that videos generated by our method were superior to those produced by conventional methods in terms of the ease of confirming the surgical area and the comfort during video viewing. Additionally, our approach showed improvements in video quality over existing techniques. Furthermore, we implemented several synthesis options for the proposed view-synthesis method and conducted a user study to assess surgeons' preferences for each option.
Authors: Orit Davidovich, Shimrit Shtern, Segev Wasserkrug, Nimrod Megiddo
Abstract: Since the 1990s, considerable empirical work has been carried out to train statistical models, such as neural networks (NNs), as learned heuristics for combinatorial optimization (CO) problems. When successful, such an approach eliminates the need for experts to design heuristics per problem type. Due to their structure, many hard CO problems are amenable to treatment through reinforcement learning (RL). Indeed, we find a wealth of literature training NNs using value-based, policy gradient, or actor-critic approaches, with promising results, both in terms of empirical optimality gaps and inference runtimes. Nevertheless, there has been a paucity of theoretical work undergirding the use of RL for CO problems. To this end, we introduce a unified framework to model CO problems through Markov decision processes (MDPs) and solve them using RL techniques. We provide easy-to-test assumptions under which CO problems can be formulated as equivalent undiscounted MDPs that provide optimal solutions to the original CO problems. Moreover, we establish conditions under which value-based RL techniques converge to approximate solutions of the CO problem with a guarantee on the associated optimality gap. Our convergence analysis provides: (1) a sufficient rate of increase in batch size and projected gradient descent steps at each RL iteration; (2) the resulting optimality gap in terms of problem parameters and targeted RL accuracy; and (3) the importance of a choice of state-space embedding. Together, our analysis illuminates the success (and limitations) of the celebrated deep Q-learning algorithm in this problem context.
Authors: Renato Cordeiro Ferreira (Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University, University of S\~ao Paulo), Aditya Dhinavahi (Jheronimus Academy of Data Science, Technical University of Eindhoven), Rowanne Trapmann (Jheronimus Academy of Data Science, Tilburg University), Willem-Jan van den Heuvel (Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University)
Abstract: ML-Enabled Systems (MLES) are inherently complex since they require multiple components to achieve their business goal. This experience report showcases the software architecture reusability techniques applied while building Ocean Guard, an MLES for anomaly detection in the maritime domain. In particular, it highlights the challenges and lessons learned to reuse the Ports and Adapters pattern to support building multiple microservices from a single codebase. This experience report hopes to inspire software engineers, machine learning engineers, and data scientists to apply the Hexagonal Architecture pattern to build their MLES.
Authors: Bohao Yang, Rui Yang, Joshua M. Biro, Haoyuan Wang, Jessica L. Handley, Brianna Richardson, Sophia Bessias, Nicoleta Economou-Zavlanos, Armando D. Bedoya, Monica Agrawal, Michael M. Zavlanos, Anand Chowdhury, Raj M. Ratwani, Kai Sun, Kathryn I. Pollak, Michael J. Pencina, Chuan Hong
Abstract: Clinical communication is central to patient outcomes, yet large-scale human annotation of patient-provider conversation remains labor-intensive, inconsistent, and difficult to scale. Existing approaches based on large language models typically rely on single-task models that lack adaptability, interpretability, and reliability, especially when applied across various communication frameworks and clinical domains. In this study, we developed a Multi-framework Structured Agentic AI system for Clinical Communication (MOSAIC), built on a LangGraph-based architecture that orchestrates four core agents, including a Plan Agent for codebook selection and workflow planning, an Update Agent for maintaining up-to-date retrieval databases, a set of Annotation Agents that applies codebook-guided retrieval-augmented generation (RAG) with dynamic few-shot prompting, and a Verification Agent that provides consistency checks and feedback. To evaluate performance, we compared MOSAIC outputs against gold-standard annotations created by trained human coders. We developed and evaluated MOSAIC using 26 gold standard annotated transcripts for training and 50 transcripts for testing, spanning rheumatology and OB/GYN domains. On the test set, MOSAIC achieved an overall F1 score of 0.928. Performance was highest in the Rheumatology subset (F1 = 0.962) and strongest for Patient Behavior (e.g., patients asking questions, expressing preferences, or showing assertiveness). Ablations revealed that MOSAIC outperforms baseline benchmarking.
Authors: Josip Kir Hromatko, Shambhuraj Sawant, \v{S}andor Ile\v{s}, S\'ebastien Gros
Abstract: Scaled model experiments are commonly used in various engineering fields to reduce experimentation costs and overcome constraints associated with full-scale systems. The relevance of such experiments relies on dimensional analysis and the principle of dynamic similarity. However, transferring controllers to full-scale systems often requires additional tuning. In this paper, we propose a method to enable a direct controller transfer using dimensionless model predictive control, tuned automatically for closed-loop performance. With this reformulation, the closed-loop behavior of an optimized controller transfers directly to a new, dynamically similar system. Additionally, the dimensionless formulation allows for the use of data from systems of different scales during parameter optimization. We demonstrate the method on a cartpole swing-up and a car racing problem, applying either reinforcement learning or Bayesian optimization for tuning the controller parameters. Software used to obtain the results in this paper is publicly available at https://github.com/josipkh/dimensionless-mpcrl.
Authors: Jannik Graebner, Ryne Beeson
Abstract: Preliminary mission design of low-thrust spacecraft trajectories in the Circular Restricted Three-Body Problem is a global search characterized by a complex objective landscape and numerous local minima. Formulating the problem as sampling from an unnormalized distribution supported on neighborhoods of locally optimal solutions, provides the opportunity to deploy Markov chain Monte Carlo methods and generative machine learning. In this work, we extend our previous self-supervised diffusion model fine-tuning framework to employ gradient-informed Markov chain Monte Carlo. We compare two algorithms - the Metropolis-Adjusted Langevin Algorithm and Hamiltonian Monte Carlo - both initialized from a distribution learned by a diffusion model. Derivatives of an objective function that balances fuel consumption, time of flight and constraint violations are computed analytically using state transition matrices. We show that incorporating the gradient drift term accelerates mixing and improves convergence of the Markov chain for a multi-revolution transfer in the Saturn-Titan system. Among the evaluated methods, MALA provides the best trade-off between performance and computational cost. Starting from samples generated by a baseline diffusion model trained on a related transfer, MALA explicitly targets Pareto-optimal solutions. Compared to a random walk Metropolis algorithm, it increases the feasibility rate from 17.34% to 63.01% and produces a denser, more diverse coverage of the Pareto front. By fine-tuning a diffusion model on the generated samples and associated reward values with reward-weighted likelihood maximization, we learn the global solution structure of the problem and eliminate the need for a tedious separate data generation phase.
Authors: S\'ebastien Pi\'erard, Adrien Deli\`ege, Marc Van Droogenbroeck
Abstract: The performance of algorithms, methods, and models tends to depend heavily on the distribution of cases on which they are applied, this distribution being specific to the applicative domain. After performing an evaluation in several domains, it is highly informative to compute a (weighted) mean performance and, as shown in this paper, to scrutinize what happens during this averaging. To achieve this goal, we adopt a probabilistic framework and consider a performance as a probability measure (e.g., a normalized confusion matrix for a classification task). It appears that the corresponding weighted mean is known to be the summarization, and that only some remarkable scores assign to the summarized performance a value equal to a weighted arithmetic mean of the values assigned to the domain-specific performances. These scores include the family of ranking scores, a continuum parameterized by user preferences, and that the weights to consider in the arithmetic mean depend on the user preferences. Based on this, we rigorously define four domains, named easiest, most difficult, preponderant, and bottleneck domains, as functions of user preferences. After establishing the theory in a general setting, regardless of the task, we develop new visual tools for two-class classification.
Authors: Kuniko Paxton, Zeinab Dehghani, Koorosh Aslansefat, Dhavalkumar Thakker, Yiannis Papadopoulos
Abstract: Skin color has historically been a focal point of discrimination, yet fairness research in machine learning for medical imaging often relies on coarse subgroup categories, overlooking individual-level variations. Such group-based approaches risk obscuring biases faced by outliers within subgroups. This study introduces a distribution-based framework for evaluating and mitigating individual fairness in skin lesion classification. We treat skin tone as a continuous attribute rather than a categorical label, and employ kernel density estimation (KDE) to model its distribution. We further compare twelve statistical distance metrics to quantify disparities between skin tone distributions and propose a distance-based reweighting (DRW) loss function to correct underrepresentation in minority tones. Experiments across CNN and Transformer models demonstrate: (i) the limitations of categorical reweighting in capturing individual-level disparities, and (ii) the superior performance of distribution-based reweighting, particularly with Fidelity Similarity (FS), Wasserstein Distance (WD), Hellinger Metric (HM), and Harmonic Mean Similarity (HS). These findings establish a robust methodology for advancing fairness at individual level in dermatological AI systems, and highlight broader implications for sensitive continuous attributes in medical image analysis.
Authors: Yi Liu, Weixiang Han, Chengjun Cai, Xingliang Yuan, Cong Wang
Abstract: With the rise of large language models, service providers offer language models as a service, enabling users to fine-tune customized models via uploaded private datasets. However, this raises concerns about sensitive data leakage. Prior methods, relying on differential privacy within device-cloud collaboration frameworks, struggle to balance privacy and utility, exposing users to inference attacks or degrading fine-tuning performance. To address this, we propose PrivTune, an efficient and privacy-preserving fine-tuning framework via Split Learning (SL). The key idea of PrivTune is to inject crafted noise into token representations from the SL bottom model, making each token resemble the $n$-hop indirect neighbors. PrivTune formulates this as an optimization problem to compute the optimal noise vector, aligning with defense-utility goals. On this basis, it then adjusts the parameters (i.e., mean) of the $d_\chi$-Privacy noise distribution to align with the optimization direction and scales the noise according to token importance to minimize distortion. Experiments on five datasets (covering both classification and generation tasks) against three embedding inversion and three attribute inference attacks show that, using RoBERTa on the Stanford Sentiment Treebank dataset, PrivTune reduces the attack success rate to 10% with only a 3.33% drop in utility performance, outperforming state-of-the-art baselines.
Authors: Viola Campos, Robin Kuschnereit, Adrian Ulges
Abstract: As AI-based code generation becomes widespread, researchers are investigating the calibration of code LLMs - ensuring their confidence scores faithfully represent the true likelihood of code correctness. To do so, we investigate multicalibration, which can capture additional factors about a coding problem, such as complexity, code length, or programming language used. We study four multicalibration approaches on three function synthesis benchmarks, using latest-generation code LLMs (Qwen3 Coder, GPT-OSS, DeepSeek-R1-Distill). Our results demonstrate that multicalibration can yield distinct improvements over both uncalibrated token likelihoods (+1.03 in skill score) and baseline calibrations (+0.37 in skill score). We study the influence of the aforementioned factors in ablations, and make our dataset (consisting of code generations, likelihoods, and correctness labels) available for future research on code LLM calibration.
Authors: Ferdinand Kapl, Emmanouil Angelis, Tobias H\"oppe, Kaitlin Maile, Johannes von Oswald, Nino Scherrer, Stefan Bauer
Abstract: Gradually growing the depth of Transformers during training can not only reduce training cost but also lead to improved reasoning performance, as shown by MIDAS (Saunshi et al., 2024). Thus far, however, a mechanistic understanding of these gains has been missing. In this work, we establish a connection to recent work showing that layers in the second half of non-grown, pre-layernorm Transformers contribute much less to the final output distribution than those in the first half - also known as the Curse of Depth (Sun et al., 2025, Csord\'as et al., 2025). Using depth-wise analyses, we demonstrate that growth via gradual middle stacking yields more effective utilization of model depth, alters the residual stream structure, and facilitates the formation of permutable computational blocks. In addition, we propose a lightweight modification of MIDAS that yields further improvements in downstream reasoning benchmarks. Overall, this work highlights how the gradual growth of model depth can lead to the formation of distinct computational circuits and overcome the limited depth utilization seen in standard non-grown models.
Authors: Jack Brady, Bernhard Sch\"olkopf, Thomas Kipf, Simon Buchholz, Wieland Brendel
Abstract: It has been hypothesized that human-level visual perception requires a generative approach in which internal representations result from inverting a decoder. Yet today's most successful vision models are non-generative, relying on an encoder that maps images to representations without decoder inversion. This raises the question of whether generation is, in fact, necessary for machines to achieve human-level visual perception. To address this, we study whether generative and non-generative methods can achieve compositional generalization, a hallmark of human perception. Under a compositional data generating process, we formalize the inductive biases required to guarantee compositional generalization in decoder-based (generative) and encoder-based (non-generative) methods. We then show theoretically that enforcing these inductive biases on encoders is generally infeasible using regularization or architectural constraints. In contrast, for generative methods, the inductive biases can be enforced straightforwardly, thereby enabling compositional generalization by constraining a decoder and inverting it. We highlight how this inversion can be performed efficiently, either online through gradient-based search or offline through generative replay. We examine the empirical implications of our theory by training a range of generative and non-generative methods on photorealistic image datasets. We find that, without the necessary inductive biases, non-generative methods often fail to generalize compositionally and require large-scale pretraining or added supervision to improve generalization. By comparison, generative methods yield significant improvements in compositional generalization, without requiring additional data, by leveraging suitable inductive biases on a decoder along with search and replay.
Authors: Mohamed Elmahallawy, Sanjay Madria, Samuel Frimpong
Abstract: Underground mining operations depend on sensor networks to monitor critical parameters such as temperature, gas concentration, and miner movement, enabling timely hazard detection and safety decisions. However, transmitting raw sensor data to a centralized server for machine learning (ML) model training raises serious privacy and security concerns. Federated Learning (FL) offers a promising alternative by enabling decentralized model training without exposing sensitive local data. Yet, applying FL in underground mining presents unique challenges: (i) Adversaries may eavesdrop on shared model updates to launch model inversion or membership inference attacks, compromising data privacy and operational safety; (ii) Non-IID data distributions across mines and sensor noise can hinder model convergence. To address these issues, we propose FedMining--a privacy-preserving FL framework tailored for underground mining. FedMining introduces two core innovations: (1) a Decentralized Functional Encryption (DFE) scheme that keeps local models encrypted, thwarting unauthorized access and inference attacks; and (2) a balancing aggregation mechanism to mitigate data heterogeneity and enhance convergence. Evaluations on real-world mining datasets demonstrate FedMining's ability to safeguard privacy while maintaining high model accuracy and achieving rapid convergence with reduced communication and computation overhead. These advantages make FedMining both secure and practical for real-time underground safety monitoring.
Authors: Mohamed Elmahallawy, Asma Jodeiri Akbarfam
Abstract: The rise of space AI is reshaping government and industry through applications such as disaster detection, border surveillance, and climate monitoring, powered by massive data from commercial and governmental low Earth orbit (LEO) satellites. Federated satellite learning (FSL) enables joint model training without sharing raw data, but suffers from slow convergence due to intermittent connectivity and introduces critical trust challenges--where biased or falsified updates can arise across satellite constellations, including those injected through cyberattacks on inter-satellite or satellite-ground communication links. We propose OrbitChain, a blockchain-backed framework that empowers trustworthy multi-vendor collaboration in LEO networks. OrbitChain (i) offloads consensus to high-altitude platforms (HAPs) with greater computational capacity, (ii) ensures transparent, auditable provenance of model updates from different orbits owned by different vendors, and (iii) prevents manipulated or incomplete contributions from affecting global FSL model aggregation. Extensive simulations show that OrbitChain reduces computational and communication overhead while improving privacy, security, and global model accuracy. Its permissioned proof-of-authority ledger finalizes over 1000 blocks with sub-second latency (0.16,s, 0.26,s, 0.35,s for 1-of-5, 3-of-5, and 5-of-5 quorums). Moreover, OrbitChain reduces convergence time by up to 30 hours on real satellite datasets compared to single-vendor, demonstrating its effectiveness for real-time, multi-vendor learning. Our code is available at https://github.com/wsu-cyber-security-lab-ai/OrbitChain.git
URLs: https://github.com/wsu-cyber-security-lab-ai/OrbitChain.git
Authors: Jessica Yin, Haozhi Qi, Youngsun Wi, Sayantan Kundu, Mike Lambeta, William Yang, Changhao Wang, Tingfan Wu, Jitendra Malik, Tess Hellebrekers
Abstract: Human video demonstrations provide abundant training data for learning robot policies, but video alone cannot capture the rich contact signals critical for mastering manipulation. We introduce OSMO, an open-source wearable tactile glove designed for human-to-robot skill transfer. The glove features 12 three-axis tactile sensors across the fingertips and palm and is designed to be compatible with state-of-the-art hand-tracking methods for in-the-wild data collection. We demonstrate that a robot policy trained exclusively on human demonstrations collected with OSMO, without any real robot data, is capable of executing a challenging contact-rich manipulation task. By equipping both the human and the robot with the same glove, OSMO minimizes the visual and tactile embodiment gap, enabling the transfer of continuous shear and normal force feedback while avoiding the need for image inpainting or other vision-based force inference. On a real-world wiping task requiring sustained contact pressure, our tactile-aware policy achieves a 72% success rate, outperforming vision-only baselines by eliminating contact-related failure modes. We release complete hardware designs, firmware, and assembly instructions to support community adoption.
Authors: Yixuan Zhu, Jiaqi Feng, Wenzhao Zheng, Yuan Gao, Xin Tao, Pengfei Wan, Jie Zhou, Jiwen Lu
Abstract: Recent advances in diffusion transformers have empowered video generation models to generate high-quality video clips from texts or images. However, world models with the ability to predict long-horizon futures from past observations and actions remain underexplored, especially for general-purpose scenarios and various forms of actions. To bridge this gap, we introduce Astra, an interactive general world model that generates real-world futures for diverse scenarios (e.g., autonomous driving, robot grasping) with precise action interactions (e.g., camera motion, robot action). We propose an autoregressive denoising architecture and use temporal causal attention to aggregate past observations and support streaming outputs. We use a noise-augmented history memory to avoid over-reliance on past frames to balance responsiveness with temporal coherence. For precise action control, we introduce an action-aware adapter that directly injects action signals into the denoising process. We further develop a mixture of action experts that dynamically route heterogeneous action modalities, enhancing versatility across diverse real-world tasks such as exploration, manipulation, and camera control. Astra achieves interactive, consistent, and general long-term video prediction and supports various forms of interactions. Experiments across multiple datasets demonstrate the improvements of Astra in fidelity, long-range prediction, and action alignment over existing state-of-the-art world models.
Authors: Shiqi Liu, Jingxin Liu, Qian Zhao, Xiangyong Cao, Huibin Li, Deyu Meng, Hongying Meng, Sheng Liu
Abstract: In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract useful knowledge or serve for the downstream tasks. In this work, we focus on supervising the influential factors extracted by the variational autoencoder(VAE). The VAE is proposed to learn independent low dimension representation while facing the problem that sometimes pre-set factors are ignored. We argue that the mutual information of the input and each learned factor of the representation plays a necessary indicator of discovering the influential factors. We find the VAE objective inclines to induce mutual information sparsity in factor dimension over the data intrinsic dimension and therefore result in some non-influential factors whose function on data reconstruction could be ignored. We show mutual information also influences the lower bound of the VAE's reconstruction error and downstream classification task. To make such indicator applicable, we design an algorithm for calculating the mutual information for the VAE and prove its consistency. Experimental results on MNIST, CelebA and DEAP datasets show that mutual information can help determine influential factors, of which some are interpretable and can be used to further generation and classification tasks, and help discover the variant that connects with emotion on DEAP dataset.
Authors: Xiangqian Sun, Xing Yan, Qi Wu
Abstract: We propose a multivariate generative model to capture the complex dependence structure often encountered in business and financial data. Our model features heterogeneous and asymmetric tail dependence between all pairs of individual dimensions while also allowing heterogeneity and asymmetry in the tails of the marginals. A significant merit of our model structure is that it is not prone to error propagation in the parameter estimation process, hence very scalable, as the dimensions of datasets grow large. However, the likelihood methods are infeasible for parameter estimation in our case due to the lack of a closed-form density function. Instead, we devise a novel moment learning algorithm to learn the parameters. To demonstrate the effectiveness of the model and its estimator, we test them on simulated as well as real-world datasets. Results show that this framework gives better finite-sample performance compared to the copula-based benchmarks as well as recent similar models.
Authors: Haotian Ye, James Zou, Linjun Zhang
Abstract: The existence of spurious correlations such as image backgrounds in the training environment can make empirical risk minimization (ERM) perform badly in the test environment. To address this problem, Kirichenko et al. (2022) empirically found that the core features that are related to the outcome can still be learned well even with the presence of spurious correlations. This opens a promising strategy to first train a feature learner rather than a classifier, and then perform linear probing (last layer retraining) in the test environment. However, a theoretical understanding of when and why this approach works is lacking. In this paper, we find that core features are only learned well when their associated non-realizable noise is smaller than that of spurious features, which is not necessarily true in practice. We provide both theories and experiments to support this finding and to illustrate the importance of non-realizable noise. Moreover, we propose an algorithm called Freeze then Train (FTT), that first freezes certain salient features and then trains the rest of the features using ERM. We theoretically show that FTT preserves features that are more beneficial to test time probing. Across two commonly used spurious correlation datasets, FTT outperforms ERM, IRM, JTT and CVaR-DRO, with substantial improvement in accuracy (by 4.5%) when the feature noise is large. FTT also performs better on general distribution shift benchmarks.
Authors: M Yashwanth, Gaurav Kumar Nayak, Arya Singh, Yogesh Simmhan, Anirban Chakraborty
Abstract: Federated Learning (FL) is a machine learning paradigm that enables clients to jointly train a global model by aggregating the locally trained models without sharing any local training data. In practice, there can often be substantial heterogeneity (e.g., class imbalance) across the local data distributions observed by each of these clients. Under such non-iid label distributions across clients, FL suffers from the 'client-drift' problem where every client drifts to its own local optimum. This results in slower convergence and poor performance of the aggregated model. To address this limitation, we propose a novel regularization technique based on adaptive self-distillation (ASD) for training models on the client side. Our regularization scheme adaptively adjusts to each client's training data based on the global model's prediction entropy and the client-data label distribution. We show in this paper that our proposed regularization (ASD) can be easily integrated atop existing, state-of-the-art FL algorithms, leading to a further boost in the performance of these off-the-shelf methods. We theoretically explain how incorporation of ASD regularizer leads to reduction in client-drift and empirically justify the generalization ability of the trained model. We demonstrate the efficacy of our approach through extensive experiments on multiple real-world benchmarks and show substantial gains in performance when the proposed regularizer is combined with popular FL methods.
Authors: Junwei Su, Lingjun Mao, Zheng Da, Chuan Wu
Abstract: Heterogeneous graphs, comprising diverse node and edge types connected through varied relations, are ubiquitous in real-world applications. Message-passing heterogeneous graph neural networks (HGNNs) have emerged as a powerful model class for such data. However, existing HGNNs typically allocate a separate set of learnable weights for each relation type to model relational heterogeneity. Despite their promise, these models are effective primarily on simple heterogeneous graphs with only a few relation types. In this paper, we show that this standard design inherently leads to parameter explosion (the number of learnable parameters grows rapidly with the number of relation types) and relation collapse (the model loses the ability to distinguish among different relations). These issues make existing HGNNs inefficient or impractical for complex heterogeneous graphs with many relation types. To address these challenges, we propose Blend&Grind-HGNN (BG-HGNN), a unified feature-representation framework that integrates and distills relational heterogeneity into a shared low-dimensional feature space. This design eliminates the need for relation-specific parameter sets and enables efficient, expressive learning even as the number of relations grows. Empirically, BG-HGNN achieves substantial gains over state-of-the-art HGNNs, improving parameter efficiency by up to 28.96x and training throughput by up to 110.30x, while matching or surpassing their accuracy on complex heterogeneous graphs.
Authors: Linnea M Wolniewicz, Peter Sadowski, Claudio Corti
Abstract: Bayesian inference methods such as Markov Chain Monte Carlo (MCMC) typically require repeated computations of the likelihood function, but in some scenarios this is infeasible and alternative methods are needed. Simulation-based inference (SBI) methods address this problem by using machine learning to amortize computations. In this work, we highlight a particular synergy between the SBI method of neural likelihood estimation and the classic MCMC method of Hamiltonian Monte Carlo. We show that approximating the likelihood function with a neural network model can provide three distinct advantages: (1) amortizing the computations for MCMC; (2) providing gradients for Hamiltonian Monte Carlo, and (3) smoothing over noisy simulations resulting from numerical instabilities. We provide practical guidelines for defining a prior, sampling a training set, and evaluating convergence. The method is demonstrated in an application modeling the heliospheric transport of galactic cosmic rays, where it enables efficient inference of latent parameters in the Parker equation.
Authors: Huizhen Yu, Yi Wan, Richard S. Sutton
Abstract: This paper investigates the stability and convergence properties of asynchronous stochastic approximation (SA) algorithms, with a focus on extensions relevant to average-reward reinforcement learning. We first extend a stability proof method of Borkar and Meyn to accommodate more general noise conditions than previously considered, thereby yielding broader convergence guarantees for asynchronous SA. To sharpen the convergence analysis, we further examine the shadowing properties of asynchronous SA, building on a dynamical systems approach of Hirsch and Bena\"{i}m. These results provide a theoretical foundation for a class of relative value iteration-based reinforcement learning algorithms -- developed and analyzed in a companion paper -- for solving average-reward Markov and semi-Markov decision processes.
Authors: Harsh Choudhary, Chandan Gupta, Vyacheslav Kungurtsev, Melvin Leok, Georgios Korpas
Abstract: Many important physical systems can be described as the evolution of a Hamiltonian system, which has the important property of being conservative, that is, energy is conserved throughout the evolution. Physics Informed Neural Networks and in particular Hamiltonian Neural Networks have emerged as a mechanism to incorporate structural inductive bias into the NN model. By ensuring physical invariances are conserved, the models exhibit significantly better sample complexity and out-of-distribution accuracy than standard NNs. Learning the Hamiltonian as a function of its canonical variables, typically position and velocity, from sample observations of the system thus becomes a critical task in system identification and long-term prediction of system behavior. However, to truly preserve the long-run physical conservation properties of Hamiltonian systems, one must use symplectic integrators for a forward pass of the system's simulation. While symplectic schemes have been used in the literature, they are thus far limited to situations when they reduce to explicit algorithms, which include the case of separable Hamiltonians or augmented non-separable Hamiltonians. We extend it to generalized non-separable Hamiltonians, and noting the self-adjoint property of symplectic integrators, we bypass computationally intensive backpropagation through an ODE solver. We show that the method is robust to noise and provides a good approximation of the system Hamiltonian when the state variables are sampled from a noisy observation. In the numerical results, we show the performance of the method concerning Hamiltonian reconstruction and conservation, indicating its particular advantage for non-separable systems.
Authors: Dahlia Devapriya, Aparna V C, Sheetal Kalyani
Abstract: In reconfigurable intelligent surface (RIS) aided systems, the joint optimization of the precoder matrix at the base station and the phase shifts of the RIS elements involves significant complexity. In this paper, we propose a complex-valued, geometry aware meta-learning neural network that maximizes the weighted sum rate in a multi-user multiple input single output system. By leveraging the complex circle geometry for phase shifts and spherical geometry for the precoder, the optimization occurs on Riemannian manifolds, leading to faster convergence. We use a complex-valued neural network for phase shifts and an Euler inspired update for the precoder network. Our approach outperforms existing neural network-based algorithms, offering higher weighted sum rates, lower power consumption, and significantly faster convergence. Specifically, it converges faster by nearly 100 epochs, with a 0.7 bps improvement in weighted sum rate and a 1.8 dB power gain when compared with existing work. Further it outperforms the state-of-the-art alternating optimization algorithm by 0.86 bps with a 2.6 dB power gain.
Authors: Bohan Wang, Yurui Chang, Wei Jin, Lu Lin
Abstract: Distribution shifts between training and testing datasets significantly impair the model performance on graph learning. A commonly-taken causal view in graph invariant learning suggests that stable predictive features of graphs are causally associated with labels, whereas varying environmental features lead to distribution shifts. In particular, covariate shifts caused by unseen environments in test graphs underscore the critical need for out-of-distribution (OOD) generalization. Existing graph augmentation methods designed to address the covariate shift often disentangle the stable and environmental features in the input space, and selectively perturb or mixup the environmental features. However, such perturbation-based methods heavily rely on an accurate separation of stable and environmental features, and their exploration ability is confined to existing environmental features in the training distribution. To overcome these limitations, we introduce a novel distributional augmentation approach enabled by a tailored score-based conditional graph generation strategies to explore and synthesize unseen environments while preserving the validity and stable features of overall graph patterns. Our comprehensive empirical evaluations demonstrate the enhanced effectiveness of our method in improving graph OOD generalization.
Authors: Jason Brown, Bohan Chen, Harris Hardiman-Mostow, Jeff Calder, Andrea L. Bertozzi
Abstract: Standard deep learning architectures used for classification generate label predictions with a projection head and softmax activation function. Although successful, these methods fail to leverage the relational information between samples for generating label predictions. In recent works, graph-based learning techniques, namely Laplace learning, have been heuristically combined with neural networks for both supervised and semi-supervised learning (SSL) tasks. However, prior works approximate the gradient of the loss function with respect to the graph learning algorithm or decouple the processes; end-to-end integration with neural networks is not achieved. In this work, we derive backpropagation equations, via the adjoint method, for inclusion of a general family of graph learning layers into a neural network. The resulting method, distinct from graph neural networks, allows us to precisely integrate similarity graph construction and graph Laplacian-based label propagation into a neural network layer, replacing a projection head and softmax activation function for general classification task. Our experimental results demonstrate smooth label transitions across data, improved generalization and robustness to adversarial attacks, and improved training dynamics compared to a standard softmax-based approach.
Authors: Jonathan Wensh{\o}j, Bob Pepin, Raghavendra Selvan
Abstract: We challenge the prevailing view that weight oscillations observed during Quantization Aware Training (QAT) are merely undesirable side-effects and argue instead that they are an essential part of QAT. We show in a univariate linear model that QAT results in an additional loss term that causes oscillations by pushing weights away from their nearest quantization level. Based on the mechanism from the analysis, we then derive a regularizer that induces oscillations in the weights of neural networks during training. Our empirical results on ResNet-18 and Tiny Vision Transformer, evaluated on CIFAR-10 and Tiny ImageNet datasets, demonstrate across a range of quantization levels that training with oscillations followed by post-training quantization (PTQ) is sufficient to recover the performance of QAT in most cases. With this work we provide further insight into the dynamics of QAT and contribute a novel insight into explaining the role of oscillations in QAT which until now have been considered to have a primarily negative effect on quantization.
Authors: Junghwan Lee, Chen Xu, Yao Xie
Abstract: Time series prediction underpins a broad range of downstream tasks across many scientific domains. Recent advances and increasing adoption of black-box machine learning models for time series prediction highlight the critical need for reliable uncertainty quantification. While conformal prediction has gained attention as a reliable uncertainty quantification method, conformal prediction for time series faces two key challenges: (1) adaptively leveraging correlations in features and non-conformity scores to overcome the exchangeability assumption, and (2) constructing prediction sets for multi-dimensional outcomes. To address these challenges jointly, we propose a novel conformal prediction method for time series using flow with classifier-free guidance. We provide coverage guarantees by establishing exact non-asymptotic marginal coverage and a finite-sample bound on conditional coverage for the proposed method. Evaluations on real-world time series datasets demonstrate that our method constructs significantly smaller prediction sets than existing conformal prediction methods while maintaining target coverage.
Authors: Xiaohuan Li, Shaowen Qin, Xin Tang, Jiawen Kang, Jin Ye, Zhonghua Zhao, Yusi Zheng, Dusit Niyato
Abstract: The Industrial Internet of Things (IIoT) leverages Federated Learning (FL) for distributed model training while preserving data privacy, and meta-computing enhances FL by optimizing and integrating distributed computing resources, improving efficiency and scalability. Efficient IIoT operations require a trade-off between model quality and training latency. Consequently, a primary challenge of FL in IIoT is to optimize overall system performance by balancing model quality and training latency. This paper designs a satisfaction function that accounts for data size, Age of Information (AoI), and training latency for meta-computing. Additionally, the satisfaction function is incorporated into the utility function to incentivize IIoT nodes to participate in model training. We model the utility functions of servers and nodes as a two-stage Stackelberg game and employ a deep reinforcement learning approach to learn the Stackelberg equilibrium. This approach ensures balanced rewards and enhances the applicability of the incentive scheme for IIoT. Simulation results demonstrate that, under the same budget constraints, the proposed incentive scheme improves utility by at least 23.7% compared to existing FL schemes without compromising model accuracy.
Authors: Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng
Abstract: Proper learning refers to the setting in which learners must emit predictors in the underlying hypothesis class $H$, and often leads to learners with simple algorithmic forms (e.g. empirical risk minimization (ERM), structural risk minimization (SRM)). The limitation of proper learning, however, is that there exist problems which can only be learned improperly, e.g. in multiclass classification. Thus, we ask: Under what assumptions on the hypothesis class or the information provided to the learner is a problem properly learnable? We first demonstrate that when the unlabeled data distribution is given, there always exists an optimal proper learner governed by distributional regularization, a randomized generalization of regularization. We refer to this setting as the distribution-fixed PAC model, and continue to evaluate the learner on its worst-case performance over all distributions. Our result holds for all metric loss functions and any finite learning problem (with no dependence on its size). Further, we demonstrate that sample complexities in the distribution-fixed PAC model can shrink by only a logarithmic factor from the classic PAC model, strongly refuting the role of unlabeled data in PAC learning (from a worst-case perspective). We complement this with impossibility results which obstruct any characterization of proper learnability in the realizable PAC model. First, we observe that there are problems whose proper learnability is logically undecidable, i.e., independent of the ZFC axioms. We then show that proper learnability is not a monotone property of the underlying hypothesis class, and that it is not a local property (in a precise sense). Our impossibility results all hold even for the fundamental setting of multiclass classification, and go through a reduction of EMX learning (Ben-David et al., 2019) to proper classification which may be of independent interest.
Authors: Robert Dilworth
Abstract: Machine Learning models thrive on vast datasets, continuously adapting to provide accurate predictions and recommendations. However, in an era dominated by privacy concerns, Machine Unlearning emerges as a transformative approach, enabling the selective removal of data from trained models. This paper examines methods such as Naive Retraining and Exact Unlearning via the SISA framework, evaluating their Computational Costs, Consistency, and feasibility using the $\texttt{HSpam14}$ dataset. We explore the potential of integrating unlearning principles into Positive Unlabeled (PU) Learning to address challenges posed by partially labeled datasets. Our findings highlight the promise of unlearning frameworks like $\textit{DaRE}$ for ensuring privacy compliance while maintaining model performance, albeit with significant computational trade-offs. This study underscores the importance of Machine Unlearning in achieving ethical AI and fostering trust in data-driven systems.
Authors: Yuhan Jing, Jingyu Wang, Lei Zhang, Haifeng Sun, Bo He, Zirui Zhuang, Chengsen Wang, Qi Qi, Jianxin Liao
Abstract: With the growing adoption of time-series anomaly detection (TAD) technology, numerous studies have employed deep learning-based detectors to analyze time-series data in the fields of Internet services, industrial systems, and sensors. The selection and optimization of anomaly detectors strongly rely on the availability of an effective evaluation for TAD performance. Since anomalies in time-series data often manifest as a sequence of points, conventional metrics that solely consider the detection of individual points are inadequate. Existing TAD evaluators typically employ point-based or event-based metrics to capture the temporal context. However, point-based evaluators tend to overestimate detectors that excel only in detecting long anomalies, while event-based evaluators are susceptible to being misled by fragmented detection results. To address these limitations, we propose OIPR (Operator Interest-based Precision and Recall metrics), a novel TAD evaluator with area-based metrics. It models the process of operators receiving detector alarms and handling anomalies, utilizing area under the operator interest curve to evaluate TAD performance. Furthermore, we build a special scenario dataset to compare the characteristics of different evaluators. Through experiments conducted on the special scenario dataset and five real-world datasets, we demonstrate the remarkable performance of OIPR in extreme and complex scenarios. It achieves a balance between point and event perspectives, overcoming their primary limitations and offering applicability to broader situations.
Authors: Qi Xu, Annie Qu
Abstract: In the era of big data, large-scale, multi-source, multi-modality datasets are increasingly ubiquitous, offering unprecedented opportunities for predictive modeling and scientific discovery. However, these datasets often exhibit complex heterogeneity, such as covariates shift, posterior drift, and blockwise missingness, which worsen predictive performance of existing supervised learning algorithms. To address these challenges simultaneously, we propose a novel Representation Retrieval (R2) framework, which integrates a dictionary of representation learning modules (representer dictionary) with data source-specific sparsity-induced machine learning model (learners). Under the R2 framework, we introduce the notion of integrativeness for each representer, and propose a novel Selective Integration Penalty (SIP) to explicitly encourage more integrative representers to improve predictive performance. Theoretically, we show that the excess risk bound of the R2 framework is characterized by the integrativeness of representers, and SIP effectively improves the excess risk. Extensive simulation studies validate the superior performance of R2 framework and the effect of SIP. We further apply our method to two real-world datasets to confirm its empirical success.
Authors: Xiaolong Yin, Xingyu Lu, Jiahang Shen, Jingzhe Ni, Hailong Li, Ruofeng Tong, Min Tang, Peng Du
Abstract: A CAD command sequence is a typical parametric design paradigm in 3D CAD systems where a model is constructed by overlaying 2D sketches with operations such as extrusion, revolution, and Boolean operations. Although there is growing academic interest in the automatic generation of command sequences, existing methods and datasets only support operations such as 2D sketching, extrusion,and Boolean operations. This limitation makes it challenging to represent more complex geometries. In this paper, we present a reinforcement learning (RL) training environment (gym) built on a CAD geometric engine. Given an input boundary representation (B-Rep) geometry, the policy network in the RL algorithm generates an action. This action, along with previously generated actions, is processed within the gym to produce the corresponding CAD geometry, which is then fed back into the policy network. The rewards, determined by the difference between the generated and target geometries within the gym, are used to update the RL network. Our method supports operations beyond sketches, Boolean, and extrusion, including revolution operations. With this training gym, we achieve state-of-the-art (SOTA) quality in generating command sequences from B-Rep geometries.
Authors: Ali Eslamian, Alireza Afzal Aghaei, Qiang Cheng
Abstract: Tabular data analysis presents unique challenges that arise from heterogeneous feature types, missing values, and complex feature interactions. While traditional machine learning methods like gradient boosting often outperform deep learning, recent advancements in neural architectures offer promising alternatives. In this study, we introduce TabKAN, a novel framework for tabular data modeling based on Kolmogorov-Arnold Networks (KANs). Unlike conventional deep learning models, KANs use learnable activation functions on edges, which improves both interpretability and training efficiency. TabKAN incorporates modular KAN-based architectures designed for tabular analysis and proposes a transfer learning framework for knowledge transfer across domains. Furthermore, we develop a model-specific interpretability approach that reduces reliance on post hoc explanations. Extensive experiments on public datasets show that TabKAN achieves superior performance in supervised learning and significantly outperforms classical and Transformer-based models in binary and multi-class classification. The results demonstrate the potential of KAN-based architectures to bridge the gap between traditional machine learning and deep learning for structured data.
Authors: Yuxuan Shu, Vasileios Lampos
Abstract: Multivariable time series forecasting methods can integrate information from exogenous variables, leading to significant prediction accuracy gains. The transformer architecture has been widely applied in various time series forecasting models due to its ability to capture long-range sequential dependencies. However, a na\"ive application of transformers often struggles to effectively model complex relationships among variables over time. To mitigate against this, we propose a novel architecture, termed Spectral Operator Neural Network (Sonnet). Sonnet applies learnable wavelet transformations to the input and incorporates spectral analysis using the Koopman operator. Its predictive skill relies on the Multivariable Coherence Attention (MVCA), an operation that leverages spectral coherence to model variable dependencies. Our empirical analysis shows that Sonnet yields the best performance on $34$ out of $47$ forecasting tasks with an average mean absolute error (MAE) reduction of $2.2\%$ against the most competitive baseline. We further show that MVCA can remedy the deficiencies of na\"ive attention in various deep learning models, reducing MAE by $10.7\%$ on average in the most challenging forecasting tasks.
Authors: Jianhao Ma, Geyu Liang, Salar Fattahi
Abstract: Implicit regularization refers to the tendency of local search algorithms to converge to low-dimensional solutions, even when such structures are not explicitly enforced. Despite its ubiquity, the mechanism underlying this behavior remains poorly understood, particularly in over-parameterized settings. We analyze gradient descent dynamics and identify three conditions under which it converges to second-order stationary points within an implicit low-dimensional region: (i) suitable initialization, (ii) efficient escape from saddle points, and (iii) sustained proximity to the region. We show that these can be achieved through infinitesimal perturbations and a small deviation rate. Building on this, we introduce Infinitesimally Perturbed Gradient Descent (IPGD), which satisfies these conditions under mild assumptions. We provide theoretical guarantees for IPGD in over-parameterized matrix sensing and empirical evidence of its broader applicability.
Authors: Mahdi Pourmirzaei, Farzaneh Esmaili, Salhuldin Alqarghuli, Mohammadreza Pourmirzaei, Ye Han, Kai Chen, Mohsen Rezaei, Duolin Wang, Dong Xu
Abstract: The diverse nature of protein prediction tasks has traditionally necessitated specialized models, hindering the development of broadly applicable and computationally efficient Protein Language Models (PLMs). In this work, we introduce Prot2Token, a unified framework that overcomes these challenges by converting a wide spectrum of protein-related predictions-from sequence-level properties and residue-specific attributes to complex inter-protein interactions-into a standardized next-token prediction format. At its core, Prot2Token employs an autoregressive decoder, conditioned on embeddings from pre-trained protein encoders and guided by learnable task tokens, to perform diverse predictions. This architecture uniquely facilitates multi-task learning, enabling general-purpose decoders to generalize across five distinct categories. We present extensive experimental validation across a variety of benchmarks, demonstrating Prot2Token's predictive power in different types of protein-prediction tasks. In 3D structure prediction, Prot2Token delivers substantial speedups (up to 1000x faster than AlphaFold2 with MSA on the same hardware) while, across other numerous tasks, matching or surpassing specialized methods. Beyond that, we introduce an auxiliary self-supervised decoder pre-training approach to improve spatially sensitive task performance. Prot2Token thus offers a step towards standardizing biological prediction into a generative interface, promising to accelerate biological discovery and the development of novel therapeutics. The code is available at https://github.com/mahdip72/prot2token .
Authors: Mingyue Cheng, Jiahao Wang, Daoyu Wang, Xiaoyu Tao, Qi Liu, Enhong Chen
Abstract: Time series forecasting (TSF) is a fundamental and widely studied task, spanning methods from classical statistical approaches to modern deep learning and multimodal language modeling. Despite their effectiveness, these methods often follow a fast thinking paradigm emphasizing pattern extraction and direct value mapping, while overlooking explicit reasoning over temporal dynamics and contextual dependencies. Meanwhile, emerging slow-thinking LLMs (e.g., ChatGPT-o1, DeepSeek-R1) have demonstrated impressive multi-step reasoning capabilities across diverse domains, suggesting a new opportunity for reframing TSF as a structured reasoning task. This motivates a key question: can slow-thinking LLMs effectively reason over temporal patterns to support time series forecasting, even in zero-shot manner? To investigate this, in this paper, we propose TimeReasoner, an extensive empirical study that formulates TSF as a conditional reasoning task. We design a series of prompting strategies to elicit inference-time reasoning from pretrained slow-thinking LLMs and evaluate their performance across diverse TSF benchmarks. Our findings reveal that slow-thinking LLMs exhibit non-trivial zero-shot forecasting capabilities, especially in capturing high-level trends and contextual shifts. While preliminary, our study surfaces important insights into the reasoning behaviors of LLMs in temporal domains highlighting both their potential and limitations. We hope this work catalyzes further research into reasoning-based forecasting paradigms and paves the way toward more interpretable and generalizable TSF frameworks.
Authors: Alexander Semenenko, Ivan Butakov, Alexey Frolov, Ivan Oseledets
Abstract: Sliced Mutual Information (SMI) is widely used as a scalable alternative to mutual information for measuring non-linear statistical dependence. Despite its advantages, such as faster convergence, robustness to high dimensionality, and nullification only under statistical independence, we demonstrate that SMI is highly susceptible to data manipulation and exhibits counterintuitive behavior. Through extensive benchmarking and theoretical analysis, we show that SMI saturates easily, fails to detect increases in statistical dependence, prioritizes redundancy over informative content, and in some cases, performs worse than correlation coefficient.
Authors: Anand Ganesh, Babhrubahan Bose, Anand Rajagopalan
Abstract: We construct four Schauder bases for the space $C[0,1]$, one using ReLU functions, another using Softplus functions, and two more using sigmoidal versions of the ReLU and Softplus functions. This establishes the existence of a basis using these functions for the first time, and improves on the universal approximation property associated with them. We also show an $O(\frac{1}{n})$ approximation bound based on our ReLU basis, and a negative result on constructing multivariate functions using finite combinations of ReLU functions.
Authors: Mohammad Emtiyaz Khan
Abstract: Adaptation is the holy grail of intelligence, but even the best AI models lack the adaptability of toddlers. In spite of great progress, little is known about the mechanisms by which machines can learn to adapt as fast as humans and animals. Here, we cast adaptation as `correction' of old posteriors and show that a wide-variety of existing adaptation methods follow this very principle, including those used for continual learning, federated learning, unlearning, and model merging. In all these settings, more accurate posteriors often lead to smaller corrections and can enable faster adaptation. Posterior correction is derived by using the dual representation of the Bayesian Learning Rule of Khan and Rue (2023), where the interference between the old representation and new information is quantified by using the natural-gradient mismatch. We present many examples demonstrating how machines can learn to adapt quickly by using posterior correction.
Authors: Salva R\"uhling Cachay, Miika Aittala, Karsten Kreis, Noah Brenowitz, Arash Vahdat, Morteza Mardani, Rose Yu
Abstract: Diffusion models are a powerful tool for probabilistic forecasting, yet most applications in high-dimensional complex systems predict future states individually. This approach struggles to model complex temporal dependencies and fails to explicitly account for the progressive growth of uncertainty inherent to the systems. While rolling diffusion frameworks, which apply increasing noise to forecasts at longer lead times, have been proposed to address this, their integration with state-of-the-art, high-fidelity diffusion techniques remains a significant challenge. We tackle this problem by introducing Elucidated Rolling Diffusion Models (ERDM), the first framework to successfully unify a rolling forecast structure with the principled, performant design of Elucidated Diffusion Models (EDM). To do this, we adapt the core EDM components-its noise schedule, network preconditioning, and Heun sampler-to the rolling forecast setting. The success of this integration is driven by three key contributions: (i) a novel loss weighting scheme that focuses model capacity on the mid-range forecast horizons where determinism gives way to stochasticity; (ii) an efficient initialization strategy using a pre-trained EDM for the initial window; and (iii) a bespoke hybrid sequence architecture for robust spatiotemporal feature extraction under progressive denoising. On 2D Navier-Stokes simulations and ERA5 global weather forecasting at 1.5-degree resolution, ERDM consistently outperforms key diffusion-based baselines, including conditional autoregressive EDM. ERDM offers a flexible and powerful general framework for tackling diffusion-based dynamics forecasting problems where modeling uncertainty propagation is paramount.
Authors: Xingyu Su, Xiner Li, Yuchao Lin, Ziqian Xie, Degui Zhi, Shuiwang Ji
Abstract: We consider controllable DNA sequence design, where sequences are generated by conditioning on specific biological properties. While language models (LMs) such as GPT and BERT have achieved remarkable success in natural language generation, their application to DNA sequence generation remains largely underexplored. In this work, we introduce ATGC-Gen, an Automated Transformer Generator for Controllable Generation, which leverages cross-modal encoding to integrate diverse biological signals. ATGC-Gen is instantiated with both decoder-only and encoder-only transformer architectures, allowing flexible training and generation under either autoregressive or masked recovery objectives. We evaluate ATGC-Gen on representative tasks including promoter and enhancer sequence design, and further introduce a new dataset based on ChIP-Seq experiments for modeling protein binding specificity. Our experiments demonstrate that ATGC-Gen can generate fluent, diverse, and biologically relevant sequences aligned with the desired properties. Compared to prior methods, our model achieves notable improvements in controllability and functional relevance, highlighting the potential of language models in advancing programmable genomic design. The source code is released at (https://github.com/divelab/AIRS/blob/main/OpenBio/ATGC_Gen).
URLs: https://github.com/divelab/AIRS/blob/main/OpenBio/ATGC_Gen).
Authors: Federico Zucchi, Thomas Lampert
Abstract: Multivariate time series classification supports applications from wearable sensing to biomedical monitoring and demands models that can capture both short-term patterns and longer-range temporal dependencies. Despite recent advances, Transformer and CNN models often remain computationally heavy and rely on many parameters. This work presents PRISM(Per-channel Resolution Informed Symmetric Module), a lightweight fully convolutional classifier. Operating in a channel-independent manner, in its early stage it applies a set of multi-resolution symmetric convolutional filters. This symmetry enforces structural constraints inspired by linear-phase FIR filters from classical signal processing, effectively halving the number of learnable parameters within the initial layers while preserving the full receptive field. Across the diverse UEA multivariate time-series archive as well as specific benchmarks in human activity recognition, sleep staging, and biomedical signals, PRISM matches or outperforms state-of-the-art CNN and Transformer models while using significantly fewer parameters and markedly lower computational cost. By bringing a principled signal processing prior into a modern neural architecture, PRISM offers an effective and computationally economical solution for multivariate time series classification.
Authors: Liyi Zhang, Jake Snell, Thomas L. Griffiths
Abstract: Fine-tuning large language models (LLMs) with low-rank adaptation (LoRA) is a cost-effective way to incorporate information from a specific dataset. However, it is often unclear how well the fine-tuned LLM will generalize, i.e., how well it will perform on unseen datasets. Methods have been proposed to improve generalization by optimizing in-context prompts, or by using meta-learning to fine-tune LLMs. However, these methods are expensive in memory and computation, requiring either long-context prompts or saving copies of parameters and using second-order gradient updates. To address these challenges, we propose Amortized Bayesian Meta-Learning for LoRA (ABMLL). This method builds on amortized Bayesian meta-learning for smaller models, adapting this approach to LLMs while maintaining its computational efficiency. We reframe task-specific and global parameters in the context of LoRA and use a new hyperparameter to balance reconstruction accuracy and the fidelity of task-specific parameters to the global ones. ABMLL provides effective generalization and scales to large models such as LLAMA3-8B. Furthermore, as a result of using a Bayesian framework, ABMLL provides improved uncertainty quantification. We test ABMLL on CrossFit and Unified-QA datasets and find that it outperforms existing methods on these benchmarks in terms of both accuracy and expected calibration error.
Authors: Jialin Wu, Shreya Saha, Yiqing Bo, Meenakshi Khosla
Abstract: Representational similarity metrics are fundamental tools in neuroscience and AI, yet we lack systematic comparisons of their discriminative power across model families. We introduce a quantitative framework to evaluate representational similarity measures based on their ability to separate model families-across architectures (CNNs, Vision Transformers, Swin Transformers, ConvNeXt) and training regimes (supervised vs. self-supervised). Using three complementary separability measures-dprime from signal detection theory, silhouette coefficients and ROC-AUC, we systematically assess the discriminative capacity of commonly used metrics including RSA, linear predictivity, Procrustes, and soft matching. We show that separability systematically increases as metrics impose more stringent alignment constraints. Among mapping-based approaches, soft-matching achieves the highest separability, followed by Procrustes alignment and linear predictivity. Non-fitting methods such as RSA also yield strong separability across families. These results provide the first systematic comparison of similarity metrics through a separability lens, clarifying their relative sensitivity and guiding metric choice for large-scale model and brain comparisons.
Authors: Santosh Patapati
Abstract: When different objectives conflict with each other in multi-task learning, gradients begin to interfere and slow convergence, thereby potentially reducing the final model's performance. To address this, we introduce SON-GOKU, a scheduler that computes gradient interference, constructs an interference graph, and then applies greedy graph-coloring to partition tasks into groups that align well with each other. At each training step, only one group (color class) of tasks are activated, and the grouping partition is constantly recomputed as task relationships evolve throughout training. By ensuring that each mini-batch contains only tasks that pull the model in the same direction, our method improves the effectiveness of any underlying multi-task learning optimizer without additional tuning. Since tasks within these groups will update in compatible directions, multi-task learning will improve model performance rather than impede it. Empirical results on six different datasets show that this interference-aware graph-coloring approach consistently outperforms baselines and state-of-the-art multi-task optimizers. We provide extensive theory showing why grouping and sequential updates improve multi-task learning, with guarantees on descent, convergence, and accurately identifying what tasks conflict or align.
Authors: Robert Parker, Oscar Dowson, Nicole LoGiudice, Manuel Garcia, Russell Bent
Abstract: We propose a reduced-space formulation for optimizing over trained neural networks where the network's outputs and derivatives are evaluated on a GPU. To do this, we treat the neural network as a "gray box" where intermediate variables and constraints are not exposed to the optimization solver. Compared to the full-space formulation, in which intermediate variables and constraints are exposed to the optimization solver, the reduced-space formulation leads to faster solves and fewer iterations in an interior point method. We demonstrate the benefits of this method on two optimization problems: Adversarial generation for a classifier trained on MNIST images and security-constrained optimal power flow with transient feasibility enforced using a neural network surrogate.
Authors: Lo\"ic Cabannes, Maximilian Beck, Gergely Szilvasy, Matthijs Douze, Maria Lomeli, Jade Copet, Pierre-Emmanuel Mazar\'e, Gabriel Synnaeve, Herv\'e J\'egou
Abstract: Recent works show that hybrid architectures combining sliding window softmax attention layers with linear recurrent neural network (RNN) layers outperform both of these architectures taken separately. However, the impact of the window length and the interplay between softmax attention and linear RNN layers remain under-studied. In this work, we introduce SWAX, a hybrid architecture consisting of sliding-window attention and xLSTM linear RNN layers. A counter-intuitive finding with SWAX is that larger sliding windows do not improve the long-context performance. In fact, short window attention encourages the model to better train the long-term memory of the xLSTM, by relying less on the softmax attention mechanism for long context-retrieval. The issue with small sliding windows is that they are detrimental for short-context tasks, which could be solved with information from moderately larger sliding windows otherwise. Therefore, we train SWAX by stochastically changing the sliding window size, forcing the model to leverage both a longer context window and the xLSTM memory. SWAX trained with stochastic window sizes significantly outperforms regular window attention both on short and long-context problems.
Authors: Yizhuo Ding, Wanying Qu, Jiawei Geng, Wenqi Shao, Yanwei Fu
Abstract: Large Language Models (LLMs) achieve strong performance across diverse tasks but face prohibitive computational and memory costs. Pruning offers a promising path by inducing sparsity while preserving architectural flexibility. However, existing methods struggle to balance efficiency and robustness: local metric approaches prune layer by layer but often collapse under high sparsity, whereas global feedback methods enforce consistency at the cost of expensive weight updates or restrictive semi-structured formats. We present UniPruning, a unified post-training pruning framework that combines the speed of local saliency metrics with the stability of global coordination, enabled by a mirror descent based optimization, all without updating model weights. UniPruning leverages fast layer-wise scoring and a lightweight global controller to allocate a single sparsity budget, supporting both unstructured and semi-structured N :M pruning within one framework. After a brief calibration, it can generate pruning masks for arbitrary sparsity levels in one shot, and adapts seamlessly to hardware-aware constraints. Extensive experiments on multiple pretrained LLM families and standard benchmarks show that UniPruning consistently delivers competitive or superior perplexity and zero-shot accuracy. Ablation studies further highlight the importance of mirror descent and local saliency anchoring. Overall, UniPruning provides an efficient, principled, and scalable solution for sparsifying large-scale LLMs. Our code is available at: https://github.com/RainbowQTT/UniPruning.
Authors: Ziyi Chen, Junyi Li, Peiran Yu, Heng Huang
Abstract: Reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO) are important techniques to align large language models (LLM) with human preference. However, the quality of RLHF and DPO training is seriously compromised by \textit{\textbf{C}orrupted} preference, reward \textit{\textbf{O}veroptimization}, and bias towards \textit{\textbf{V}erbosity}. To our knowledge, most existing works tackle only one of these important issues, and the few other works require much computation to estimate multiple reward models and lack theoretical guarantee of generalization ability. In this work, we propose RLHF-\textbf{COV} and DPO-\textbf{COV} algorithms that can simultaneously mitigate these three issues, in both offline and online settings. This ability is theoretically demonstrated by obtaining length-regularized generalization error rates for our DPO-COV algorithms trained on corrupted data, which match the best-known rates for simpler cases with clean data and without length regularization. Moreover, our DPO-COV algorithm is simple to implement without reward estimation, and is proved to be equivalent to our RLHF-COV algorithm, which directly implies the equivalence between the vanilla RLHF and DPO algorithms. Experiments demonstrate the effectiveness of our DPO-COV algorithms under both offline and online settings.
Authors: Rui Liu, Tao Zhe, Yanjie Fu, Feng Xia, Ted Senator, Dongjie Wang
Abstract: Feature selection eliminates redundancy among features to improve downstream task performance while reducing computational overhead. Existing methods often struggle to capture intricate feature interactions and adapt across diverse application scenarios. Recent advances employ generative intelligence to alleviate these drawbacks. However, these methods remain constrained by permutation sensitivity in embedding and reliance on convexity assumptions in gradient-based search. To address these limitations, our initial work introduces a novel framework that integrates permutation-invariant embedding with policy-guided search. Although effective, it still left opportunities to adapt to realistic distributed scenarios. In practice, data across local clients is highly imbalanced, heterogeneous and constrained by strict privacy regulations, limiting direct sharing. These challenges highlight the need for a framework that can integrate feature selection knowledge across clients without exposing sensitive information. In this extended journal version, we advance the framework from two perspectives: 1) developing a privacy-preserving knowledge fusion strategy to derive a unified representation space without sharing sensitive raw data. 2) incorporating a sample-aware weighting strategy to address distributional imbalance among heterogeneous local clients. Extensive experiments validate the effectiveness, robustness, and efficiency of our framework. The results further demonstrate its strong generalization ability in federated learning scenarios. The code and data are publicly available: https://anonymous.4open.science/r/FedCAPS-08BF.
Authors: Rui Bu, Haofeng Zhong, Wenzheng Chen, Yangyan Li
Abstract: Large models based on the Transformer architecture are susceptible to extreme-token phenomena, such as attention sinks and value-state drains. These issues, which degrade model performance, quantization fidelity, and interpretability, arise from a problematic mutual reinforcement mechanism where the model learns an inefficient 'no-op' behavior by focusing attention on tokens with near-zero value states. In this paper, we propose Value-State Gated Attention (VGA), a simple, dedicated, and stable architectural mechanism for performing 'no-op' attention efficiently by directly breaking this cycle. VGA introduces a learnable, data-dependent gate, computed directly from the value vectors (V), to modulate the output. Through a theoretical analysis of the underlying gradients, we show that gating the value-state with a function of itself is more effective at decoupling value and attention score updates than prior methods that gate on input embeddings. This creates a direct regulatory pathway that allows the model to suppress a token's contribution based on its emergent value representation. Our experiments demonstrate that VGA significantly mitigates the formation of attention sinks and stabilizes value-state norms, leading to improved performance, robust quantization fidelity, and enhanced model interpretability.
Authors: Jingyu Xing, Chenwei Tang, Xinyu Liu, Deng Xiong, Shudong Huang, Wei Ju, Jiancheng Lv, Ziyue Qiao
Abstract: Reinforcement Learning (RL) has emerged as a powerful paradigm for advancing Large Language Models (LLMs), achieving remarkable performance in complex reasoning domains such as mathematics and code generation. However, current RL methods face a fundamental scalability bottleneck due to their heavy reliance on human-curated preference data or labeled datasets for reward modeling. To overcome this limitation, we explore RL on unlabeled data where models learn autonomously from continuous experience streams. The core challenge in this setting lies in reliable reward estimation without ground-truth supervision. Existing approaches like Test-Time RL address this through self-consistent consensus, but risk reinforcing incorrect pseudo-labels derived from majority voting. We introduce COMPASS (Composite Path and Answer Self-Scoring), a novel test-time reward mechanism that operates without external supervision. COMPASS integrates two complementary components: the Dual-Calibration Answer Reward (DCAR), which stabilizes training by establishing trustworthy pseudo-labels through confidence and credibility calibration, and the Decisive Path Reward (DPR), which directly optimizes the reasoning process quality beyond mere outcome supervision. By jointly reinforcing trustworthy consensus answers and highly decisive reasoning chains, the COMPASS systematically enhances the model's analytical capabilities. Extensive experiments show that COMPASS achieves significant and consistent performance gains across diverse reasoning tasks and model architectures, advancing a more scalable direction for LLMs to learn from continuous experience.
Authors: Zhao Yu, Xiuping Wu, Liangjun Ke
Abstract: Reinforcement learning (RL) has been recognized as a powerful tool for robot control tasks. RL typically employs reward functions to define task objectives and guide agent learning. However, since the reward function serves the dual purpose of defining the optimal goal and guiding learning, it is challenging to design the reward function manually, which often results in a suboptimal task representation. To tackle the reward design challenge in RL, inspired by the satisficing theory, we propose a Test-driven Reinforcement Learning (TdRL) framework. In the TdRL framework, multiple test functions are used to represent the task objective rather than a single reward function. Test functions can be categorized as pass-fail tests and indicative tests, each dedicated to defining the optimal objective and guiding the learning process, respectively, thereby making defining tasks easier. Building upon such a task definition, we first prove that if a trajectory return function assigns higher returns to trajectories closer to the optimal trajectory set, maximum entropy policy optimization based on this return function will yield a policy that is closer to the optimal policy set. Then, we introduce a lexicographic heuristic approach to compare the relative distance relationship between trajectories and the optimal trajectory set for learning the trajectory return function. Furthermore, we develop an algorithm implementation of TdRL. Experimental results on the DeepMind Control Suite benchmark demonstrate that TdRL matches or outperforms handcrafted reward methods in policy training, with greater design simplicity and inherent support for multi-objective optimization. We argue that TdRL offers a novel perspective for representing task objectives, which could be helpful in addressing the reward design challenges in RL applications.
Authors: Casper L. Christensen, Logan Riggs
Abstract: Recent work in mechanistic interpretability has shown that decomposing models in parameter space may yield clean handles for analysis and intervention. Previous methods have demonstrated successful applications on a wide range of toy models, but the gap to "real models" has not yet been bridged. In this work, we extend Stochastic Parameter Decomposition (SPD) to Transformer models, proposing an updated causal importance function suited for sequential data and a new loss function. We demonstrate that SPD can successfully decompose a toy induction-head model and recover the expected 2-step circuit. We also show that applying SPD to GPT-2-small can successfully locate subcomponents corresponding to interpretable concepts like "golf" and "basketball". These results take the first step in the direction of extending SPD to modern models, and show that we can use the method to surface interpretable parameter-space mechanisms.
Authors: Zhenshuo Zhang, Minxuan Duan, Youran Ye, Hongyang R. Zhang
Abstract: We study the problem of efficiently estimating policies that simultaneously optimize multiple objectives in reinforcement learning (RL). Given $n$ objectives (or tasks), we seek the optimal partition of these objectives into $k \ll n$ groups, where each group comprises related objectives that can be trained together. This problem arises in applications such as robotics, control, and preference optimization in language models, where learning a single policy for all $n$ objectives is suboptimal as $n$ grows. We introduce a two-stage procedure -- meta-training followed by fine-tuning -- to address this problem. We first learn a meta-policy for all objectives using multitask learning. Then, we adapt the meta-policy to multiple randomly sampled subsets of objectives. The adaptation step leverages a first-order approximation property of well-trained policy networks, which is empirically verified to be accurate within a 2% error margin across various RL environments. The resulting algorithm, PolicyGradEx, efficiently estimates an aggregate task-affinity score matrix given a policy evaluation algorithm. Based on the estimated affinity score matrix, we cluster the $n$ objectives into $k$ groups by maximizing the intra-cluster affinity scores. Experiments on three robotic control and the Meta-World benchmarks demonstrate that our approach outperforms state-of-the-art baselines by 16% on average, while delivering up to $26\times$ faster speedup relative to performing full training to obtain the clusters. Ablation studies validate each component of our approach. For instance, compared with random grouping and gradient-similarity-based grouping, our loss-based clustering yields an improvement of 19%. Finally, we analyze the generalization error of policy networks by measuring the Hessian trace of the loss surface, which gives non-vacuous measures relative to the observed generalization errors.
Authors: Kaichi Irie, Shuhei Watanabe, Masaki Onishi
Abstract: Bayesian optimization (BO) efficiently finds high-performing parameters by maximizing an acquisition function, which models the promise of parameters. A major computational bottleneck arises in acquisition function optimization, where multi-start optimization (MSO) with quasi-Newton (QN) methods is required due to the non-convexity of the acquisition function. BoTorch, a widely used BO library, currently optimizes the summed acquisition function over multiple points, leading to the speedup of MSO owing to PyTorch batching. Nevertheless, this paper empirically demonstrates the suboptimality of this approach in terms of off-diagonal approximation errors in the inverse Hessian of a QN method, slowing down its convergence. To address this problem, we propose to decouple QN updates using a coroutine while batching the acquisition function calls. Our approach not only yields the theoretically identical convergence to the sequential MSO but also drastically reduces the wall-clock time compared to the previous approaches. Our approach is available in GPSampler in Optuna, effectively reducing its computational overhead.
Authors: Nicolas M. Cuadrado A., Mohannad Takrouri, Ji\v{r}\'i N\v{e}me\v{c}ek, Martin Tak\'a\v{c}, Jakub Mare\v{c}ek
Abstract: Investment planning in power utilities, such as generation and transmission expansion, requires decade-long forecasts under profound uncertainty. Forecasting of energy mix and energy use decades ahead is nontrivial. Classical approaches focus on generating a finite number of scenarios (modeled as a mixture of Diracs in statistical theory terms), which limits insight into scenario-specific volatility and hinders robust decision-making. We propose an alternative using tractable probabilistic models (TPMs), particularly sum-product networks (SPNs). These models enable exact, scalable inference of key quantities such as scenario likelihoods, marginals, and conditional probabilities, supporting robust scenario expansion and risk assessment. This framework enables direct embedding of chance-constrained optimization into investment planning, enforcing safety or reliability with prescribed confidence levels. TPMs allow both scenario analysis and volatility quantification by compactly representing high-dimensional uncertainties. We demonstrate the effectiveness of the approach through a representative power system planning case study, illustrating its computational and reliability advantages over traditional scenario-based models.
Authors: Jie Ou, Shuaihong Jiang, Yingjun Du, Cees G. M. Snoek
Abstract: Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, DoRA, and HiRA, enable lightweight adaptation of large pre-trained models via low-rank updates. However, existing PEFT approaches apply static, input-agnostic updates to all tokens, disregarding the varying importance and difficulty of different inputs. This uniform treatment can lead to overfitting on trivial content or under-adaptation on more informative regions, especially in autoregressive settings with distinct prefill and decoding dynamics. In this paper, we propose GateRA, a unified framework that introduces token-aware modulation to dynamically adjust the strength of PEFT updates. By incorporating adaptive gating into standard PEFT branches, GateRA enables selective, token-level adaptation, preserving pre-trained knowledge for well-modeled inputs while focusing capacity on challenging cases. Empirical visualizations reveal phase-sensitive behaviors, where GateRA automatically suppresses updates for redundant prefill tokens while emphasizing adaptation during decoding. To promote confident and efficient modulation, we further introduce an entropy-based regularization that encourages near-binary gating decisions. This regularization prevents diffuse update patterns and leads to interpretable, sparse adaptation without hard thresholding. Finally, we present a theoretical analysis showing that GateRA induces a soft gradient-masking effect over the PEFT path, enabling continuous and differentiable control over adaptation. Experiments on multiple commonsense reasoning benchmarks demonstrate that GateRA consistently outperforms or matches prior PEFT methods.
Authors: Kanav Arora, Girish Narayanswamy, Shwetak Patel, Richard Li
Abstract: Heart rate estimation from photoplethysmography (PPG) signals generated by wearable devices such as smartwatches and fitness trackers has significant implications for the health and well-being of individuals. Although prior work has demonstrated deep learning models with strong performance in the heart rate estimation task, in order to deploy these models on wearable devices, these models must also adhere to strict memory and latency constraints. In this work, we explore and characterize how large pre-trained PPG models may be distilled to smaller models appropriate for real-time inference on the edge. We evaluate four distillation strategies through comprehensive sweeps of teacher and student model capacities: (1) hard distillation, (2) soft distillation, (3) decoupled knowledge distillation (DKD), and (4) feature distillation. We present a characterization of the resulting scaling laws describing the relationship between model size and performance. This early investigation lays the groundwork for practical and predictable methods for building edge-deployable models for physiological sensing.
Authors: Ziyue Wang, Yayati Jadhav, Peter Pak, Amir Barati Farimani
Abstract: Mechanical design and manufacturing workflows conventionally begin with conceptual design, followed by the creation of a computer-aided design (CAD) model and fabrication through material-extrusion (MEX) printing. This process requires converting CAD geometry into machine-readable G-code through slicing and path planning. While each step is well established, dependence on CAD modeling remains a major bottleneck: constructing object-specific 3D geometry is slow and poorly suited to rapid prototyping. Even minor design variations typically necessitate manual updates in CAD software, making iteration time-consuming and difficult to scale. To address this limitation, we introduce Image2Gcode, an end-to-end data-driven framework that bypasses the CAD stage and generates printer-ready G-code directly from images and part drawings. Instead of relying on an explicit 3D model, a hand-drawn or captured 2D image serves as the sole input. The framework first extracts slice-wise structural cues from the image and then employs a denoising diffusion probabilistic model (DDPM) over G-code sequences. Through iterative denoising, the model transforms Gaussian noise into executable print-move trajectories with corresponding extrusion parameters, establishing a direct mapping from visual input to native toolpaths. By producing structured G-code directly from 2D imagery, Image2Gcode eliminates the need for CAD or STL intermediates, lowering the entry barrier for additive manufacturing and accelerating the design-to-fabrication cycle. This approach supports on-demand prototyping from simple sketches or visual references and integrates with upstream 2D-to-3D reconstruction modules to enable an automated pipeline from concept to physical artifact. The result is a flexible, computationally efficient framework that advances accessibility in design iteration, repair workflows, and distributed manufacturing.
Authors: Locke Cai, Ivan Provilkov
Abstract: Training Large Language Models (LLMs) to reason often relies on Reinforcement Learning (RL) with task-specific verifiers. However, many real-world reasoning-intensive tasks lack verifiers, despite offering abundant expert demonstrations that remain under-utilized for reasoning-focused training. We introduce RARO (Relativistic Adversarial Reasoning Optimization) that learns strong reasoning capabilities from only expert demonstrations via Inverse Reinforcement Learning. Our method sets up an adversarial game between a policy and a relativistic critic: the policy learns to mimic expert answers, while the critic aims to identify the experts among (expert, policy) answer pairs. Both the policy and the critic are trained jointly and continuously via RL, and we identify the key stabilization techniques required for robust learning. Empirically, RARO significantly outperforms strong verifier-free baselines on all of our evaluation tasks -- Countdown, DeepMath, and Poetry Writing -- and enjoys the same robust scaling trends as RL with verifiers. These results demonstrate that our method effectively elicits strong reasoning performance from expert demonstrations alone, enabling robust reasoning learning even when task-specific verifiers are unavailable.
Authors: Yuchen Zeng, Shuibai Zhang, Wonjun Kang, Shutong Wu, Lynnix Zou, Ying Fan, Heeju Kim, Ziqian Lin, Jungtaek Kim, Hyung Il Koo, Dimitris Papailiopoulos, Kangwook Lee
Abstract: Large Reasoning Models (LRMs) are Large Language Models (LLMs) explicitly trained to generate long-form Chain-of-Thoughts (CoTs), achieving impressive success on challenging tasks like math and programming. However, their underlying reasoning "algorithms" remain poorly understood. To investigate this, we propose ReJump, which represents a reasoning trace as a visitation order over nodes in a tree of intermediate problem-solving steps. Transitions between nodes, which we term jumps, include adjacent moves that capture behaviors such as calculation, and non-adjacent moves that capture behaviors such as backtracking and verification. ReJump enables analyzing LLM reasoning with diverse metrics that quantify exploration, exploitation, overthinking, forgetting, and verification. Using our proposed LLM agent to extract reasoning traces into ReJump format, we evaluate state-of-the-art LRMs on two tasks and find that models with similar accuracy can exhibit distinct reasoning behaviors, while different tasks favor different reasoning styles (e.g., varying balance between exploration and exploitation). To further understand how learning strategies shape reasoning, we use ReJump to compare distilled LRMs with their teachers, CoT-prompted LLMs with LRMs, and to examine how the number of reasoning examples and reinforcement learning affect reasoning behavior. Finally, we show that ReJump can improve reasoning quality at test time through strategies such as ReJump-guided Best-of-N selection and prompt selection. Our code is publicly available at https://github.com/UW-Madison-Lee-Lab/ReJump.
Authors: Dongseok Kim, Hyoungsun Choi, Mohamed Jismy Aashik Rasool, Gisung Oh
Abstract: We present CLAPS, a posterior-aware conformal regression method that pairs a Last-Layer Laplace Approximation with split-conformal calibration. From the resulting Gaussian posterior, CLAPS defines a simple two-sided posterior CDF score that aligns the conformity metric with the full predictive shape, not just a point estimate. This alignment yields narrower prediction intervals at the same target coverage, especially on small to medium tabular datasets where data are scarce and uncertainty modeling matters. We also provide a lightweight diagnostic suite that separates aleatoric and epistemic components and visualizes posterior behavior, helping practitioners understand why intervals shrink when they do. Across multiple benchmarks using the same MLP backbone, CLAPS consistently attains nominal coverage with improved efficiency and minimal overhead, offering a clear, practical upgrade to residual-based conformal baselines.
Authors: Daniele Masti, Francesco Basciani, Arianna Fedeli, Girgio Gnecco, Francesco Smarra
Abstract: Digital Twins (DTs) are increasingly used as autonomous decision-makers in complex socio-technical systems. However, their mathematically optimal decisions often diverge from human expectations, revealing a persistent mismatch between algorithmic and bounded human rationality. This work addresses this challenge by proposing a framework that introduces fairness as a learnable objective within optimization-based Digital Twins. In this respect, a preference-driven learning workflow that infers latent fairness objectives directly from human pairwise preferences over feasible decisions is introduced. A dedicated Siamese neural network is developed to generate convex quadratic cost functions conditioned on contextual information. The resulting surrogate objectives drive the optimization procedure toward solutions that better reflect human-perceived fairness while maintaining computational efficiency. The effectiveness of the approach is demonstrated on a COVID-19 hospital resource allocation scenario. Overall, this work offers a practical solution to integrate human-centered fairness into the design of autonomous decision-making systems.
Authors: Philippe Rigollet
Abstract: We develop a mathematical framework that interprets Transformer attention as an interacting particle system and studies its continuum (mean-field) limits. By idealizing attention on the sphere, we connect Transformer dynamics to Wasserstein gradient flows, synchronization models (Kuramoto), and mean-shift clustering. Central to our results is a global clustering phenomenon whereby tokens cluster asymptotically after long metastable states where they are arranged into multiple clusters. We further analyze a tractable equiangular reduction to obtain exact clustering rates, show how commonly used normalization schemes alter contraction speeds, and identify a phase transition for long-context attention. The results highlight both the mechanisms that drive representation collapse and the regimes that preserve expressive, multi-cluster structure in deep attention architectures.
Authors: Md. Najmul Islam, Md. Miner Hossain Rimon, Shah Sadek-E-Akbor Shamim, Zarif Mohaimen Fahad, Md. Jehadul Islam Mony, Md. Jalal Uddin Chowdhury
Abstract: Diabetes is a serious worldwide health issue, and successful intervention depends on early detection. However, overlapping risk factors and data asymmetry make prediction difficult. To use extensive health survey data to create a machine learning framework for diabetes classification that is both accurate and comprehensible, to produce results that will aid in clinical decision-making. Using the BRFSS dataset, we assessed a number of supervised learning techniques. SMOTE and Tomek Links were used to correct class imbalance. To improve prediction performance, both individual models and ensemble techniques such as stacking were investigated. The 2015 BRFSS dataset, which includes roughly 253,680 records with 22 numerical features, is used in this study. Strong ROC-AUC performance of approximately 0.96 was attained by the individual models Random Forest, XGBoost, CatBoost, and LightGBM.The stacking ensemble with XGBoost and KNN yielded the best overall results with 94.82\% accuracy, ROC-AUC of 0.989, and PR-AUC of 0.991, indicating a favourable balance between recall and precision. In our study, we proposed and developed a React Native-based application with a Python Flask backend to support early diabetes prediction, providing users with an accessible and efficient health monitoring tool.
Authors: Noa Rubin, Orit Davidovich, Zohar Ringel
Abstract: Two pressing topics in the theory of deep learning are the interpretation of feature learning mechanisms and the determination of implicit bias of networks in the rich regime. Current theories of rich feature learning, often appear in the form of high-dimensional non-linear equations, which require computationally intensive numerical solutions. Given the many details that go into defining a deep learning problem, this complexity is a significant and often unavoidable challenge. Here, we propose a powerful heuristic route for predicting the data and width scales at which various patterns of feature learning emerge. This form of scale analysis is considerably simpler than exact theories and reproduces the scaling exponents of various known results. In addition, we make novel predictions on complex toy architectures, such as three-layer non-linear networks and attention heads, thus extending the scope of first-principle theories of deep learning.
Authors: Y. Sungtaek Ju
Abstract: Kolmogorov-Arnold Networks have emerged as interpretable alternatives to traditional multi-layer perceptrons. However, standard implementations lack principled uncertainty quantification capabilities essential for many scientific applications. We present a framework integrating sparse variational Gaussian process inference with the Kolmogorov-Arnold topology, enabling scalable Bayesian inference with computational complexity quasi-linear in sample size. Through analytic moment matching, we propagate uncertainty through deep additive structures while maintaining interpretability. We use three example studies to demonstrate the framework's ability to distinguish aleatoric from epistemic uncertainty: calibration of heteroscedastic measurement noise in fluid flow reconstruction, quantification of prediction confidence degradation in multi-step forecasting of advection-diffusion dynamics, and out-of-distribution detection in convolutional autoencoders. These results suggest Sparse Variational Gaussian Process Kolmogorov-Arnold Networks (SVGP KANs) is a promising architecture for uncertainty-aware learning in scientific machine learning.
Authors: Honglu Sun, Hao Jing, Zhixiang Dai, Sa Xiao, Wei Xue, Jian Sun, Qifeng Lu
Abstract: A fundamental challenge in numerical weather prediction is to efficiently produce high-resolution forecasts. A common solution is applying downscaling methods, which include dynamical downscaling and statistical downscaling, to the outputs of global models. This work focuses on statistical downscaling, which establishes statistical relationships between low-resolution and high-resolution historical data using statistical models. Deep learning has emerged as a powerful tool for this task, giving rise to various high-performance super-resolution models, which can be directly applied for downscaling, such as diffusion models and Generative Adversarial Networks. This work relies on a diffusion-based downscaling framework named CorrDiff. In contrast to the original work of CorrDiff, the region considered in this work is nearly 40 times larger, and we not only consider surface variables as in the original work, but also encounter high-level variables (six pressure levels) as target downscaling variables. In addition, a global residual connection is added to improve accuracy. In order to generate the 3km forecasts for the China region, we apply our trained models to the 25km global grid forecasts of CMA-GFS, an operational global model of the China Meteorological Administration (CMA), and SFF, a data-driven deep learning-based weather model developed from Spherical Fourier Neural Operators (SFNO). CMA-MESO, a high-resolution regional model, is chosen as the baseline model. The experimental results demonstrate that the forecasts downscaled by our method generally outperform the direct forecasts of CMA-MESO in terms of MAE for the target variables. Our forecasts of radar composite reflectivity show that CorrDiff, as a generative model, can generate fine-scale details that lead to more realistic predictions compared to the corresponding deterministic regression models.
Authors: Nino Antulov-Fantulin
Abstract: In this article, we present a framework for designing neural networks that remain consistent with the underlying principles of agent-based models. We begin by highlighting the limitations of standard neural differential equations in modeling complex systems, where physical invariants (like energy) are often absent but other constraints (like mass conservation, information locality, bounded rationality) must be enforced. To address this, we introduce Agent-Based-Model informed Neural Networks (ABM-NNs), which leverage restricted graph neural networks and hierarchical decomposition to learn interpretable, structure-preserving dynamics. We validate the framework across three case studies of increasing complexity: (i) a generalized Generalized Lotka--Volterra system, where we recover ground-truth parameters from short trajectories in presence of interventions; (ii) a graph-based SIR contagion model, where our method outperforms state-of-the-art graph learning baselines (GCN, GraphSAGE, Graph Transformer) in out-of-sample forecasting and noise robustness; and (iii) a real-world macroeconomic model of the ten largest economies, where we learn coupled GDP dynamics from empirical data and demonstrate counterfactual analysis for policy interventions
Authors: Qiwei Tian, Chenhao Lin, Zhengyu Zhao, Chao Shen
Abstract: To address the trade-off between robustness and performance for robust VLM, we observe that function words could incur vulnerability of VLMs against cross-modal adversarial attacks, and propose Function-word De-Attention (FDA) accordingly to mitigate the impact of function words. Similar to differential amplifiers, our FDA calculates the original and the function-word cross-attention within attention heads, and differentially subtracts the latter from the former for more aligned and robust VLMs. Comprehensive experiments include 2 SOTA baselines under 6 different attacks on 2 downstream tasks, 3 datasets, and 3 models. Overall, our FDA yields an average 18/13/53% ASR drop with only 0.2/0.3/0.6% performance drops on the 3 tested models on retrieval, and a 90% ASR drop with a 0.3% performance gain on visual grounding. We demonstrate the scalability, generalization, and zero-shot performance of FDA experimentally, as well as in-depth ablation studies and analysis. Code will be made publicly at https://github.com/michaeltian108/FDA.
Authors: Qingyuan Yang, Shizhuo Deng, Dongyue Chen, Da Teng, Zehua Gan
Abstract: Traditional Transformers face a major bottleneck in long-sequence time series forecasting due to their quadratic complexity $(\mathcal{O}(T^2))$ and their limited ability to effectively exploit frequency-domain information. Inspired by RWKV's $\mathcal{O}(T)$ linear attention and frequency-domain modeling, we propose FRWKV, a frequency-domain linear-attention framework that overcomes these limitations. Our model integrates linear attention mechanisms with frequency-domain analysis, achieving $\mathcal{O}(T)$ computational complexity in the attention path while exploiting spectral information to enhance temporal feature representations for scalable long-sequence modeling. Across eight real-world datasets, FRWKV achieves a first-place average rank. Our ablation studies confirm the critical roles of both the linear attention and frequency-encoder components. This work demonstrates the powerful synergy between linear attention and frequency analysis, establishing a new paradigm for scalable time series modeling. Code is available at this repository: https://github.com/yangqingyuan-byte/FRWKV.
Authors: Miroslav Dud\'ik, Robert E. Schapire, Matus Telgarsky
Abstract: Not all convex functions on $\mathbb{R}^n$ have finite minimizers; some can only be minimized by a sequence as it heads to infinity. In this work, we aim to develop a theory for understanding such minimizers at infinity. We study astral space, a compact extension of $\mathbb{R}^n$ to which such points at infinity have been added. Astral space is constructed to be as small as possible while still ensuring that all linear functions can be continuously extended to the new space. Although astral space includes all of $\mathbb{R}^n$, it is not a vector space, nor even a metric space. However, it is sufficiently well-structured to allow useful and meaningful extensions of concepts of convexity, conjugacy, and subdifferentials. We develop these concepts and analyze various properties of convex functions on astral space, including the detailed structure of their minimizers, exact characterizations of continuity, and convergence of descent algorithms.
Authors: Xiao Yuan
Abstract: The process of identifying and characterizing B-cell epitopes, which are the portions of antigens recognized by antibodies, is important for our understanding of the immune system, and for many applications including vaccine development, therapeutics, and diagnostics. Computational epitope prediction is challenging yet rewarding as it significantly reduces the time and cost of laboratory work. Most of the existing tools do not have satisfactory performance and only discriminate epitopes from non-epitopes. This paper presents a new deep learning-based multi-task framework for linear B-cell epitope prediction as well as antibody type-specific epitope classification. Specifically, a sequenced-based neural network model using recurrent layers and Transformer blocks is developed. We propose an amino acid encoding method based on eigen decomposition to help the model learn the representations of epitopes. We introduce modifications to standard cross-entropy loss functions by extending a logit adjustment technique to cope with the class imbalance. Experimental results on data curated from the largest public epitope database demonstrate the validity of the proposed methods and the superior performance compared to competing ones.
Authors: Mehdi Letafati, Samad Ali, Matti Latva-aho
Abstract: A comprehensive study on the applications of denoising diffusion models for wireless systems is provided. The article highlights the capabilities of diffusion models in learning complicated signal distributions, modeling wireless channels, and denoising and reconstructing distorted signals. First, fundamental working mechanism of diffusion models is introduced. Then the recent advances in applying diffusion models to wireless systems are reviewed. Next, two case studies are provided, where conditional diffusion models (CDiff) are proposed for data reconstruction enhancement, covering both the conventional digital communication systems, as well as the semantic communication (SemCom) setups. The first case study highlights about 10 dB improvement in data reconstruction under low-SNR regimes, while mitigating the need to transmit redundant bits for error correction codes in digital systems. The second study further extends the case to a SemCom setup, where diffusion autoencoders showcase superior performance compared to legacy autoencoders and variational autoencoder (VAE) architectures. Finally, future directions and existing challenges are discussed.
Authors: Shuo-Hui Li, Yao-Wen Zhang, Ding Pan
Abstract: It is a long-standing challenge to accurately and efficiently compute thermodynamic quantities of many-body systems at thermal equilibrium. The conventional methods, e.g., Markov chain Monte Carlo, require many steps to equilibrate. The recently developed deep learning methods can perform direct sampling, but only work at a single trained temperature point and risk biased sampling. Here, we propose a variational method for canonical ensembles with differentiable temperature, which gives thermodynamic quantities as continuous functions of temperature akin to an analytical solution. The proposed method is a general framework that works with any tractable density generative model. At optimal, the model is theoretically guaranteed to be the unbiased Boltzmann distribution. We validated our method by calculating phase transitions in the Ising and XY models, demonstrating that our direct-sampling simulations are as accurate as Markov chain Monte Carlo, but more efficient. Moreover, our differentiable free energy aligns closely with the exact one to the second-order derivative, indicating that the variational model captures the subtle thermal transitions at the phase transitions. This functional dependence on external parameters is a fundamental advancement in combining the exceptional fitting ability of deep learning with rigorous physical analysis.
Authors: Shengkai Liu, Yaofeng Cheng, Fusheng Zha, Wei Guo, Lining Sun, Zhenshan Bing, Chenguang Yang
Abstract: Pruning at initialization (PaI) reduces training costs by removing weights before training, which becomes increasingly crucial with the growing network size. However, current PaI methods still have a large accuracy gap with iterative pruning, especially at high sparsity levels. This raises an intriguing question: can we get inspiration from iterative pruning to improve the PaI performance? In the lottery ticket hypothesis, the iterative rewind pruning (IRP) finds subnetworks retroactively by rewinding the parameter to the original initialization in every pruning iteration, which means all the subnetworks are based on the initial state. Here, we hypothesise the surviving subnetworks are more important and bridge the initial feature and their surviving score as the PaI criterion. We employ an end-to-end neural network (\textbf{AutoS}parse) to learn this correlation, input the model's initial features, output their score and then prune the lowest score parameters before training. To validate the accuracy and generalization of our method, we performed PaI across various models. Results show that our approach outperforms existing methods in high-sparsity settings. Notably, as the underlying logic of model pruning is consistent in different models, only one-time IRP on one model is needed (e.g., once IRP on ResNet-18/CIFAR-10, AutoS can be generalized to VGG-16/CIFAR-10, ResNet-18/TinyImageNet, et al.). As the first neural network-based PaI method, we conduct extensive experiments to validate the factors influencing this approach. These results reveal the learning tendencies of neural networks and provide new insights into our understanding and research of PaI from a practical perspective. Our code is available at: https://github.com/ChengYaofeng/AutoSparse.git.
Authors: Zhuoxin Chen, Will Ma
Abstract: In the Newsvendor problem, the goal is to guess the number that will be drawn from some distribution, with asymmetric consequences for guessing too high vs. too low. In the data-driven version, the distribution is unknown, and one must work with samples from the distribution. Data-driven Newsvendor has been studied under many variants: additive vs. multiplicative regret, high probability vs. expectation bounds, and different distribution classes. This paper studies all combinations of these variants, filling in many gaps in the literature and simplifying many proofs. In particular, we provide a unified analysis based on the notion of clustered distributions, which in conjunction with our new lower bounds, shows that the entire spectrum of regrets between $1/\sqrt{n}$ and $1/n$ can be possible. Simulations on commonly-used distributions demonstrate that our notion is the "correct" predictor of empirical regret across varying data sizes.
Authors: Jordan Jomsky (for the Frontotemporal Lobar Degeneration Neuroimaging Initiative,for the Alzheimer's Disease Neuroimaging Initiative), Kay C. Igwe (for the Frontotemporal Lobar Degeneration Neuroimaging Initiative,for the Alzheimer's Disease Neuroimaging Initiative), Zongyu Li (for the Frontotemporal Lobar Degeneration Neuroimaging Initiative,for the Alzheimer's Disease Neuroimaging Initiative), Yiren Zhang (for the Frontotemporal Lobar Degeneration Neuroimaging Initiative,for the Alzheimer's Disease Neuroimaging Initiative), Max Lashley (for the Frontotemporal Lobar Degeneration Neuroimaging Initiative,for the Alzheimer's Disease Neuroimaging Initiative), Tal Nuriel (for the Frontotemporal Lobar Degeneration Neuroimaging Initiative,for the Alzheimer's Disease Neuroimaging Initiative), Andrew Laine (for the Frontotemporal Lobar Degeneration Neuroimaging Initiative,for the Alzheimer's Disease Neuroimaging Initiative), Jia Guo (for the Frontotemporal Lobar Degeneration Neuroimaging Initiative,for the Alzheimer's Disease Neuroimaging Initiative)
Abstract: Brain age gap estimation (BrainAGE) is a promising imaging-derived biomarker of neurobiological aging and disease risk, yet current approaches rely predominantly on T1-weighted structural MRI (T1w), overlooking functional vascular changes that may precede tissue damage and cognitive decline. Artificial intelligence-generated cerebral blood volume (AICBV) maps, synthesized from non-contrast MRI, offer an alternative to contrast-enhanced perfusion imaging by capturing vascular information relevant to early neurodegeneration. We developed a multimodal BrainAGE framework that integrates brain age predictions using linear regression from two separate 3D VGG-based networks, one model trained on only structural T1w scans and one trained on only AICBV maps generated from a pre-trained 3D patch-based deep learning model. Each model was trained and validated on 2,851 scans from 13 open-source datasets and was evaluated for concordance with mild cognitive impairment (MCI) and Alzheimer's disease (AD) using ADNI subjects (n=1,233). The combined model achieved the most accurate brain age gap for cognitively normal (CN) controls, with a mean absolute error (MAE) of 3.95 years ($R^2$=0.943), outperforming models trained on T1w (MAE=4.10) or AICBV alone (MAE=4.49). Saliency maps revealed complementary modality contributions: T1w emphasized white matter and cortical atrophy, while AICBV highlighted vascular-rich and periventricular regions implicated in hypoperfusion and early cerebrovascular dysfunction, consistent with normal aging. Next, we observed that BrainAGE increased stepwise across diagnostic strata (CN < MCI < AD) and correlated with cognitive impairment (CDRSB r=0.403; MMSE r=-0.310). AICBV-based BrainAGE showed particularly strong separation between stable vs. progressive MCI (p=$1.47 \times 10^{-8}$), suggesting sensitivity to prodromal vascular changes that precede overt atrophy.
Authors: Johann Wenckstern, Eeshaan Jain, Yexiang Cheng, Benedikt von Querfurth, Kiril Vasilev, Matteo Pariset, Phil F. Cheng, Petros Liakopoulos, Olivier Michielin, Andreas Wicki, Gabriele Gut, Charlotte Bunne
Abstract: Spatial proteomics technologies have transformed our understanding of complex tissue architecture in cancer but present unique challenges for computational analysis. Each study uses a different marker panel and protocol, and most methods are tailored to single cohorts, which limits knowledge transfer and robust biomarker discovery. Here we present Virtual Tissues (VirTues), a general-purpose foundation model for spatial proteomics that learns marker-aware, multi-scale representations of proteins, cells, niches and tissues directly from multiplex imaging data. From a single pretrained backbone, VirTues supports marker reconstruction, cell typing and niche annotation, spatial biomarker discovery, and patient stratification, including zero-shot annotation across heterogeneous panels and datasets. In triple-negative breast cancer, VirTues-derived biomarkers predict anti-PD-L1 chemo-immunotherapy response and stratify disease-free survival in an independent cohort, outperforming state-of-the-art biomarkers derived from the same datasets and current clinical stratification schemes.
Authors: Yuri Chervonyi, Trieu H. Trinh, Miroslav Ol\v{s}\'ak, Xiaomeng Yang, Hoang Nguyen, Marcelo Menegali, Junehyuk Jung, Junsu Kim, Vikas Verma, Quoc V. Le, Thang Luong
Abstract: We present AlphaGeometry2 (AG2), a significantly improved version of AlphaGeometry introduced in (Trinh et al., 2024), which has now surpassed an average gold medalist in solving Olympiad geometry problems. To achieve this, we first extend the original AlphaGeometry language to tackle problems involving movements of objects, and problems containing linear equations of angles, ratios, and distances. This, together with support for non-constructive problems, has markedly improved the coverage rate of the AlphaGeometry language on International Math Olympiads (IMO) 2000-2024 geometry problems from 66% to 88%. The search process of AG2 has also been greatly improved through the use of Gemini architecture for better language modeling, and a novel knowledge-sharing mechanism that enables effective communication between search trees. Together with further enhancements to the symbolic engine and synthetic data generation, we have significantly boosted the overall solving rate of AG to 84% on all geometry problems over the last 25 years, compared to 54% previously. AG2 was also part of the system that achieved the silver-medal standard at IMO 2024 https://deepmind.google/blog/ai-solves-imo-problems-at-silver-medal-level/. Finally, we report progress towards using AG2 as a part of a fully automated system that reliably solves geometry problems from natural language input. Code: https://github.com/google-deepmind/alphageometry2.
URLs: https://deepmind.google/blog/ai-solves-imo-problems-at-silver-medal-level/., https://github.com/google-deepmind/alphageometry2.
Authors: A. Martina Neuman, Andres Felipe Lerma Pineda, Jason J. Bramburger, Simone Brugiapaglia
Abstract: Recovering frequency-localized functions from pointwise data is a fundamental task in signal processing. We examine this problem from an approximation-theoretic perspective, focusing on least squares and deep learning-based methods. First, we establish a novel recovery theorem for least squares approximations using the Slepian basis from uniform random samples in low dimensions, explicitly tracking the dependence of the bandwidth on the sampling complexity. Building on these results, we then present a recovery guarantee for approximating bandlimited functions via deep learning from pointwise data. This result, framed as a practical existence theorem, provides conditions on the network architecture, training procedure, and data acquisition sufficient for accurate approximation. To complement our theoretical findings, we perform numerical comparisons between least squares and deep learning for approximating one- and two-dimensional functions. We conclude with a discussion of the theoretical limitations and the practical gaps between theory and implementation.
Authors: Robert Dilworth
Abstract: This paper explores vulnerabilities in the Dynamic Host Configuration Protocol (DHCP) and their implications on the Confidentiality, Integrity, and Availability (CIA) Triad. Through an analysis of various attacks, including DHCP Starvation, Rogue DHCP Servers, Replay Attacks, and TunnelVision exploits, the paper provides a taxonomic classification of threats, assesses risks, and proposes appropriate controls. The discussion also highlights the dangers of VPN decloaking through DHCP exploits and underscores the importance of safeguarding network infrastructures. By bringing awareness to the TunnelVision exploit, this paper aims to mitigate risks associated with these prevalent vulnerabilities.
Authors: Yui Tomo, Daisuke Yoneoka
Abstract: This study proposes median consensus embedding (MCE) to address variability in low-dimensional embeddings caused by random initialization in nonlinear dimensionality reduction techniques such as $t$-distributed stochastic neighbor embedding. MCE is defined as the geometric median of multiple embeddings. By assuming multiple embeddings as independent and identically distributed random samples and applying large deviation theory, we prove that MCE achieves consistency at an exponential rate. Furthermore, we develop a practical algorithm to implement MCE by constructing a distance function between embeddings based on the Frobenius norm of the pairwise distance matrix of data points. Application to actual data demonstrates that MCE converges rapidly and effectively reduces instability. We further combine MCE with multiple imputation to address missing values and consider multiscale hyperparameters. Results confirm that MCE effectively mitigates instability issues in embedding methods arising from random initialization and other sources.
Authors: Tingyang Wei, Jiao Liu, Abhishek Gupta, Puay Siew Tan, Yew-Soon Ong
Abstract: Multi-task optimization is typically characterized by a fixed and finite set of tasks. The present paper relaxes this condition by considering a non-fixed and potentially infinite set of optimization tasks defined in a parameterized, continuous and bounded task space. We refer to this unique problem setting as parametric multi-task optimization (PMTO). Assuming the bounds of the task parameters to be ($\boldsymbol{\theta}_l$, $\boldsymbol{\theta}_u$), a novel ($\boldsymbol{\theta}_l$, $\boldsymbol{\theta}_u$)-PMTO algorithm is crafted to operate in two complementary modes. In an offline optimization mode, a joint search over solution and task spaces is carried out with the creation of two approximation models: (1) for mapping points in a unified solution space to the objective spaces of all tasks, which provably accelerates convergence by acting as a conduit for inter-task knowledge transfers, and (2) for probabilistically mapping tasks to their corresponding solutions, which facilitates evolutionary exploration of under-explored regions of the task space. In the online mode, the derived models enable direct optimization of any task within the bounds without the need to search from scratch. This outcome is validated on both synthetic test problems and practical case studies, with the significant real-world applicability of PMTO shown towards fast reconfiguration of robot controllers under changing task conditions. The potential of PMTO to vastly speedup the search for solutions to minimax optimization problems is also demonstrated through an example in robust engineering design.
Authors: Minjie Deng, Yan Wei, An Wu, Yuncan Ouyang, Hao Zhai, Qianyao Peng
Abstract: In image fusion tasks, the absence of real fused images as priors forces most deep learning approaches to rely on large-scale paired datasets to extract global weighting features or to generate pseudo-supervised images through algorithmic constructions. Unlike previous methods, this work re-examines prior-guided learning under few-shot conditions by introducing rough set theory. We regard the traditional algorithm as a prior generator, while the network re-inferrs and adaptively optimizes the prior through a dynamic loss function, reducing the inference burden of the network and enabling effective few-shot learning.To provide the prior, we propose the Granular Ball Pixel Computation (GBPC) algorithm. GBPC models pixel pairs in a luminance subspace using meta-granular balls and mines intra-ball information at multiple granular levels. At the fine-grained level, sliding granular balls assign adaptive weights to individual pixels to produce pixel-level prior fusion. At the coarse-grained level, the algorithm performs split computation within a single image to estimate positive and boundary domain distributions, enabling modality awareness and prior confidence estimation, which dynamically guide the loss weighting.The network and the algorithmic prior are coupled through the loss function to form an integrated framework. Thanks to the dynamic weighting mechanism, the network can adaptively adjust to different priors during training, enhancing its perception and fusion capability across modalities. We name this framework GBFF (Granular Ball Fusion Framework). Experiments on four fusion tasks demonstrate that even with only ten training image pairs per task, GBFF achieves superior performance in both visual quality and model compactness. Code is available at: https://github.com/DMinjie/GBFF
Authors: Prabhat Agarwal, Anirudhan Badrinath, Laksh Bhasin, Jaewon Yang, Edoardo Botta, Jiajing Xu, Charles Rosenberg
Abstract: Generative retrieval methods utilize generative sequential modeling techniques, such as transformers, to generate candidate items for recommender systems. These methods have demonstrated promising results in academic benchmarks, surpassing traditional retrieval models like two-tower architectures. However, current generative retrieval methods lack the scalability required for industrial recommender systems, and they are insufficiently flexible to satisfy the multiple metric requirements of modern systems. This paper introduces PinRec, a novel generative retrieval model developed for applications at Pinterest. PinRec utilizes outcome-conditioned generation, enabling modelers to specify how to balance various outcome metrics, such as the number of saves and clicks, to effectively align with business goals and user exploration. Additionally, PinRec incorporates multi-token generation to enhance output diversity while optimizing generation. Our experiments demonstrate that PinRec can successfully balance performance, diversity, and efficiency, delivering a significant positive impact to users using generative models. This paper marks a significant milestone in generative retrieval, as it presents, to our knowledge, the first rigorous study on implementing generative retrieval at the scale of Pinterest.
Authors: Kangyao Huang, Hao Wang, Jingyu Chen, Jintao Chen, Yu Luo, Di Guo, Xiangkui Zhang, Xiangyang Ji, Huaping Liu
Abstract: Deploying robot learning methods to aerial robots in unstructured environments remains both challenging and promising. While recent advances in deep reinforcement learning (DRL) have enabled end-to-end flight control, the field still lacks systematic design guidelines and a unified infrastructure to support reproducible training and real-world deployment. We present a task-oriented framework for end-to-end DRL in quadrotors that integrates design principles for complex task specification and reveals the interdependencies among simulated task definition, training design principles, and physical deployment. Our framework involves software infrastructure, hardware platforms, and open-source firmware to support a full-stack learning infrastructure and workflow. Extensive empirical results demonstrate robust flight and sim-to-real generalization under real-world disturbances. By reducing the entry barrier for deploying learning-based controllers on aerial robots, our work lays a practical foundation for advancing autonomous flight in dynamic and unstructured environments.
Authors: Sajjad Shahabodini, Mobina Mansoori, Farnoush Bayatmakou, Jamshid Abouei, Konstantinos N. Plataniotis, Arash Mohammadi
Abstract: Image segmentation remains a challenging task in computer vision, demanding robust mask generation and precise classification. Recent mask-based approaches yield high-quality masks by capturing global context. However, accurately classifying these masks, especially in the presence of ambiguous boundaries and imbalanced class distributions, remains an open challenge. In this work, we introduce ViT-P, a novel two-stage segmentation framework that decouples mask generation from classification. The first stage employs a proposal generator to produce class-agnostic mask proposals, while the second stage utilizes a point-based classification model built on the Vision Transformer (ViT) to refine predictions by focusing on mask central points. ViT-P serves as a pre-training-free adapter, allowing the integration of various pre-trained vision transformers without modifying their architecture, ensuring adaptability to dense prediction tasks. Furthermore, we demonstrate that coarse and bounding box annotations can effectively enhance classification without requiring additional training on fine annotation datasets, reducing annotation costs while maintaining strong performance. Extensive experiments across COCO, ADE20K, and Cityscapes datasets validate the effectiveness of ViT-P, achieving state-of-the-art results with 54.0 PQ on ADE20K panoptic segmentation, 87.4 mIoU on Cityscapes semantic segmentation, and 63.6 mIoU on ADE20K semantic segmentation. The code and pretrained models are available at: https://github.com/sajjad-sh33/ViT-P}{https://github.com/sajjad-sh33/ViT-P.
URLs: https://github.com/sajjad-sh33/ViT-P, https://github.com/sajjad-sh33/ViT-P.
Authors: Sahil Verma, Keegan Hines, Jeff Bilmes, Charlotte Siska, Luke Zettlemoyer, Hila Gonen, Chandan Singh
Abstract: The emerging capabilities of large language models (LLMs) have sparked concerns about their immediate potential for harmful misuse. The core approach to mitigate these concerns is the detection of harmful queries to the model. Current detection approaches are fallible, and are particularly susceptible to attacks that exploit mismatched generalization of model capabilities (e.g., prompts in low-resource languages or prompts provided in non-text modalities such as image and audio). To tackle this challenge, we propose Omniguard, an approach for detecting harmful prompts across languages and modalities. Our approach (i) identifies internal representations of an LLM/MLLM that are aligned across languages or modalities and then (ii) uses them to build a language-agnostic or modality-agnostic classifier for detecting harmful prompts. Omniguard improves harmful prompt classification accuracy by 11.57\% over the strongest baseline in a multilingual setting, by 20.44\% for image-based prompts, and sets a new SOTA for audio-based prompts. By repurposing embeddings computed during generation, Omniguard is also very efficient ($\approx\!120 \times$ faster than the next fastest baseline). Code and data are available at: https://github.com/vsahil/OmniGuard.
Authors: Gunjan Auti, Hirofumi Daiguji, Gouhei Tanaka
Abstract: Physical transport processes organize through local interactions that redistribute imbalance while preserving conservation. Classical solvers enforce this organization by applying fixed discrete operators on rigid grids. We introduce the Hebbian Physics Network (HPN), a computational framework that replaces this rigid scaffolding with a plastic transport geometry. An HPN is a coupled dynamical system of physical states on nodes and constitutive weights on edges in a graph. Residuals--local violations of continuity, momentum balance, or energy conservation--act as thermodynamic forces that drive the joint evolution of both the state and the operator (i.e. the adaptive weights). The weights adapt through a three-factor Hebbian rule, which we prove constitutes a strictly local gradient descent on the residual energy. This mechanism ensures thermodynamic stability: near equilibrium, the learned operator naturally converges to a symmetric, positive-definite form, rigorously reproducing Onsager\'s reciprocal relations without explicit enforcement. Far from equilibrium, the system undergoes a self-organizing search for a transport topology that restores global coercivity. Unlike optimization-based approaches that impose physics through global loss functions, HPNs embed conservation intrinsically: transport is restored locally by the evolving operator itself, without a global Poisson solve or backpropagated objective. We demonstrate the framework on scalar diffusion and incompressible lid-driven cavity flow, showing that physically consistent transport geometries and flow structures emerge from random initial conditions solely through residual-driven local adaptation. HPNs thus reframe computation not as the solution of a fixed equation, but as a thermodynamic relaxation process where the constitutive geometry and physical state co-evolve.
Authors: F. Gallavotti, A. Zaccone
Abstract: We introduce a three-dimensional vectorial extension of the Hopfield associative-memory model in which each neuron is a unit vector on $S^2$ and synaptic couplings are $3\times 3$ blocks generated through a vectorial Hebbian rule. The resulting block-structured operator is mathematically analogous to the Hessian of amorphous solids and induces a rigid energy landscape with deep minima for stored patterns. Simulations and spectral analysis show that the vectorial network substantially outperforms the classical binary Hopfield model. For moderate connectivity, the critical storage ratio $\gamma_c$ grows approximately linearly with the coordination number $Z$, while for $Z\gtrsim 40$ a high-connectivity regime emerges in which $\gamma_c$ systematically exceeds the extrapolated low-$Z$ linear fit. At the same time, a persistent spectral gap separates pattern modes from the bulk and basins of attraction enlarge, yielding enhanced robustness to initialization noise. Thus geometric constraints combined with amorphous-solid-inspired structure produce associative memories with superior storage and retrieval performance, especially in the high-connectivity ($Z \gtrsim 20$-$30$) regime.
Authors: Bernarda Petek, David Nabergoj, Erik \v{S}trumbelj
Abstract: We present a general approach to visualizing uncertainty in static 2-D statistical graphics. If we treat a visualization as a function of its underlying quantities, uncertainty in those quantities induces a distribution over images. We show how to aggregate these images into a single visualization that represents the uncertainty. The approach can be viewed as a generalization of sample-based approaches that use overlay. Notably, standard representations, such as confidence intervals and bands, emerge with their usual coverage guarantees without being explicitly quantified or visualized. As a proof of concept, we implement our approach in the IID setting using resampling, provided as an open-source Python library. Because the approach operates directly on images, the user needs only to supply the data and the code for visualizing the quantities of interest without uncertainty. Through several examples, we show how both familiar and novel forms of uncertainty visualization can be created. The implementation is not only a practical validation of the underlying theory but also an immediately usable tool that can complement existing uncertainty-visualization libraries.
Authors: Ganesh Narasimha, Mykola Telychko, Wooin Yang, Arthur P. Baddorf, P. Ganesh, An-Ping Li, Rama Vasudevan
Abstract: Manipulating matter with a scanning tunneling microscope (STM) enables creation of atomically defined artificial structures that host designer quantum states. However, the time-consuming nature of the manipulation process, coupled with the sensitivity of the STM tip, constrains the exploration of diverse configurations and limits the size of designed features. In this study, we present a reinforcement learning (RL)-based framework for creating artificial structures by spatially manipulating carbon monoxide (CO) molecules on a copper substrate using the STM tip. The automated workflow combines molecule detection and manipulation, employing deep learning-based object detection to locate CO molecules and linear assignment algorithms to allocate these molecules to designated target sites. We initially perform molecule maneuvering based on randomized parameter sampling for sample bias, tunneling current setpoint and manipulation speed. This dataset is then structured into an action trajectory used to train an RL agent. The model is subsequently deployed on the STM for real-time fine-tuning of manipulation parameters during structure construction. Our approach incorporates path planning protocols coupled with active drift compensation to enable atomically precise fabrication of structures with significantly reduced human input while realizing larger-scale artificial lattices with desired electronic properties. Using our approach, we demonstrate the automated construction of an extended artificial graphene lattice and confirm the existence of characteristic Dirac point in its electronic structure. Further challenges to RL-based structural assembly scalability are discussed.
Authors: Bogdan Butyrin, Artemy Rubtsov, Alexey Naumov, Vladimir Ulyanov, Sergey Samsonov
Abstract: In this paper, we establish non-asymptotic bounds for accuracy of normal approximation for linear two-timescale stochastic approximation (TTSA) algorithms driven by martingale difference or Markov noise. Focusing on both the last iterate and Polyak-Ruppert averaging regimes, we derive bounds for normal approximation in terms of the convex distance between probability distributions. Our analysis reveals a non-trivial interaction between the fast and slow timescales: the normal approximation rate for the last iterate improves as the timescale separation increases, while it decreases in the Polyak-Ruppert averaged setting. We also provide the high-order moment bounds for the error of linear TTSA algorithm, which may be of independent interest.
Authors: Abdullah Al Nomaan Nafi, Habibur Rahaman, Zafaryab Haider, Tanzim Mahfuz, Fnu Suya, Swarup Bhunia, Prabuddha Chakraborty
Abstract: Numerous techniques have been proposed for generating adversarial examples in white-box settings under strict Lp-norm constraints. However, such norm-bounded examples often fail to align well with human perception, and only recently have a few methods begun specifically exploring perceptually aligned adversarial examples. Moreover, it remains unclear whether insights from Lp-constrained attacks can be effectively leveraged to improve perceptual efficacy. In this paper, we introduce DAASH, a fully differentiable meta-attack framework that generates effective and perceptually aligned adversarial examples by strategically composing existing Lp-based attack methods. DAASH operates in a multi-stage fashion: at each stage, it aggregates candidate adversarial examples from multiple base attacks using learned, adaptive weights and propagates the result to the next stage. A novel meta-loss function guides this process by jointly minimizing misclassification loss and perceptual distortion, enabling the framework to dynamically modulate the contribution of each base attack throughout the stages. We evaluate DAASH on adversarially trained models across CIFAR-10, CIFAR-100, and ImageNet. Despite relying solely on Lp-constrained based methods, DAASH significantly outperforms state-of-the-art perceptual attacks such as AdvAD -- achieving higher attack success rates (e.g., 20.63\% improvement) and superior visual quality, as measured by SSIM, LPIPS, and FID (improvements $\approx$ of 11, 0.015, and 5.7, respectively). Furthermore, DAASH generalizes well to unseen defenses, making it a practical and strong baseline for evaluating robustness without requiring handcrafted adaptive attacks for each new defense.
Authors: Aneesh Rangnekar, Harini Veeraraghavan
Abstract: Accurate detection and segmentation of cancerous lesions from computed tomography (CT) scans is essential for automated treatment planning and cancer treatment response assessment. Transformer-based models with self-supervised pretraining can produce reliably accurate segmentation from in-distribution (ID) data but degrade when applied to out-of-distribution (OOD) datasets. We address this challenge with RF-Deep, a random forest classifier that utilizes deep features from a pretrained transformer encoder of the segmentation model to detect OOD scans and enhance segmentation reliability. The segmentation model comprises a Swin Transformer encoder, pretrained with masked image modeling (SimMIM) on 10,432 unlabeled 3D CT scans covering cancerous and non-cancerous conditions, with a convolution decoder, trained to segment lung cancers in 317 3D scans. Independent testing was performed on 603 3D CT public datasets that included one ID dataset and four OOD datasets comprising chest CTs with pulmonary embolism (PE) and COVID-19, and abdominal CTs with kidney cancers and healthy volunteers. RF-Deep detected OOD cases with a FPR95 of 18.26%, 27.66%, and less than 0.1% on PE, COVID-19, and abdominal CTs, consistently outperforming established OOD approaches. The RF-Deep classifier provides a simple and effective approach to enhance reliability of cancer segmentation in ID and OOD scenarios.
Authors: Moeen Nehzati
Abstract: A wide range of optimization problems can often be written in terms of generalized convex functions (GCFs). When this structure is present, it can convert certain nested bilevel objectives into single-level problems amenable to standard first-order optimization methods. We provide a new differentiable layer with a convex parameter space and show (Theorems 5.1 and 5.2) that it and its gradient are universal approximators for GCFs and their gradients. We demonstrate how this parameterization can be leveraged in practice by (i) learning optimal transport maps with general cost functions and (ii) learning optimal auctions of multiple goods. In both these cases, we show how our layer can be used to convert the existing bilevel or min-max formulations into single-level problems that can be solved efficiently with first-order methods.
Authors: Millicent Li, Alberto Mario Ceballos Arroyo, Giordano Rogers, Naomi Saphra, Byron C. Wallace
Abstract: Recent interpretability methods have proposed to translate LLM internal representations into natural language descriptions using a second verbalizer LLM. This is intended to illuminate how the target model represents and operates on inputs. But do such activation verbalization approaches actually provide privileged knowledge about the internal workings of the target model, or do they merely convey information about its inputs? We critically evaluate popular verbalization methods across datasets used in prior work and find that they can succeed at benchmarks without any access to target model internals, suggesting that these datasets may not be ideal for evaluating verbalization methods. We then run controlled experiments which reveal that verbalizations often reflect the parametric knowledge of the verbalizer LLM which generated them, rather than the knowledge of the target LLM whose activations are decoded. Taken together, our results indicate a need for targeted benchmarks and experimental controls to rigorously assess whether verbalization methods provide meaningful insights into the operations of LLMs.
Authors: Huu Nguyen (Sonny), Victor May (Sonny), Harsh Raj (Sonny), Marianna Nezhurina (Sonny), Yishan Wang (Sonny), Yanqi Luo (Sonny), Minh Chien Vu (Sonny), Taishi Nakamura (Sonny), Ken Tsui (Sonny), Van Khue Nguyen (Sonny), David Salinas (Sonny), Aleksandra Krasnod\k{e}bska (Sonny), Christoph Schuhmann (Sonny), Mats Leon Richter (Sonny), Xuan-Son (Sonny), Vu, Jenia Jitsev
Abstract: We present MixtureVitae, an open-access pretraining corpus built to minimize legal risk while providing strong model performance. MixtureVitae follows a risk-mitigated sourcing strategy that combines public-domain and permissively licensed text (e.g., CC-BY/Apache) with carefully justified low-risk additions (e.g., government works and EU TDM-eligible sources), alongside targeted instruction, reasoning and synthetic data with documented provenance. We detail a transparent, multi-stage pipeline for license-aware filtering, safety and quality screening, and domain-aware mixing, and we release the dataset and curation recipes to support reproducible research. In controlled experiments using the open-sci-ref training protocol (fixed architectures at 130M/400M/1.3B/1.7B parameters; training budgets of 50B and 300B tokens), models trained on MixtureVitae consistently outperform other permissive datasets across a suite of standard benchmarks, and at the 1.7B/300B setting they surpass FineWeb-Edu and approach DCLM in the later stages of training. Performance is particularly strong on math/code and competitive on QA tasks. These results demonstrate that permissive-first, risk-mitigated data provides a practical and legally mitigated foundation for training capable LLMs, reducing reliance on indiscriminate web scraping without sacrificing competitiveness. Code: https://github.com/ontocord/mixturevitae
Authors: Mohammad Zbeeb, Hasan Abed Al Kader Hammoud, Sina Mukalled, Nadine Rizk, Fatima Karnib, Issam Lakkis, Ammar Mohanna, Bernard Ghanem
Abstract: We present AraLingBench: a fully human annotated benchmark for evaluating the Arabic linguistic competence of large language models (LLMs). The benchmark spans five core categories: grammar, morphology, spelling, reading comprehension, and syntax, through 150 expert-designed multiple choice questions that directly assess structural language understanding. Evaluating 35 Arabic and bilingual LLMs reveals that current models demonstrate strong surface level proficiency but struggle with deeper grammatical and syntactic reasoning. AraLingBench highlights a persistent gap between high scores on knowledge-based benchmarks and true linguistic mastery, showing that many models succeed through memorization or pattern recognition rather than authentic comprehension. By isolating and measuring fundamental linguistic skills, AraLingBench provides a diagnostic framework for developing Arabic LLMs. The full evaluation code is publicly available on GitHub.
Authors: Manish Jain, Satheesh Kumar Ponnambalam, Salman Faroz, Chandrakanth Lns, Vinay Sharma
Abstract: Large Language Models (LLMs) demonstrate exceptional capabilities across general domains, yet their application to specialized sectors such as mortgage finance requires domain-specific knowledge augmentation while preserving instruction-following fidelity. We present MortgageLLM, a novel domain-specific large language model that addresses this dual challenge. It is developed using a dual-track specialization framework from a single base model (LLaMA-3.1-8B). We opted for this dual-expert approach as a single multi-task model suffers from performance trade-offs, where optimizing for structured tasks (via SFT) degrades conversational fidelity (via DPO). Our dual-track method solves this by creating two specialists, allowing each to be optimally trained for its distinct capability. Our approach applies the instruction residual technique to restore instruction-following capabilities post-domain adaptation without supervised fine-tuning. We contribute: (1) application of this residual technique to the highly specialized mortgage finance domain; (2) a dual-expert architecture combining a conversational Q&A model and a structured task model for classification and summarization; and (3) an intelligent task routing mechanism using few-shot classification performed by one of the expert models itself. We validate our approach on domain-specific benchmarks, where our final model (MLM v2) significantly outperforms the base LLaMA-3.1-8B-Instruct, achieving an LLM-as-a-Judge summarization score of 4.58 (vs. 3.99), a Q&A score of 4.09 (vs. 4.0), and a classification score of 2.6 (vs. 1.2). On semantic similarity, our model achieved a BERTScore of 0.77 for summarization (vs. 0.74), 0.68 for Q&A (vs. 0.58), and 0.75 for classification (vs. 0.73), substantially outperforming baseline approaches.
Authors: Zhongjie Jiang
Abstract: Although synthetic data is widely promoted as a remedy, its prevailing production paradigm -- one optimizing for statistical smoothness -- systematically removes the long-tail, cognitively grounded irregularities that characterize human text. Prolonged training on such statistically optimal but cognitively impoverished data accelerates model collapse. This paper proposes a paradigm shift: instead of imitating the surface properties of data, we simulate the cognitive processes that generate human text. We introduce the Prompt-driven Cognitive Computing Framework (PMCSF), whose core consists of a Cognitive State Decoder (CSD) that reverse-engineers unstructured text into structured cognitive vectors, and a Cognitive Text Encoder (CTE) that re-materializes these states into text enriched with human-typical imperfections via mathematically defined Cognitive Perturbation Operators. The framework is validated through a two-stage objective evaluation pipeline. First, in cognitive codec verification, CTE text yields a Jensen-Shannon divergence of 0.0614 from human text (vs. 0.4431 for standard LLM output), passes double-blind professional media review, and achieves an intraclass correlation coefficient ICC > 0.9 for cognitive profile alignment across heterogeneous models. Second, in functional gain evaluation, isomorphic stress tests in the A-share market show that strategies incorporating CTE-generated data reduce maximum drawdown by 47.4% during the 2015 crash and deliver 8.6% Defensive Alpha, exceeding transaction costs by a factor of 33. Our findings demonstrate that modelling human cognitive limitations -- not copying surface data -- enables synthetic data with genuine functional gain, offering a viable technical pathway toward resolving the AI data-collapse crisis.
Authors: Xiaosen Lyu, Jiayu Xiong, Yuren Chen, Wanlong Wang, Xiaoqing Dai, Jing Wang
Abstract: Multimodal Emotion Recognition in Conversation (MERC) aims to predict speakers' emotions by integrating textual, acoustic, and visual cues. Existing approaches either struggle to capture complex cross-modal interactions or experience gradient conflicts and unstable training when using deeper architectures. To address these issues, we propose Cross-Space Synergy (CSS), which couples a representation component with an optimization component. Synergistic Polynomial Fusion (SPF) serves the representation role, leveraging low-rank tensor factorization to efficiently capture high-order cross-modal interactions. Pareto Gradient Modulator (PGM) serves the optimization role, steering updates along Pareto-optimal directions across competing objectives to alleviate gradient conflicts and improve stability. Experiments show that CSS outperforms existing representative methods on IEMOCAP and MELD in both accuracy and training stability, demonstrating its effectiveness in complex multimodal scenarios.
Authors: Hoang Duc Nguyen, Anh Van Pham, Hien D. Nguyen
Abstract: This work presents the Polynomiogram framework, an integrated computational platform for exploring, visualizing, and generating art from polynomial root systems. The main innovation is a flexible sampling scheme in which two independent parameters are drawn from user defined domains and mapped to the polynomial coefficients through a generating function. This design allows the same mathematical foundation to support both scientific investigation and generative algorithmic art. The framework integrates two complementary numerical engines: NumPy companion matrix solver for fast, large scale computation and MPSolve for high precision, scientifically rigorous validation. This dual architecture enables efficient visualization for creative use and accurate computation for research and education. Numerical accuracy was verified using classical ensembles, including the Kac and Lucas polynomials. The method was applied to the cubic polynomial system to analyze its bifurcation structure, demonstrating its value as both a scientific tool for exploring root phenomena and an educational aid for visualizing fundamental concepts in algebra and dynamical systems. Beyond analysis, the Polynomiogram also demonstrated its potential as a tool for personalized generative art. Examples include the use of the platform to generate a natural form resembling a hibiscus flower and to create personalized artwork expressing gratitude toward advances in artificial intelligence and large language models through a tribute composition.
Authors: Monishwaran Maheswaran, Rishabh Tiwari, Yuezhou Hu, Kerem Dilmen, Coleman Hooper, Haocheng Xi, Nicholas Lee, Mehrdad Farajtabar, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
Abstract: Modern Large Language Models achieve impressive reasoning capabilities with long Chain of Thoughts, but they incur substantial computational cost during inference, and this motivates techniques to improve the performance-cost ratio. Among these techniques, Speculative Decoding accelerates inference by employing a fast but inaccurate draft model to autoregressively propose tokens, which are then verified in parallel by a more capable target model. However, due to unnecessary rejections caused by token mismatches in semantically equivalent steps, traditional token-level Speculative Decoding struggles in reasoning tasks. Although recent works have shifted to step-level semantic verification, which improve efficiency by accepting or rejecting entire reasoning steps, existing step-level methods still regenerate many rejected steps with little improvement, wasting valuable target compute. To address this challenge, we propose Arbitrage, a novel step-level speculative generation framework that routes generation dynamically based on the relative advantage between draft and target models. Instead of applying a fixed acceptance threshold, Arbitrage uses a lightweight router trained to predict when the target model is likely to produce a meaningfully better step. This routing approximates an ideal Arbitrage Oracle that always chooses the higher-quality step, achieving near-optimal efficiency-accuracy trade-offs. Across multiple mathematical reasoning benchmarks, Arbitrage consistently surpasses prior step-level Speculative Decoding baselines, reducing inference latency by up to $\sim2\times$ at matched accuracy.
Authors: Ajinkya Bhole, Mohammad Mahmoudi Filabadi, Guillaume Crevecoeur, Tom Lefebvre
Abstract: This paper develops a unified perspective on several stochastic optimal control formulations through the lens of Kullback-Leibler regularization. We propose a central problem that separates the KL penalties on policies and transitions, assigning them independent weights, thereby generalizing the standard trajectory-level KL-regularization commonly used in probabilistic and KL-regularized control. This generalized formulation acts as a generative structure allowing to recover various control problems. These include the classical Stochastic Optimal Control (SOC), Risk-Sensitive Optimal Control (RSOC), and their policy-based KL-regularized counterparts. The latter we refer to as soft-policy SOC and RSOC, facilitating alternative problems with tractable solutions. Beyond serving as regularized variants, we show that these soft-policy formulations majorize the original SOC and RSOC problem. This means that the regularized solution can be iterated to retrieve the original solution. Furthermore, we identify a structurally synchronized case of the risk-seeking soft-policy RSOC formulation, wherein the policy and transition KL-regularization weights coincide. Remarkably, this specific setting gives rise to several powerful properties such as a linear Bellman equation, path integral solution, and, compositionality, thereby extending these computationally favourable properties to a broad class of control problems.
Authors: Martin G. Herold, Evangelos Kipouridis, Joachim Spoerhase
Abstract: We revisit the $(f,g)$-clustering problem that we introduced in a recent work [SODA'25], and which subsumes fundamental clustering problems such as $k$-Center, $k$-Median, Min-Sum of Radii, and Min-Load $k$-Clustering. This problem assigns each of the $k$ clusters a cost determined by the monotone, symmetric norm $f$ applied to the vector distances in the cluster, and aims at minimizing the norm $g$ applied to the vector of cluster costs. Previously, we focused on certain special cases for which we designed constant-factor approximation algorithms. Our bounds for more general settings left, however, large gaps to the known bounds for the basic problems they capture. In this work, we provide a clearer picture of the approximability of these more general settings. First, we design an $O(\log^2 n)$-approximation algorithm for $(f, L_{1})$-clustering for any $f$. This improves upon our previous $\widetilde{O}(\sqrt{n})$-approximation. Second, we provide an $O(k)$-approximation for the general $(f,g)$-clustering problem, which improves upon our previous $\widetilde{O}(\sqrt{kn})$-approximation algorithm and matches the best-known upper bound for Min-Load $k$-Clustering. We then design an approximation algorithm for $(f,g)$-clustering that interpolates, up to polylog factors, between the best known bounds for $k$-Center, $k$-Median, Min-Sum of Radii, Min-Load $k$-Clustering, (Top, $L_{1}$)-clustering, and $(L_{\infty},g)$-clustering based on a newly defined parameter of $f$ and $g$.
Authors: Rushiraj Gadhvi, Sandeep Manjanna
Abstract: For centuries, khalasi (Gujarati for sailor) have skillfully harnessed ocean currents to navigate vast waters with minimal effort. Emulating this intuition in autonomous systems remains a significant challenge, particularly for Autonomous Surface Vehicles tasked with long duration missions under strict energy budgets. In this work, we present a learning-based approach for energy-efficient surface vehicle navigation in vortical flow fields, where partial observability often undermines traditional path-planning methods. We present an end to end reinforcement learning framework based on Soft Actor Critic that learns flow-aware navigation policies using only local velocity measurements. Through extensive evaluation across diverse and dynamically rich scenarios, our method demonstrates substantial energy savings and robust generalization to previously unseen flow conditions, offering a promising path toward long term autonomy in ocean environments. The navigation paths generated by our proposed approach show an improvement in energy conservation 30 to 50 percent compared to the existing state of the art techniques.
Authors: Josep M. Rocafort, Shaolin Su, Alexandra Gomez-Villa, Javier Vazquez-Corral
Abstract: Recent image Super-Resolution (SR) models are achieving impressive effects in reconstructing details and delivering visually pleasant outputs. However, the overpowering generative ability can sometimes hallucinate and thus change the image content despite gaining high visual quality. This type of high-level change can be easily identified by humans yet not well-studied in existing low-level image quality metrics. In this paper, we establish the importance of measuring high-level fidelity for SR models as a complementary criterion to reveal the reliability of generative SR models. We construct the first annotated dataset with fidelity scores from different SR models, and evaluate how state-of-the-art (SOTA) SR models actually perform in preserving high-level fidelity. Based on the dataset, we then analyze how existing image quality metrics correlate with fidelity measurement, and further show that this high-level task can be better addressed by foundation models. Finally, by fine-tuning SR models based on our fidelity feedback, we show that both semantic fidelity and perceptual quality can be improved, demonstrating the potential value of our proposed criteria, both in model evaluation and optimization. We will release the dataset, code, and models upon acceptance.
Authors: Raunak Jain, Mudita Khurana
Abstract: LLM-based agents are increasingly deployed for expert decision support, yet human-AI teams in high-stakes settings do not yet reliably outperform the best individual. We argue this complementarity gap reflects a fundamental mismatch: current agents are trained as answer engines, not as partners in the collaborative sensemaking through which experts actually make decisions. Sensemaking (the ability to co-construct causal explanations, surface uncertainties, and adapt goals) is the key capability that current training pipelines do not explicitly develop or evaluate. We propose Collaborative Causal Sensemaking (CCS) as a research agenda to develop this capability from the ground up, spanning new training environments that reward collaborative thinking, representations for shared human-AI mental models, and evaluation centred on trust and complementarity. These directions can advance MAS research toward agents that think with their human partners rather than for them.