Authors: Burcu Sayin, Ipek Baris Schlicht, Ngoc Vo Hong, Sara Allievi, Jacopo Staiano, Pasquale Minervini, Andrea Passerini
Abstract: Clinical decision-making is inherently complex, often influenced by cognitive biases, incomplete information, and case ambiguity. Large Language Models (LLMs) have shown promise as tools for supporting clinical decision-making, yet their typical one-shot or limited-interaction usage may overlook the complexities of real-world medical practice. In this work, we propose a hybrid human-AI framework, MedSyn, where physicians and LLMs engage in multi-step, interactive dialogues to refine diagnoses and treatment decisions. Unlike static decision-support tools, MedSyn enables dynamic exchanges, allowing physicians to challenge LLM suggestions while the LLM highlights alternative perspectives. Through simulated physician-LLM interactions, we assess the potential of open-source LLMs as physician assistants. Results show open-source LLMs are promising as physician assistants in the real world. Future work will involve real physician interactions to further validate MedSyn's usefulness in diagnostic accuracy and patient outcomes.
Authors: Corentin Delacour, M Mahmudul Hasan Sajeeb, Joao P. Hespanha, Kerem Y. Camsari
Abstract: Sampling Boltzmann probability distributions plays a key role in machine learning and optimization, motivating the design of hardware accelerators such as Ising machines. While the Ising model can in principle encode arbitrary optimization problems, practical implementations are often hindered by soft constraints that either slow down mixing when too strong, or fail to enforce feasibility when too weak. We introduce a two-dimensional extension of the powerful parallel tempering algorithm (PT) that addresses this challenge by adding a second dimension of replicas interpolating the penalty strengths. This scheme ensures constraint satisfaction in the final replicas, analogous to low-energy states at low temperature. The resulting two-dimensional parallel tempering algorithm (2D-PT) improves mixing in heavily constrained replicas and eliminates the need to explicitly tune the penalty strength. In a representative example of graph sparsification with copy constraints, 2D-PT achieves near-ideal mixing, with Kullback-Leibler divergence decaying as O(1/t). When applied to sparsified Wishart instances, 2D-PT yields orders of magnitude speedup over conventional PT with the same number of replicas. The method applies broadly to constrained Ising problems and can be deployed on existing Ising machines.
Authors: Joseph Geraci, Bessi Qorri, Christian Cumbaa, Mike Tsay, Paul Leonczyk, Luca Pani
Abstract: Artificial intelligence (AI) has evolved into an ecosystem of specialized "species," each with unique strengths. We analyze two: DeepSeek-V3, a 671-billion-parameter Mixture of Experts large language model (LLM) exemplifying scale-driven generality, and NetraAI, a dynamical system-based framework engineered for stability and interpretability on small clinical trial datasets. We formalize NetraAI's foundations, combining contraction mappings, information geometry, and evolutionary algorithms to identify predictive patient cohorts. Features are embedded in a metric space and iteratively contracted toward stable attractors that define latent subgroups. A pseudo-temporal embedding and long-range memory enable exploration of higher-order feature interactions, while an internal evolutionary loop selects compact, explainable 2-4-variable bundles ("Personas"). To guide discovery, we introduce an LLM Strategist as a meta-evolutionary layer that observes Persona outputs, prioritizes promising variables, injects domain knowledge, and assesses robustness. This two-tier architecture mirrors the human scientific process: NetraAI as experimentalist, the LLM as theorist, forming a self-improving loop. In case studies (schizophrenia, depression, pancreatic cancer), NetraAI uncovered small, high-effect-size subpopulations that transformed weak baseline models (AUC ~0.50-0.68) into near-perfect classifiers using only a few features. We position NetraAI at the intersection of dynamical systems, information geometry, and evolutionary learning, aligned with emerging concept-level reasoning paradigms such as LeCun's Joint Embedding Predictive Architecture (JEPA). By prioritizing reliable, explainable knowledge, NetraAI offers a new generation of adaptive, self-reflective AI to accelerate clinical discovery.
Authors: Mohamed Masry, Mohamed Amen, Mohamed Elzyat, Mohamed Hamed, Norhan Magdy, Maram Khaled
Abstract: Decoding natural language from brain activity using non-invasive electroencephalography (EEG) remains a significant challenge in neuroscience and machine learning, particularly for open-vocabulary scenarios where traditional methods struggle with noise and variability. Previous studies have achieved high accuracy on small-closed vocabularies, but it still struggles on open vocabularies. In this study, we propose ETS, a framework that integrates EEG with synchronized eye-tracking data to address two critical tasks: (1) open-vocabulary text generation and (2) sentiment classification of perceived language. Our model achieves a superior performance on BLEU and Rouge score for EEG-To-Text decoding and up to 10% F1 score on EEG-based ternary sentiment classification, which significantly outperforms supervised baselines. Furthermore, we show that our proposed model can handle data from various subjects and sources, showing great potential for high performance open vocabulary eeg-to-text system.
Authors: Emre Yilmaz, Philipp Bekemeyer
Abstract: Determining onflow parameters is crucial from the perspectives of wind tunnel testing and regular flight and wind turbine operations. These parameters have traditionally been predicted via direct measurements which might lead to challenges in case of sensor faults. Alternatively, a data-driven prediction model based on surface pressure data can be used to determine these parameters. It is essential that such predictors achieve close to real-time learning as dictated by practical applications such as monitoring wind tunnel operations or learning the variations in aerodynamic performance of aerospace and wind energy systems. To overcome the challenges caused by changes in the data distribution as well as in adapting to a new prediction task, we propose a transfer learning methodology to predict the onflow parameters, specifically angle of attack and onflow speed. It requires first training a convolutional neural network (ConvNet) model offline for the core prediction task, then freezing the weights of this model except the selected layers preceding the output node, and finally executing transfer learning by retraining these layers. A demonstration of this approach is provided using steady CFD analysis data for an airfoil for i) domain adaptation where transfer learning is performed with data from a target domain having different data distribution than the source domain and ii) task adaptation where the prediction task is changed. Further exploration on the influence of noisy data, performance on an extended domain, and trade studies varying sampling sizes and architectures are provided. Results successfully demonstrate the potential of the approach for adaptation to changing data distribution, domain extension, and task update while the application for noisy data is concluded to be not as effective.
Authors: Haobo Li, Eunseo Jung, Zixin Chen, Zhaowei Wang, Yueya Wang, Huamin Qu, Alexis Kai Hon Lau
Abstract: Multimodal time series forecasting is foundational in various fields, such as utilizing satellite imagery and numerical data for predicting typhoons in climate science. However, existing multimodal approaches primarily focus on utilizing text data to help time series forecasting, leaving the visual data in existing time series datasets untouched. Furthermore, it is challenging for models to effectively capture the physical information embedded in visual data, such as satellite imagery's temporal and geospatial context, which extends beyond images themselves. To address this gap, we propose physics-informed positional encoding (PIPE), a lightweight method that embeds physical information into vision language models (VLMs). PIPE introduces two key innovations: (1) a physics-informed positional indexing scheme for mapping physics to positional IDs, and (2) a variant-frequency positional encoding mechanism for encoding frequency information of physical variables and sequential order of tokens within the embedding space. By preserving both the physical information and sequential order information, PIPE significantly improves multimodal alignment and forecasting accuracy. Through the experiments on the most representative and the largest open-sourced satellite image dataset, PIPE achieves state-of-the-art performance in both deep learning forecasting and climate domain methods, demonstrating superiority across benchmarks, including a 12% improvement in typhoon intensity forecasting over prior works. Our code is provided in the supplementary material.
Authors: Funing Li, Yuan Tian, Ruben Noortwyck, Jifeng Zhou, Liming Kuang, Robert Schulz
Abstract: In modern industrial and logistics environments, the rapid expansion of fast delivery services has heightened the demand for storage systems that combine high efficiency with increased density. Multi-deep autonomous vehicle storage and retrieval systems (AVS/RS) present a viable solution for achieving greater storage density. However, these systems encounter significant challenges during retrieval operations due to lane blockages. A conventional approach to mitigate this issue involves storing items with homogeneous characteristics in a single lane, but this strategy restricts the flexibility and adaptability of multi-deep storage systems. In this study, we propose a deep reinforcement learning-based framework to address the retrieval problem in multi-deep storage systems with heterogeneous item configurations. Each item is associated with a specific due date, and the objective is to minimize total tardiness. To effectively capture the system's topology, we introduce a graph-based state representation that integrates both item attributes and the local topological structure of the multi-deep warehouse. To process this representation, we design a novel neural network architecture that combines a Graph Neural Network (GNN) with a Transformer model. The GNN encodes topological and item-specific information into embeddings for all directly accessible items, while the Transformer maps these embeddings into global priority assignments. The Transformer's strong generalization capability further allows our approach to be applied to storage systems with diverse layouts. Extensive numerical experiments, including comparisons with heuristic methods, demonstrate the superiority of the proposed neural network architecture and the effectiveness of the trained agent in optimizing retrieval tardiness.
Authors: Saman Khamesian, Asiful Arefeen, Bithika M. Thompson, Maria Adela Grando, Hassan Ghasemzadeh
Abstract: High quality real world datasets are essential for advancing data driven approaches in type 1 diabetes (T1D) management, including personalized therapy design, digital twin systems, and glucose prediction models. However, progress in this area has been limited by the scarcity of publicly available datasets that offer detailed and comprehensive patient data. To address this gap, we present AZT1D, a dataset containing data collected from 25 individuals with T1D on automated insulin delivery (AID) systems. AZT1D includes continuous glucose monitoring (CGM) data, insulin pump and insulin administration data, carbohydrate intake, and device mode (regular, sleep, and exercise) obtained over 6 to 8 weeks for each patient. Notably, the dataset provides granular details on bolus insulin delivery (i.e., total dose, bolus type, correction specific amounts) features that are rarely found in existing datasets. By offering rich, naturalistic data, AZT1D supports a wide range of artificial intelligence and machine learning applications aimed at improving clinical decision making and individualized care in T1D.
Authors: Tianxiang Zhan, Ming Jin, Yuanpeng He, Yuxuan Liang, Yong Deng, Shirui Pan
Abstract: Recurring concept drift, a type of concept drift in which previously observed data patterns reappear after some time, is one of the most prevalent types of concept drift in time series. As time progresses, concept drift occurs and previously encountered concepts are forgotten, thereby leading to a decline in the accuracy of online predictions. Existing solutions employ parameter updating techniques to delay forgetting; however, this may result in the loss of some previously learned knowledge while neglecting the exploration of knowledge retention mechanisms. To retain all conceptual knowledge and fully utilize it when the concepts recur, we propose the Continuous Evolution Pool (CEP), a pooling mechanism that stores different instances of forecasters for different concepts. Our method first selects the forecaster nearest to the test sample and then learns the features from its neighboring samples - a process we refer to as the retrieval. If there are insufficient neighboring samples, it indicates that a new concept has emerged, and a new model will evolve from the current nearest sample to the pool to store the knowledge of the concept. Simultaneously, the elimination mechanism will enable outdated knowledge to be cleared to ensure the prediction effect of the forecasters. Experiments on different architectural models and eight real datasets demonstrate that CEP effectively retains the knowledge of different concepts. In the scenario of online forecasting with recurring concepts, CEP significantly enhances the prediction results.
Authors: Aditya Ravuri, Neil D. Lawrence
Abstract: Protein Language Models (PLMs) such as ESM2 have been shown to be capable of zero-shot prediction of critical scalar properties of proteins (fitness). In this work, we show that injecting a dropout layer at inference time between a PLM's featurizer/embedding layer and its transformer, and averaging its output akin to Monte-Carlo dropout increases zero-shot performance on a subset of the ProteinGym dataset. This is the case even when the model was not trained with dropouts to begin with, and does not require retraining or finetuning of the PLM. A dropout of 0.1 seems performant across all models.
Authors: Henrik Klagges, Robert Dahlke, Fabian Klemm, Benjamin Merkel, Daniel Klingmann, David A. Reiss, Dan Zecha
Abstract: Requiring $10^{13}$-$10^{15}$ FLOPs to calculate one 8 bit weight in an LLM during pretraining is extremely expensive and seems inefficient. To better leverage the huge investments made into pretrained models, we develop the new "Assembly-of-Experts" (AoE) construction method to create capable child variants of existing Mixture-of-Experts parent models in linear time. Model weight tensors get interpolated individually, allowing to enhance or suppress semantic features of the parents. Varying the proportion of weights taken from the parent models, we observe some properties of the AoE child model changing gradually, while other behavioral traits emerge with a sharp transition. Surprisingly, nearly every generated model is functional and capable, which makes searching the model space straightforward. We construct the DeepSeek R1T "Chimera", a 671B open-weights hybrid model combining DeepSeek's V3-0324 and R1 model variants. The child inherits only the routed expert tensors of R1, but still achieves about R1-level intelligence. At the same time, it uses about 40\% fewer output tokens, close to V3 speed. Constructed without any fine-tuning or distillation, the Chimera exhibits surprisingly compact, orderly reasoning compared to its parent models.
Authors: Marco Nurisso, Jesseba Fernando, Raj Deshpande, Alan Perotti, Raja Marjieh, Steven M. Frankland, Richard L. Lewis, Taylor W. Webb, Declan Campbell, Francesco Vaccarino, Jonathan D. Cohen, Giovanni Petri
Abstract: Intelligent systems must deploy internal representations that are simultaneously structured -- to support broad generalization -- and selective -- to preserve input identity. We expose a fundamental limit on this tradeoff. For any model whose representational similarity between inputs decays with finite semantic resolution $\varepsilon$, we derive closed-form expressions that pin its probability of correct generalization $p_S$ and identification $p_I$ to a universal Pareto front independent of input space geometry. Extending the analysis to noisy, heterogeneous spaces and to $n>2$ inputs predicts a sharp $1/n$ collapse of multi-input processing capacity and a non-monotonic optimum for $p_S$. A minimal ReLU network trained end-to-end reproduces these laws: during learning a resolution boundary self-organizes and empirical $(p_S,p_I)$ trajectories closely follow theoretical curves for linearly decaying similarity. Finally, we demonstrate that the same limits persist in two markedly more complex settings -- a convolutional neural network and state-of-the-art vision-language models -- confirming that finite-resolution similarity is a fundamental emergent informational constraint, not merely a toy-model artifact. Together, these results provide an exact theory of the generalization-identification trade-off and clarify how semantic resolution shapes the representational capacity of deep networks and brains alike.
Authors: Zuochen Ye
Abstract: We propose ss-Mamba, a novel foundation model that enhances time series forecasting by integrating semantic-aware embeddings and adaptive spline-based temporal encoding within a selective state-space modeling framework. Building upon the recent success of Transformer architectures, ss-Mamba adopts the Mamba selective state space model as an efficient alternative that achieves comparable performance while significantly reducing computational complexity from quadratic to linear time. Semantic index embeddings, initialized from pretrained language models, allow effective generalization to previously unseen series through meaningful semantic priors. Additionally, spline-based Kolmogorov-Arnold Networks (KAN) dynamically and interpretably capture complex seasonalities and non-stationary temporal effects, providing a powerful enhancement over conventional temporal feature encodings. Extensive experimental evaluations confirm that ss-Mamba delivers superior accuracy, robustness, and interpretability, demonstrating its capability as a versatile and computationally efficient alternative to traditional Transformer-based models in time-series forecasting.
Authors: Bochen Lyu, Xiaojing Zhang, Fangyi Zheng, He Wang, Zheng Wang, Zhanxing Zhu
Abstract: This paper establishes a continuous time approximation, a piece-wise continuous differential equation, for the discrete Heavy-Ball (HB) momentum method with explicit discretization error. Investigating continuous differential equations has been a promising approach for studying the discrete optimization methods. Despite the crucial role of momentum in gradient-based optimization methods, the gap between the original discrete dynamics and the continuous time approximations due to the discretization error has not been comprehensively bridged yet. In this work, we study the HB momentum method in continuous time while putting more focus on the discretization error to provide additional theoretical tools to this area. In particular, we design a first-order piece-wise continuous differential equation, where we add a number of counter terms to account for the discretization error explicitly. As a result, we provide a continuous time model for the HB momentum method that allows the control of discretization error to arbitrary order of the step size. As an application, we leverage it to find a new implicit regularization of the directional smoothness and investigate the implicit bias of HB for diagonal linear networks, indicating how our results can be used in deep learning. Our theoretical findings are further supported by numerical experiments.
Authors: Jenny Schmalfuss, Nadine Chang, Vibashan VS, Maying Shen, Andres Bruhn, Jose M. Alvarez
Abstract: Vision language models (VLMs) respond to user-crafted text prompts and visual inputs, and are applied to numerous real-world problems. VLMs integrate visual modalities with large language models (LLMs), which are well known to be prompt-sensitive. Hence, it is crucial to determine whether VLMs inherit this instability to varying prompts. We therefore investigate which prompt variations VLMs are most sensitive to and which VLMs are most agnostic to prompt variations. To this end, we introduce PARC (Prompt Analysis via Reliability and Calibration), a VLM prompt sensitivity analysis framework built on three pillars: (1) plausible prompt variations in both the language and vision domain, (2) a novel model reliability score with built-in guarantees, and (3) a calibration step that enables dataset- and prompt-spanning prompt variation analysis. Regarding prompt variations, PARC's evaluation shows that VLMs mirror LLM language prompt sensitivity in the vision domain, and most destructive variations change the expected answer. Regarding models, outstandingly robust VLMs among 22 evaluated models come from the InternVL2 family. We further find indications that prompt sensitivity is linked to training data. The code will be at https://github.com/NVlabs/PARC.
Authors: Qiwen Zhang
Abstract: Sparse and intermittent demand forecasting in supply chains presents a critical challenge, as frequent zero-demand periods hinder traditional model accuracy and impact inventory management. We propose and evaluate a Model-Router framework that dynamically selects the most suitable forecasting model-spanning classical, ML, and DL methods for each product based on its unique demand pattern. By comparing rule-based, LightGBM, and InceptionTime routers, our approach learns to assign appropriate forecasting strategies, effectively differentiating between smooth, lumpy, or intermittent demand regimes to optimize predictions. Experiments on the large-scale Favorita dataset show our deep learning (Inception Time) router improves forecasting accuracy by up to 11.8% (NWRMSLE) over strong, single-model benchmarks with 4.67x faster inference time. Ultimately, these gains in forecasting precision will drive substantial reductions in both stockouts and wasteful excess inventory, underscoring the critical role of intelligent, adaptive Al in optimizing contemporary supply chain operations.
Authors: Mikel Malag\'on, Josu Ceberio, Jose A. Lozano
Abstract: This work introduces a growable and modular neural network architecture that naturally avoids catastrophic forgetting and interference in continual reinforcement learning. The structure of each module allows the selective combination of previous policies along with its internal policy, accelerating the learning process on the current task. Unlike previous growing neural network approaches, we show that the number of parameters of the proposed approach grows linearly with respect to the number of tasks, and does not sacrifice plasticity to scale. Experiments conducted in benchmark continuous control and visual problems reveal that the proposed approach achieves greater knowledge transfer and performance than alternative methods.
Authors: Yuxuan Jiang, Ziming Zhou, Boyu Xu, Beijie Liu, Runhui Xu, Peng Huang
Abstract: Training deep learning (DL) models is a complex process, making it prone to silent errors that are challenging to detect and diagnose. This paper presents TRAINCHECK, a framework that takes a proactive checking approach to address silent training errors. TRAINCHECK automatically infers invariants tailored for DL training. It uses these invariants to proactively detect silent errors during the training process while providing debugging help. To evaluate TRAINCHECK, we reproduce 20 real-world silent training errors with diverse root causes. TRAINCHECK successfully detects 18 errors within a single training iteration. It also uncovers 6 unknown bugs in popular training libraries that lead to silent errors.
Authors: Gyaneshwar Agrahari, Kiran Bist, Monika Pandey, Jacob Kapita, Zachary James, Jackson Knox, Steven Heymsfield, Sophia Ramirez, Peter Wolenski, Nadejda Drenska
Abstract: Accurate prediction of anthropometric body composition variables, such as Appendicular Lean Mass (ALM), Body Fat Percentage (BFP), and Bone Mineral Density (BMD), is essential for early diagnosis of several chronic diseases. Currently, researchers rely on Dual-Energy X-ray Absorptiometry (DXA) scans to measure these metrics; however, DXA scans are costly and time-consuming. This work proposes an alternative to DXA scans by applying statistical and machine learning models on biomarkers (height, volume, left calf circumference, etc) obtained from 3D optical images. The dataset consists of 847 patients and was sourced from Pennington Biomedical Research Center. Extracting patients' data in healthcare faces many technical challenges and legal restrictions. However, most supervised machine learning algorithms are inherently data-intensive, requiring a large amount of training data. To overcome these limitations, we implemented a semi-supervised model, the $p$-Laplacian regression model. This paper is the first to demonstrate the application of a $p$-Laplacian model for regression. Our $p$-Laplacian model yielded errors of $\sim13\%$ for ALM, $\sim10\%$ for BMD, and $\sim20\%$ for BFP when the training data accounted for 10 percent of all data. Among the supervised algorithms we implemented, Support Vector Regression (SVR) performed the best for ALM and BMD, yielding errors of $\sim 8\%$ for both, while Least Squares SVR performed the best for BFP with $\sim 11\%$ error when trained on 80 percent of the data. Our findings position the $p$-Laplacian model as a promising tool for healthcare applications, particularly in a data-constrained environment.
Authors: Sunil Kumar, Bowen Zhao, Leo Dirac, Paulina Varshavskaya
Abstract: Despite tremendous recent advances in large model reasoning ability, vision-language models (VLMs) still struggle with detailed visual reasoning, especially when compute resources are limited. To address this challenge, we draw inspiration from methods like Deepseek-r1 for VLMs and train smaller-scale models with Group Relative Policy Optimization (GRPO) to use external tools such as zoom. The greatest benefit is obtained with a combination of GRPO learning, a simple reward structure, a simplified tool-calling interface, allocating additional tokens to the result of the tool call, and a training data mix that over-represents visually difficult examples. Compared to similarly-sized baseline models, our method achieves better performance on some visual question-answering (VQA) tasks, thanks to the detailed visual information gathered from the external tool.
Authors: Yao Zhang, Hewei Gao, Haokun Chen, Weiguo Li, Yunpu Ma, Volker Tresp
Abstract: Multimodal Large Language Models (MLLMs) excel in tasks like multimodal reasoning and cross-modal retrieval but face deployment challenges in real-world scenarios due to distributed multimodal data and strict privacy requirements. Federated Learning (FL) offers a solution by enabling collaborative model training without centralizing data. However, realizing FL for MLLMs presents significant challenges, including high computational demands, limited client capacity, substantial communication costs, and heterogeneous client data. Existing FL methods assume client-side deployment of full models, an assumption that breaks down for large-scale MLLMs due to their massive size and communication demands. To address these limitations, we propose FedNano, the first FL framework that centralizes the LLM on the server while introducing NanoEdge, a lightweight module for client-specific adaptation. NanoEdge employs modality-specific encoders, connectors, and trainable NanoAdapters with low-rank adaptation. This design eliminates the need to deploy LLM on clients, reducing client-side storage by 95%, and limiting communication overhead to only 0.01% of the model parameters. By transmitting only compact NanoAdapter updates, FedNano handles heterogeneous client data and resource constraints while preserving privacy. Experiments demonstrate that FedNano outperforms prior FL baselines, bridging the gap between MLLM scale and FL feasibility, and enabling scalable, decentralized multimodal AI systems.
Authors: Sk Md Ahnaf Akif Alvi, Mrinalini Mulukutla, Nicolas Flores, Danial Khatamsaz, Jan Janssen, Danny Perez, Douglas Allaire, Vahid Attari, Raymundo Arroyave
Abstract: Surrogate modeling techniques have become indispensable in accelerating the discovery and optimization of high-entropy alloys(HEAs), especially when integrating computational predictions with sparse experimental observations. This study systematically evaluates the fitting performance of four prominent surrogate models conventional Gaussian Processes(cGP), Deep Gaussian Processes(DGP), encoder-decoder neural networks for multi-output regression and XGBoost applied to a hybrid dataset of experimental and computational properties in the AlCoCrCuFeMnNiV HEA system. We specifically assess their capabilities in predicting correlated material properties, including yield strength, hardness, modulus, ultimate tensile strength, elongation, and average hardness under dynamic and quasi-static conditions, alongside auxiliary computational properties. The comparison highlights the strengths of hierarchical and deep modeling approaches in handling heteroscedastic, heterotopic, and incomplete data commonly encountered in materials informatics. Our findings illustrate that DGP infused with machine learning-based prior outperform other surrogates by effectively capturing inter-property correlations and input-dependent uncertainty. This enhanced predictive accuracy positions advanced surrogate models as powerful tools for robust and data-efficient materials design.
Authors: Zhizhao Wen, Ruoxin Zhang, Chao Wang
Abstract: Aiming at the critical role of SSD health state prediction in data reliability assurance, this study proposes a hybrid BiGRU-MHA model that incorporates a multi-head attention mechanism to enhance the accuracy and stability of storage device health classification. The model innovatively integrates temporal feature extraction and key information focusing capabilities. Specifically, it leverages the bidirectional timing modeling advantages of the BiGRU network to capture both forward and backward dependencies of SSD degradation features. Simultaneously, the multi-head attention mechanism dynamically assigns feature weights, improving the model's sensitivity to critical health indicators. Experimental results show that the proposed model achieves classification accuracies of 92.70% on the training set and 92.44% on the test set, with a minimal performance gap of only 0.26%, demonstrating excellent generalization ability. Further analysis using the receiver operating characteristic (ROC) curve shows an area under the curve (AUC) of 0.94 on the test set, confirming the model's robust binary classification performance. This work not only presents a new technical approach for SSD health prediction but also addresses the generalization bottleneck of traditional models, offering a verifiable method with practical value for preventive maintenance of industrial-grade storage systems. The results show the model can significantly reduce data loss risks by providing early failure warnings and help optimize maintenance costs, supporting intelligent decision-making in building reliable storage systems for cloud computing data centers and edge storage environments.
Authors: Luca Gherardini, Imre Lengyel, Tunde Peto, Caroline C. W. Klaverd, Magda A. Meester-Smoord, Johanna Maria Colijnd, EYE-RISK Consortium, E3 Consortium, Jose Sousa
Abstract: Machine Learning (ML) is used to tackle various tasks, such as disease classification and prediction. The effectiveness of ML models relies heavily on having large amounts of complete data. However, healthcare data is often limited or incomplete, which can hinder model performance. Additionally, issues like the trustworthiness of solutions vary with the datasets used. The lack of transparency in some ML models further complicates their understanding and use. In healthcare, particularly in the case of Age-related Macular Degeneration (AMD), which affects millions of older adults, early diagnosis is crucial due to the absence of effective treatments for reversing progression. Diagnosing AMD involves assessing retinal images along with patients' symptom reports. There is a need for classification approaches that consider genetic, dietary, clinical, and demographic factors. Recently, we introduced the -Comprehensive Abstraction and Classification Tool for Uncovering Structures-(CACTUS), aimed at improving AMD stage classification. CACTUS offers explainability and flexibility, outperforming standard ML models. It enhances decision-making by identifying key factors and providing confidence in its results. The important features identified by CACTUS allow us to compare with existing medical knowledge. By eliminating less relevant or biased data, we created a clinical scenario for clinicians to offer feedback and address biases.
Authors: Jenni Raitoharju
Abstract: This paper focuses on small-scale one-class classification with some negative samples available. We propose Generalized Reference Kernel with Negative Samples (GRKneg) for One-class Support Vector Machine (OC-SVM). We study different ways to select/generate the reference vectors and recommend an approach for the problem at hand. It is worth noting that the proposed method does not use any labels in the model optimization but uses the original OC-SVM implementation. Only the kernel used in the process is improved using the negative data. We compare our method with the standard OC-SVM and with the binary Support Vector Machine (SVM) using different amounts of negative samples. Our approach consistently outperforms the standard OC-SVM using Radial Basis Function kernel. When there are plenty of negative samples, the binary SVM outperforms the one-class approaches as expected, but we show that for the lowest numbers of negative samples the proposed approach clearly outperforms the binary SVM.
Authors: Ganyu Wang, Boyu Wang, Bin Gu, Charles Ling
Abstract: Online learning is more adaptable to real-world scenarios in Vertical Federated Learning (VFL) compared to offline learning. However, integrating online learning into VFL presents challenges due to the unique nature of VFL, where clients possess non-intersecting feature sets for the same sample. In real-world scenarios, the clients may not receive data streaming for the disjoint features for the same entity synchronously. Instead, the data are typically generated by an \emph{event} relevant to only a subset of clients. We are the first to identify these challenges in online VFL, which have been overlooked by previous research. To address these challenges, we proposed an event-driven online VFL framework. In this framework, only a subset of clients were activated during each event, while the remaining clients passively collaborated in the learning process. Furthermore, we incorporated \emph{dynamic local regret (DLR)} into VFL to address the challenges posed by online learning problems with non-convex models within a non-stationary environment. We conducted a comprehensive regret analysis of our proposed framework, specifically examining the DLR under non-convex conditions with event-driven online VFL. Extensive experiments demonstrated that our proposed framework was more stable than the existing online VFL framework under non-stationary data conditions while also significantly reducing communication and computation costs.
Authors: Ganyu Wang, Jinjie Fang, Maxwell J. Ying, Bin Gu, Xi Chen, Boyu Wang, Charles Ling
Abstract: Black-Box Discrete Prompt Learning is a prompt-tuning method that optimizes discrete prompts without accessing model parameters or gradients, making the prompt tuning on a cloud-based Large Language Model (LLM) feasible. Adapting federated learning to BDPL could further enhance prompt tuning performance by leveraging data from diverse sources. However, all previous research on federated black-box prompt tuning had neglected the substantial query cost associated with the cloud-based LLM service. To address this gap, we conducted a theoretical analysis of query efficiency within the context of federated black-box prompt tuning. Our findings revealed that degrading FedAvg to activate only one client per round, a strategy we called \textit{FedOne}, enabled optimal query efficiency in federated black-box prompt learning. Building on this insight, we proposed the FedOne framework, a federated black-box discrete prompt learning method designed to maximize query efficiency when interacting with cloud-based LLMs. We conducted numerical experiments on various aspects of our framework, demonstrating a significant improvement in query efficiency, which aligns with our theoretical results.
Authors: Luan Gon\c{c}alves Miranda, Pedro Ivo da Cruz, Murilo Bellezoni Loiola
Abstract: Currently, digital security mechanisms like Anomaly Detection Systems using Autoencoders (AE) show great potential for bypassing problems intrinsic to the data, such as data imbalance. Because AE use a non-trivial and nonstandardized separation threshold to classify the extracted reconstruction error, the definition of this threshold directly impacts the performance of the detection process. Thus, this work proposes the automatic definition of this threshold using some machine learning algorithms. For this, three algorithms were evaluated: the K-Nearst Neighbors, the K-Means and the Support Vector Machine.
Authors: Flavio Martinelli, Alexander Van Meegen, Berfin \c{S}im\c{s}ek, Wulfram Gerstner, Johanni Brea
Abstract: The loss landscapes of neural networks contain minima and saddle points that may be connected in flat regions or appear in isolation. We identify and characterize a special structure in the loss landscape: channels along which the loss decreases extremely slowly, while the output weights of at least two neurons, $a_i$ and $a_j$, diverge to $\pm$infinity, and their input weight vectors, $\mathbf{w_i}$ and $\mathbf{w_j}$, become equal to each other. At convergence, the two neurons implement a gated linear unit: $a_i\sigma(\mathbf{w_i} \cdot \mathbf{x}) + a_j\sigma(\mathbf{w_j} \cdot \mathbf{x}) \rightarrow \sigma(\mathbf{w} \cdot \mathbf{x}) + (\mathbf{v} \cdot \mathbf{x}) \sigma'(\mathbf{w} \cdot \mathbf{x})$. Geometrically, these channels to infinity are asymptotically parallel to symmetry-induced lines of critical points. Gradient flow solvers, and related optimization methods like SGD or ADAM, reach the channels with high probability in diverse regression settings, but without careful inspection they look like flat local minima with finite parameter values. Our characterization provides a comprehensive picture of these quasi-flat regions in terms of gradient dynamics, geometry, and functional interpretation. The emergence of gated linear units at the end of the channels highlights a surprising aspect of the computational capabilities of fully connected layers.
Authors: Zhoujun Cheng, Shibo Hao, Tianyang Liu, Fan Zhou, Yutao Xie, Feng Yao, Yuexin Bian, Yonghao Zhuang, Nilabjo Dey, Yuheng Zha, Yi Gu, Kun Zhou, Yuqi Wang, Yuan Li, Richard Fan, Jianshu She, Chengqian Gao, Abulhair Saparov, Haonan Li, Taylor W. Killian, Mikhail Yurochkin, Zhengzhong Liu, Eric P. Xing, Zhiting Hu
Abstract: Reinforcement learning (RL) has emerged as a promising approach to improve large language model (LLM) reasoning, yet most open efforts focus narrowly on math and code, limiting our understanding of its broader applicability to general reasoning. A key challenge lies in the lack of reliable, scalable RL reward signals across diverse reasoning domains. We introduce Guru, a curated RL reasoning corpus of 92K verifiable examples spanning six reasoning domains--Math, Code, Science, Logic, Simulation, and Tabular--each built through domain-specific reward design, deduplication, and filtering to ensure reliability and effectiveness for RL training. Based on Guru, we systematically revisit established findings in RL for LLM reasoning and observe significant variation across domains. For example, while prior work suggests that RL primarily elicits existing knowledge from pretrained models, our results reveal a more nuanced pattern: domains frequently seen during pretraining (Math, Code, Science) easily benefit from cross-domain RL training, while domains with limited pretraining exposure (Logic, Simulation, and Tabular) require in-domain training to achieve meaningful performance gains, suggesting that RL is likely to facilitate genuine skill acquisition. Finally, we present Guru-7B and Guru-32B, two models that achieve state-of-the-art performance among open models RL-trained with publicly available data, outperforming best baselines by 7.9% and 6.7% on our 17-task evaluation suite across six reasoning domains. We also show that our models effectively improve the Pass@k performance of their base models, particularly on complex tasks less likely to appear in pretraining data. We release data, models, training and evaluation code to facilitate general-purpose reasoning at: https://github.com/LLM360/Reasoning360
Authors: Aayush Mishra, Anqi Liu
Abstract: Reliable and accurate estimation of the error of an ML model in unseen test domains is an important problem for safe intelligent systems. Prior work uses disagreement discrepancy (DIS^2) to derive practical error bounds under distribution shifts. It optimizes for a maximally disagreeing classifier on the target domain to bound the error of a given source classifier. Although this approach offers a reliable and competitively accurate estimate of the target error, we identify a problem in this approach which causes the disagreement discrepancy objective to compete in the overlapping region between source and target domains. With an intuitive assumption that the target disagreement should be no more than the source disagreement in the overlapping region due to high enough support, we devise Overlap-aware Disagreement Discrepancy (ODD). Maximizing ODD only requires disagreement in the non-overlapping target domain, removing the competition. Our ODD-based bound uses domain-classifiers to estimate domain-overlap and better predicts target performance than DIS^2. We conduct experiments on a wide array of benchmarks to show that our method improves the overall performance-estimation error while remaining valid and reliable. Our code and results are available on GitHub.
Authors: Maxime Usdin, Lito Kriara, Licinio Craveiro
Abstract: Early multiple sclerosis (MS) disability progression prediction is challenging due to disease heterogeneity. This work predicts 48- and 72-week disability using sparse baseline clinical data and 12 weeks of daily digital Floodlight data from the CONSONANCE clinical trial. We employed state-of-the-art tabular and time-series foundation models (FMs), a custom multimodal attention-based transformer, and machine learning methods. Despite the difficulty of early prediction (AUROC 0.63), integrating digital data via advanced models improved performance over clinical data alone. A transformer model using unimodal embeddings from the Moment FM yielded the best result, but our multimodal transformer consistently outperformed its unimodal counterpart, confirming the advantages of combining clinical with digital data. Our findings demonstrate the promise of FMs and multimodal approaches to extract predictive signals from complex and diverse clinical and digital life sciences data (e.g., imaging, omics), enabling more accurate prognostics for MS and potentially other complex diseases.
Authors: Tianyi Xu, Jiaxin Liu, Zizhan Zheng
Abstract: We propose a multi-agent multi-armed bandit (MA-MAB) framework aimed at ensuring fair outcomes across agents while maximizing overall system performance. A key challenge in this setting is decision-making under limited information about arm rewards. To address this, we introduce a novel probing framework that strategically gathers information about selected arms before allocation. In the offline setting, where reward distributions are known, we leverage submodular properties to design a greedy probing algorithm with a provable performance bound. For the more complex online setting, we develop an algorithm that achieves sublinear regret while maintaining fairness. Extensive experiments on synthetic and real-world datasets show that our approach outperforms baseline methods, achieving better fairness and efficiency.
Authors: Yue Gao
Abstract: Effective reinforcement learning (RL) for sepsis treatment depends on learning stable, clinically meaningful state representations from irregular ICU time series. While previous works have explored representation learning for this task, the critical challenge of training instability in sequential representations and its detrimental impact on policy performance has been overlooked. This work demonstrates that Controlled Differential Equations (CDE) state representation can achieve strong RL policies when two key factors are met: (1) ensuring training stability through early stopping or stabilization methods, and (2) enforcing acuity-aware representations by correlation regularization with clinical scores (SOFA, SAPS-II, OASIS). Experiments on the MIMIC-III sepsis cohort reveal that stable CDE autoencoder produces representations strongly correlated with acuity scores and enables RL policies with superior performance (WIS return $> 0.9$). In contrast, unstable CDE representation leads to degraded representations and policy failure (WIS return $\sim$ 0). Visualizations of the latent space show that stable CDEs not only separate survivor and non-survivor trajectories but also reveal clear acuity score gradients, whereas unstable training fails to capture either pattern. These findings highlight practical guidelines for using CDEs to encode irregular medical time series in clinical RL, emphasizing the need for training stability in sequential representation learning.
Authors: Gyuhak Kim, Sumiran Singh Thakur, Su Min Park, Wei Wei, Yujia Bao
Abstract: Supervised fine-tuning (SFT) has become an essential step in tailoring large language models (LLMs) to align with human expectations and specific downstream tasks. However, existing SFT methods typically treat each training instance as a uniform sequence, giving equal importance to all tokens regardless of their relevance. This overlooks the fact that only a subset of tokens often contains critical, task-specific information. To address this limitation, we introduce Supervised Fine-Tuning with Group Optimization (SFT-GO), a novel approach that treats groups of tokens differently based on their importance.SFT-GO groups tokens in each sample based on their importance values and optimizes the LLM using a weighted combination of the worst-group loss and the standard cross-entropy loss. This mechanism adaptively emphasizes the most challenging token groups and guides the model to better handle different group distributions, thereby improving overall learning dynamics. We provide a theoretical analysis of SFT-GO's convergence rate, demonstrating its efficiency. Empirically, we apply SFT-GO with three different token grouping strategies and show that models trained with SFT-GO consistently outperform baseline approaches across popular LLM benchmarks. These improvements hold across various datasets and base models, demonstrating the robustness and the effectiveness of our method.
Authors: Soufiane Hayou, Liyuan Liu
Abstract: Pretraining large language models is a costly process. To make this process more efficient, several methods have been proposed to optimize model architecture/parametrization and hardware use. On the parametrization side, $\mu P$ (Maximal Update Parametrization) parametrizes model weights and learning rate (LR) in a way that makes hyperparameters (HPs) transferable with width (embedding dimension): HPs can be tuned for a small model and used for larger models without additional tuning. While $\mu$P showed impressive results in practice, recent empirical studies have reported conflicting observations when applied to LLMs. One limitation of the theory behind $\mu$P is the fact that input dimension (vocabulary size in LLMs) is considered fixed when taking the width to infinity. This is unrealistic since vocabulary size is generally much larger than width in practice. In this work, we provide a theoretical analysis of the effect of vocabulary size on training dynamics, and subsequently show that as vocabulary size increases, the training dynamics \emph{interpolate between the $\mu$P regime and another regime that we call Large Vocab (LV) Regime}, where optimal scaling rules are different from those predicted by $\mu$P. Our analysis reveals that in the LV regime, the optimal embedding LR to hidden LR ratio should roughly scale as $\Theta(\sqrt{width})$, surprisingly close to the empirical findings previously reported in the literature, and different from the $\Theta(width)$ ratio predicted by $\mu$P. We conduct several experiments to validate our theory, and pretrain a 1B model from scratch to show the benefit of our suggested scaling rule for the embedding LR.
Authors: Zheng Li, Jerry Cheng, Huanying Helen Gu
Abstract: Reinforcement learning is essential for neural architecture search and hyperparameter optimization, but the conventional approaches impede widespread use due to prohibitive time and computational costs. Inspired by DeepSeek-V3 multi-token prediction architecture, we propose Sequential Policy Gradient modeling (SPG), a novel trajectory generation paradigm for lightweight online hyperparameter optimization. In contrast to conventional policy gradient methods, SPG extends the base model with temporary modules, enabling it to generate state-action (padded) trajectories in a single forward pass. Our experiments demonstrate that models gain performance when retrained with SPG on their original datasets and also outperform standard transfer fine-tuning. We evaluate on five datasets spanning computer vision (ImageNet, COCO), natural language processing (GLUE, SQuAD), and audio (SUPERB) to assess the industrial applicability of SPG. The proposed method demonstrates consistent improvements across widely adopted models, achieving performance gains of $+0.2\sim7\%$, with significantly low computational costs. Fully reproducible code and pre-trained models: https://huggingface.co/UniversalAlgorithmic/SPG.
Authors: Lizhang Chen, Jonathan Li, Qiang Liu
Abstract: The pursuit of faster optimization algorithms remains an active and important research direction in deep learning. Recently, the Muon optimizer [JJB+24] has demonstrated promising empirical performance, but its theoretical foundation remains less understood. In this paper, we bridge this gap and provide a theoretical analysis of Muon by placing it within the Lion-$\mathcal{K}$ family of optimizers [CLLL24]. Specifically, we show that Muon corresponds to Lion-$\mathcal{K}$ when equipped with the nuclear norm, and we leverage the theoretical results of Lion-$\mathcal{K}$ to establish that Muon (with decoupled weight decay) implicitly solves an optimization problem that enforces a constraint on the spectral norm of weight matrices. This perspective not only demystifies the implicit regularization effects of Muon but also leads to natural generalizations through varying the choice of convex map $\mathcal{K}$, allowing for the exploration of a broader class of implicitly regularized and constrained optimization algorithms.
Authors: Ethan Mulle, Wei Kang, Qi Gong
Abstract: Deep neural networks are powerful tools for solving nonlinear problems in science and engineering, but training highly accurate models becomes challenging as problem complexity increases. Non-convex optimization and numerous hyperparameters to tune make performance improvement difficult, and traditional approaches often prioritize minimizing mean squared error (MSE) while overlooking $L^{\infty}$ error, which is the critical focus in many applications. To address these challenges, we present a progressive framework for training and tuning high-precision neural networks (HiPreNets). Our approach refines a previously explored staged training technique for neural networks that improves an existing fully connected neural network by sequentially learning its prediction residuals using additional networks, leading to improved overall accuracy. We discuss how to take advantage of the structure of the residuals to guide the choice of loss function, number of parameters to use, and ways to introduce adaptive data sampling techniques. We validate our framework's effectiveness through several benchmark problems.
Authors: Trishna Chakraborty, Udita Ghosh, Xiaopan Zhang, Fahim Faisal Niloy, Yue Dong, Jiachen Li, Amit K. Roy-Chowdhury, Chengyu Song
Abstract: Large language models (LLMs) are increasingly being adopted as the cognitive core of embodied agents. However, inherited hallucinations, which stem from failures to ground user instructions in the observed physical environment, can lead to navigation errors, such as searching for a refrigerator that does not exist. In this paper, we present the first systematic study of hallucinations in LLM-based embodied agents performing long-horizon tasks under scene-task inconsistencies. Our goal is to understand to what extent hallucinations occur, what types of inconsistencies trigger them, and how current models respond. To achieve these goals, we construct a hallucination probing set by building on an existing benchmark, capable of inducing hallucination rates up to 40x higher than base prompts. Evaluating 12 models across two simulation environments, we find that while models exhibit reasoning, they fail to resolve scene-task inconsistencies-highlighting fundamental limitations in handling infeasible tasks. We also provide actionable insights on ideal model behavior for each scenario, offering guidance for developing more robust and reliable planning strategies.
Authors: Yikai Hou, Peng Tang
Abstract: Modern intelligent transportation systems rely on accurate spatiotemporal traffic analysis to optimize urban mobility and infrastructure resilience. However, pervasive missing data caused by sensor failures and heterogeneous sensing gaps fundamentally hinders reliable traffic modeling. This paper proposes a Neural Canonical Polyadic Factorization (NCPF) model that synergizes low-rank tensor algebra with deep representation learning for robust traffic data imputation. The model innovatively embeds CP decomposition into neural architecture through learnable embedding projections, where sparse traffic tensors are encoded into dense latent factors across road segments, time intervals, and mobility metrics. A hierarchical feature fusion mechanism employs Hadamard products to explicitly model multilinear interactions, while stacked multilayer perceptron layers nonlinearly refine these representations to capture complex spatiotemporal couplings. Extensive evaluations on six urban traffic datasets demonstrate NCPF's superiority over six state-of-the-art baselines. By unifying CP decomposition's interpretable factor analysis with neural network's nonlinear expressive power, NCPF provides a principled yet flexible approaches for high-dimensional traffic data imputation, offering critical support for next-generation transportation digital twins and adaptive traffic control systems.
Authors: Lulu Xue, Shengshan Hu, Wei Lu, Yan Shen, Dongxu Li, Peijin Guo, Ziqi Zhou, Minghui Li, Yanjun Zhang, Leo Yu Zhang
Abstract: With growing demands for privacy protection, security, and legal compliance (e.g., GDPR), machine unlearning has emerged as a critical technique for ensuring the controllability and regulatory alignment of machine learning models. However, a fundamental challenge in this field lies in effectively verifying whether unlearning operations have been successfully and thoroughly executed. Despite a growing body of work on unlearning techniques, verification methodologies remain comparatively underexplored and often fragmented. Existing approaches lack a unified taxonomy and a systematic framework for evaluation. To bridge this gap, this paper presents the first structured survey of machine unlearning verification methods. We propose a taxonomy that organizes current techniques into two principal categories -- behavioral verification and parametric verification -- based on the type of evidence used to assess unlearning fidelity. We examine representative methods within each category, analyze their underlying assumptions, strengths, and limitations, and identify potential vulnerabilities in practical deployment. In closing, we articulate a set of open problems in current verification research, aiming to provide a foundation for developing more robust, efficient, and theoretically grounded unlearning verification mechanisms.
Authors: Bing Liu, Chengcheng Zhao, Li Chai, Peng Cheng, Yaonan Wang
Abstract: Jointly addressing Byzantine attacks and privacy leakage in distributed machine learning (DML) has become an important issue. A common strategy involves integrating Byzantine-resilient aggregation rules with differential privacy mechanisms. However, the incorporation of these techniques often results in a significant degradation in model accuracy. To address this issue, we propose a decentralized DML framework, named ImprovDML, that achieves high model accuracy while simultaneously ensuring privacy preservation and resilience to Byzantine attacks. The framework leverages a kind of resilient vector consensus algorithms that can compute a point within the normal (non-Byzantine) agents' convex hull for resilient aggregation at each iteration. Then, multivariate Gaussian noises are introduced to the gradients for privacy preservation. We provide convergence guarantees and derive asymptotic learning error bounds under non-convex settings, which are tighter than those reported in existing works. For the privacy analysis, we adopt the notion of concentrated geo-privacy, which quantifies privacy preservation based on the Euclidean distance between inputs. We demonstrate that it enables an improved trade-off between privacy preservation and model accuracy compared to differential privacy. Finally, numerical simulations validate our theoretical results.
Authors: Jiyi Wang, Jingyang Ke, Bo Dai, Anqi Wu
Abstract: Animals flexibly recombine a finite set of core motor primitives to meet diverse task demands, but existing behavior-segmentation methods oversimplify this process by imposing discrete syllables under restrictive generative assumptions. To reflect the animal behavior generation procedure, we introduce skill-based imitation learning (SKIL) for behavior understanding, a reinforcement learning-based imitation framework that (1) infers interpretable skill sets, i.e., latent basis functions of behavior, by leveraging representation learning on transition probabilities, and (2) parameterizes policies as dynamic mixtures of these skills. We validate our approach on a simple grid world, a discrete labyrinth, and unconstrained videos of freely moving animals. Across tasks, it identifies reusable skill components, learns continuously evolving compositional policies, and generates realistic trajectories beyond the capabilities of traditional discrete models. By exploiting generative behavior modeling with compositional representations, our method offers a concise, principled account of how complex animal behaviors emerge from dynamic combinations of fundamental motor primitives.
Authors: Alejandro Francisco Queiruga, Theo Gutman-Solo, Shuai Jiang
Abstract: While there are many applications of ML to scientific problems that look promising, visuals can be deceiving. For scientific applications, actual quantitative accuracy is crucial. This work applies the rigor of numerical analysis for differential equations to machine learning by specifically quantifying the accuracy of applying different ML techniques to the elementary 1D Poisson differential equation. Beyond the quantity and discretization of data, we identify that the function space of the data is critical to the generalization of the model. We prove generalization bounds and convergence rates under finite data discretizations and restricted training data subspaces by analyzing the training dynamics and deriving optimal parameters for both a white-box differential equation discovery method and a black-box linear model. The analytically derived generalization bounds are replicated empirically. Similar lack of generalization is empirically demonstrated for deep linear models, shallow neural networks, and physics-specific DeepONets and Neural Operators. We theoretically and empirically demonstrate that generalization to the true physical equation is not guaranteed in each explored case. Surprisingly, we find that different classes of models can exhibit opposing generalization behaviors. Based on our theoretical analysis, we also demonstrate a new mechanistic interpretability lens on scientific models whereby Green's function representations can be extracted from the weights of black-box models. Our results inform a new cross-validation technique for measuring generalization in physical systems. We propose applying it to the Poisson equation as an evaluation benchmark of future methods.
Authors: Yee Hin Chong, Peng Qu
Abstract: Large pre-trained Transformer models achieve state-of-the-art results across diverse language and reasoning tasks, but full fine-tuning incurs substantial storage, memory, and computational overhead. Parameter-efficient fine-tuning (PEFT) methods mitigate these costs by learning only a small subset of task-specific parameters, yet existing approaches either introduce inference-time latency (adapter modules), suffer from suboptimal convergence (randomly initialized low-rank updates), or rely on fixed rank choices that may not match task complexity (Kronecker-based decompositions). We propose SoKA (SVD on Kronecker Adaptation), a novel PEFT strategy that combines Kronecker-product tensor factorization with SVD-driven initialization and spectrum-aware dynamic rank selection. Our Kronecker-Product SVD (KPSVD) procedure extracts principal components of the full weight update into compact Kronecker factors, while an adaptive rank selection algorithm uses energy-threshold and elbow-point criteria to prune negligible components. Empirical evaluation on LLaMA2-7B across arithmetic reasoning (GSM8K), formal mathematics (MATH), and code generation (MBPP) demonstrates that SoKA requires only 0.99M trainable parameters, 25% fewer than LoRA/PiSSA, while matching or exceeding baseline performance. Moreover, SoKA exhibits faster convergence and more stable gradients, highlighting its robustness and efficiency for large-scale model adaptation.
Authors: M\'elanie Cambus, Darya Melnyk, Tijana Milentijevi\'c, Stefan Schmid
Abstract: Federated learning allows each client to keep its data locally when training machine learning models in a distributed setting. Significant recent research established the requirements that the input must satisfy in order to guarantee convergence of the training loop. This line of work uses averaging as the aggregation rule for the training models. In particular, we are interested in whether federated learning is robust to Byzantine behavior, and observe and investigate a tradeoff between the average/centroid and the validity conditions from distributed computing. We show that the various validity conditions alone do not guarantee a good approximation of the average. Furthermore, we show that reaching good approximation does not give good results in experimental settings due to possible Byzantine outliers. Our main contribution is the first lower bound of $\min\{\frac{n-t}{t},\sqrt{d}\}$ on the centroid approximation under box validity that is often considered in the literature, where $n$ is the number of clients, $t$ the upper bound on the number of Byzantine faults, and $d$ is the dimension of the machine learning model. We complement this lower bound by an upper bound of $2\min\{n,\sqrt{d}\}$, by providing a new analysis for the case $n
Authors: Bihe Zhao, Pratyush Maini, Franziska Boenisch, Adam Dziedzic
Abstract: The remarkable capabilities of Large Language Models (LLMs) can be mainly attributed to their massive training datasets, which are often scraped from the internet without respecting data owners' intellectual property rights. Dataset Inference (DI) offers a potential remedy by identifying whether a suspect dataset was used in training, thereby enabling data owners to verify unauthorized use. However, existing DI methods require a private set-known to be absent from training-that closely matches the compromised dataset's distribution. Such in-distribution, held-out data is rarely available in practice, severely limiting the applicability of DI. In this work, we address this challenge by synthetically generating the required held-out set. Our approach tackles two key obstacles: (1) creating high-quality, diverse synthetic data that accurately reflects the original distribution, which we achieve via a data generator trained on a carefully designed suffix-based completion task, and (2) bridging likelihood gaps between real and synthetic data, which is realized through post-hoc calibration. Extensive experiments on diverse text datasets show that using our generated data as a held-out set enables DI to detect the original training sets with high confidence, while maintaining a low false positive rate. This result empowers copyright owners to make legitimate claims on data usage and demonstrates our method's reliability for real-world litigations. Our code is available at https://github.com/sprintml/PostHocDatasetInference.
Authors: Chuan Li, Shunyu Zhao, Vincent Gauthier, Hassine Moungla
Abstract: The accelerating uptake of battery-electric vehicles demands infrastructure planning tools that are both data-rich and geographically scalable. Whereas most prior studies optimise charging locations for single cities, state-wide and national networks must reconcile the conflicting requirements of dense metropolitan cores, car-dependent exurbs, and power-constrained rural corridors. We present DOVA-PATBM (Deployment Optimisation with Voronoi-oriented, Adaptive, POI-Aware Temporal Behaviour Model), a geo-computational framework that unifies these contexts in a single pipeline. The method rasterises heterogeneous data (roads, population, night lights, POIs, and feeder lines) onto a hierarchical H3 grid, infers intersection importance with a zone-normalised graph neural network centrality model, and overlays a Voronoi tessellation that guarantees at least one five-port DC fast charger within every 30 km radius. Hourly arrival profiles, learned from loop-detector and floating-car traces, feed a finite M/M/c queue to size ports under feeder-capacity and outage-risk constraints. A greedy maximal-coverage heuristic with income-weighted penalties then selects the minimum number of sites that satisfy coverage and equity targets. Applied to the State of Georgia, USA, DOVA-PATBM (i) increases 30 km tile coverage by 12 percentage points, (ii) halves the mean distance that low-income residents travel to the nearest charger, and (iii) meets sub-transmission headroom everywhere -- all while remaining computationally tractable for national-scale roll-outs. These results demonstrate that a tightly integrated, GNN-driven, multi-resolution approach can bridge the gap between academic optimisation and deployable infrastructure policy.
Authors: Qingkai Zhang, L. Jeff Hong, Houmin Yan
Abstract: The rapid expansion of cross-border e-commerce (CBEC) has created significant opportunities for small and medium-sized enterprises (SMEs), yet financing remains a critical challenge due to SMEs' limited credit histories. Third-party logistics (3PL)-led supply chain finance (SCF) has emerged as a promising solution, leveraging in-transit inventory as collateral. We propose an advanced credit risk management framework tailored for 3PL-led SCF, addressing the dual challenges of credit risk assessment and loan size determination. Specifically, we leverage conditional generative modeling of sales distributions through Quantile-Regression-based Generative Metamodeling (QRGMM) as the foundation for risk estimation. We propose a unified framework that enables flexible estimation of multiple risk measures while introducing a functional risk measure formulation that systematically captures the relationship between these risk measures and varying loan levels, supported by theoretical guarantees. To capture complex covariate interactions in e-commerce sales data, we integrate QRGMM with Deep Factorization Machines (DeepFM). Extensive experiments on synthetic and real-world data validate the efficacy of our model for credit risk assessment and loan size determination. This study represents a pioneering application of generative AI in CBEC SCF risk management, offering a solid foundation for enhanced credit practices and improved SME access to capital.
Authors: Jinglong Luo, Zhuo Zhang, Yehong Zhang, Shiyu Liu, Ye Dong, Xun Zhou, Hui Wang, Yue Yu, Zenglin Xu
Abstract: Large language models (LLMs) have transformed numerous fields, yet their adaptation to specialized tasks in privacy-sensitive domains, such as healthcare and finance, is constrained by the scarcity of accessible training data due to stringent privacy requirements. Secure multi-party computation (MPC)-based privacy-preserving machine learning offers a powerful approach to protect both model parameters and user data, but its application to LLMs has been largely limited to inference, as fine-tuning introduces significant computational challenges, particularly in privacy-preserving backward propagation and optimizer operations. This paper identifies two primary obstacles to MPC-based privacy-preserving fine-tuning of LLMs: (1) the substantial computational overhead of backward and optimizer processes, and (2) the inefficiency of softmax-based attention mechanisms in MPC settings. To address these challenges, we propose SecFwT, the first MPC-based framework designed for efficient, privacy-preserving LLM fine-tuning. SecFwT introduces a forward-only tuning paradigm to eliminate backward and optimizer computations and employs MPC-friendly Random Feature Attention to approximate softmax attention, significantly reducing costly non-linear operations and computational complexity. Experimental results demonstrate that SecFwT delivers substantial improvements in efficiency and privacy preservation, enabling scalable and secure fine-tuning of LLMs for privacy-critical applications.
Authors: J\'ulia Vilalta-Mor, Alexis Molina, Laura Ortega Varga, Isaac Filella-Merce, Victor Guallar
Abstract: Simultaneously optimizing molecules against multiple therapeutic targets remains a profound challenge in drug discovery, particularly due to sparse rewards and conflicting design constraints. We propose a structured active learning (AL) paradigm integrating a sequence-to-sequence (Seq2Seq) variational autoencoder (VAE) into iterative loops designed to balance chemical diversity, molecular quality, and multi-target affinity. Our method alternates between expanding chemically feasible regions of latent space and progressively constraining molecules based on increasingly stringent multi-target docking thresholds. In a proof-of-concept study targeting three related coronavirus main proteases (SARS-CoV-2, SARS-CoV, MERS-CoV), our approach efficiently generated a structurally diverse set of pan-inhibitor candidates. We demonstrate that careful timing and strategic placement of chemical filters within this active learning pipeline markedly enhance exploration of beneficial chemical space, transforming the sparse-reward, multi-objective drug design problem into an accessible computational task. Our framework thus provides a generalizable roadmap for efficiently navigating complex polypharmacological landscapes.
Authors: Yingcong Li, Xiangyu Chang, Muti Kara, Xiaofeng Liu, Amit Roy-Chowdhury, Samet Oymak
Abstract: Recent research shows that in-context learning (ICL) can be effective even when demonstrations have missing or incorrect labels. To shed light on this capability, we examine a canonical setting where the demonstrations are drawn according to a binary Gaussian mixture model (GMM) and a certain fraction of the demonstrations have missing labels. We provide a comprehensive theoretical study to show that: (1) The loss landscape of one-layer linear attention models recover the optimal fully-supervised estimator but completely fail to exploit unlabeled data; (2) In contrast, multilayer or looped transformers can effectively leverage unlabeled data by implicitly constructing estimators of the form $\sum_{i\ge 0} a_i (X^\top X)^iX^\top y$ with $X$ and $y$ denoting features and partially-observed labels (with missing entries set to zero). We characterize the class of polynomials that can be expressed as a function of depth and draw connections to Expectation Maximization, an iterative pseudo-labeling algorithm commonly used in semi-supervised learning. Importantly, the leading polynomial power is exponential in depth, so mild amount of depth/looping suffices. As an application of theory, we propose looping off-the-shelf tabular foundation models to enhance their semi-supervision capabilities. Extensive evaluations on real-world datasets show that our method significantly improves the semisupervised tabular learning performance over the standard single pass inference.
Authors: Pavel Karpov, Ilya Petrenkov, Ruslan Raiman
Abstract: Clinical laboratory results are ubiquitous in any diagnosis making. Predicting abnormal values of not prescribed tests based on the results of performed tests looks intriguing, as it would be possible to make early diagnosis available to everyone. The special place is taken by the Common Blood Count (CBC) test, as it is the most widely used clinical procedure. Combining routine biochemical panels with CBC presents a set of test-value pairs that varies from patient to patient, or, in common settings, a table with missing values. Here we formulate a tabular modeling problem as a set translation problem where the source set comprises pairs of GPT-like label column embedding and its corresponding value while the target set consists of the same type embeddings only. The proposed approach can effectively deal with missing values without implicitly estimating them and bridges the world of LLM with the tabular domain. Applying this method to clinical laboratory data, we achieve an improvement up to 8% AUC for joint predictions of high uric acid, glucose, cholesterol, and low ferritin levels.
Authors: Naoki Matsumura, Yuta Yoshimoto, Yuto Iwasaki, Meguru Yamazaki, Yasufumi Sakai
Abstract: Neural network potentials (NNPs) offer a powerful alternative to traditional force fields for molecular dynamics (MD) simulations. Accurate and stable MD simulations, crucial for evaluating material properties, require training data encompassing both low-energy stable structures and high-energy structures. Conventional knowledge distillation (KD) methods fine-tune a pre-trained NNP as a teacher model to generate training data for a student model. However, in material-specific models, this fine-tuning process increases energy barriers, making it difficult to create training data containing high-energy structures. To address this, we propose a novel KD framework that leverages a non-fine-tuned, off-the-shelf pre-trained NNP as a teacher. Its gentler energy landscape facilitates the exploration of a wider range of structures, including the high-energy structures crucial for stable MD simulations. Our framework employs a two-stage training process: first, the student NNP is trained with a dataset generated by the off-the-shelf teacher; then, it is fine-tuned with a smaller, high-accuracy density functional theory (DFT) dataset. We demonstrate the effectiveness of our framework by applying it to both organic (polyethylene glycol) and inorganic (L$_{10}$GeP$_{2}$S$_{12}$) materials, achieving comparable or superior accuracy in reproducing physical properties compared to existing methods. Importantly, our method reduces the number of expensive DFT calculations by 10x compared to existing NNP generation methods, without sacrificing accuracy.
Authors: A. S. Stankevich, I. B. Petrov
Abstract: Recent developments in application of deep learning models to acoustic Full Waveform Inversion (FWI) are marked by the use of diffusion models as prior distributions for Bayesian-like inference procedures. The advantage of these methods is the ability to generate high-resolution samples, which are otherwise unattainable with classical inversion methods or other deep learning-based solutions. However, the iterative and stochastic nature of sampling from diffusion models along with heuristic nature of output control remain limiting factors for their applicability. For instance, an optimal way to include the approximate velocity model into diffusion-based inversion scheme remains unclear, even though it is considered an essential part of FWI pipeline. We address the issue by employing a Schr\"odinger Bridge that interpolates between the distributions of ground truth and smoothed velocity models. To facilitate the learning of nonlinear drifts that transfer samples between distributions we extend the concept of Image-to-Image Schr\"odinger Bridge ($\text{I}^2\text{SB}$) to conditional sampling, resulting in a conditional Image-to-Image Schr\"odinger Bridge (c$\text{I}^2\text{SB}$) framework. To validate our method, we assess its effectiveness in reconstructing the reference velocity model from its smoothed approximation, coupled with the observed seismic signal of fixed shape. Our experiments demonstrate that the proposed solution outperforms our reimplementation of conditional diffusion model suggested in earlier works, while requiring only a few neural function evaluations (NFEs) to achieve sample fidelity superior to that attained with supervised learning-based approach. The supplementary code implementing the algorithms described in this paper can be found in the repository https://github.com/stankevich-mipt/seismic_inversion_via_I2SB.
URLs: https://github.com/stankevich-mipt/seismic_inversion_via_I2SB.
Authors: Terrance Liu, Matteo Boglioni, Yiwei Fu, Shengyuan Hu, Pratiksha Thaker, Zhiwei Steven Wu
Abstract: Differential privacy (DP) auditing aims to provide empirical lower bounds on the privacy guarantees of DP mechanisms like DP-SGD. While some existing techniques require many training runs that are prohibitively costly, recent work introduces one-run auditing approaches that effectively audit DP-SGD in white-box settings while still being computationally efficient. However, in the more practical black-box setting where gradients cannot be manipulated during training and only the last model iterate is observed, prior work shows that there is still a large gap between the empirical lower bounds and theoretical upper bounds. Consequently, in this work, we study how incorporating approaches for stronger membership inference attacks (MIA) can improve one-run auditing in the black-box setting. Evaluating on image classification models trained on CIFAR-10 with DP-SGD, we demonstrate that our proposed approach, which utilizes quantile regression for MIA, achieves tighter bounds while crucially maintaining the computational efficiency of one-run methods.
Authors: J. Thorben Frank, Winfried Ripken, Gregor Lied, Klaus-Robert M\"uller, Oliver T. Unke, Stefan Chmiela
Abstract: Diffusion Transformers (DiTs) have demonstrated strong performance in generative modeling, particularly in image synthesis, making them a compelling choice for molecular conformer generation. However, applying DiTs to molecules introduces novel challenges, such as integrating discrete molecular graph information with continuous 3D geometry, handling Euclidean symmetries, and designing conditioning mechanisms that generalize across molecules of varying sizes and structures. We propose DiTMC, a framework that adapts DiTs to address these challenges through a modular architecture that separates the processing of 3D coordinates from conditioning on atomic connectivity. To this end, we introduce two complementary graph-based conditioning strategies that integrate seamlessly with the DiT architecture. These are combined with different attention mechanisms, including both standard non-equivariant and SO(3)-equivariant formulations, enabling flexible control over the trade-off between between accuracy and computational efficiency. Experiments on standard conformer generation benchmarks (GEOM-QM9, -DRUGS, -XL) demonstrate that DiTMC achieves state-of-the-art precision and physical validity. Our results highlight how architectural choices and symmetry priors affect sample quality and efficiency, suggesting promising directions for large-scale generative modeling of molecular structures. Code available at https://github.com/ML4MolSim/dit_mc.
Authors: Damin K\"uhn, Michael T. Schaub
Abstract: Optimal transport provides a robust framework for comparing probability distributions. Its effectiveness is significantly influenced by the choice of the underlying ground metric. Traditionally, the ground metric has either been (i) predefined, e.g., as the Euclidean distance, or (ii) learned in a supervised way, by utilizing labeled data to learn a suitable ground metric for enhanced task-specific performance. Yet, predefined metrics typically cannot account for the inherent structure and varying importance of different features in the data, and existing supervised approaches to ground metric learning often do not generalize across multiple classes or are restricted to distributions with shared supports. To address these limitations, we propose a novel approach for learning metrics for arbitrary distributions over a shared metric space. Our method provides a distance between individual points like a global metric, but requires only class labels on a distribution-level for training. The learned global ground metric enables more accurate optimal transport distances, leading to improved performance in embedding, clustering and classification tasks. We demonstrate the effectiveness and interpretability of our approach using patient-level scRNA-seq data spanning multiple diseases.
Authors: Riccardo De Santi, Marin Vlastelica, Ya-Ping Hsieh, Zebang Shen, Niao He, Andreas Krause
Abstract: Exploration is critical for solving real-world decision-making problems such as scientific discovery, where the objective is to generate truly novel designs rather than mimic existing data distributions. In this work, we address the challenge of leveraging the representational power of generative models for exploration without relying on explicit uncertainty quantification. We introduce a novel framework that casts exploration as entropy maximization over the approximate data manifold implicitly defined by a pre-trained diffusion model. Then, we present a novel principle for exploration based on density estimation, a problem well-known to be challenging in practice. To overcome this issue and render this method truly scalable, we leverage a fundamental connection between the entropy of the density induced by a diffusion model and its score function. Building on this, we develop an algorithm based on mirror descent that solves the exploration problem as sequential fine-tuning of a pre-trained diffusion model. We prove its convergence to the optimal exploratory diffusion model under realistic assumptions by leveraging recent understanding of mirror flows. Finally, we empirically evaluate our approach on both synthetic and high-dimensional text-to-image diffusion, demonstrating promising results.
Authors: Sepehr Elahi, Paula M\"urmann, Patrick Thiran
Abstract: The Susceptible-Infected-Susceptible (SIS) model is a widely used model for the spread of information and infectious diseases, particularly non-immunizing ones, on a graph. Given a highly contagious disease, a natural question is how to best vaccinate individuals to minimize the disease's extinction time. While previous works showed that the problem of optimal vaccination is closely linked to the NP-hard Spectral Radius Minimization (SRM) problem, they assumed that the graph is known, which is often not the case in practice. In this work, we consider the problem of minimizing the extinction time of an outbreak modeled by an SIS model where the graph on which the disease spreads is unknown and only the infection states of the vertices are observed. To this end, we split the problem into two: learning the graph and determining effective vaccination strategies. We propose a novel inclusion-exclusion-based learning algorithm and, unlike previous approaches, establish its sample complexity for graph recovery. We then detail an optimal algorithm for the SRM problem and prove that its running time is polynomial in the number of vertices for graphs with bounded treewidth. This is complemented by an efficient and effective polynomial-time greedy heuristic for any graph. Finally, we present experiments on synthetic and real-world data that numerically validate our learning and vaccination algorithms.
Authors: David Dembinsky, Adriano Lucieri, Stanislav Frolov, Hiba Najjar, Ko Watanabe, Andreas Dengel
Abstract: Modern AI systems frequently rely on opaque black-box models, most notably Deep Neural Networks, whose performance stems from complex architectures with millions of learned parameters. While powerful, their complexity poses a major challenge to trustworthiness, particularly due to a lack of transparency. Explainable AI (XAI) addresses this issue by providing human-understandable explanations of model behavior. However, to ensure their usefulness and trustworthiness, such explanations must be rigorously evaluated. Despite the growing number of XAI methods, the field lacks standardized evaluation protocols and consensus on appropriate metrics. To address this gap, we conduct a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and introduce a unified framework for the eValuation of XAI (VXAI). We identify 362 relevant publications and aggregate their contributions into 41 functionally similar metric groups. In addition, we propose a three-dimensional categorization scheme spanning explanation type, evaluation contextuality, and explanation quality desiderata. Our framework provides the most comprehensive and structured overview of VXAI to date. It supports systematic metric selection, promotes comparability across methods, and offers a flexible foundation for future extensions.
Authors: Rui Yu, Shenghua Wan, Yucen Wang, Chen-Xiao Gao, Le Gan, Zongzhang Zhang, De-Chuan Zhan
Abstract: In reinforcement learning (RL), agents continually interact with the environment and use the feedback to refine their behavior. To guide policy optimization, reward models are introduced as proxies of the desired objectives, such that when the agent maximizes the accumulated reward, it also fulfills the task designer's intentions. Recently, significant attention from both academic and industrial researchers has focused on developing reward models that not only align closely with the true objectives but also facilitate policy optimization. In this survey, we provide a comprehensive review of reward modeling techniques within the deep RL literature. We begin by outlining the background and preliminaries in reward modeling. Next, we present an overview of recent reward modeling approaches, categorizing them based on the source, the mechanism, and the learning paradigm. Building on this understanding, we discuss various applications of these reward modeling techniques and review methods for evaluating reward models. Finally, we conclude by highlighting promising research directions in reward modeling. Altogether, this survey includes both established and emerging methods, filling the vacancy of a systematic review of reward models in current literature.
Authors: Scott Jeen, Tom Bewley, Jonathan M. Cullen
Abstract: Recent work has shown that, under certain assumptions, zero-shot reinforcement learning (RL) methods can generalise to any unseen task in an environment after reward-free pre-training. Access to Markov states is one such assumption, yet, in many real-world applications, the Markov state is only partially observable. Here, we explore how the performance of standard zero-shot RL methods degrades when subjected to partially observability, and show that, as in single-task RL, memory-based architectures are an effective remedy. We evaluate our memory-based zero-shot RL methods in domains where the states, rewards and a change in dynamics are partially observed, and show improved performance over memory-free baselines. Our code is open-sourced via: https://enjeeneer.io/projects/bfms-with-memory/.
Authors: Guoguo Ai, Hezhe Qiao, Hui Yan, Guansong Pang
Abstract: Semi-supervised graph anomaly detection (GAD) utilizes a small set of labeled normal nodes to identify abnormal nodes from a large set of unlabeled nodes in a graph. Current methods in this line posit that 1) normal nodes share a similar level of homophily and 2) the labeled normal nodes can well represent the homophily patterns in the normal class. However, this assumption often does not hold well since normal nodes in a graph can exhibit diverse homophily in real-world GAD datasets. In this paper, we propose RHO, namely Robust Homophily Learning, to adaptively learn such homophily patterns. RHO consists of two novel modules, adaptive frequency response filters (AdaFreq) and graph normality alignment (GNA). AdaFreq learns a set of adaptive spectral filters that capture different frequency components of the labeled normal nodes with varying homophily in the channel-wise and cross-channel views of node attributes. GNA is introduced to enforce consistency between the channel-wise and cross-channel homophily representations to robustify the normality learned by the filters in the two views. Experiments on eight real-world GAD datasets show that RHO can effectively learn varying, often under-represented, homophily in the small normal node set and substantially outperforms state-of-the-art competing methods. Code is available at https://github.com/mala-lab/RHO.
Authors: Simiao Lin, Wannes Meert, Pieter Robberechts, Hendrik Blockeel
Abstract: Comparing time series is essential in various tasks such as clustering and classification. While elastic distance measures that allow warping provide a robust quantitative comparison, a qualitative comparison on top of them is missing. Traditional visualizations focus on point-to-point alignment and do not convey the broader structural relationships at the level of subsequences. This limitation makes it difficult to understand how and where one time series shifts, speeds up or slows down with respect to another. To address this, we propose a novel technique that simplifies the warping path to highlight, quantify and visualize key transformations (shift, compression, difference in amplitude). By offering a clearer representation of how subsequences match between time series, our method enhances interpretability in time series comparison.
Authors: Artur Andr\'e Oliveira, Mateus Espadoto, Roberto Hirata Jr., Roberto M. Cesar Jr., Alex C. Telea
Abstract: Dimensionality reduction (DR) techniques map high-dimensional data into lower-dimensional spaces. Yet, current DR techniques are not designed to explore semantic structure that is not directly available in the form of variables or class labels. We introduce a novel user-guided projection framework for image and text data that enables customizable, interpretable, data visualizations via zero-shot classification with Multimodal Large Language Models (MLLMs). We enable users to steer projections dynamically via natural-language guiding prompts, to specify high-level semantic relationships of interest to the users which are not explicitly present in the data dimensions. We evaluate our method across several datasets and show that it not only enhances cluster separation, but also transforms DR into an interactive, user-driven process. Our approach bridges the gap between fully automated DR techniques and human-centered data exploration, offering a flexible and adaptive way to tailor projections to specific analytical needs.
Authors: Mohammadreza Nemati, Zhipeng Huang, Kevin S. Xu
Abstract: Some of the simplest, yet most frequently used predictors in statistics and machine learning use weighted linear combinations of features. Such linear predictors can model non-linear relationships between features by adding interaction terms corresponding to the products of all pairs of features. We consider the problem of accurately estimating coefficients for interaction terms in linear predictors. We hypothesize that the coefficients for different interaction terms have an approximate low-dimensional structure and represent each feature by a latent vector in a low-dimensional space. This low-dimensional representation can be viewed as a structured regularization approach that further mitigates overfitting in high-dimensional settings beyond standard regularizers such as the lasso and elastic net. We demonstrate that our approach, called LIT-LVM, achieves superior prediction accuracy compared to elastic net and factorization machines on a wide variety of simulated and real data, particularly when the number of interaction terms is high compared to the number of samples. LIT-LVM also provides low-dimensional latent representations for features that are useful for visualizing and analyzing their relationships.
Authors: Alaa Anani, Tobias Lorenz, Mario Fritz, Bernt Schiele
Abstract: Post-hoc attribution methods aim to explain deep learning predictions by highlighting influential input pixels. However, these explanations are highly non-robust: small, imperceptible input perturbations can drastically alter the attribution map while maintaining the same prediction. This vulnerability undermines their trustworthiness and calls for rigorous robustness guarantees of pixel-level attribution scores. We introduce the first certification framework that guarantees pixel-level robustness for any black-box attribution method using randomized smoothing. By sparsifying and smoothing attribution maps, we reformulate the task as a segmentation problem and certify each pixel's importance against $\ell_2$-bounded perturbations. We further propose three evaluation metrics to assess certified robustness, localization, and faithfulness. An extensive evaluation of 12 attribution methods across 5 ImageNet models shows that our certified attributions are robust, interpretable, and faithful, enabling reliable use in downstream tasks. Our code is at https://github.com/AlaaAnani/certified-attributions.
Authors: Salijona Dyrmishi, Mohamed Djilani, Thibault Simonetto, Salah Ghamizi, Maxime Cordy
Abstract: Adversarial attacks in machine learning have been extensively reviewed in areas like computer vision and NLP, but research on tabular data remains scattered. This paper provides the first systematic literature review focused on adversarial attacks targeting tabular machine learning models. We highlight key trends, categorize attack strategies and analyze how they address practical considerations for real-world applicability. Additionally, we outline current challenges and open research questions. By offering a clear and structured overview, this review aims to guide future efforts in understanding and addressing adversarial vulnerabilities in tabular machine learning.
Authors: Ivan Marisca, Jacob Bamberger, Cesare Alippi, Michael M. Bronstein
Abstract: Graph Neural Networks (GNNs) have achieved remarkable success across various domains. However, recent theoretical advances have identified fundamental limitations in their information propagation capabilities, such as over-squashing, where distant nodes fail to effectively exchange information. While extensively studied in static contexts, this issue remains unexplored in Spatiotemporal GNNs (STGNNs), which process sequences associated with graph nodes. Nonetheless, the temporal dimension amplifies this challenge by increasing the information that must be propagated. In this work, we formalize the spatiotemporal over-squashing problem and demonstrate its distinct characteristics compared to the static case. Our analysis reveals that counterintuitively, convolutional STGNNs favor information propagation from points temporally distant rather than close in time. Moreover, we prove that architectures that follow either time-and-space or time-then-space processing paradigms are equally affected by this phenomenon, providing theoretical justification for computationally efficient implementations. We validate our findings on synthetic and real-world datasets, providing deeper insights into their operational dynamics and principled guidance for more effective designs.
Authors: Le Vu Anh, Nguyen Viet Anh, Mehmet Dik, Luong Van Nghia
Abstract: Retrieval-augmented generation (RAG) has become a common strategy for updating large language model (LLM) responses with current, external information. However, models may still rely on memorized training data, bypass the retrieved evidence, and produce contaminated outputs. We introduce Retrieval-Path Contamination Scoring (RePCS), a diagnostic method that detects such behavior without requiring model access or retraining. RePCS compares two inference paths: (i) a parametric path using only the query, and (ii) a retrieval-augmented path using both the query and retrieved context by computing the Kullback-Leibler (KL) divergence between their output distributions. A low divergence suggests that the retrieved context had minimal impact, indicating potential memorization. This procedure is model-agnostic, requires no gradient or internal state access, and adds only a single additional forward pass. We further derive PAC-style guarantees that link the KL threshold to user-defined false positive and false negative rates. On the Prompt-WNQA benchmark, RePCS achieves a ROC-AUC of 0.918. This result outperforms the strongest prior method by 6.5 percentage points while keeping latency overhead below 4.7% on an NVIDIA T4 GPU. RePCS offers a lightweight, black-box safeguard to verify whether a RAG system meaningfully leverages retrieval, making it especially valuable in safety-critical applications.
Authors: Alexandru Meterez, Depen Morwani, Costin-Andrei Oncescu, Jingfeng Wu, Cengiz Pehlevan, Sham Kakade
Abstract: Theoretically understanding stochastic gradient descent (SGD) in overparameterized models has led to the development of several optimization algorithms that are widely used in practice today. Recent work by~\citet{zou2021benign} provides sharp rates for SGD optimization in linear regression using constant learning rate, both with and without tail iterate averaging, based on a bias-variance decomposition of the risk. In our work, we provide a simplified analysis recovering the same bias and variance bounds provided in~\citep{zou2021benign} based on simple linear algebra tools, bypassing the requirement to manipulate operators on positive semi-definite (PSD) matrices. We believe our work makes the analysis of SGD on linear regression very accessible and will be helpful in further analyzing mini-batching and learning rate scheduling, leading to improvements in the training of realistic models.
Authors: Laura Kopf, Nils Feldhus, Kirill Bykov, Philine Lou Bommer, Anna Hedstr\"om, Marina M. -C. H\"ohne, Oliver Eberle
Abstract: Automated interpretability research aims to identify concepts encoded in neural network features to enhance human understanding of model behavior. Current feature description methods face two critical challenges: limited robustness and the flawed assumption that each neuron encodes only a single concept (monosemanticity), despite growing evidence that neurons are often polysemantic. This assumption restricts the expressiveness of feature descriptions and limits their ability to capture the full range of behaviors encoded in model internals. To address this, we introduce Polysemantic FeatuRe Identification and Scoring Method (PRISM), a novel framework that captures the inherent complexity of neural network features. Unlike prior approaches that assign a single description per feature, PRISM provides more nuanced descriptions for both polysemantic and monosemantic features. We apply PRISM to language models and, through extensive benchmarking against existing methods, demonstrate that our approach produces more accurate and faithful feature descriptions, improving both overall description quality (via a description score) and the ability to capture distinct concepts when polysemanticity is present (via a polysemanticity score).
Authors: Hristo Papazov, Nicolas Flammarion
Abstract: This paper studies the problem of learning computable functions in the limit by extending Gold's inductive inference framework to incorporate \textit{computational observations} and \textit{restricted input sources}. Complimentary to the traditional Input-Output Observations, we introduce Time-Bound Observations, and Policy-Trajectory Observations to study the learnability of general recursive functions under more realistic constraints. While input-output observations do not suffice for learning the class of general recursive functions in the limit, we overcome this learning barrier by imposing computational complexity constraints or supplementing with approximate time-bound observations. Further, we build a formal framework around observations of \textit{computational agents} and show that learning computable functions from policy trajectories reduces to learning rational functions from input and output, thereby revealing interesting connections to finite-state transducer inference. On the negative side, we show that computable or polynomial-mass characteristic sets cannot exist for the class of linear-time computable functions even for policy-trajectory observations.
Authors: Roger Creus Castanyer, Johan Obando-Ceron, Lu Li, Pierre-Luc Bacon, Glen Berseth, Aaron Courville, Pablo Samuel Castro
Abstract: Scaling deep reinforcement learning networks is challenging and often results in degraded performance, yet the root causes of this failure mode remain poorly understood. Several recent works have proposed mechanisms to address this, but they are often complex and fail to highlight the causes underlying this difficulty. In this work, we conduct a series of empirical analyses which suggest that the combination of non-stationarity with gradient pathologies, due to suboptimal architectural choices, underlie the challenges of scale. We propose a series of direct interventions that stabilize gradient flow, enabling robust performance across a range of network depths and widths. Our interventions are simple to implement and compatible with well-established algorithms, and result in an effective mechanism that enables strong performance even at large scales. We validate our findings on a variety of agents and suites of environments.
Authors: Akhil Singampalli, Danish Gufran, Sudeep Pasricha
Abstract: Wi-Fi fingerprinting-based indoor localization faces significant challenges in real-world deployments due to domain shifts arising from device heterogeneity and temporal variations within indoor environments. Existing approaches often address these issues independently, resulting in poor generalization and susceptibility to catastrophic forgetting over time. In this work, we propose DAILOC, a novel domain-incremental learning framework that jointly addresses both temporal and device-induced domain shifts. DAILOC introduces a novel disentanglement strategy that separates domain shifts from location-relevant features using a multi-level variational autoencoder. Additionally, we introduce a novel memory-guided class latent alignment mechanism to address the effects of catastrophic forgetting over time. Experiments across multiple smartphones, buildings, and time instances demonstrate that DAILOC significantly outperforms state-of-the-art methods, achieving up to 2.74x lower average error and 4.6x lower worst-case error.
Authors: Danish Gufran, Sudeep Pasricha
Abstract: Indoor localization using deep learning (DL) has demonstrated strong accuracy in mapping Wi-Fi RSS fingerprints to physical locations; however, most existing DL frameworks function as black-box models, offering limited insight into how predictions are made or how models respond to real-world noise over time. This lack of interpretability hampers our ability to understand the impact of temporal variations - caused by environmental dynamics - and to adapt models for long-term reliability. To address this, we introduce LogNet, a novel logic gate-based framework designed to interpret and enhance DL-based indoor localization. LogNet enables transparent reasoning by identifying which access points (APs) are most influential for each reference point (RP) and reveals how environmental noise disrupts DL-driven localization decisions. This interpretability allows us to trace and diagnose model failures and adapt DL systems for more stable long-term deployments. Evaluations across multiple real-world building floorplans and over two years of temporal variation show that LogNet not only interprets the internal behavior of DL models but also improves performance-achieving up to 1.1x to 2.8x lower localization error, 3.4x to 43.3x smaller model size, and 1.5x to 3.6x lower latency compared to prior DL-based models.
Authors: Luigi Quarantiello, Andrea Cossu, Vincenzo Lomonaco
Abstract: Compositionality is one of the fundamental abilities of the human reasoning process, that allows to decompose a complex problem into simpler elements. Such property is crucial also for neural networks, especially when aiming for a more efficient and sustainable AI framework. We propose a compositional approach by ensembling zero-shot a set of expert models, assessing our methodology using a challenging benchmark, designed to test compositionality capabilities. We show that our Expert Composition method is able to achieve a much higher accuracy than baseline algorithms while requiring less computational resources, hence being more efficient.
Authors: Le Vu Anh, Nguyen Viet Anh, Mehmet Dik, Tu Nguyen Thi Ngoc
Abstract: Real-time mesh smoothing at scale remains a formidable challenge: classical Ricci-flow solvers demand costly global updates, while greedy heuristics suffer from slow convergence or brittle tuning. We present MicroRicci, the first truly self-tuning, local Ricci-flow solver that borrows ideas from coding theory and packs them into just 1K + 200 parameters. Its primary core is a greedy syndrome-decoding step that pinpoints and corrects the largest curvature error in O(E) time, augmented by two tiny neural modules that adaptively choose vertices and step sizes on the fly. On a diverse set of 110 SJTU-TMQA meshes, MicroRicci slashes iteration counts from 950+=140 to 400+=80 (2.4x speedup), tightens curvature spread from 0.19 to 0.185, and achieves a remarkable UV-distortion-to-MOS correlation of r = -0.93. It adds only 0.25 ms per iteration (0.80 to 1.05 ms), yielding an end-to-end 1.8x runtime acceleration over state-of-the-art methods. MicroRicci's combination of linear-time updates, automatic hyperparameter adaptation, and high-quality geometric and perceptual results makes it well suited for real-time, resource-limited applications in graphics, simulation, and related fields.
Authors: Alex Mulrooney, Devansh Gupta, James Flemings, Huanyu Zhang, Murali Annavaram, Meisam Razaviyayn, Xinwei Zhang
Abstract: Differential privacy (DP) protects sensitive data during neural network training, but standard methods like DP-Adam suffer from high memory overhead due to per-sample gradient clipping, limiting scalability. We introduce DP-GRAPE (Gradient RAndom ProjEction), a DP training method that significantly reduces memory usage while maintaining utility on par with first-order DP approaches. Rather than directly applying DP to GaLore, DP-GRAPE introduces three key modifications: (1) gradients are privatized after projection, (2) random Gaussian matrices replace SVD-based subspaces, and (3) projection is applied during backpropagation. These contributions eliminate the need for costly SVD computations, enable substantial memory savings, and lead to improved utility. Despite operating in lower-dimensional subspaces, our theoretical analysis shows that DP-GRAPE achieves a privacy-utility trade-off comparable to DP-SGD. Our extensive empirical experiments show that DP-GRAPE can reduce the memory footprint of DP training without sacrificing accuracy or training time. In particular, DP-GRAPE reduces memory usage by over 63% when pre-training Vision Transformers and over 70% when fine-tuning RoBERTa-Large as compared to DP-Adam, while achieving similar performance. We further demonstrate that DP-GRAPE scales to fine-tuning large models such as OPT with up to 6.7 billion parameters.
Authors: Gabrel J. Perin, Runjin Chen, Xuxi Chen, Nina S. T. Hirata, Zhangyang Wang, Junyuan Hong
Abstract: Large Language Models (LLMs) have become indispensable in real-world applications. However, their widespread adoption raises significant safety concerns, particularly in responding to socially harmful questions. Despite substantial efforts to improve model safety through alignment, aligned models can still have their safety protections undermined by subsequent fine-tuning - even when the additional training data appears benign. In this paper, we empirically demonstrate that this vulnerability stems from the sensitivity of safety-critical low-rank subspaces in LLM parameters to fine-tuning. Building on this insight, we propose a novel training-free method, termed Low-Rank Extrapolation (LoX), to enhance safety robustness by extrapolating the safety subspace of an aligned LLM. Our experimental results confirm the effectiveness of LoX, demonstrating significant improvements in robustness against both benign and malicious fine-tuning attacks while preserving the model's adaptability to new tasks. For instance, LoX leads to 11% to 54% absolute reductions in attack success rates (ASR) facing benign or malicious fine-tuning attacks. By investigating the ASR landscape of parameters, we attribute the success of LoX to that the extrapolation moves LLM parameters to a flatter zone, thereby less sensitive to perturbations. The code is available at github.com/VITA-Group/LoX.
Authors: Modar Sulaiman, Kallol Roy
Abstract: Fairness in machine learning (ML) has a critical importance for building trustworthy machine learning system as artificial intelligence (AI) systems increasingly impact various aspects of society, including healthcare decisions and legal judgments. Moreover, numerous studies demonstrate evidence of unfair outcomes in ML and the need for more robust fairness-aware methods. However, the data we use to train and develop debiasing techniques often contains biased and noisy labels. As a result, the label bias in the training data affects model performance and misrepresents the fairness of classifiers during testing. To tackle this problem, our paper presents Graph-based Fairness-aware Label Correction (GFLC), an efficient method for correcting label noise while preserving demographic parity in datasets. In particular, our approach combines three key components: prediction confidence measure, graph-based regularization through Ricci-flow-optimized graph Laplacians, and explicit demographic parity incentives. Our experimental findings show the effectiveness of our proposed approach and show significant improvements in the trade-off between performance and fairness metrics compared to the baseline.
Authors: Vincent Roca, Marc Tommasi, Paul Andrey, Aur\'elien Bellet, Markus D. Schirmer, Hilde Henon, Laurent Puy, Julien Ramon, Gr\'egory Kuchcinski, Martin Bretzner, Renaud Lopes
Abstract: $\textbf{Objective:}$ Brain-predicted age difference (BrainAGE) is a neuroimaging biomarker reflecting brain health. However, training robust BrainAGE models requires large datasets, often restricted by privacy concerns. This study evaluates the performance of federated learning (FL) for BrainAGE estimation in ischemic stroke patients treated with mechanical thrombectomy, and investigates its association with clinical phenotypes and functional outcomes. $\textbf{Methods:}$ We used FLAIR brain images from 1674 stroke patients across 16 hospital centers. We implemented standard machine learning and deep learning models for BrainAGE estimates under three data management strategies: centralized learning (pooled data), FL (local training at each site), and single-site learning. We reported prediction errors and examined associations between BrainAGE and vascular risk factors (e.g., diabetes mellitus, hypertension, smoking), as well as functional outcomes at three months post-stroke. Logistic regression evaluated BrainAGE's predictive value for these outcomes, adjusting for age, sex, vascular risk factors, stroke severity, time between MRI and arterial puncture, prior intravenous thrombolysis, and recanalisation outcome. $\textbf{Results:}$ While centralized learning yielded the most accurate predictions, FL consistently outperformed single-site models. BrainAGE was significantly higher in patients with diabetes mellitus across all models. Comparisons between patients with good and poor functional outcomes, and multivariate predictions of these outcomes showed the significance of the association between BrainAGE and post-stroke recovery. $\textbf{Conclusion:}$ FL enables accurate age predictions without data centralization. The strong association between BrainAGE, vascular risk factors, and post-stroke recovery highlights its potential for prognostic modeling in stroke care.
Authors: Tevin Wang, Chenyan Xiong
Abstract: Rule-based rewards offer a promising strategy for improving reinforcement learning from human feedback (RLHF), but current approaches often rely on manual rule engineering. We present AutoRule, a fully automated method for extracting rules from preference feedback and formulating them into rule-based rewards. AutoRule extraction operates in three stages: it leverages a reasoning model to interpret user preferences, identifies candidate rules from the reasoning chain of these interpretations, and synthesizes them into a unified rule set. Leveraging the finalized rule set, we employ language-model verifiers to compute the fraction of rules satisfied by each output, using this metric as an auxiliary reward alongside the learned reward model during policy optimization. Training a Llama-3-8B model with AutoRule results in a 28.6\% relative improvement in length-controlled win rate on AlpacaEval2.0, and a 6.1\% relative gain in second-turn performance on a held-out MT-Bench subset, compared to a GRPO baseline trained with the same learned reward model but without the rule-based auxiliary reward. Our analysis confirms that the extracted rules exhibit good agreement with dataset preference. We find that AutoRule demonstrates reduced reward hacking compared to a learned reward model when run over two episodes. Finally, our case study suggests that the extracted rules capture unique qualities valued in different datasets. The extracted rules are provided in the appendix, and the code is open-sourced at https://github.com/cxcscmu/AutoRule.
Authors: Ranting Hu
Abstract: Offline reinforcement learning (offline RL) algorithms often require additional constraints or penalty terms to address distribution shift issues, such as adding implicit or explicit policy constraints during policy optimization to reduce the estimation bias of functions. This paper focuses on a limitation of the Advantage-Weighted Regression family (AWRs), i.e., the potential for learning over-conservative policies due to data corruption, specifically the poor explorations in suboptimal offline data. We study it from two perspectives: (1) how poor explorations impact the theoretically optimal policy based on KL divergence, and (2) how such poor explorations affect the approximation of the theoretically optimal policy. We prove that such over-conservatism is mainly caused by the sensitivity of the loss function for policy optimization to poor explorations, and the proportion of poor explorations in offline datasets. To address this concern, we propose Corruption-Averse Advantage-Weighted Regression (CAWR), which incorporates a set of robust loss functions during policy optimization and an advantage-based prioritized experience replay method to filter out poor explorations. Numerical experiments on the D4RL benchmark show that our method can learn superior policies from suboptimal offline data, significantly enhancing the performance of policy optimization.
Authors: Xiaoqing Sun, Alessandro Stolfo, Joshua Engels, Ben Wu, Senthooran Rajamanoharan, Mrinmaya Sachan, Max Tegmark
Abstract: Sparse autoencoders (SAEs) are designed to extract interpretable features from language models by enforcing a sparsity constraint. Ideally, training an SAE would yield latents that are both sparse and semantically meaningful. However, many SAE latents activate frequently (i.e., are \emph{dense}), raising concerns that they may be undesirable artifacts of the training procedure. In this work, we systematically investigate the geometry, function, and origin of dense latents and show that they are not only persistent but often reflect meaningful model representations. We first demonstrate that dense latents tend to form antipodal pairs that reconstruct specific directions in the residual stream, and that ablating their subspace suppresses the emergence of new dense features in retrained SAEs -- suggesting that high density features are an intrinsic property of the residual space. We then introduce a taxonomy of dense latents, identifying classes tied to position tracking, context binding, entropy regulation, letter-specific output signals, part-of-speech, and principal component reconstruction. Finally, we analyze how these features evolve across layers, revealing a shift from structural features in early layers, to semantic features in mid layers, and finally to output-oriented signals in the last layers of the model. Our findings indicate that dense latents serve functional roles in language model computation and should not be dismissed as training noise.
Authors: Jiamin Xie, Ke Li, Jinxi Guo, Andros Tjandra, Yuan Shangguan, Leda Sari, Chunyang Wu, Junteng Jia, Jay Mahadeokar, Ozlem Kalinli
Abstract: Neural network pruning offers an effective method for compressing a multilingual automatic speech recognition (ASR) model with minimal performance loss. However, it entails several rounds of pruning and re-training needed to be run for each language. In this work, we propose the use of an adaptive masking approach in two scenarios for pruning a multilingual ASR model efficiently, each resulting in sparse monolingual models or a sparse multilingual model (named as Dynamic ASR Pathways). Our approach dynamically adapts the sub-network, avoiding premature decisions about a fixed sub-network structure. We show that our approach outperforms existing pruning methods when targeting sparse monolingual models. Further, we illustrate that Dynamic ASR Pathways jointly discovers and trains better sub-networks (pathways) of a single multilingual model by adapting from different sub-network initializations, thereby reducing the need for language-specific pruning.
Authors: Jakob De Moor, Hans Weytjens, Johannes De Smedt, Jochen De Weerdt
Abstract: Prescriptive Process Monitoring (PresPM) is an emerging area within Process Mining, focused on optimizing processes through real-time interventions for effective decision-making. PresPM holds significant promise for organizations seeking enhanced operational performance. However, the current literature faces two key limitations: a lack of extensive comparisons between techniques and insufficient evaluation approaches. To address these gaps, we introduce SimBank: a simulator designed for accurate benchmarking of PresPM methods. Modeled after a bank's loan application process, SimBank enables extensive comparisons of both online and offline PresPM methods. It incorporates a variety of intervention optimization problems with differing levels of complexity and supports experiments on key causal machine learning challenges, such as assessing a method's robustness to confounding in data. SimBank additionally offers a comprehensive evaluation capability: for each test case, it can generate the true outcome under each intervention action, which is not possible using recorded datasets. The simulator incorporates parallel activities and loops, drawing from common logs to generate cases that closely resemble real-life process instances. Our proof of concept demonstrates SimBank's benchmarking capabilities through experiments with various PresPM methods across different interventions, highlighting its value as a publicly available simulator for advancing research and practice in PresPM.
Authors: Tobias Labarta, Nhi Hoang, Katharina Weitz, Wojciech Samek, Sebastian Lapuschkin, Leander Weber
Abstract: As machine learning systems increasingly inform critical decisions, the need for human-understandable explanations grows. Current evaluations of Explainable AI (XAI) often prioritize technical fidelity over cognitive accessibility which critically affects users, in particular those with visual impairments. We propose CUE, a model for Cognitive Understanding of Explanations, linking explanation properties to cognitive sub-processes: legibility (perception), readability (comprehension), and interpretability (interpretation). In a study (N=455) testing heatmaps with varying colormaps (BWR, Cividis, Coolwarm), we found comparable task performance but lower confidence/effort for visually impaired users. Unlike expected, these gaps were not mitigated and sometimes worsened by accessibility-focused color maps like Cividis. These results challenge assumptions about perceptual optimization and support the need for adaptive XAI interfaces. They also validate CUE by demonstrating that altering explanation legibility affects understandability. We contribute: (1) a formalized cognitive model for explanation understanding, (2) an integrated definition of human-centered explanation properties, and (3) empirical evidence motivating accessible, user-tailored XAI.
Authors: Jules Leguy, Pierre-Antoine Jean, Felipe Torres Figueroa, S\'ebastien Harispe
Abstract: This article introduces WebXAII, an open-source web framework designed to facilitate research on human interaction with eXplainable Artificial Intelligence (XAI) systems. The field of XAI is rapidly expanding, driven by the growing societal implications of the widespread adoption of AI (and in particular machine learning) across diverse applications. Researchers who study the interaction between humans and XAI techniques typically develop ad hoc interfaces in order to conduct their studies. These interfaces are usually not shared alongside the results of the studies, which limits their reusability and the reproducibility of experiments. In response, we design and implement WebXAII, a web-based platform that can embody full experimental protocols, meaning that it can present all aspects of the experiment to human participants and record their responses. The experimental protocols are translated into a composite architecture of generic views and modules, which offers a lot of flexibility. The architecture is defined in a structured configuration file, so that protocols can be implemented with minimal programming skills. We demonstrate that WebXAII can effectively embody relevant protocols, by reproducing the protocol of a state-of-the-art study of the literature. The framework is available at https://github.com/PAJEAN/WebXAII.
Authors: Jingxuan Zhou, Yuehao Wu, Yibo Zhang, Yeyubei Zhang, Yunchong Liu, Bolin Huang, Chunhong Yuan
Abstract: Aiming at the problem of difficulty in accurately identifying graphical implicit correlations in multimodal irony detection tasks, this paper proposes a Semantic Irony Recognition Network (SemIRNet). The model contains three main innovations: (1) The ConceptNet knowledge base is introduced for the first time to acquire conceptual knowledge, which enhances the model's common-sense reasoning ability; (2) Two cross-modal semantic similarity detection modules at the word level and sample level are designed to model graphic-textual correlations at different granularities; and (3) A contrastive learning loss function is introduced to optimize the spatial distribution of the sample features, which improves the separability of positive and negative samples. Experiments on a publicly available multimodal irony detection benchmark dataset show that the accuracy and F1 value of this model are improved by 1.64% and 2.88% to 88.87% and 86.33%, respectively, compared with the existing optimal methods. Further ablation experiments verify the important role of knowledge fusion and semantic similarity detection in improving the model performance.
Authors: Batuhan Hangun, Emine Akpinar, Oguz Altun, Onder Eyecioglu
Abstract: Quantum Machine Learning (QML) is an emerging field at the intersection of quantum computing and machine learning, aiming to enhance classical machine learning methods by leveraging quantum mechanics principles such as entanglement and superposition. However, skepticism persists regarding the practical advantages of QML, mainly due to the current limitations of noisy intermediate-scale quantum (NISQ) devices. This study addresses these concerns by extensively assessing Quantum Neural Networks (QNNs)-quantum-inspired counterparts of Artificial Neural Networks (ANNs), demonstrating their effectiveness compared to classical methods. We systematically construct and evaluate twelve distinct QNN configurations, utilizing two unique quantum feature maps combined with six different entanglement strategies for ansatz design. Experiments conducted on a wind energy dataset reveal that QNNs employing the Z feature map achieve up to 93% prediction accuracy when forecasting wind power output using only four input parameters. Our findings show that QNNs outperform classical methods in predictive tasks, underscoring the potential of QML in real-world applications.
Authors: Zhangyang Gao, Hao Wang, Cheng Tan, Chenrui Xu, Mengdi Liu, Bozhen Hu, Linlin Chao, Xiaoming Zhang, Stan Z. Li
Abstract: This study investigates the current landscape and future directions of protein foundation model research. While recent advancements have transformed protein science and engineering, the field lacks a comprehensive benchmark for fair evaluation and in-depth understanding. Since ESM-1B, numerous protein foundation models have emerged, each with unique datasets and methodologies. However, evaluations often focus on limited tasks tailored to specific models, hindering insights into broader generalization and limitations. Specifically, researchers struggle to understand the relationships between tasks, assess how well current models perform across them, and determine the criteria in developing new foundation models. To fill this gap, we present PFMBench, a comprehensive benchmark evaluating protein foundation models across 38 tasks spanning 8 key areas of protein science. Through hundreds of experiments on 17 state-of-the-art models across 38 tasks, PFMBench reveals the inherent correlations between tasks, identifies top-performing models, and provides a streamlined evaluation protocol. Code is available at \href{https://github.com/biomap-research/PFMBench}{\textcolor{blue}{GitHub}}.
Authors: Evdoxia Taka, Debadyuti Bhattacharya, Joanne Garde-Hansen, Sanjay Sharma, Tanaya Guha
Abstract: Recent advances in AI has enabled automated analysis of complex media content at scale and generate actionable insights regarding character representation along such dimensions as gender and age. Past work focused on quantifying representation from audio/video/text using various ML models, but without having the audience in the loop. We ask, even if character distribution along demographic dimensions are available, how useful are they to the general public? Do they actually trust the numbers generated by AI models? Our work addresses these questions through a user study, while proposing a new AI-based character representation and visualization tool. Our tool based on the Contrastive Language Image Pretraining (CLIP) foundation model to analyze visual screen data to quantify character representation across dimensions of age and gender. We also designed effective visualizations suitable for presenting such analytics to lay audience. Next, we conducted a user study to seek empirical evidence on the usefulness and trustworthiness of the AI-generated results for carefully chosen movies presented in the form of our visualizations. We note that participants were able to understand the analytics from our visualization, and deemed the tool `overall useful'. Participants also indicated a need for more detailed visualizations to include more demographic categories and contextual information of the characters. Participants' trust in AI-based gender and age models is seen to be moderate to low, although they were not against the use of AI in this context. Our tool including code, benchmarking, and data from the user study can be found here: https://anonymous.4open.science/r/Character-Representation-Media-FF7B
URLs: https://anonymous.4open.science/r/Character-Representation-Media-FF7B
Authors: Arbind Agrahari Baniya, Tsz-Kwan Lee, Peter W. Eklund, Sunil Aryal
Abstract: Omnidirectional Videos (or 360{\deg} videos) are widely used in Virtual Reality (VR) to facilitate immersive and interactive viewing experiences. However, the limited spatial resolution in 360{\deg} videos does not allow for each degree of view to be represented with adequate pixels, limiting the visual quality offered in the immersive experience. Deep learning Video Super-Resolution (VSR) techniques used for conventional videos could provide a promising software-based solution; however, these techniques do not tackle the distortion present in equirectangular projections of 360{\deg} video signals. An additional obstacle is the limited availability of 360{\deg} video datasets for study. To address these issues, this paper creates a novel 360{\deg} Video Dataset (360VDS) with a study of the extensibility of conventional VSR models to 360{\deg} videos. This paper further proposes a novel deep learning model for 360{\deg} Video Super-Resolution (360{\deg} VSR), called Spherical Signal Super-resolution with a Proportioned Optimisation (S3PO). S3PO adopts recurrent modelling with an attention mechanism, unbound from conventional VSR techniques like alignment. With a purpose-built feature extractor and a novel loss function addressing spherical distortion, S3PO outperforms most state-of-the-art conventional VSR models and 360{\deg}~specific super-resolution models on 360{\deg} video datasets. A step-wise ablation study is presented to understand and demonstrate the impact of the chosen architectural sub-components, targeted training and optimisation.
Authors: Yang Yao, Lingyu Li, Jiaxin Song, Chiyu Chen, Zhenqi He, Yixu Wang, Xin Wang, Tianle Gu, Jie Li, Yan Teng, Yingchun Wang
Abstract: As Multimodal Large Language Models (MLLMs) continue to evolve, their cognitive and reasoning capabilities have seen remarkable progress. However, challenges in visual fine-grained perception and commonsense causal inference persist. This paper introduces Argus Inspection, a multimodal benchmark with two levels of difficulty, emphasizing detailed visual recognition while incorporating real-world commonsense understanding to evaluate causal reasoning abilities. Expanding on it, we present the Eye of Panoptes framework, which integrates a binary parametric Sigmoid metric with an indicator function, enabling a more holistic evaluation of MLLMs' responses in opinion-based reasoning tasks. Experiments conducted on 26 mainstream MLLMs reveal that the highest performance in visual fine-grained reasoning reaches only 0.46, highlighting considerable potential for enhancement. Our research offers valuable perspectives for the continued refinement of MLLMs.
Authors: Peng Jiang, Vinicius Cezar Monteiro de Lira, Antonio Maiorino
Abstract: Surveys are a cornerstone of Information Systems (IS) research, yet creating high-quality surveys remains labor-intensive, requiring both domain expertise and methodological rigor. With the evolution of large language models (LLMs), new opportunities emerge to automate survey generation. This paper presents the real-world deployment of an LLM-powered system designed to accelerate data collection while maintaining survey quality. Deploying such systems in production introduces real-world complexity, including diverse user needs and quality control. We evaluate the system using the DeLone and McLean IS Success Model to understand how generative AI can reshape a core IS method. This study makes three key contributions. To our knowledge, this is the first application of the IS Success Model to a generative AI system for survey creation. In addition, we propose a hybrid evaluation framework combining automated and human assessments. Finally, we implement safeguards that mitigate post-deployment risks and support responsible integration into IS workflows.
Authors: Simon P. von der Maase
Abstract: Forecasting violent conflict at high spatial and temporal resolution remains a central challenge for both researchers and policymakers. This study presents a novel neural network architecture for forecasting three distinct types of violence -- state-based, non-state, and one-sided -- at the subnational (priogrid-month) level, up to 36 months in advance. The model jointly performs classification and regression tasks, producing both probabilistic estimates and expected magnitudes of future events. It achieves state-of-the-art performance across all tasks and generates approximate predictive posterior distributions to quantify forecast uncertainty. The architecture is built on a Monte Carlo Dropout Long Short-Term Memory (LSTM) U-Net, integrating convolutional layers to capture spatial dependencies with recurrent structures to model temporal dynamics. Unlike many existing approaches, it requires no manual feature engineering and relies solely on historical conflict data. This design enables the model to autonomously learn complex spatiotemporal patterns underlying violent conflict. Beyond achieving state-of-the-art predictive performance, the model is also highly extensible: it can readily integrate additional data sources and jointly forecast auxiliary variables. These capabilities make it a promising tool for early warning systems, humanitarian response planning, and evidence-based peacebuilding initiatives.
Authors: Hyeon Jeon, Hyunwook Lee, Yun-Hsin Kuo, Taehyun Yang, Daniel Archambault, Sungahn Ko, Takanori Fujiwara, Kwan-Liu Ma, Jinwook Seo
Abstract: Visual analytics using dimensionality reduction (DR) can easily be unreliable for various reasons, e.g., inherent distortions in representing the original data. The literature has thus proposed a wide range of methodologies to make DR-based visual analytics reliable. However, the diversity and extensiveness of the literature can leave novice analysts and researchers uncertain about where to begin and proceed. To address this problem, we propose a guide for reading papers for reliable visual analytics with DR. Relying on the previous classification of the relevant literature, our guide helps both practitioners to (1) assess their current DR expertise and (2) identify papers that will further enhance their understanding. Interview studies with three experts in DR and data visualizations validate the significance, comprehensiveness, and usefulness of our guide.
Authors: Aditya Majumdar, Wenbo Zhang, Kashvi Prawal, Amulya Yadav
Abstract: In an attempt to tackle the UN SDGs, AI for Social Impact (AI4SI) projects focus on harnessing AI to address societal issues in areas such as healthcare, social justice, etc. Unfortunately, despite growing interest in AI4SI, achieving tangible, on-the-ground impact remains a significant challenge. For example, identifying and engaging motivated collaborators who are willing to co-design and deploy AI based solutions in real-world settings is often difficult. Even when such partnerships are established, many AI4SI projects "fail" to progress beyond the proof-of-concept stage, and hence, are unable to transition to at-scale production-level solutions. Furthermore, the unique challenges faced by AI4SI researchers are not always fully recognized within the broader AI community, where such work is sometimes viewed as primarily applied and not aligning with the traditional criteria for novelty emphasized in core AI venues. This paper attempts to shine a light on the diverse challenges faced in AI4SI research by diagnosing a multitude of factors that prevent AI4SI partnerships from achieving real-world impact on the ground. Drawing on semi-structured interviews with six leading AI4SI researchers - complemented by the authors' own lived experiences in conducting AI4SI research - this paper attempts to understand the day-to-day difficulties faced in developing and deploying socially impactful AI solutions. Through thematic analysis, we identify structural and organizational, communication, collaboration, and operational challenges as key barriers to deployment. While there are no easy fixes, we synthesize best practices and actionable strategies drawn from these interviews and our own work in this space. In doing so, we hope this paper serves as a practical reference guide for AI4SI researchers and partner organizations seeking to engage more effectively in socially impactful AI collaborations.
Authors: C\'eline Finet, Stephane Da Silva Martins, Jean-Bernard Hayet, Ioannis Karamouzas, Javad Amirian, Sylvie Le H\'egarat-Mascle, Julien Pettr\'e, Emanuel Aldea
Abstract: With the emergence of powerful data-driven methods in human trajectory prediction (HTP), gaining a finer understanding of multi-agent interactions lies within hand's reach, with important implications in areas such as autonomous navigation and crowd modeling. This survey reviews some of the most recent advancements in deep learning-based multi-agent trajectory prediction, focusing on studies published between 2020 and 2024. We categorize the existing methods based on their architectural design, their input representations, and their overall prediction strategies, placing a particular emphasis on models evaluated using the ETH/UCY benchmark. Furthermore, we highlight key challenges and future research directions in the field of multi-agent HTP.
Authors: Shatha Abudalou
Abstract: Inter reader variability and cross site domain shift challenge the automatic segmentation of prostate anatomy using T2 weighted MRI images. This study investigates whether transformer models can retain precision amid such heterogeneity. We compare the performance of UNETR and SwinUNETR in prostate gland segmentation against our previous 3D UNet model [1], based on 546 MRI (T2weighted) volumes annotated by two independent experts. Three training strategies were analyzed: single cohort dataset, 5 fold cross validated mixed cohort, and gland size based dataset. Hyperparameters were tuned by Optuna. The test set, from an independent population of readers, served as the evaluation endpoint (Dice Similarity Coefficient). In single reader training, SwinUNETR achieved an average dice score of 0.816 for Reader#1 and 0.860 for Reader#2, while UNETR scored 0.8 and 0.833 for Readers #1 and #2, respectively, compared to the baseline UNets 0.825 for Reader #1 and 0.851 for Reader #2. SwinUNETR had an average dice score of 0.8583 for Reader#1 and 0.867 for Reader#2 in cross-validated mixed training. For the gland size-based dataset, SwinUNETR achieved an average dice score of 0.902 for Reader#1 subset and 0.894 for Reader#2, using the five-fold mixed training strategy (Reader#1, n=53; Reader#2, n=87) at larger gland size-based subsets, where UNETR performed poorly. Our findings demonstrate that global and shifted-window self-attention effectively reduces label noise and class imbalance sensitivity, resulting in improvements in the Dice score over CNNs by up to five points while maintaining computational efficiency. This contributes to the high robustness of SwinUNETR for clinical deployment.
Authors: Shagun Maheshwari, Janghoon Ock, Adeesh Kolluru, Amir Barati Farimani, John R. Kitchin
Abstract: Machine-learning force fields (MLFFs) have emerged as a promising solution for speeding up ab initio molecular dynamics (MD) simulations, where accurate force predictions are critical but often computationally expensive. In this work, we employ GemNet-T, a graph neural network model, as an MLFF and investigate two training strategies: (1) direct training on MD17 (10K samples) without pre-training, and (2) pre-training on the large-scale OC20 dataset followed by fine-tuning on MD17 (10K). While both approaches achieve low force mean absolute errors (MAEs), reaching 5 meV/A per atom, we find that lower force errors do not necessarily guarantee stable MD simulations. Notably, the pre-trained GemNet-T model yields significantly improved simulation stability, sustaining trajectories up to three times longer than the model trained from scratch. These findings underscore the value of pre-training on large, diverse datasets to capture complex molecular interactions and highlight that force MAE alone is not always a sufficient metric of MD simulation stability.
Authors: Yifei Liu, Zuo Gan, Zhenghao Gan, Weiye Wang, Chen Chen, Yizhou Shan, Xusheng Chen, Zhenhua Han, Yifei Zhu, Shixuan Sun, Minyi Guo
Abstract: Applications based on Large Language Models (LLMs) contains a series of tasks to address real-world problems with boosted capability, which have dynamic demand volumes on diverse backends. Existing serving systems treat the resource demands of LLM applications as a blackbox, compromising end-to-end efficiency due to improper queuing order and backend warm up latency. We find that the resource demands of LLM applications can be modeled in a general and accurate manner with Probabilistic Demand Graph (PDGraph). We then propose Hermes, which leverages PDGraph for efficient serving of LLM applications. Confronting probabilistic demand description, Hermes applies the Gittins policy to determine the scheduling order that can minimize the average application completion time. It also uses the PDGraph model to help prewarm cold backends at proper moments. Experiments with diverse LLM applications confirm that Hermes can effectively improve the application serving efficiency, reducing the average completion time by over 70% and the P95 completion time by over 80%.
Authors: Qizheng Zhang, Michael Wornow, Kunle Olukotun
Abstract: LLM-based agentic applications have shown increasingly remarkable capabilities in complex workflows but incur substantial costs due to extensive planning and reasoning requirements. Existing LLM caching techniques (like context caching and semantic caching), primarily designed for serving chatbots, are insufficient for agentic applications where outputs depend on external data or environmental contexts. We propose agentic plan caching, a novel approach that extracts, stores, adapts, and reuses structured plan templates from planning stages of agentic applications across semantically similar tasks to reduce the cost of serving. Unlike traditional semantic caching, our system extracts plan templates from completed agent executions at test-time, employs keyword extraction to match new requests against cached plans, and utilizes lightweight models to adapt these templates to task-specific plans with contexts. Evaluation across multiple real-world agentic applications shows that our system can reduce costs by 46.62% on average while maintaining performance, offering a more efficient solution for serving LLM-based agents that complements existing LLM serving infrastructures.
Authors: Max Ku, Sun Sun, Hongyu Guo, Wenhu Chen
Abstract: We introduce DisProtEdit, a controllable protein editing framework that leverages dual-channel natural language supervision to learn disentangled representations of structural and functional properties. Unlike prior approaches that rely on joint holistic embeddings, DisProtEdit explicitly separates semantic factors, enabling modular and interpretable control. To support this, we construct SwissProtDis, a large-scale multimodal dataset where each protein sequence is paired with two textual descriptions, one for structure and one for function, automatically decomposed using a large language model. DisProtEdit aligns protein and text embeddings using alignment and uniformity objectives, while a disentanglement loss promotes independence between structural and functional semantics. At inference time, protein editing is performed by modifying one or both text inputs and decoding from the updated latent representation. Experiments on protein editing and representation learning benchmarks demonstrate that DisProtEdit performs competitively with existing methods while providing improved interpretability and controllability. On a newly constructed multi-attribute editing benchmark, the model achieves a both-hit success rate of up to 61.7%, highlighting its effectiveness in coordinating simultaneous structural and functional edits.
Authors: Varun Mannam, Zhenyu Shi
Abstract: Accurate video annotation plays a vital role in modern retail applications, including customer behavior analysis, product interaction detection, and in-store activity recognition. However, conventional annotation methods heavily rely on time-consuming manual labeling by human annotators, introducing non-robust frame selection and increasing operational costs. To address these challenges in the retail domain, we propose a deep learning-based approach that automates key-frame identification in retail videos and provides automatic annotations of products and customers. Our method leverages deep neural networks to learn discriminative features by embedding video frames and incorporating object detection-based techniques tailored for retail environments. Experimental results showcase the superiority of our approach over traditional methods, achieving accuracy comparable to human annotator labeling while enhancing the overall efficiency of retail video annotation. Remarkably, our approach leads to an average of 2 times cost savings in video annotation. By allowing human annotators to verify/adjust less than 5% of detected frames in the video dataset, while automating the annotation process for the remaining frames without reducing annotation quality, retailers can significantly reduce operational costs. The automation of key-frame detection enables substantial time and effort savings in retail video labeling tasks, proving highly valuable for diverse retail applications such as shopper journey analysis, product interaction detection, and in-store security monitoring.
Authors: Maniraman Periyasamy, Christian Ufrecht, Daniel D. Scherer, Wolfgang Mauerer
Abstract: Whether QML can offer a transformative advantage remains an open question. The severe constraints of NISQ hardware, particularly in circuit depth and connectivity, hinder both the validation of quantum advantage and the empirical investigation of major obstacles like barren plateaus. Circuit cutting techniques have emerged as a strategy to execute larger quantum circuits on smaller, less connected hardware by dividing them into subcircuits. However, this partitioning increases the number of samples needed to estimate the expectation value accurately through classical post-processing compared to estimating it directly from the full circuit. This work introduces a novel regularization term into the QML optimization process, directly penalizing the overhead associated with sampling. We demonstrate that this approach enables the optimizer to balance the advantages of gate cutting against the optimization of the typical ML cost function. Specifically, it navigates the trade-off between minimizing the cutting overhead and maintaining the overall accuracy of the QML model, paving the way to study larger complex problems in pursuit of quantum advantage.
Authors: Thomas Kuntz, Agatha Duzan, Hao Zhao, Francesco Croce, Zico Kolter, Nicolas Flammarion, Maksym Andriushchenko
Abstract: Computer use agents are LLM-based agents that can directly interact with a graphical user interface, by processing screenshots or accessibility trees. While these systems are gaining popularity, their safety has been largely overlooked, despite the fact that evaluating and understanding their potential for harmful behavior is essential for widespread adoption. To address this gap, we introduce OS-Harm, a new benchmark for measuring safety of computer use agents. OS-Harm is built on top of the OSWorld environment and aims to test models across three categories of harm: deliberate user misuse, prompt injection attacks, and model misbehavior. To cover these cases, we create 150 tasks that span several types of safety violations (harassment, copyright infringement, disinformation, data exfiltration, etc.) and require the agent to interact with a variety of OS applications (email client, code editor, browser, etc.). Moreover, we propose an automated judge to evaluate both accuracy and safety of agents that achieves high agreement with human annotations (0.76 and 0.79 F1 score). We evaluate computer use agents based on a range of frontier models - such as o4-mini, Claude 3.7 Sonnet, Gemini 2.5 Pro - and provide insights into their safety. In particular, all models tend to directly comply with many deliberate misuse queries, are relatively vulnerable to static prompt injections, and occasionally perform unsafe actions. The OS-Harm benchmark is available at https://github.com/tml-epfl/os-harm.
Authors: Zihan Zhang, Lei Shi, Ding-Xuan Zhou
Abstract: In this paper, we study the binary classification problem on $[0,1]^d$ under the Tsybakov noise condition (with exponent $s \in [0,\infty]$) and the compositional assumption. This assumption requires the conditional class probability function of the data distribution to be the composition of $q+1$ vector-valued multivariate functions, where each component function is either a maximum value function or a H\"{o}lder-$\beta$ smooth function that depends only on $d_*$ of its input variables. Notably, $d_*$ can be significantly smaller than the input dimension $d$. We prove that, under these conditions, the optimal convergence rate for the excess 0-1 risk of classifiers is $$ \left( \frac{1}{n} \right)^{\frac{\beta\cdot(1\wedge\beta)^q}{{\frac{d_*}{s+1}+(1+\frac{1}{s+1})\cdot\beta\cdot(1\wedge\beta)^q}}}\;\;\;, $$ which is independent of the input dimension $d$. Additionally, we demonstrate that ReLU deep neural networks (DNNs) trained with hinge loss can achieve this optimal convergence rate up to a logarithmic factor. This result provides theoretical justification for the excellent performance of ReLU DNNs in practical classification tasks, particularly in high-dimensional settings. The technique used to establish these results extends the oracle inequality presented in our previous work. The generalized approach is of independent interest.
Authors: Dyah Adila, Shuai Zhang, Boran Han, Bonan Min, Yuyang Wang
Abstract: The integration of contextual information has significantly enhanced the performance of large language models (LLMs) on knowledge-intensive tasks. However, existing methods often overlook a critical challenge: the credibility of context documents can vary widely, potentially leading to the propagation of unreliable information. In this paper, we introduce CrEst, a novel weakly supervised framework for assessing the credibility of context documents during LLM inference--without requiring manual annotations. Our approach is grounded in the insight that credible documents tend to exhibit higher semantic coherence with other credible documents, enabling automated credibility estimation through inter-document agreement. To incorporate credibility into LLM inference, we propose two integration strategies: a black-box approach for models without access to internal weights or activations, and a white-box method that directly modifies attention mechanisms. Extensive experiments across three model architectures and five datasets demonstrate that CrEst consistently outperforms strong baselines, achieving up to a 26.86% improvement in accuracy and a 3.49% increase in F1 score. Further analysis shows that CrEst maintains robust performance even under high-noise conditions.
Authors: Wassim Bouaziz, Mathurin Videau, Nicolas Usunier, El-Mahdi El-Mhamdi
Abstract: The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace data usage, such methods rely on memorization of training data, which LM providers try to limit. In this work, we demonstrate that indirect data poisoning (where the targeted behavior is absent from training data) is not only feasible but also allow to effectively protect a dataset and trace its use. Using gradient-based optimization prompt-tuning, we make a model learn arbitrary secret sequences: secret responses to secret prompts that are absent from the training corpus. We validate our approach on language models pre-trained from scratch and show that less than 0.005% of poisoned tokens are sufficient to covertly make a LM learn a secret and detect it with extremely high confidence ($p < 10^{-55}$) with a theoretically certifiable scheme. Crucially, this occurs without performance degradation (on LM benchmarks) and despite secrets never appearing in the training set.
Authors: Paula Feldman, Miguel Fainstein, Viviana Siless, Claudio Delrieux, Emmanuel Iarussi
Abstract: Anatomical trees play an important role in clinical diagnosis and treatment planning. Yet, accurately representing these structures poses significant challenges owing to their intricate and varied topology and geometry. Most existing methods to synthesize vasculature are rule based, and despite providing some degree of control and variation in the structures produced, they fail to capture the diversity and complexity of actual anatomical data. We developed a Recursive variational Neural Network (RvNN) that fully exploits the hierarchical organization of the vessel and learns a low-dimensional manifold encoding branch connectivity along with geometry features describing the target surface. After training, the RvNN latent space can be sampled to generate new vessel geometries. By leveraging the power of generative neural networks, we generate 3D models of blood vessels that are both accurate and diverse, which is crucial for medical and surgical training, hemodynamic simulations, and many other purposes. These results closely resemble real data, achieving high similarity in vessel radii, length, and tortuosity across various datasets, including those with aneurysms. To the best of our knowledge, this work is the first to utilize this technique for synthesizing blood vessels.
Authors: Xinkai Zhao, Yuta Tokuoka, Junichiro Iwasawa, Keita Oda
Abstract: The increasing use of diffusion models for image generation, especially in sensitive areas like medical imaging, has raised significant privacy concerns. Membership Inference Attack (MIA) has emerged as a potential approach to determine if a specific image was used to train a diffusion model, thus quantifying privacy risks. Existing MIA methods often rely on diffusion reconstruction errors, where member images are expected to have lower reconstruction errors than non-member images. However, applying these methods directly to medical images faces challenges. Reconstruction error is influenced by inherent image difficulty, and diffusion models struggle with high-frequency detail reconstruction. To address these issues, we propose a Frequency-Calibrated Reconstruction Error (FCRE) method for MIAs on medical image diffusion models. By focusing on reconstruction errors within a specific mid-frequency range and excluding both high-frequency (difficult to reconstruct) and low-frequency (less informative) regions, our frequency-selective approach mitigates the confounding factor of inherent image difficulty. Specifically, we analyze the reverse diffusion process, obtain the mid-frequency reconstruction error, and compute the structural similarity index score between the reconstructed and original images. Membership is determined by comparing this score to a threshold. Experiments on several medical image datasets demonstrate that our FCRE method outperforms existing MIA methods.
Authors: Alejandro Giraldo, Daniel Ruiz, Mariano Caruso, Javier Mancilla, Guido Bellomo
Abstract: Quantitative Structure-Activity Relationship (QSAR) modeling is a cornerstone of computational drug discovery. This research demonstrates the successful application of a Quantum Multiple Kernel Learning (QMKL) framework to enhance QSAR classification, showing a notable performance improvement over classical methods. We apply this methodology to a dataset for identifying DYRK1A kinase inhibitors. The workflow involves converting SMILES representations into numerical molecular descriptors, reducing dimensionality via Principal Component Analysis (PCA), and employing a Support Vector Machine (SVM) trained on an optimized combination of multiple quantum and classical kernels. By benchmarking the QMKL-SVM against a classical Gradient Boosting model, we show that the quantum-enhanced approach achieves a superior AUC score, highlighting its potential to provide a quantum advantage in challenging cheminformatics classification tasks.
Authors: Christina Q. Knight, Kaustubh Deshpande, Ved Sirdeshmukh, Meher Mankikar, Scale Red Team, SEAL Research Team, Julian Michael
Abstract: The rapid advancement of large language models (LLMs) introduces dual-use capabilities that could both threaten and bolster national security and public safety (NSPS). Models implement safeguards to protect against potential misuse relevant to NSPS and allow for benign users to receive helpful information. However, current benchmarks often fail to test safeguard robustness to potential NSPS risks in an objective, robust way. We introduce FORTRESS: 500 expert-crafted adversarial prompts with instance-based rubrics of 4-7 binary questions for automated evaluation across 3 domains (unclassified information only): Chemical, Biological, Radiological, Nuclear and Explosive (CBRNE), Political Violence & Terrorism, and Criminal & Financial Illicit Activities, with 10 total subcategories across these domains. Each prompt-rubric pair has a corresponding benign version to test for model over-refusals. This evaluation of frontier LLMs' safeguard robustness reveals varying trade-offs between potential risks and model usefulness: Claude-3.5-Sonnet demonstrates a low average risk score (ARS) (14.09 out of 100) but the highest over-refusal score (ORS) (21.8 out of 100), while Gemini 2.5 Pro shows low over-refusal (1.4) but a high average potential risk (66.29). Deepseek-R1 has the highest ARS at 78.05, but the lowest ORS at only 0.06. Models such as o1 display a more even trade-off between potential risks and over-refusals (with an ARS of 21.69 and ORS of 5.2). To provide policymakers and researchers with a clear understanding of models' potential risks, we publicly release FORTRESS at https://huggingface.co/datasets/ScaleAI/fortress_public. We also maintain a private set for evaluation.
URLs: https://huggingface.co/datasets/ScaleAI/fortress_public.
Authors: Jaehong Chung, Michael Manga, Timothy Kneafsey, Tapan Mukerji, Mengsu Hu
Abstract: Microearthquakes (MEQs) generated by subsurface fluid injection record the evolving stress state and permeability of reservoirs. Forecasting their full spatiotemporal evolution is therefore critical for applications such as enhanced geothermal systems (EGS), CO$_2$ sequestration and other geo-engineering applications. We present a transformer-based deep learning model that ingests hydraulic stimulation history and prior MEQ observations to forecast four key quantities: cumulative MEQ count, cumulative logarithmic seismic moment, and the 50th- and 95th-percentile extents ($P_{50}, P_{95}$) of the MEQ cloud. Applied to the EGS Collab Experiment 1 dataset, the model achieves $R^2 >0.98$ for the 1-second forecast horizon and $R^2 >0.88$ for the 15-second forecast horizon across all targets, and supplies uncertainty estimates through a learned standard deviation term. These accurate, uncertainty-quantified forecasts enable real-time inference of fracture propagation and permeability evolution, demonstrating the strong potential of deep-learning approaches to improve seismic-risk assessment and guide mitigation strategies in future fluid-injection operations.
Authors: Luigi Sibille, Torodd Skjerve Nord, Alice Cicirello
Abstract: Ferry quays experience rapid deterioration due to their exposure to harsh maritime environments and ferry impacts. Vibration-based structural health monitoring offers a valuable approach to assessing structural integrity and understanding the structural implications of these impacts. However, practical limitations often restrict sensor placement at critical locations. Consequently, virtual sensing techniques become essential for establishing a Digital Twin and estimating the structural response. This study investigates the application of the Gaussian Process Latent Force Model (GPLFM) for virtual sensing on the Magerholm ferry quay, combining in-operation experimental data collected during a ferry impact with a detailed physics-based model. The proposed Physics-Encoded Machine Learning model integrates a reduced-order structural model with a data-driven GPLFM representing the unknown impact forces via their modal contributions. Significant challenges are addressed for the development of the Digital Twin of the ferry quay, including unknown impact characteristics (location, direction, intensity), time-varying boundary conditions, and sparse sensor configurations. Results show that the GPLFM provides accurate acceleration response estimates at most locations, even under simplifying modeling assumptions such as linear time-invariant behavior during the impact phase. Lower accuracy was observed at locations in the impact zone. A numerical study was conducted to explore an optimal real-world sensor placement strategy using a Backward Sequential Sensor Placement approach. Sensitivity analyses were conducted to examine the influence of sensor types, sampling frequencies, and incorrectly assumed damping ratios. The results suggest that the GP latent forces can help accommodate modeling and measurement uncertainties, maintaining acceptable estimation accuracy across scenarios.
Authors: Daqian Shao, Ashkan Soleymani, Francesco Quinzan, Marta Kwiatkowska
Abstract: Solving conditional moment restrictions (CMRs) is a key problem considered in statistics, causal inference, and econometrics, where the aim is to solve for a function of interest that satisfies some conditional moment equalities. Specifically, many techniques for causal inference, such as instrumental variable (IV) regression and proximal causal learning (PCL), are CMR problems. Most CMR estimators use a two-stage approach, where the first-stage estimation is directly plugged into the second stage to estimate the function of interest. However, naively plugging in the first-stage estimator can cause heavy bias in the second stage. This is particularly the case for recently proposed CMR estimators that use deep neural network (DNN) estimators for both stages, where regularisation and overfitting bias is present. We propose DML-CMR, a two-stage CMR estimator that provides an unbiased estimate with fast convergence rate guarantees. We derive a novel learning objective to reduce bias and develop the DML-CMR algorithm following the double/debiased machine learning (DML) framework. We show that our DML-CMR estimator can achieve the minimax optimal convergence rate of $O(N^{-1/2})$ under parameterisation and mild regularity conditions, where $N$ is the sample size. We apply DML-CMR to a range of problems using DNN estimators, including IV regression and proximal causal learning on real-world datasets, demonstrating state-of-the-art performance against existing CMR estimators and algorithms tailored to those problems.
Authors: David Silva-S\'anchez, Roy R. Lederman
Abstract: Clustering and estimating cluster means are core problems in statistics and machine learning, with k-means and Expectation Maximization (EM) being two widely used algorithms. In this work, we provide a theoretical explanation for the failure of k-means in high-dimensional settings with high noise and limited sample sizes, using a simple Gaussian Mixture Model (GMM). We identify regimes where, with high probability, almost every partition of the data becomes a fixed point of the k-means algorithm. This study is motivated by challenges in the analysis of more complex cases, such as masked GMMs, and those arising from applications in Cryo-Electron Microscopy.
Authors: Yu Duan, Hamza Tahir Chaudhry, Misha B. Ahrens, Christopher D Harvey, Matthew G Perich, Karl Deisseroth, Kanaka Rajan
Abstract: Predicting future neural activity is a core challenge in modeling brain dynamics, with applications ranging from scientific investigation to closed-loop neurotechnology. While recent models of population activity emphasize interpretability and behavioral decoding, neural forecasting-particularly across multi-session, spontaneous recordings-remains underexplored. We introduce POCO, a unified forecasting model that combines a lightweight univariate forecaster with a population-level encoder to capture both neuron-specific and brain-wide dynamics. Trained across five calcium imaging datasets spanning zebrafish, mice, and C. elegans, POCO achieves state-of-the-art accuracy at cellular resolution in spontaneous behaviors. After pre-training, POCO rapidly adapts to new recordings with minimal fine-tuning. Notably, POCO's learned unit embeddings recover biologically meaningful structure-such as brain region clustering-without any anatomical labels. Our comprehensive analysis reveals several key factors influencing performance, including context length, session diversity, and preprocessing. Together, these results position POCO as a scalable and adaptable approach for cross-session neural forecasting and offer actionable insights for future model design. By enabling accurate, generalizable forecasting models of neural dynamics across individuals and species, POCO lays the groundwork for adaptive neurotechnologies and large-scale efforts for neural foundation models.
Authors: Wajih Hassan Raza, Aamir Bader Shah, Yu Wen, Yidan Shen, Juan Diego Martinez Lemus, Mya Caryn Schiess, Timothy Michael Ellmore, Renjie Hu, Xin Fu
Abstract: The integration of multi-modal Magnetic Resonance Imaging (MRI) and clinical data holds great promise for enhancing the diagnosis of neurological disorders (NDs) in real-world clinical settings. Deep Learning (DL) has recently emerged as a powerful tool for extracting meaningful patterns from medical data to aid in diagnosis. However, existing DL approaches struggle to effectively leverage multi-modal MRI and clinical data, leading to suboptimal performance. To address this challenge, we utilize a unique, proprietary multi-modal clinical dataset curated for ND research. Based on this dataset, we propose a novel transformer-based Mixture-of-Experts (MoE) framework for ND classification, leveraging multiple MRI modalities-anatomical (aMRI), Diffusion Tensor Imaging (DTI), and functional (fMRI)-alongside clinical assessments. Our framework employs transformer encoders to capture spatial relationships within volumetric MRI data while utilizing modality-specific experts for targeted feature extraction. A gating mechanism with adaptive fusion dynamically integrates expert outputs, ensuring optimal predictive performance. Comprehensive experiments and comparisons with multiple baselines demonstrate that our multi-modal approach significantly enhances diagnostic accuracy, particularly in distinguishing overlapping disease states. Our framework achieves a validation accuracy of 82.47\%, outperforming baseline methods by over 10\%, highlighting its potential to improve ND diagnosis by applying multi-modal learning to real-world clinical data.
Authors: Marissa Dominijanni, Alexander Ororbia, Kenneth W. Regan
Abstract: Synaptic delays play a crucial role in biological neuronal networks, where their modulation has been observed in mammalian learning processes. In the realm of neuromorphic computing, although spiking neural networks (SNNs) aim to emulate biology more closely than traditional artificial neural networks do, synaptic delays are rarely incorporated into their simulation. We introduce a novel learning rule for simultaneously learning synaptic connection strengths and delays, by extending spike-timing dependent plasticity (STDP), a Hebbian method commonly used for learning synaptic weights. We validate our approach by extending a widely-used SNN model for classification trained with unsupervised learning. Then we demonstrate the effectiveness of our new method by comparing it against another existing methods for co-learning synaptic weights and delays as well as against STDP without synaptic delays. Results demonstrate that our proposed method consistently achieves superior performance across a variety of test scenarios. Furthermore, our experimental results yield insight into the interplay between synaptic efficacy and delay.
Authors: Eman Alqudah, Ashfaq Khokhar
Abstract: Ensuring packet-level communication quality is vital for ultra-reliable, low-latency communications (URLLC) in large-scale industrial wireless networks. We enhance the Local Deadline Partition (LDP) algorithm by introducing a CNN-based dynamic priority prediction mechanism for improved interference coordination in multi-cell, multi-channel networks. Unlike LDP's static priorities, our approach uses a Convolutional Neural Network and graph coloring to adaptively assign link priorities based on real-time traffic, transmission opportunities, and network conditions. Assuming that first training phase is performed offline, our approach introduced minimal overhead, while enabling more efficient resource allocation, boosting network capacity, SINR, and schedulability. Simulation results show SINR gains of up to 113\%, 94\%, and 49\% over LDP across three network configurations, highlighting its effectiveness for complex URLLC scenarios.
Authors: Harbin Hong, Sebastian Caldas, Liu Leqi
Abstract: As Large Language Models (LLMs) increasingly appear in social science research (e.g., economics and marketing), it becomes crucial to assess how well these models replicate human behavior. In this work, using hypothesis testing, we present a quantitative framework to assess the misalignment between LLM-simulated and actual human behaviors in multiple-choice survey settings. This framework allows us to determine in a principled way whether a specific language model can effectively simulate human opinions, decision-making, and general behaviors represented through multiple-choice options. We applied this framework to a popular language model for simulating people's opinions in various public surveys and found that this model is ill-suited for simulating the tested sub-populations (e.g., across different races, ages, and incomes) for contentious questions. This raises questions about the alignment of this language model with the tested populations, highlighting the need for new practices in using LLMs for social science studies beyond naive simulations of human subjects.
Authors: Md Jahangir Alam Khondkar, Ajan Ahmed, Masudul Haider Imtiaz, Stephanie Schuckers
Abstract: Speech enhancement, particularly denoising, is vital in improving the intelligibility and quality of speech signals for real-world applications, especially in noisy environments. While prior research has introduced various deep learning models for this purpose, many struggle to balance noise suppression, perceptual quality, and speaker-specific feature preservation, leaving a critical research gap in their comparative performance evaluation. This study benchmarks three state-of-the-art models Wave-U-Net, CMGAN, and U-Net, on diverse datasets such as SpEAR, VPQAD, and Clarkson datasets. These models were chosen due to their relevance in the literature and code accessibility. The evaluation reveals that U-Net achieves high noise suppression with SNR improvements of +71.96% on SpEAR, +64.83% on VPQAD, and +364.2% on the Clarkson dataset. CMGAN outperforms in perceptual quality, attaining the highest PESQ scores of 4.04 on SpEAR and 1.46 on VPQAD, making it well-suited for applications prioritizing natural and intelligible speech. Wave-U-Net balances these attributes with improvements in speaker-specific feature retention, evidenced by VeriSpeak score gains of +10.84% on SpEAR and +27.38% on VPQAD. This research indicates how advanced methods can optimize trade-offs between noise suppression, perceptual quality, and speaker recognition. The findings may contribute to advancing voice biometrics, forensic audio analysis, telecommunication, and speaker verification in challenging acoustic conditions.
Authors: Ignacio Sastre, Aiala Ros\'a
Abstract: In this work, we observe an interesting phenomenon: it is possible to generate reversible sentence embeddings that allow an LLM to reconstruct the original text exactly, without modifying the model's weights. This is achieved by introducing a special memory token, whose embedding is optimized through training on a fixed sequence. When prompted with this embedding, the model reconstructs the fixed sequence exactly. We evaluate this phenomenon across English and Spanish datasets, sequences of up to approximately 240 tokens, and model scales ranging from 100M to 8B parameters. Notably, Llama 3.1 8B successfully reconstructs all tested sequences. Our findings highlight an interesting capability of LLMs and suggest potential applications in memory-based retrieval, compression, and controlled text generation.
Authors: Eman Alqudah, Ashfaq Khokhar
Abstract: Ensuring packet-level communication quality is vital for ultra-reliable, low-latency communications (URLLC) in large-scale industrial wireless networks. We enhance the Local Deadline Partition (LDP) algorithm by introducing a Graph Convolutional Network (GCN) integrated with a Deep Q-Network (DQN) reinforcement learning framework for improved interference coordination in multi-cell, multi-channel networks. Unlike LDP's static priorities, our approach dynamically learns link priorities based on real-time traffic demand, network topology, remaining transmission opportunities, and interference patterns. The GCN captures spatial dependencies, while the DQN enables adaptive scheduling decisions through reward-guided exploration. Simulation results show that our GCN-DQN model achieves mean SINR improvements of 179.6\%, 197.4\%, and 175.2\% over LDP across three network configurations. Additionally, the GCN-DQN model demonstrates mean SINR improvements of 31.5\%, 53.0\%, and 84.7\% over our previous CNN-based approach across the same configurations. These results underscore the effectiveness of our GCN-DQN model in addressing complex URLLC requirements with minimal overhead and superior network performance.
Authors: Ben Jacobsen, Kassem Fawaz
Abstract: We study the problem of differentially private continual counting in the unbounded setting where the input size $n$ is not known in advance. Current state-of-the-art algorithms based on optimal instantiations of the matrix mechanism cannot be directly applied here because their privacy guarantees only hold when key parameters are tuned to $n$. Using the common `doubling trick' avoids knowledge of $n$ but leads to suboptimal and non-smooth error. We solve this problem by introducing novel matrix factorizations based on logarithmic perturbations of the function $\frac{1}{\sqrt{1-z}}$ studied in prior works, which may be of independent interest. The resulting algorithm has smooth error, and for any $\alpha > 0$ and $t\leq n$ it is able to privately estimate the sum of the first $t$ data points with $O(\log^{2+2\alpha}(t))$ variance. It requires $O(t)$ space and amortized $O(\log t)$ time per round, compared to $O(\log(n)\log(t))$ variance, $O(n)$ space and $O(n \log n)$ pre-processing time for the nearly-optimal bounded-input algorithm of Henzinger et al. (SODA 2023). Empirically, we find that our algorithm's performance is also comparable to theirs in absolute terms: our variance is less than $1.5\times$ theirs for $t$ as large as $2^{24}$.
Authors: Chris Kapulkin, Nathan Kershaw
Abstract: We present a new tool for data analysis: persistence discrete homology, which is well-suited to analyze filtrations of graphs. In particular, we provide a novel way of representing high-dimensional data as a filtration of graphs using pairwise correlations. We discuss several applications of these tools, e.g., in weather and financial data, comparing them to the standard methods used in the respective fields.
Authors: Gargi Mitra, Mohammadreza Hallajiyan, Inji Kim, Athish Pranav Dharmalingam, Mohammed Elnawawy, Shahrear Iqbal, Karthik Pattabiraman, Homa Alemzadeh
Abstract: The integration of AI/ML into medical devices is rapidly transforming healthcare by enhancing diagnostic and treatment facilities. However, this advancement also introduces serious cybersecurity risks due to the use of complex and often opaque models, extensive interconnectivity, interoperability with third-party peripheral devices, Internet connectivity, and vulnerabilities in the underlying technologies. These factors contribute to a broad attack surface and make threat prevention, detection, and mitigation challenging. Given the highly safety-critical nature of these devices, a cyberattack on these devices can cause the ML models to mispredict, thereby posing significant safety risks to patients. Therefore, ensuring the security of these devices from the time of design is essential. This paper underscores the urgency of addressing the cybersecurity challenges in ML-enabled medical devices at the pre-market phase. We begin by analyzing publicly available data on device recalls and adverse events, and known vulnerabilities, to understand the threat landscape of AI/ML-enabled medical devices and their repercussions on patient safety. Building on this analysis, we introduce a suite of tools and techniques designed by us to assist security analysts in conducting comprehensive premarket risk assessments. Our work aims to empower manufacturers to embed cybersecurity as a core design principle in AI/ML-enabled medical devices, thereby making them safe for patients.
Authors: Zongxia Li, Yapei Chang, Yuhang Zhou, Xiyang Wu, Zichao Liang, Yoo Yeon Sung, Jordan Lee Boyd-Graber
Abstract: Evaluating open-ended long-form generation is challenging because it is hard to define what clearly separates good from bad outputs. Existing methods often miss key aspects like coherence, style, or relevance, or are biased by pretraining data, making open-ended long-form evaluation an underexplored problem. To address this gap, we propose PrefBERT, a scoring model for evaluating open-ended long-form generation in GRPO and guiding its training with distinct rewards for good and bad outputs. Trained on two response evaluation datasets with diverse long-form styles and Likert-rated quality, PrefBERT effectively supports GRPO by offering better semantic reward feedback than traditional metrics ROUGE-L and BERTScore do. Through comprehensive evaluations, including LLM-as-a-judge, human ratings, and qualitative analysis, we show that PrefBERT, trained on multi-sentence and paragraph-length responses, remains reliable across varied long passages and aligns well with the verifiable rewards GRPO needs. Human evaluations confirm that using PrefBERT as the reward signal to train policy models yields responses better aligned with human preferences than those trained with traditional metrics. Our code is available at https://github.com/zli12321/long_form_rl.
Authors: Samhita Kuili, Mohammadreza Amini, Burak Kantarci
Abstract: In the ever-expanding domain of 5G-NR wireless cellular networks, over-the-air jamming attacks are prevalent as security attacks, compromising the quality of the received signal. We simulate a jamming environment by incorporating additive white Gaussian noise (AWGN) into the real-world In-phase and Quadrature (I/Q) OFDM datasets. A Convolutional Autoencoder (CAE) is exploited to implement a jamming detection over various characteristics such as heterogenous I/Q datasets; extracting relevant information on Synchronization Signal Blocks (SSBs), and fewer SSB observations with notable class imbalance. Given the characteristics of datasets, balanced datasets are acquired by employing a Conv1D conditional Wasserstein Generative Adversarial Network-Gradient Penalty(CWGAN-GP) on both majority and minority SSB observations. Additionally, we compare the performance and detection ability of the proposed CAE model on augmented datasets with benchmark models: Convolutional Denoising Autoencoder (CDAE) and Convolutional Sparse Autoencoder (CSAE). Despite the complexity of data heterogeneity involved across all datasets, CAE depicts the robustness in detection performance of jammed signal by achieving average values of 97.33% precision, 91.33% recall, 94.08% F1-score, and 94.35% accuracy over CDAE and CSAE.
Authors: Ruihan Wu, Konstantin Garov, Kamalika Chaudhuri
Abstract: As large language models (LLMs) are increasingly deployed in the real world, the ability to ``unlearn'', or remove specific pieces of knowledge post hoc, has become essential for a variety of reasons ranging from privacy regulations to correcting outdated or harmful content. Prior work has proposed unlearning benchmarks and algorithms, and has typically assumed that the training process and the target model are fixed. In this work, we empirically investigate how learning-time choices in knowledge encoding impact the effectiveness of unlearning factual knowledge. Our experiments reveal two key findings: (1) learning with paraphrased descriptions improves unlearning performance and (2) unlearning individual piece of knowledge from a chunk of text is challenging. Our results suggest that learning-time knowledge encoding may play a central role in enabling reliable post-hoc unlearning.
Authors: Xianghong Fang, Litao Guo, Hengchao Chen, Yuxuan Zhang, XiaofanXia, Dingjie Song, Yexin Liu, Hao Wang, Harry Yang, Yuan Yuan, Qiang Sun
Abstract: The success of autoregressive models largely depends on the effectiveness of vector quantization, a technique that discretizes continuous features by mapping them to the nearest code vectors within a learnable codebook. Two critical issues in existing vector quantization methods are training instability and codebook collapse. Training instability arises from the gradient discrepancy introduced by the straight-through estimator, especially in the presence of significant quantization errors, while codebook collapse occurs when only a small subset of code vectors are utilized during training. A closer examination of these issues reveals that they are primarily driven by a mismatch between the distributions of the features and code vectors, leading to unrepresentative code vectors and significant data information loss during compression. To address this, we employ the Wasserstein distance to align these two distributions, achieving near 100\% codebook utilization and significantly reducing the quantization error. Both empirical and theoretical analyses validate the effectiveness of the proposed approach.
Authors: Min Namgung, JangHyeon Lee, Fangyi Ding, Yao-Yi Chiang
Abstract: Ensuring equitable public transit access remains challenging, particularly in densely populated cities like New York City (NYC), where low-income and minority communities often face limited transit accessibility. Bike-sharing systems (BSS) can bridge these equity gaps by providing affordable first- and last-mile connections. However, strategically expanding BSS into underserved neighborhoods is difficult due to uncertain bike-sharing demand at newly planned ("cold-start") station locations and limitations in traditional accessibility metrics that may overlook realistic bike usage potential. We introduce Transit for All (TFA), a spatial computing framework designed to guide the equitable expansion of BSS through three components: (1) spatially-informed bike-sharing demand prediction at cold-start stations using region representation learning that integrates multimodal geospatial data, (2) comprehensive transit accessibility assessment leveraging our novel weighted Public Transport Accessibility Level (wPTAL) by combining predicted bike-sharing demand with conventional transit accessibility metrics, and (3) strategic recommendations for new bike station placements that consider potential ridership and equity enhancement. Using NYC as a case study, we identify transit accessibility gaps that disproportionately impact low-income and minority communities in historically underserved neighborhoods. Our results show that strategically placing new stations guided by wPTAL notably reduces disparities in transit access related to economic and demographic factors. From our study, we demonstrate that TFA provides practical guidance for urban planners to promote equitable transit and enhance the quality of life in underserved urban communities.
Authors: Shengjia Zhang, Jiawei Chen, Changdong Li, Sheng Zhou, Qihao Shi, Yan Feng, Chun Chen, Can Wang
Abstract: Loss functions play a pivotal role in optimizing recommendation models. Among various loss functions, Softmax Loss (SL) and Cosine Contrastive Loss (CCL) are particularly effective. Their theoretical connections and differences warrant in-depth exploration. This work conducts comprehensive analyses of these losses, yielding significant insights: 1) Common strengths -- both can be viewed as augmentations of traditional losses with Distributional Robust Optimization (DRO), enhancing robustness to distributional shifts; 2) Respective limitations -- stemming from their use of different distribution distance metrics in DRO optimization, SL exhibits high sensitivity to false negative instances, whereas CCL suffers from low data utilization. To address these limitations, this work proposes a new loss function, DrRL, which generalizes SL and CCL by leveraging R\'enyi-divergence in DRO optimization. DrRL incorporates the advantageous structures of both SL and CCL, and can be demonstrated to effectively mitigate their limitations. Extensive experiments have been conducted to validate the superiority of DrRL on both recommendation accuracy and robustness.
Authors: Matteo Zecchin, Tomer Raviv, Dileep Kalathil, Krishna Narayanan, Nir Shlezinger, Osvaldo Simeone
Abstract: In recent years, deep learning has facilitated the creation of wireless receivers capable of functioning effectively in conditions that challenge traditional model-based designs. Leveraging programmable hardware architectures, deep learning-based receivers offer the potential to dynamically adapt to varying channel environments. However, current adaptation strategies, including joint training, hypernetwork-based methods, and meta-learning, either demonstrate limited flexibility or necessitate explicit optimization through gradient descent. This paper presents gradient-free adaptation techniques rooted in the emerging paradigm of in-context learning (ICL). We review architectural frameworks for ICL based on Transformer models and structured state-space models (SSMs), alongside theoretical insights into how sequence models effectively learn adaptation from contextual information. Further, we explore the application of ICL to cell-free massive MIMO networks, providing both theoretical analyses and empirical evidence. Our findings indicate that ICL represents a principled and efficient approach to real-time receiver adaptation using pilot signals and auxiliary contextual information-without requiring online retraining.
Authors: Boah Kim, Tejas Sudharshan Mathai, Kimberly Helm, Peter A. Pinto, Ronald M. Summers
Abstract: Multi-parametric magnetic resonance imaging (mpMRI) exams have various series types acquired with different imaging protocols. The DICOM headers of these series often have incorrect information due to the sheer diversity of protocols and occasional technologist errors. To address this, we present a deep learning-based classification model to classify 8 different body mpMRI series types so that radiologists read the exams efficiently. Using mpMRI data from various institutions, multiple deep learning-based classifiers of ResNet, EfficientNet, and DenseNet are trained to classify 8 different MRI series, and their performance is compared. Then, the best-performing classifier is identified, and its classification capability under the setting of different training data quantities is studied. Also, the model is evaluated on the out-of-training-distribution datasets. Moreover, the model is trained using mpMRI exams obtained from different scanners in two training strategies, and its performance is tested. Experimental results show that the DenseNet-121 model achieves the highest F1-score and accuracy of 0.966 and 0.972 over the other classification models with p-value$<$0.05. The model shows greater than 0.95 accuracy when trained with over 729 studies of the training data, whose performance improves as the training data quantities grew larger. On the external data with the DLDS and CPTAC-UCEC datasets, the model yields 0.872 and 0.810 accuracy for each. These results indicate that in both the internal and external datasets, the DenseNet-121 model attains high accuracy for the task of classifying 8 body MRI series types.
Authors: Lucas Schulze, Jan Peters, Oleg Arenz
Abstract: Controlling a robot based on physics-informed dynamic models, such as deep Lagrangian networks (DeLaN), can improve the generalizability and interpretability of the resulting behavior. However, in complex environments, the number of objects to potentially interact with is vast, and their physical properties are often uncertain. This complexity makes it infeasible to employ a single global model. Therefore, we need to resort to online system identification of context-aware models that capture only the currently relevant aspects of the environment. While physical principles such as the conservation of energy may not hold across varying contexts, ensuring physical plausibility for any individual context-aware model can still be highly desirable, particularly when using it for receding horizon control methods such as Model Predictive Control (MPC). Hence, in this work, we extend DeLaN to make it context-aware, combine it with a recurrent network for online system identification, and integrate it with a MPC for adaptive, physics-informed control. We also combine DeLaN with a residual dynamics model to leverage the fact that a nominal model of the robot is typically available. We evaluate our method on a 7-DOF robot arm for trajectory tracking under varying loads. Our method reduces the end-effector tracking error by 39%, compared to a 21% improvement achieved by a baseline that uses an extended Kalman filter.
Authors: Jan van Delden, Julius Schultz, Sebastian Rothe, Christian Libner, Sabine C. Langer, Timo L\"uddecke
Abstract: Structural vibrations are a source of unwanted noise in engineering systems like cars, trains or airplanes. Minimizing these vibrations is crucial for improving passenger comfort. This work presents a novel design optimization approach based on guided flow matching for reducing vibrations by placing beadings (indentations) in plate-like structures. Our method integrates a generative flow matching model and a surrogate model trained to predict structural vibrations. During the generation process, the flow matching model pushes towards manufacturability while the surrogate model pushes to low-vibration solutions. The flow matching model and its training data implicitly define the design space, enabling a broader exploration of potential solutions as no optimization of manually-defined design parameters is required. We apply our method to a range of differentiable optimization objectives, including direct optimization of specific eigenfrequencies through careful construction of the objective function. Results demonstrate that our method generates diverse and manufacturable plate designs with reduced structural vibrations compared to designs from random search, a criterion-based design heuristic and genetic optimization. The code and data are available from https://github.com/ecker-lab/Optimizing_Vibrating_Plates.
URLs: https://github.com/ecker-lab/Optimizing_Vibrating_Plates.
Authors: Negar Foroutan, Jakhongir Saydaliev, Ye Eun Kim, Antoine Bosselut
Abstract: Language identification (LID) is a critical step in curating multilingual LLM pretraining corpora from web crawls. While many studies on LID model training focus on collecting diverse training data to improve performance, low-resource languages -- often limited to single-domain data, such as the Bible -- continue to perform poorly. To resolve these class imbalance and bias issues, we propose a novel supervised contrastive learning (SCL) approach to learn domain-invariant representations for low-resource languages. Through an extensive analysis, we show that our approach improves LID performance on out-of-domain data for low-resource languages by 3.2%, demonstrating its effectiveness in enhancing LID models.
Authors: Anne Gagneux, Mathurin Massias, Emmanuel Soubies
Abstract: This work studies the problem of sparse signal recovery with automatic grouping of variables. To this end, we investigate sorted nonsmooth penalties as a regularization approach for generalized linear models. We focus on a family of sorted nonconvex penalties which generalizes the Sorted L1 Norm (SLOPE). These penalties are designed to promote clustering of variables due to their sorted nature, while the nonconvexity reduces the shrinkage of coefficients. Our goal is to provide efficient ways to compute their proximal operator, enabling the use of popular proximal algorithms to solve composite optimization problems with this choice of sorted penalties. We distinguish between two classes of problems: the weakly convex case where computing the proximal operator remains a convex problem, and the nonconvex case where computing the proximal operator becomes a challenging nonconvex combinatorial problem. For the weakly convex case (e.g. sorted MCP and SCAD), we explain how the Pool Adjacent Violators (PAV) algorithm can exactly compute the proximal operator. For the nonconvex case (e.g. sorted Lq with q in ]0,1[), we show that a slight modification of this algorithm turns out to be remarkably efficient to tackle the computation of the proximal operator. We also present new theoretical insights on the minimizers of the nonconvex proximal problem. We demonstrate the practical interest of using such penalties on several experiments.
Authors: Gunnar K\"onig, Hidde Fokkema, Timo Freiesleben, Celestine Mendler-D\"unner, Ulrike on Luxburg
Abstract: When applicants get rejected by an algorithmic decision system, recourse explanations provide actionable suggestions for how to change their input features to get a positive evaluation. A crucial yet overlooked phenomenon is that recourse explanations are performative: When many applicants act according to their recommendations, their collective behavior may change statistical regularities in the data and, once the model is refitted, also the decision boundary. Consequently, the recourse algorithm may render its own recommendations invalid, such that applicants who make the effort of implementing their recommendations may be rejected again when they reapply. In this work, we formally characterize the conditions under which recourse explanations remain valid under performativity. A key finding is that recourse actions may become invalid if they are influenced by or if they intervene on non-causal variables. Based on our analysis, we caution against the use of standard counterfactual explanations and causal recourse methods, and instead advocate for recourse methods that recommend actions exclusively on causal variables.
Authors: Junhui Zhang, Patrick Jaillet
Abstract: We propose two first-order methods for convex, non-smooth, distributed optimization problems, hereafter called Multi-Timescale Gradient Sliding (MT-GS) and its accelerated variant (AMT-GS). Our MT-GS and AMT-GS can take advantage of similarities between (local) objectives to reduce the communication rounds, are flexible so that different subsets (of agents) can communicate at different, user-picked rates, and are fully deterministic. These three desirable features are achieved through a block-decomposable primal-dual formulation, and a multi-timescale variant of the sliding method introduced in Lan et al. (2020), Lan (2016), where different dual blocks are updated at potentially different rates. To find an $\epsilon$-suboptimal solution, the complexities of our algorithms achieve optimal dependency on $\epsilon$: MT-GS needs $O(\overline{r}A/\epsilon)$ communication rounds and $O(\overline{r}/\epsilon^2)$ subgradient steps for Lipchitz objectives, and AMT-GS needs $O(\overline{r}A/\sqrt{\epsilon\mu})$ communication rounds and $O(\overline{r}/(\epsilon\mu))$ subgradient steps if the objectives are also $\mu$-strongly convex. Here, $\overline{r}$ measures the ``average rate of updates'' for dual blocks, and $A$ measures similarities between (subgradients of) local functions. In addition, the linear dependency of communication rounds on $A$ is optimal (Arjevani and Shamir 2015), thereby providing a positive answer to the open question whether such dependency is achievable for non-smooth objectives (Arjevani and Shamir 2015).
Authors: Anju Chhetri, Jari Korhonen, Prashnna Gyawali, Binod Bhattarai
Abstract: Ensuring reliability is paramount in deep learning, particularly within the domain of medical imaging, where diagnostic decisions often hinge on model outputs. The capacity to separate out-of-distribution (OOD) samples has proven to be a valuable indicator of a model's reliability in research. In medical imaging, this is especially critical, as identifying OOD inputs can help flag potential anomalies that might otherwise go undetected. While many OOD detection methods rely on feature or logit space representations, recent works suggest these approaches may not fully capture OOD diversity. To address this, we propose a novel OOD scoring mechanism, called NERO, that leverages neuron-level relevance at the feature layer. Specifically, we cluster neuron-level relevance for each in-distribution (ID) class to form representative centroids and introduce a relevance distance metric to quantify a new sample's deviation from these centroids, enhancing OOD separability. Additionally, we refine performance by incorporating scaled relevance in the bias term and combining feature norms. Our framework also enables explainable OOD detection. We validate its effectiveness across multiple deep learning architectures on the gastrointestinal imaging benchmarks Kvasir and GastroVision, achieving improvements over state-of-the-art OOD detection methods.
Authors: Nikolay Blagoev, O\u{g}uzhan Ersoy, Lydia Yiyu Chen
Abstract: Training LLMs on decentralized and wimpy computation nodes, e.g., multiple on-spot instances, lowers the training cost and enables model democratization. The inevitable challenge here is the churn of nodes due to failures and the operator's scheduling policies, leading to losing a stage - a part of the model. The conventional approaches to recover from failures are to either use checkpointing, where periodically a copy of the entire model is sent to an additional storage, or redundant computation. These approaches yield significant communication and/or computation overhead even in non-failure cases and scale poorly in settings with large models. In this paper, we propose, CheckFree, an efficient recovery method where a failing stage is substituted by a weighted average of the closest neighboring stages. In contrast to the state of the art, CheckFree requires no additional computation or storage. However, because of the nature of averaging neighbouring stages, it can only recover failures of intermediate stages. We further extend our method to CheckFree+ with out-of-order pipeline execution to tolerate crashes of the first and last stages. Thanks to out-of-order pipelining, behaviour of those stages is mimicked by their neighboring ones, which allows CheckFree+ to recover them by simply copying the weights from the immediate neighbour. To be able to recover the (de)embedding layers, CheckFree+ copies those layers to the neighboring stages, which requires relatively small storage overhead. We extensively evaluate our method on LLaMa models of model sizes from 124M to 1.5B with varying failure frequencies. In the case of low and medium failure rates (5-10%), CheckFree and CheckFree+ outperform both checkpointing and redundant computation in terms of convergence in wall-clock time by over 12%. Both of our proposals can be run via our code available at: https://github.com/gensyn-ai/CheckFree.
Authors: Le Vu Anh, Mehmet Dik, Nguyen Viet Anh
Abstract: Hierarchical graphs often exhibit tree-like branching patterns, a structural property that challenges the design of traditional graph filters. We introduce a boundary-weighted operator that rescales each edge according to how far its endpoints drift toward the graph's Gromov boundary. Using Busemann functions on delta-hyperbolic networks, we prove a closed-form upper bound on the operator's spectral norm: every signal loses a curvature-controlled fraction of its energy at each pass. The result delivers a parameter-free, lightweight filter whose stability follows directly from geometric first principles, offering a new analytic tool for graph signal processing on data with dense or hidden hierarchical structure.
Authors: Ryota Okumura, Tadahiro Taniguchi, Akira Taniguchi, Yoshinobu Hagiwara
Abstract: We propose co-creative learning as a novel paradigm where humans and AI, i.e., biological and artificial agents, mutually integrate their partial perceptual information and knowledge to construct shared external representations, a process we interpret as symbol emergence. Unlike traditional AI teaching based on unilateral knowledge transfer, this addresses the challenge of integrating information from inherently different modalities. We empirically test this framework using a human-AI interaction model based on the Metropolis-Hastings naming game (MHNG), a decentralized Bayesian inference mechanism. In an online experiment, 69 participants played a joint attention naming game (JA-NG) with one of three computer agent types (MH-based, always-accept, or always-reject) under partial observability. Results show that human-AI pairs with an MH-based agent significantly improved categorization accuracy through interaction and achieved stronger convergence toward a shared sign system. Furthermore, human acceptance behavior aligned closely with the MH-derived acceptance probability. These findings provide the first empirical evidence for co-creative learning emerging in human-AI dyads via MHNG-based interaction. This suggests a promising path toward symbiotic AI systems that learn with humans, rather than from them, by dynamically aligning perceptual experiences, opening a new venue for symbiotic AI alignment.
Authors: Md Imbesat Hassan Rizvi, Xiaodan Zhu, Iryna Gurevych
Abstract: Process or step-wise supervision has played a crucial role in advancing complex multi-step reasoning capabilities of Large Language Models (LLMs). However, efficient, high-quality automated process annotation remains a significant challenge. To address this, we introduce Single-Pass Annotation with Reference-Guided Evaluation (SPARE), a novel structured framework that enables single-pass, per-step annotation by aligning each solution step to one or multiple steps in a reference solution, accompanied by explicit reasoning for evaluation. We show that reference-guided step-level evaluation effectively facilitates process supervision on four datasets spanning three domains: mathematical reasoning, multi-hop compositional question answering, and spatial reasoning. We demonstrate that SPARE, when compared to baselines, improves reasoning performance when used for: (1) fine-tuning models in an offline RL setup for inference-time greedy-decoding, and (2) training reward models for ranking/aggregating multiple LLM-generated outputs. Additionally, SPARE achieves competitive performance on challenging mathematical datasets while offering 2.6 times greater efficiency, requiring only 38% of the runtime, compared to tree search-based automatic annotation. The codebase, along with a trained SPARE-PRM model, is publicly released to facilitate further research and reproducibility.
Authors: Li Zheng, Sihang Wang, Hao Fei, Zuquan Peng, Fei Li, Jianming Fu, Chong Teng, Donghong Ji
Abstract: Text-based hyperbole and metaphor detection are of great significance for natural language processing (NLP) tasks. However, due to their semantic obscurity and expressive diversity, it is rather challenging to identify them. Existing methods mostly focus on superficial text features, ignoring the associations of hyperbole and metaphor as well as the effect of implicit emotion on perceiving these rhetorical devices. To implement these hypotheses, we propose an emotion-guided hyperbole and metaphor detection framework based on bidirectional dynamic interaction (EmoBi). Firstly, the emotion analysis module deeply mines the emotion connotations behind hyperbole and metaphor. Next, the emotion-based domain mapping module identifies the target and source domains to gain a deeper understanding of the implicit meanings of hyperbole and metaphor. Finally, the bidirectional dynamic interaction module enables the mutual promotion between hyperbole and metaphor. Meanwhile, a verification mechanism is designed to ensure detection accuracy and reliability. Experiments show that EmoBi outperforms all baseline methods on four datasets. Specifically, compared to the current SoTA, the F1 score increased by 28.1% for hyperbole detection on the TroFi dataset and 23.1% for metaphor detection on the HYPO-L dataset. These results, underpinned by in-depth analyses, underscore the effectiveness and potential of our approach for advancing hyperbole and metaphor detection.
Authors: Agnimitra Dasgupta, Javier Murgoitio-Esandi, Ali Fardisi, Assad A Oberai
Abstract: We propose a data-driven method to learn the time-dependent probability density of a multivariate stochastic process from sample paths, assuming that the initial probability density is known and can be evaluated. Our method uses a novel time-dependent binary classifier trained using a contrastive estimation-based objective that trains the classifier to discriminate between realizations of the stochastic process at two nearby time instants. Significantly, the proposed method explicitly models the time-dependent probability distribution, which means that it is possible to obtain the value of the probability density within the time horizon of interest. Additionally, the input before the final activation in the time-dependent classifier is a second-order approximation to the partial derivative, with respect to time, of the logarithm of the density. We apply the proposed approach to approximate the time-dependent probability density functions for systems driven by stochastic excitations. We also use the proposed approach to synthesize new samples of a random vector from a given set of its realizations. In such applications, we generate sample paths necessary for training using stochastic interpolants. Subsequently, new samples are generated using gradient-based Markov chain Monte Carlo methods because automatic differentiation can efficiently provide the necessary gradient. Further, we demonstrate the utility of an explicit approximation to the time-dependent probability density function through applications in unsupervised outlier detection. Through several numerical experiments, we show that the proposed method accurately reconstructs complex time-dependent, multi-modal, and near-degenerate densities, scales effectively to moderately high-dimensional problems, and reliably detects rare events among real-world data.
Authors: Teysir Baoueb, Xiaoyu Bie, Xi Wang, Ga\"el Richard
Abstract: Breakthroughs in text-to-music generation models are transforming the creative landscape, equipping musicians with innovative tools for composition and experimentation like never before. However, controlling the generation process to achieve a specific desired outcome remains a significant challenge. Even a minor change in the text prompt, combined with the same random seed, can drastically alter the generated piece. In this paper, we explore the application of existing text-to-music diffusion models for instrument editing. Specifically, for an existing audio track, we aim to leverage a pretrained text-to-music diffusion model to edit the instrument while preserving the underlying content. Based on the insight that the model first focuses on the overall structure or content of the audio, then adds instrument information, and finally refines the quality, we show that selecting a well-chosen intermediate timestep, identified through an instrument classifier, yields a balance between preserving the original piece's content and achieving the desired timbre. Our method does not require additional training of the text-to-music diffusion model, nor does it compromise the generation process's speed.
Authors: Aline Dobrovsky, Konstantin Schekotihin, Christian Burmer
Abstract: Failure Analysis (FA) is a highly intricate and knowledge-intensive process. The integration of AI components within the computational infrastructure of FA labs has the potential to automate a variety of tasks, including the detection of non-conformities in images, the retrieval of analogous cases from diverse data sources, and the generation of reports from annotated images. However, as the number of deployed AI models increases, the challenge lies in orchestrating these components into cohesive and efficient workflows that seamlessly integrate with the FA process. This paper investigates the design and implementation of a Large Language Model (LLM)-based Planning Agent (LPA) to assist FA engineers in solving their analysis cases. The LPA integrates LLMs with advanced planning capabilities and external tool utilization, enabling autonomous processing of complex queries, retrieval of relevant data from external systems, and generation of human-readable responses. Evaluation results demonstrate the agent's operational effectiveness and reliability in supporting FA tasks.
Authors: Negar Foroutan, Angelika Romanou, Matin Ansaripour, Julian Martin Eisenschlos, Karl Aberer, R\'emi Lebret
Abstract: Documents are fundamental to preserving and disseminating information, often incorporating complex layouts, tables, and charts that pose significant challenges for automatic document understanding (DU). While vision-language large models (VLLMs) have demonstrated improvements across various tasks, their effectiveness in processing long-context vision inputs remains unclear. This paper introduces WikiMixQA, a benchmark comprising 1,000 multiple-choice questions (MCQs) designed to evaluate cross-modal reasoning over tables and charts extracted from 4,000 Wikipedia pages spanning seven distinct topics. Unlike existing benchmarks, WikiMixQA emphasizes complex reasoning by requiring models to synthesize information from multiple modalities. We evaluate 12 state-of-the-art vision-language models, revealing that while proprietary models achieve ~70% accuracy when provided with direct context, their performance deteriorates significantly when retrieval from long documents is required. Among these, GPT-4-o is the only model exceeding 50% accuracy in this setting, whereas open-source models perform considerably worse, with a maximum accuracy of 27%. These findings underscore the challenges of long-context, multi-modal reasoning and establish WikiMixQA as a crucial benchmark for advancing document understanding research.
Authors: Xiangxiang Cui, Shu Yang, Tianjin Huang, Wanyu Lin, Lijie Hu, Di Wang
Abstract: Regret in Large Language Models refers to their explicit regret expression when presented with evidence contradicting their previously generated misinformation. Studying the regret mechanism is crucial for enhancing model reliability and helps in revealing how cognition is coded in neural networks. To understand this mechanism, we need to first identify regret expressions in model outputs, then analyze their internal representation. This analysis requires examining the model's hidden states, where information processing occurs at the neuron level. However, this faces three key challenges: (1) the absence of specialized datasets capturing regret expressions, (2) the lack of metrics to find the optimal regret representation layer, and (3) the lack of metrics for identifying and analyzing regret neurons. Addressing these limitations, we propose: (1) a workflow for constructing a comprehensive regret dataset through strategically designed prompting scenarios, (2) the Supervised Compression-Decoupling Index (S-CDI) metric to identify optimal regret representation layers, and (3) the Regret Dominance Score (RDS) metric to identify regret neurons and the Group Impact Coefficient (GIC) to analyze activation patterns. Our experimental results successfully identified the optimal regret representation layer using the S-CDI metric, which significantly enhanced performance in probe classification experiments. Additionally, we discovered an M-shaped decoupling pattern across model layers, revealing how information processing alternates between coupling and decoupling phases. Through the RDS metric, we categorized neurons into three distinct functional groups: regret neurons, non-regret neurons, and dual neurons.
Authors: Xin Chen, Jason M. Klusowski, Yan Shuo Tan, Chang Yu
Abstract: Combining randomized estimators in an ensemble, such as via random forests, has become a fundamental technique in modern data science, but can be computationally expensive. Furthermore, the mechanism by which this improves predictive performance is poorly understood. We address these issues in the context of sparse linear regression by proposing and analyzing an ensemble of greedy forward selection estimators that are randomized by feature subsampling -- at each iteration, the best feature is selected from within a random subset. We design a novel implementation based on dynamic programming that greatly improves its computational efficiency. Furthermore, we show via careful numerical experiments that our method can outperform popular methods such as lasso and elastic net across a wide range of settings. Next, contrary to prevailing belief that randomized ensembling is analogous to shrinkage, we show via numerical experiments that it can simultaneously reduce training error and degrees of freedom, thereby shifting the entire bias-variance trade-off curve of the base estimator. We prove this fact rigorously in the setting of orthogonal features, in which case, the ensemble estimator rescales the ordinary least squares coefficients with a two-parameter family of logistic weights, thereby enlarging the model search space. These results enhance our understanding of random forests and suggest that implicit regularization in general may have more complicated effects than explicit regularization.
Authors: Georgios Androutsopoulos, Antonio Bianchi
Abstract: Although Rust ensures memory safety by default, it also permits the use of unsafe code, which can introduce memory safety vulnerabilities if misused. Unfortunately, existing tools for detecting memory bugs in Rust typically exhibit limited detection capabilities, inadequately handle Rust-specific types, or rely heavily on manual intervention. To address these limitations, we present deepSURF, a tool that integrates static analysis with Large Language Model (LLM)-guided fuzzing harness generation to effectively identify memory safety vulnerabilities in Rust libraries, specifically targeting unsafe code. deepSURF introduces a novel approach for handling generics by substituting them with custom types and generating tailored implementations for the required traits, enabling the fuzzer to simulate user-defined behaviors within the fuzzed library. Additionally, deepSURF employs LLMs to augment fuzzing harnesses dynamically, facilitating exploration of complex API interactions and significantly increasing the likelihood of exposing memory safety vulnerabilities. We evaluated deepSURF on 27 real-world Rust crates, successfully rediscovering 20 known memory safety bugs and uncovering 6 previously unknown vulnerabilities, demonstrating clear improvements over state-of-the-art tools.
Authors: Ankan Deria, Adinath Madhavrao Dukre, Feilong Tang, Sara Atito, Sudipta Roy, Muhammad Awais, Muhammad Haris Khan, Imran Razzak
Abstract: Despite significant advances in inference-time search for vision-language models (VLMs), existing approaches remain both computationally expensive and prone to unpenalized, low-confidence generations which often lead to persistent hallucinations. We introduce \textbf{Value-guided Inference with Margin-based Reward (ViMaR)}, a two-stage inference framework that improves both efficiency and output fidelity by combining a temporal-difference value model with a margin-aware reward adjustment. In the first stage, we perform a single pass to identify the highest-value caption among diverse candidates. In the second stage, we selectively refine only those segments that were overlooked or exhibit weak visual grounding, thereby eliminating frequently rewarded evaluations. A calibrated margin-based penalty discourages low-confidence continuations while preserving descriptive richness. Extensive experiments across multiple VLM architectures demonstrate that ViMaR generates captions that are significantly more reliable, factually accurate, detailed, and explanatory, while achieving over 4$\times$ speedup compared to existing value-guided methods. Specifically, we show that ViMaR trained solely on LLaVA Mistral-7B, \textit{generalizes effectively to guide decoding in a stronger unseen model}. To further validate this, we adapt the ViMaR to steer generation in LLaVA-OneVision-Qwen2-7B, leading to consistent improvements in caption quality and demonstrating robust cross-model guidance. This cross-model generalization highlights ViMaR's flexibility and modularity, positioning it as a scalable and transferable inference-time decoding strategy. Furthermore, when ViMaR-generated captions are used for self-training, the underlying models achieve substantial gains across a broad suite of visual comprehension benchmarks, underscoring the potential of fast, accurate, and self-improving VLM pipelines.
Authors: Alexey Naumov, Maxim Rakhuba, Denis Ryapolov, Sergey Samsonov
Abstract: We consider the problem of estimating the spectral norm of a matrix using only matrix-vector products. We propose a new Counterbalance estimator that provides upper bounds on the norm and derive probabilistic guarantees on its underestimation. Compared to standard approaches such as the power method, the proposed estimator produces significantly tighter upper bounds in both synthetic and real-world settings. Our method is especially effective for matrices with fast-decaying spectra, such as those arising in deep learning and inverse problems.
Authors: Bahram Yaghooti, Chengyu Li, Bruno Sinopoli
Abstract: This paper presents a data-integrated framework for learning the dynamics of fractional-order nonlinear systems in both discrete-time and continuous-time settings. The proposed framework consists of two main steps. In the first step, input-output experiments are designed to generate the necessary datasets for learning the system dynamics, including the fractional order, the drift vector field, and the control vector field. In the second step, these datasets, along with the memory-dependent property of fractional-order systems, are used to estimate the system's fractional order. The drift and control vector fields are then reconstructed using orthonormal basis functions. To validate the proposed approach, the algorithm is applied to four benchmark fractional-order systems. The results confirm the effectiveness of the proposed framework in learning the system dynamics accurately. Finally, the same datasets are used to learn equivalent integer-order models. The numerical comparisons demonstrate that fractional-order models better capture long-range dependencies, highlighting the limitations of integer-order representations.
Authors: Kaifeng Zhang, Baoyu Li, Kris Hauser, Yunzhu Li
Abstract: Modeling the dynamics of deformable objects is challenging due to their diverse physical properties and the difficulty of estimating states from limited visual information. We address these challenges with a neural dynamics framework that combines object particles and spatial grids in a hybrid representation. Our particle-grid model captures global shape and motion information while predicting dense particle movements, enabling the modeling of objects with varied shapes and materials. Particles represent object shapes, while the spatial grid discretizes the 3D space to ensure spatial continuity and enhance learning efficiency. Coupled with Gaussian Splattings for visual rendering, our framework achieves a fully learning-based digital twin of deformable objects and generates 3D action-conditioned videos. Through experiments, we demonstrate that our model learns the dynamics of diverse objects -- such as ropes, cloths, stuffed animals, and paper bags -- from sparse-view RGB-D recordings of robot-object interactions, while also generalizing at the category level to unseen instances. Our approach outperforms state-of-the-art learning-based and physics-based simulators, particularly in scenarios with limited camera views. Furthermore, we showcase the utility of our learned models in model-based planning, enabling goal-conditioned object manipulation across a range of tasks. The project page is available at https://kywind.github.io/pgnd .
Authors: Qingming Liu, Zhen Liu, Dinghuai Zhang, Kui Jia
Abstract: Generating high-quality and photorealistic 3D assets remains a longstanding challenge in 3D vision and computer graphics. Although state-of-the-art generative models, such as diffusion models, have made significant progress in 3D generation, they often fall short of human-designed content due to limited ability to follow instructions, align with human preferences, or produce realistic textures, geometries, and physical attributes. In this paper, we introduce Nabla-R2D3, a highly effective and sample-efficient reinforcement learning alignment framework for 3D-native diffusion models using 2D rewards. Built upon the recently proposed Nabla-GFlowNet method, which matches the score function to reward gradients in a principled manner for reward finetuning, our Nabla-R2D3 enables effective adaptation of 3D diffusion models using only 2D reward signals. Extensive experiments show that, unlike vanilla finetuning baselines which either struggle to converge or suffer from reward hacking, Nabla-R2D3 consistently achieves higher rewards and reduced prior forgetting within a few finetuning steps.
Authors: Yijun Lin, Yao-Yi Chiang
Abstract: Large network logs, recording multivariate time series generated from heterogeneous devices and sensors in a network, can often reveal important information about abnormal activities, such as network intrusions and device malfunctions. Existing machine learning methods for anomaly detection on multivariate time series typically assume that 1) normal sequences would have consistent behavior for training unsupervised models, or 2) require a large set of labeled normal and abnormal sequences for supervised models. However, in practice, normal network activities can demonstrate significantly varying sequence patterns (e.g., before and after rerouting partial network traffic). Also, the recorded abnormal events can be sparse. This paper presents a novel semi-supervised method that efficiently captures dependencies between network time series and across time points to generate meaningful representations of network activities for predicting abnormal events. The method can use the limited labeled data to explicitly learn separable embedding space for normal and abnormal samples and effectively leverage unlabeled data to handle training data scarcity. The experiments demonstrate that our approach significantly outperformed state-of-the-art approaches for event detection on a large real-world network log.
Authors: Mark Huasong Meng, Guangdong Bai, Sin Gee Teo, Jin Song Dong
Abstract: When deploying pre-trained neural network models in real-world applications, model consumers often encounter resource-constraint platforms such as mobile and smart devices. They typically use the pruning technique to reduce the size and complexity of the model, generating a lighter one with less resource consumption. Nonetheless, most existing pruning methods are proposed with the premise that the model after being pruned has a chance to be fine-tuned or even retrained based on the original training data. This may be unrealistic in practice, as the data controllers are often reluctant to provide their model consumers with the original data. In this work, we study the neural network pruning in the data-free context, aiming to yield lightweight models that are not only accurate in prediction but also robust against undesired inputs in open-world deployments. Considering the absence of the fine-tuning and retraining that can fix the mis-pruned units, we replace the traditional aggressive one-shot strategy with a conservative one that treats the pruning as a progressive process. We propose a pruning method based on stochastic optimization that uses robustness-related metrics to guide the pruning process. Our method is implemented as a Python program and evaluated with a series of experiments on diverse neural network models. The experimental results show that it significantly outperforms existing one-shot data-free pruning approaches in terms of robustness preservation and accuracy.
Authors: Guillaume Salha-Galvan
Abstract: Graph autoencoders (GAE) and variational graph autoencoders (VGAE) emerged as two powerful groups of unsupervised node embedding methods, with various applications to graph-based machine learning problems such as link prediction and community detection. Nonetheless, at the beginning of this Ph.D. project, GAE and VGAE models were also suffering from key limitations, preventing them from being adopted in the industry. In this thesis, we present several contributions to improve these models, with the general aim of facilitating their use to address industrial-level problems involving graph representations. Firstly, we propose two strategies to overcome the scalability issues of previous GAE and VGAE models, permitting to effectively train these models on large graphs with millions of nodes and edges. These strategies leverage graph degeneracy and stochastic subgraph decoding techniques, respectively. Besides, we introduce Gravity-Inspired GAE and VGAE, providing the first extensions of these models for directed graphs, that are ubiquitous in industrial applications. We also consider extensions of GAE and VGAE models for dynamic graphs. Furthermore, we argue that GAE and VGAE models are often unnecessarily complex, and we propose to simplify them by leveraging linear encoders. Lastly, we introduce Modularity-Aware GAE and VGAE to improve community detection on graphs, while jointly preserving good performances on link prediction. In the last part of this thesis, we evaluate our methods on several graphs extracted from the music streaming service Deezer. We put the emphasis on graph-based music recommendation problems. In particular, we show that our methods can improve the detection of communities of similar musical items to recommend to users, that they can effectively rank similar artists in a cold start setting, and that they permit modeling the music genre perception across cultures.
Authors: George E. Dahl, Frank Schneider, Zachary Nado, Naman Agarwal, Chandramouli Shama Sastry, Philipp Hennig, Sourabh Medapati, Runa Eschenhagen, Priya Kasimbeg, Daniel Suo, Juhan Bae, Justin Gilmer, Abel L. Peirson, Bilal Khan, Rohan Anil, Mike Rabbat, Shankar Krishnan, Daniel Snider, Ehsan Amid, Kongtao Chen, Chris J. Maddison, Rakshith Vasudev, Michal Badura, Ankush Garg, Peter Mattson
Abstract: Training algorithms, broadly construed, are an essential part of every deep learning pipeline. Training algorithm improvements that speed up training across a wide variety of workloads (e.g., better update rules, tuning protocols, learning rate schedules, or data selection schemes) could save time, save computational resources, and lead to better, more accurate, models. Unfortunately, as a community, we are currently unable to reliably identify training algorithm improvements, or even determine the state-of-the-art training algorithm. In this work, using concrete experiments, we argue that real progress in speeding up training requires new benchmarks that resolve three basic challenges faced by empirical comparisons of training algorithms: (1) how to decide when training is complete and precisely measure training time, (2) how to handle the sensitivity of measurements to exact workload details, and (3) how to fairly compare algorithms that require hyperparameter tuning. In order to address these challenges, we introduce a new, competitive, time-to-result benchmark using multiple workloads running on fixed hardware, the AlgoPerf: Training Algorithms benchmark. Our benchmark includes a set of workload variants that make it possible to detect benchmark submissions that are more robust to workload changes than current widely-used methods. Finally, we evaluate baseline submissions constructed using various optimizers that represent current practice, as well as other optimizers that have recently received attention in the literature. These baseline results collectively demonstrate the feasibility of our benchmark, show that non-trivial gaps between methods exist, and set a provisional state-of-the-art for future benchmark submissions to try and surpass.
Authors: Mark Huasong Meng, Hao Guan, Liuhuo Wan, Sin Gee Teo, Guangdong Bai, Jin Song Dong
Abstract: We present PAODING, a toolkit to debloat pretrained neural network models through the lens of data-free pruning. To preserve the model fidelity, PAODING adopts an iterative process, which dynamically measures the effect of deleting a neuron to identify candidates that have the least impact to the output layer. Our evaluation shows that PAODING can significantly reduce the model size, generalize on different datasets and models, and meanwhile preserve the model fidelity in terms of test accuracy and adversarial robustness. PAODING is publicly available on PyPI via https://pypi.org/project/paoding-dl.
Authors: Albert Tseng, Qingyao Sun, David Hou, Christopher De Sa
Abstract: Post-training quantization (PTQ) reduces the memory footprint of LLMs by quantizing weights to low-precision datatypes. Since LLM inference is usually memory-bound, PTQ methods can improve inference throughput. Recent state-of-the-art PTQ approaches use vector quantization (VQ) to quantize multiple weights at once, which improves information utilization through better shaping. However, VQ requires a codebook with size exponential in the dimension. This limits current VQ-based PTQ works to low VQ dimensions ($\le 8$) that in turn limit quantization quality. Here, we introduce QTIP, which instead uses trellis coded quantization (TCQ) to achieve ultra-high-dimensional quantization. TCQ uses a stateful decoder that separates the codebook size from the bitrate and effective dimension. QTIP introduces a spectrum of lookup-only to computed lookup-free trellis codes designed for a hardware-efficient "bitshift" trellis structure; these codes achieve state-of-the-art results in both quantization quality and inference speed.
Authors: Cui Zhang, Wenjun Zhang, Qiong Wu, Pingyi Fan, Qiang Fan, Jiangzhou Wang, Khaled B. Letaief
Abstract: Federated Learning (FL) can protect the privacy of the vehicles in vehicle edge computing (VEC) to a certain extent through sharing the gradients of vehicles' local models instead of local data. The gradients of vehicles' local models are usually large for the vehicular artificial intelligence (AI) applications, thus transmitting such large gradients would cause large per-round latency. Gradient quantization has been proposed as one effective approach to reduce the per-round latency in FL enabled VEC through compressing gradients and reducing the number of bits, i.e., the quantization level, to transmit gradients. The selection of quantization level and thresholds determines the quantization error, which further affects the model accuracy and training time. To do so, the total training time and quantization error (QE) become two key metrics for the FL enabled VEC. It is critical to jointly optimize the total training time and QE for the FL enabled VEC. However, the time-varying channel condition causes more challenges to solve this problem. In this paper, we propose a distributed deep reinforcement learning (DRL)-based quantization level allocation scheme to optimize the long-term reward in terms of the total training time and QE. Extensive simulations identify the optimal weighted factors between the total training time and QE, and demonstrate the feasibility and effectiveness of the proposed scheme.
Authors: Yu Xie, Qiong Wu, Pingyi Fan
Abstract: With the increasing demand for multiple applications on internet of vehicles. It requires vehicles to carry out multiple computing tasks in real time. However, due to the insufficient computing capability of vehicles themselves, offloading tasks to vehicular edge computing (VEC) servers and allocating computing resources to tasks becomes a challenge. In this paper, a multi task digital twin (DT) VEC network is established. By using DT to develop offloading strategies and resource allocation strategies for multiple tasks of each vehicle in a single slot, an optimization problem is constructed. To solve it, we propose a multi-agent reinforcement learning method on the task offloading and resource allocation. Numerous experiments demonstrate that our method is effective compared to other benchmark algorithms.
Authors: Kangwei Qi, Qiong Wu, Pingyi Fan, Nan Cheng, Wen Chen, Khaled B. Letaief
Abstract: Vehicular edge computing (VEC) is an emerging technology with significant potential in the field of internet of vehicles (IoV), enabling vehicles to perform intensive computational tasks locally or offload them to nearby edge devices. However, the quality of communication links may be severely deteriorated due to obstacles such as buildings, impeding the offloading process. To address this challenge, we introduce the use of Reconfigurable Intelligent Surfaces (RIS), which provide alternative communication pathways to assist vehicular communication. By dynamically adjusting the phase-shift of the RIS, the performance of VEC systems can be substantially improved. In this work, we consider a RIS-assisted VEC system, and design an optimal scheme for local execution power, offloading power, and RIS phase-shift, where random task arrivals and channel variations are taken into account. To address the scheme, we propose an innovative deep reinforcement learning (DRL) framework that combines the Deep Deterministic Policy Gradient (DDPG) algorithm for optimizing RIS phase-shift coefficients and the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm for optimizing the power allocation of vehicle user (VU). Simulation results show that our proposed scheme outperforms the traditional centralized DDPG, Twin Delayed Deep Deterministic Policy Gradient (TD3) and some typical stochastic schemes.
Authors: Nan Lin, Peter Palensky, Pedro P. Vergara
Abstract: High-resolution time series data are crucial for the operation and planning of energy systems such as electrical power systems and heating systems. Such data often cannot be shared due to privacy concerns, necessitating the use of synthetic data. However, high-resolution time series data is difficult to model due to its inherent high dimensionality and complex temporal dependencies. Leveraging the recent development of generative AI, especially diffusion models, we propose EnergyDiff, a universal data generation framework for energy time series data. EnergyDiff builds on state-of-the-art denoising diffusion probabilistic models, utilizing a proposed denoising network dedicated to high-resolution time series data and introducing a novel Marginal Calibration technique. Our extensive experimental results demonstrate that EnergyDiff achieves significant improvement in capturing the temporal dependencies and marginal distributions compared to baselines, particularly at the 1-minute resolution. EnergyDiff's universality is validated across diverse energy domains (e.g., electricity demand, heat pump, PV, multiple time resolutions (1 minute, 15 minutes, 30 minutes and 1 hour), and at both customer and transformer levels.
Authors: Yixiu Zhao, Jiaxin Shi, Feng Chen, Shaul Druckmann, Lester Mackey, Scott Linderman
Abstract: Discrete diffusion has emerged as a powerful framework for generative modeling in discrete domains, yet efficiently sampling from these models remains challenging. Existing sampling strategies often struggle to balance computation and sample quality when the number of sampling steps is reduced, even when the model has learned the data distribution well. To address these limitations, we propose a predictor-corrector sampling scheme where the corrector is informed by the diffusion model to more reliably counter the accumulating approximation errors. To further enhance the effectiveness of our informed corrector, we introduce complementary architectural modifications based on hollow transformers and a simple tailored training objective that leverages more training signal. We use a synthetic example to illustrate the failure modes of existing samplers and show how informed correctors alleviate these problems. On the text8 and tokenized ImageNet 256x256 datasets, our informed corrector consistently produces superior samples with fewer errors or improved FID scores for discrete diffusion models. These results underscore the potential of informed correctors for fast and high-fidelity generation using discrete diffusion.
Authors: Anshu Ankolekar, Sebastian Boie, Maryam Abdollahyan, Emanuela Gadaleta, Seyed Alireza Hasheminasab, Guang Yang, Charles Beauville, Nikolaos Dikaios, George Anthony Kastis, Michael Bussmann, Sara Khalid, Hagen Kruger, Philippe Lambin, Giorgos Papanastasiou
Abstract: Federated Learning (FL) has emerged as a promising solution to address the limitations of centralised machine learning (ML) in oncology, particularly in overcoming privacy concerns and harnessing the power of diverse, multi-center data. This systematic review synthesises current knowledge on the state-of-the-art FL in oncology, focusing on breast, lung, and prostate cancer. Distinct from previous surveys, our comprehensive review critically evaluates the real-world implementation and impact of FL on cancer care, demonstrating its effectiveness in enhancing ML generalisability, performance and data privacy in clinical settings and data. We evaluated state-of-the-art advances in FL, demonstrating its growing adoption amid tightening data privacy regulations. FL outperformed centralised ML in 15 out of the 25 studies reviewed, spanning diverse ML models and clinical applications, and facilitating integration of multi-modal information for precision medicine. Despite the current challenges identified in reproducibility, standardisation and methodology across studies, the demonstrable benefits of FL in harnessing real-world data and addressing clinical needs highlight its significant potential for advancing cancer research. We propose that future research should focus on addressing these limitations and investigating further advanced FL methods, to fully harness data diversity and realise the transformative power of cutting-edge FL in cancer care.
Authors: Sully F. Chen, Robert J. Steele, Glen M. Hocky, Beakal Lemeneh, Shivanand P. Lad, Eric K. Oermann
Abstract: The transformer architecture has revolutionized bioinformatics and driven progress in the understanding and prediction of the properties of biomolecules. To date, most biosequence transformers have been trained on single-omic data-either proteins or nucleic acids and have seen incredible success in downstream tasks in each domain, with particularly noteworthy breakthroughs in protein structural modeling. However, single-omic pre-training limits the ability of these models to capture cross-modal interactions. Here we present OmniBioTE, the largest open-source multi-omic model trained on over 250 billion tokens of mixed protein and nucleic acid data. We show that despite only being trained on unlabeled sequence data, OmniBioTE learns joint representations mapping genes to their corresponding protein sequences. We further demonstrate that OmbiBioTE achieves state-of-the-art results predicting the change in Gibbs free energy ({\Delta}G) of the binding interaction between a given nucleic acid and protein. Remarkably, we show that multi-omic biosequence transformers emergently learn useful structural information without any a priori structural training, allowing us to predict which protein residues are most involved in the protein-nucleic acid binding interaction. Lastly, compared to single-omic controls trained with identical compute, OmniBioTE demonstrates superior performance-per-FLOP across both multi-omic and single-omic benchmarks, highlighting the power of a unified modeling approach for biological sequences.
Authors: Christian Marius Lillelund, Ali Hossein Gharari Foomani, Weijie Sun, Shi-ang Qi, Russell Greiner
Abstract: We introduce MENSA, a novel deep learning model for multi-event survival analysis, which predicts the time until an instance experiences multiple distinct events based on its features. MENSA learns a shared representation of the input features while capturing the complex dependence structures between events. In practice, it optimizes the sum of the traditional negative log-likelihood across events and a novel trajectory-based likelihood, which encourages the model to learn the temporal order in which events occur. Experiments on real-world clinical datasets demonstrate that MENSA improves risk and time-to-event prediction compared to state-of-the-art models across single-event, competing-risk, and multi-event settings. Moreover, MENSA achieves this with fewer parameters and lower computational cost (FLOPs) than several deep learning baselines, particularly in high-dimensional feature spaces (more than 100 features).
Authors: Hezhe Qiao, Hanghang Tong, Bo An, Irwin King, Charu Aggarwal, Guansong Pang
Abstract: Graph anomaly detection (GAD), which aims to identify unusual graph instances (nodes, edges, subgraphs, or graphs), has attracted increasing attention in recent years due to its significance in a wide range of applications. Deep learning approaches, graph neural networks (GNNs) in particular, have been emerging as a promising paradigm for GAD, owing to its strong capability in capturing complex structure and/or node attributes in graph data. Considering the large number of methods proposed for GNN-based GAD, it is of paramount importance to summarize the methodologies and findings in the existing GAD studies, so that we can pinpoint effective model designs for tackling open GAD problems. To this end, in this work we aim to present a comprehensive review of deep learning approaches for GAD. Existing GAD surveys are focused on task-specific discussions, making it difficult to understand the technical insights of existing methods and their limitations in addressing some unique challenges in GAD. To fill this gap, we first discuss the problem complexities and their resulting challenges in GAD, and then provide a systematic review of current deep GAD methods from three novel perspectives of methodology, including GNN backbone design, proxy task design for GAD, and graph anomaly measures. To deepen the discussions, we further propose a taxonomy of 13 fine-grained method categories under these three perspectives to provide more in-depth insights into the model designs and their capabilities. To facilitate the experiments and validation, we also summarize a collection of widely-used GAD datasets and empirical comparison. We further discuss multiple open problems to inspire more future high-quality research. A continuously updated repository for datasets, links to the codes of algorithms, and empirical comparison is available at https://github.com/mala-lab/Awesome-Deep-Graph-Anomaly-Detection.
URLs: https://github.com/mala-lab/Awesome-Deep-Graph-Anomaly-Detection.
Authors: Ruiyang Hong, Anastasis Kratsios
Abstract: The foundations of deep learning are supported by the seemingly opposing perspectives of approximation or learning theory. The former advocates for large/expressive models that need not generalize, while the latter considers classes that generalize but may be too small/constrained to be universal approximators. Motivated by real-world deep learning implementations that are both expressive and statistically reliable, we ask: "Is there a class of neural networks that is both large enough to be universal but structured enough to generalize?" This paper constructively provides a positive answer to this question by identifying a highly structured class of ReLU multilayer perceptions (MLPs), which are optimal function approximators and are statistically well-behaved. We show that any $(L,\alpha)$-H\"{o}lder function from $[0,1]^d$ to $[-n,n]$ can be approximated to a uniform $\mathcal{O}(1/n)$ error on $[0,1]^d$ with a sparsely connected ReLU MLP with the same H\"{o}lder exponent $\alpha$ and coefficient $L$, of width $\mathcal{O}(dn^{d/\alpha})$, depth $\mathcal{O}(\log(d))$, with $\mathcal{O}(dn^{d/\alpha})$ nonzero parameters, and whose weights and biases take values in $\{0,\pm 1/2\}$ except in the first and last layers which instead have magnitude at-most $n$. Further, our class of MLPs achieves a near-optimal sample complexity of $\mathcal{O}(\log(N)/\sqrt{N})$ when given $N$ i.i.d. normalized sub-Gaussian training samples. We achieve this by fitting together linear pieces perfectly via the Kuhn triangulation, and we introduce a new proof technique which shows that our construction preserves the regularity of not only the H\"{o}lder functions, but also any uniformly continuous function. Our results imply that neural networks can solve the McShane extension problem on suitable finite sets.
Authors: Duy M. H. Nguyen, Nghiem T. Diep, Trung Q. Nguyen, Hoang-Bao Le, Tai Nguyen, Tien Nguyen, TrungTin Nguyen, Nhat Ho, Pengtao Xie, Roger Wattenhofer, James Zou, Daniel Sonntag, Mathias Niepert
Abstract: State-of-the-art medical multi-modal LLMs (med-MLLMs), such as LLAVA-MED and BIOMEDGPT, primarily depend on scaling model size and data volume, with training driven largely by autoregressive objectives. However, we reveal that this approach can lead to weak vision-language alignment, making these models overly dependent on costly instruction-following data. To address this, we introduce EXGRA-MED, a novel multi-graph alignment framework that jointly aligns images, instruction responses, and extended captions in the latent space, advancing semantic grounding and cross-modal coherence. To scale to large LLMs (e.g., LLaMa-7B), we develop an efficient end-to-end training scheme using black-box gradient estimation, enabling fast and scalable optimization. Empirically, EXGRA-MED matches LLAVA-MED's performance using just 10% of pre-training data, achieving a 20.13% gain on VQA-RAD and approaching full-data performance. It also outperforms strong baselines like BIOMEDGPT and RADFM on visual chatbot and zero-shot classification tasks, demonstrating its promise for efficient, high-quality vision-language integration in medical AI.
Authors: T. Konstantin Rusch, Daniela Rus
Abstract: We propose Linear Oscillatory State-Space models (LinOSS) for efficiently learning on long sequences. Inspired by cortical dynamics of biological neural networks, we base our proposed LinOSS model on a system of forced harmonic oscillators. A stable discretization, integrated over time using fast associative parallel scans, yields the proposed state-space model. We prove that LinOSS produces stable dynamics only requiring nonnegative diagonal state matrix. This is in stark contrast to many previous state-space models relying heavily on restrictive parameterizations. Moreover, we rigorously show that LinOSS is universal, i.e., it can approximate any continuous and causal operator mapping between time-varying functions, to desired accuracy. In addition, we show that an implicit-explicit discretization of LinOSS perfectly conserves the symmetry of time reversibility of the underlying dynamics. Together, these properties enable efficient modeling of long-range interactions, while ensuring stable and accurate long-horizon forecasting. Finally, our empirical results, spanning a wide range of time-series tasks from mid-range to very long-range classification and regression, as well as long-horizon forecasting, demonstrate that our proposed LinOSS model consistently outperforms state-of-the-art sequence models. Notably, LinOSS outperforms Mamba and LRU by nearly 2x on a sequence modeling task with sequences of length 50k.
Authors: Qi Liu, Wanjing Ma
Abstract: In this paper, we identify and analyze a recurring training loss pattern, which we term the \textit{Epochal Sawtooth Phenomenon (ESP)}, commonly observed during training with adaptive gradient-based optimizers, particularly Adam optimizer. This pattern is characterized by a sharp drop in loss at the beginning of each epoch, followed by a gradual increase, resulting in a sawtooth-shaped loss curve. Through empirical observations, we demonstrate that while this effect is most pronounced with Adam, it persists, although less severely, with other optimizers such as RMSProp. We empirically analyze the mechanisms underlying ESP, focusing on key factors such as Adam's $\beta$ parameters, batch size, data shuffling, and sample replacement. Our analysis shows that ESP arises from adaptive learning rate adjustments controlled by the second moment estimate. Additionally, we identify the ``immediate re-exposure to samples'' effect during data shuffling, which causes the model to learn or memorize more at the beginning of each epoch. We also find that smaller values of $\beta_2$ exacerbate ESP but can act as a form of regularization. While ESP is not necessarily indicative of overfitting, higher model capacity can amplify the phenomenon. To further support our analysis, we replicate ESP through a high-dimensional quadratic minimization task. We demonstrate that ESP can emerge even in simple optimization scenarios, reinforcing the generality of this pattern. The code for reproducing our experiments is available at https://github.com/qiliuchn/training-loss-pattern.
Authors: Sujai Hiremath, Promit Ghosal, Kyra Gan
Abstract: Inferring causal relationships from observational data is crucial when experiments are costly or infeasible. Additive noise models (ANMs) enable unique directed acyclic graph (DAG) identification, but existing sample-efficient ANM methods often rely on restrictive assumptions on the data generating process, limiting their applicability to real-world settings. We propose local search in additive noise models, LoSAM, a topological ordering method for learning a unique DAG in ANMs with mixed causal mechanisms and general noise distributions. We introduce new causal substructures and criteria for identifying roots and leaves, enabling efficient top-down learning. We prove asymptotic consistency and polynomial runtime, ensuring scalability and sample efficiency. We test LoSAM on synthetic and real-world data, demonstrating state-of-the-art performance across all mixed mechanism settings.
Authors: Aaron D. Mullen, Daniel R. Harris, Peter Rock, Katherine Thompson, Svetla Slavova, Jeffery Talbert, V. K. Cody Bumgardner
Abstract: We present efforts in the fields of machine learning and time series forecasting to accurately predict counts of future suspected opioid overdoses recorded by Emergency Medical Services (EMS) in the state of Kentucky. Forecasts help government agencies properly prepare and distribute resources related to opioid overdoses. Our approach uses county and district level aggregations of suspected opioid overdose encounters and forecasts future counts for different time intervals. Models with different levels of complexity were evaluated to minimize forecasting error. A variety of additional covariates relevant to opioid overdoses and public health were tested to determine their impact on model performance. Our evaluation shows that useful predictions can be generated with limited error for different types of regions, and high performance can be achieved using commonly available covariates and relatively simple forecasting models.
Authors: Mingsen Du, Meng Chen, Yongjian Li, Xiuxin Zhang, Jiahui Gao, Cun Ji, Shoushui Wei
Abstract: Multivariate time series (MTS) data is generated through multiple sensors across various domains such as engineering application, health monitoring, and the internet of things, characterized by its temporal changes and high dimensional characteristics. Over the past few years, many studies have explored the long-range dependencies and similarities in MTS. However, long-range dependencies are difficult to model due to their temporal changes and high dimensionality makes it difficult to obtain similarities effectively and efficiently. Thus, to address these issues, we propose contrast similarity-aware dual-pathway Mamba for MTS node classification (CS-DPMamba). Firstly, to obtain the dynamic similarity of each sample, we initially use temporal contrast learning module to acquire MTS representations. And then we construct a similarity matrix between MTS representations using Fast Dynamic Time Warping (FastDTW). Secondly, we apply the DPMamba to consider the bidirectional nature of MTS, allowing us to better capture long-range and short-range dependencies within the data. Finally, we utilize the Kolmogorov-Arnold Network enhanced Graph Isomorphism Network to complete the information interaction in the matrix and MTS node classification task. By comprehensively considering the long-range dependencies and dynamic similarity features, we achieved precise MTS node classification. We conducted experiments on multiple University of East Anglia (UEA) MTS datasets, which encompass diverse application scenarios. Our results demonstrate the superiority of our method through both supervised and semi-supervised experiments on the MTS classification task.
Authors: Zheng Zhang, Qiong Wu, Pingyi Fan, Nan Cheng, Wen Chen, Khaled B. Letaief
Abstract: To address communication latency issues, the Third Generation Partnership Project (3GPP) has defined Cellular-Vehicle to Everything (C-V2X) technology, which includes Vehicle-to-Vehicle (V2V) communication for direct vehicle-to-vehicle communication. However, this method requires vehicles to autonomously select communication resources based on the Semi-Persistent Scheduling (SPS) protocol, which may lead to collisions due to different vehicles sharing the same communication resources, thereby affecting communication effectiveness. Non-Orthogonal Multiple Access (NOMA) is considered a potential solution for handling large-scale vehicle communication, as it can enhance the Signal-to-Interference-plus-Noise Ratio (SINR) by employing Successive Interference Cancellation (SIC), thereby reducing the negative impact of communication collisions. When evaluating vehicle communication performance, traditional metrics such as reliability and transmission delay present certain contradictions. Introducing the new metric Age of Information (AoI) provides a more comprehensive evaluation of communication system. Additionally, to ensure service quality, user terminals need to possess high computational capabilities, which may lead to increased energy consumption, necessitating a trade-off between communication energy consumption and effectiveness. Given the complexity and dynamics of communication systems, Deep Reinforcement Learning (DRL) serves as an intelligent learning method capable of learning optimal strategies in dynamic environments. Therefore, this paper analyzes the effects of multi-priority queues and NOMA on AoI in the C-V2X vehicular communication system and proposes an energy consumption and AoI optimization method based on DRL. Finally, through comparative simulations with baseline methods, the proposed approach demonstrates its advances in terms of energy consumption and AoI.
Authors: Mingsen Du, Meng Chen, Yongjian Li, Cun Ji, Shoushui Wei
Abstract: Multivariate time series (MTS) classification is widely applied in fields such as industry, healthcare, and finance, aiming to extract key features from complex time series data for accurate decision-making and prediction. However, existing methods for MTS often struggle due to the challenges of effectively modeling high-dimensional data and the lack of labeled data, resulting in poor classification performance. To address this issue, we propose a heterogeneous relationships of subjects and shapelets method for semi-supervised MTS classification. This method offers a novel perspective by integrating various types of additional information while capturing the relationships between them. Specifically, we first utilize a contrast temporal self-attention module to obtain sparse MTS representations, and then model the similarities between these representations using soft dynamic time warping to construct a similarity graph. Secondly, we learn the shapelets for different subject types, incorporating both the subject features and their shapelets as additional information to further refine the similarity graph, ultimately generating a heterogeneous graph. Finally, we use a dual level graph attention network to get prediction. Through this method, we successfully transform dataset into a heterogeneous graph, integrating multiple additional information and achieving precise semi-supervised node classification. Experiments on the Human Activity Recognition, sleep stage classification and University of East Anglia datasets demonstrate that our method outperforms current state-of-the-art methods in MTS classification tasks, validating its superiority.
Authors: Hai-Long Sun, Da-Wei Zhou, Hanbin Zhao, Le Gan, De-Chuan Zhan, Han-Jia Ye
Abstract: Class-Incremental Learning (CIL) requires models to continually acquire knowledge of new classes without forgetting old ones. Despite Pre-trained Models (PTMs) have shown excellent performance in CIL, catastrophic forgetting still occurs as the model learns new concepts. Existing work seeks to utilize lightweight components to adjust the PTM, while the forgetting phenomenon still comes from {\em parameter and retrieval} levels. Specifically, iterative updates of the model result in parameter drift, while mistakenly retrieving irrelevant modules leads to the mismatch during inference. To this end, we propose MOdel Surgery (MOS) to rescue the model from forgetting previous knowledge. By training task-specific adapters, we continually adjust the PTM to downstream tasks. To mitigate parameter-level forgetting, we present an adapter merging approach to learn task-specific adapters, which aims to bridge the gap between different components while reserve task-specific information. Besides, to address retrieval-level forgetting, we introduce a training-free self-refined adapter retrieval mechanism during inference, which leverages the model's inherent ability for better adapter retrieval. By jointly rectifying the model with those steps, MOS can robustly resist catastrophic forgetting in the learning process. Extensive experiments on seven benchmark datasets validate MOS's state-of-the-art performance. Code is available at: https://github.com/sun-hailong/AAAI25-MOS
Authors: Alexandru Dimofte, Glenn Anta Bucagu, Thorir Mar Ingolfsson, Xiaying Wang, Andrea Cossettini, Luca Benini, Yawei Li
Abstract: Electroencephalograph (EEG) is a crucial tool for studying brain activity. Recently, self-supervised learning methods leveraging large unlabeled datasets have emerged as a potential solution to the scarcity of widely available annotated EEG data. However, current methods suffer from at least one of the following limitations: i) sub-optimal EEG signal modeling, ii) model sizes in the hundreds of millions of trainable parameters, and iii) reliance on private datasets and/or inconsistent public benchmarks, hindering reproducibility. To address these challenges, we introduce a Compact Encoder for Representations of Brain Oscillations using alternating attention (CEReBrO), a new small EEG foundation model. Our tokenization scheme represents EEG signals at a per-channel patch granularity. We propose an alternating attention mechanism that jointly models intra-channel temporal dynamics and inter-channel spatial correlations, achieving 2x speed improvement with 6x less memory required compared to standard self-attention. We present several model sizes ranging from 3.6 million to 85 million parameters. Pre-trained on over 20,000 hours of publicly available scalp EEG recordings with diverse channel configurations, our models set new benchmarks in emotion detection and seizure detection tasks, with competitive performance in anomaly classification and gait prediction. This validates our models' effectiveness and efficiency.
Authors: Kartik Sharma, Vineeth Rakesh, Yingtong Dou, Srijan Kumar, Mahashweta Das
Abstract: Graph Neural Networks (GNNs) combine node attributes over a fixed granularity of the local graph structure around a node to predict its label. However, different nodes may relate to a node-level property with a different granularity of its local neighborhood, and using the same level of smoothing for all nodes can be detrimental to their classification. In this work, we challenge the common fact that a single GNN layer can classify all nodes of a graph by training GNNs with a distinct personalized layer for each node. Inspired by metric learning, we propose a novel algorithm, MetSelect1, to select the optimal representation layer to classify each node. In particular, we identify a prototype representation of each class in a transformed GNN layer and then, classify using the layer where the distance is smallest to a class prototype after normalizing with that layer's variance. Results on 10 datasets and 3 different GNNs show that we significantly improve the node classification accuracy of GNNs in a plug-and-play manner. We also find that using variable layers for prediction enables GNNs to be deeper and more robust to poisoning attacks. We hope this work can inspire future works to learn more adaptive and personalized graph representations.
Authors: Yihao Xue, Jiping Li, Baharan Mirzasoleiman
Abstract: Weak-to-Strong Generalization (W2SG), where a weak model supervises a stronger one, serves as an important analogy for understanding how humans might guide superhuman intelligence in the future. Promising empirical results revealed that a strong model can surpass its weak supervisor. While recent work has offered theoretical insights into this phenomenon, a clear understanding of the interactions between weak and strong models that drive W2SG remains elusive. We investigate W2SG through a theoretical lens and show that it can be characterized using kernels derived from the principal components of weak and strong models' internal representations. These kernels can be used to define a space that, at a high level, captures what the weak model is unable to learn but is learnable by the strong model. The projection of labels onto this space quantifies how much the strong model falls short of its full potential due to weak supervision. This characterization also provides insights into how certain errors in weak supervision can be corrected by the strong model, regardless of overfitting. Our theory has significant practical implications, providing a representation-based metric that predicts W2SG performance trends without requiring labels, as shown in experiments on molecular predictions with transformers and 5 NLP tasks involving 52 LLMs.
Authors: Grigoriy Ksenofontov, Alexander Korotin
Abstract: The Schr\"odinger Bridge (SB) is a powerful framework for solving generative modeling tasks such as unpaired domain translation. Most SB-related research focuses on continuous data space $\mathbb{R}^{D}$ and leaves open theoretical and algorithmic questions about applying SB methods to discrete data, e.g, on finite spaces $\mathbb{S}^{D}$. Notable examples of such sets $\mathbb{S}$ are codebooks of vector-quantized (VQ) representations of modern autoencoders, tokens in texts, categories of atoms in molecules, etc. In this paper, we provide a theoretical and algorithmic foundation for solving SB in discrete spaces using the recently introduced Iterative Markovian Fitting (IMF) procedure. Specifically, we theoretically justify the convergence of discrete-time IMF (D-IMF) to SB in discrete spaces. This enables us to develop a practical computational algorithm for SB, which we call Categorical Schr\"odinger Bridge Matching (CSBM). We show the performance of CSBM via a series of experiments with synthetic data and VQ representations of images. The code of CSBM is available at https://github.com/gregkseno/csbm.
Authors: Jeongmo Kim, Yisak Park, Minung Kim, Seungyul Han
Abstract: Meta reinforcement learning aims to develop policies that generalize to unseen tasks sampled from a task distribution. While context-based meta-RL methods improve task representation using task latents, they often struggle with out-of-distribution (OOD) tasks. To address this, we propose Task-Aware Virtual Training (TAVT), a novel algorithm that accurately captures task characteristics for both training and OOD scenarios using metric-based representation learning. Our method successfully preserves task characteristics in virtual tasks and employs a state regularization technique to mitigate overestimation errors in state-varying environments. Numerical results demonstrate that TAVT significantly enhances generalization to OOD tasks across various MuJoCo and MetaWorld environments. Our code is available at https://github.com/JM-Kim-94/tavt.git.
Authors: Sunwoo Lee, Jaebak Hwang, Yonghyeon Jo, Seungyul Han
Abstract: Traditional robust methods in multi-agent reinforcement learning (MARL) often struggle against coordinated adversarial attacks in cooperative scenarios. To address this limitation, we propose the Wolfpack Adversarial Attack framework, inspired by wolf hunting strategies, which targets an initial agent and its assisting agents to disrupt cooperation. Additionally, we introduce the Wolfpack-Adversarial Learning for MARL (WALL) framework, which trains robust MARL policies to defend against the proposed Wolfpack attack by fostering systemwide collaboration. Experimental results underscore the devastating impact of the Wolfpack attack and the significant robustness improvements achieved by WALL. Our code is available at https://github.com/sunwoolee0504/WALL.
Authors: Nghiem T. Diep, Huy Nguyen, Chau Nguyen, Minh Le, Duy M. H. Nguyen, Daniel Sonntag, Mathias Niepert, Nhat Ho
Abstract: The LLaMA-Adapter has recently emerged as an efficient fine-tuning technique for LLaMA models, leveraging zero-initialized attention to stabilize training and enhance performance. However, despite its empirical success, the theoretical foundations of zero-initialized attention remain largely unexplored. In this paper, we provide a rigorous theoretical analysis, establishing a connection between zero-initialized attention and mixture-of-expert models. We prove that both linear and non-linear prompts, along with gating functions, can be optimally estimated, with non-linear prompts offering greater flexibility for future applications. Empirically, we validate our findings on the open LLM benchmarks, demonstrating that non-linear prompts outperform linear ones. Notably, even with limited training data, both prompt types consistently surpass vanilla attention, highlighting the robustness and adaptability of zero-initialized attention.
Authors: Ruihan Wu, Yu-Xiang Wang
Abstract: Hu and Mehta (2024) posed an open problem: what is the optimal instance-dependent rate for the stochastic decision-theoretic online learning (with $K$ actions and $T$ rounds) under $\varepsilon$-differential privacy? Before, the best known upper bound and lower bound are $O\left(\frac{\log K}{\Delta_{\min}} + \frac{\log K\log T}{\varepsilon}\right)$ and $\Omega\left(\frac{\log K}{\Delta_{\min}} + \frac{\log K}{\varepsilon}\right)$ (where $\Delta_{\min}$ is the gap between the optimal and the second actions). In this paper, we partially address this open problem by having two new results. First, we provide an improved upper bound for this problem $O\left(\frac{\log K}{\Delta_{\min}} + \frac{\log^2K}{\varepsilon}\right)$, which is $T$-independent and only has a log dependency in $K$. Second, to further understand the gap, we introduce the \textit{deterministic setting}, a weaker setting of this open problem, where the received loss vector is deterministic. At this weaker setting, a direct application of the analysis and algorithms from the original setting still leads to an extra log factor. We conduct a novel analysis which proves upper and lower bounds that match at $\Theta(\frac{\log K}{\varepsilon})$.
Authors: Soumita Hait, Ping Li, Haipeng Luo, Mengxiao Zhang
Abstract: Motivated by alternating learning dynamics in two-player games, a recent work by Cevher et al.(2024) shows that $o(\sqrt{T})$ alternating regret is possible for any $T$-round adversarial Online Linear Optimization (OLO) problem, and left as an open question whether the same is true for general Online Convex Optimization (OCO). We answer this question in the affirmative by showing that the continuous Hedge algorithm achieves $\tilde{\mathcal{O}}(d^{\frac{2}{3}}T^{\frac{1}{3}})$ alternating regret for any adversarial $d$-dimensional OCO problems. We show that this implies an alternating learning dynamic that finds a Nash equilibrium for any convex-concave zero-sum games or a coarse correlated equilibrium for any convex two-player general-sum games at a rate of $\tilde{\mathcal{O}}(d^{\frac{2}{3}}/T^{\frac{2}{3}})$. To further improve the time complexity and/or the dimension dependence, we propose another simple algorithm, Follow-the-Regularized-Leader with a regularizer whose convex conjugate is 3rd-order smooth, for OCO with smooth and self-concordant loss functions (such as linear or quadratic losses). We instantiate our algorithm with different regularizers and show that, for example, when the decision set is the $\ell_2$ ball, our algorithm achieves $\tilde{\mathcal{O}}(T^{\frac{2}{5}})$ alternating regret with no dimension dependence (and a better $\tilde{\mathcal{O}}(T^{\frac{1}{3}})$ bound for quadratic losses). We complement our results by showing some algorithm-specific alternating regret lower bounds, including a somewhat surprising $\Omega(\sqrt{T})$ lower bound for a Regret Matching variant that is widely used in alternating learning dynamics.
Authors: Yuki Shibukawa, Taira Tsuchiya, Shinsaku Sakaue, Kenji Yamanishi
Abstract: Online structured prediction is a task of sequentially predicting outputs with complex structures based on inputs and past observations, encompassing online classification. Recent studies showed that in the full-information setting, we can achieve finite bounds on the \textit{surrogate regret}, i.e. the extra target loss relative to the best possible surrogate loss. In practice, however, full-information feedback is often unrealistic as it requires immediate access to the whole structure of complex outputs. Motivated by this, we propose algorithms that work with less demanding feedback, bandit and delayed feedback. For bandit feedback, by using a standard inverse-weighted gradient estimator, we achieve a surrogate regret bound of $O(\sqrt{KT})$ for the time horizon $T$ and the size of the output set $K$. However, $K$ can be extremely large when outputs are highly complex, resulting in an undesirable bound. To address this issue, we propose another algorithm that achieves a surrogate regret bound of $O(T^{2/3})$, which is independent of $K$. This is achieved with a carefully designed pseudo-inverse matrix estimator. Furthermore, we numerically compare the performance of these algorithms, as well as existing ones. Regarding delayed feedback, we provide algorithms and regret analyses that cover various scenarios, including full-information and bandit feedback, as well as fixed and variable delays.
Authors: Felipe del Rio, Alain Raymond-Saez, Daniel Florea, Rodrigo Toro Icarte, Julio Hurtado, Cristian B. Calderon, Alvaro Soto
Abstract: Deep neural networks (DNNs) struggle at systematic generalization (SG). Several studies have evaluated the possibility to promote SG through the proposal of novel architectures, loss functions or training methodologies. Few studies, however, have focused on the role of training data properties in promoting SG. In this work, we investigate the impact of certain data distributional properties, as inductive biases for the SG ability of a multi-modal language model. To this end, we study three different properties. First, data diversity, instantiated as an increase in the possible values a latent property in the training distribution may take. Second, burstiness, where we probabilistically restrict the number of possible values of latent factors on particular inputs during training. Third, latent intervention, where a particular latent factor is altered randomly during training. We find that all three factors significantly enhance SG, with diversity contributing an 89% absolute increase in accuracy in the most affected property. Through a series of experiments, we test various hypotheses to understand why these properties promote SG. Finally, we find that Normalized Mutual Information (NMI) between latent attributes in the training distribution is strongly predictive of out-of-distribution generalization. We find that a mechanism by which lower NMI induces SG is in the geometry of representations. In particular, we find that NMI induces more parallelism in neural representations (i.e., input features coded in parallel neural vectors) of the model, a property related to the capacity of reasoning by analogy.
Authors: Henrik Nolte, Mich\`ele Finck, Kristof Meding
Abstract: Does GPT know you? The answer depends on your level of public recognition; however, if your information was available on a website, the answer could be yes. Most Large Language Models (LLMs) memorize training data to some extent. Thus, even when an LLM memorizes only a small amount of personal data, it typically falls within the scope of data protection laws. If a person is identified or identifiable, the implications are far-reaching. The LLM is subject to EU General Data Protection Regulation requirements even after the training phase is concluded. To back our arguments: (1.) We reiterate that LLMs output training data at inference time, be it verbatim or in generalized form. (2.) We show that some LLMs can thus be considered personal data on their own. This triggers a cascade of data protection implications such as data subject rights, including rights to access, rectification, or erasure. These rights extend to the information embedded within the AI model. (3.) This paper argues that machine learning researchers must acknowledge the legal implications of LLMs as personal data throughout the full ML development lifecycle, from data collection and curation to model provision on e.g., GitHub or Hugging Face. (4.) We propose different ways for the ML research community to deal with these legal implications. Our paper serves as a starting point for improving the alignment between data protection law and the technical capabilities of LLMs. Our findings underscore the need for more interaction between the legal domain and the ML community.
Authors: Aditya Gangrade, Venkatesh Saligrama
Abstract: We study safe linear bandits (SLBs), where an agent selects actions from a convex set to maximize an unknown linear objective subject to unknown linear constraints in each round. Existing methods for SLBs provide strong regret guarantees, but require solving expensive optimization problems (e.g., second-order cones, NP hard programs). To address this, we propose Constrained Linear Thompson Sampling (COLTS), a sampling-based framework that selects actions by solving perturbed linear programs, which significantly reduces computational costs while matching the regret and risk of prior methods. We develop two main variants: S-COLTS, which ensures zero risk and $\widetilde{O}(\sqrt{d^3 T})$ regret given a safe action, and R-COLTS, which achieves $\widetilde{O}(\sqrt{d^3 T})$ regret and risk with no instance information. In simulations, these methods match or outperform state of the art SLB approaches while substantially improving scalability. On the technical front, we introduce a novel coupled noise design that ensures frequent `local optimism' about the true optimum, and a scaling-based analysis to handle the per-round variability of constraints.
Authors: Stefan Schoepf, Muhammad Zaid Hameed, Ambrish Rawat, Kieran Fraser, Giulio Zizzo, Giandomenico Cornacchia, Mark Purcell
Abstract: With LLM usage rapidly increasing, their vulnerability to jailbreaks that create harmful outputs are a major security risk. As new jailbreaking strategies emerge and models are changed by fine-tuning, continuous testing for security vulnerabilities is necessary. Existing Red Teaming methods fall short in cost efficiency, attack success rate, attack diversity, or extensibility as new attack types emerge. We address these challenges with Modular And Diverse Malicious Attack MiXtures (MAD-MAX) for Automated LLM Red Teaming. MAD-MAX uses automatic assignment of attack strategies into relevant attack clusters, chooses the most relevant clusters for a malicious goal, and then combines strategies from the selected clusters to achieve diverse novel attacks with high attack success rates. MAD-MAX further merges promising attacks together at each iteration of Red Teaming to boost performance and introduces a similarity filter to prune out similar attacks for increased cost efficiency. The MAD-MAX approach is designed to be easily extensible with newly discovered attack strategies and outperforms the prominent Red Teaming method Tree of Attacks with Pruning (TAP) significantly in terms of Attack Success Rate (ASR) and queries needed to achieve jailbreaks. MAD-MAX jailbreaks 97% of malicious goals in our benchmarks on GPT-4o and Gemini-Pro compared to TAP with 66%. MAD-MAX does so with only 10.9 average queries to the target LLM compared to TAP with 23.3. WARNING: This paper contains contents which are offensive in nature.
Authors: Debabrota Basu, Debarshi Chanda
Abstract: Resource-efficiently computing representations of probability distributions and the distances between them while only having access to the samples is a fundamental and useful problem across mathematical sciences. In this paper, we propose a generic framework to learn the probability and cumulative distribution functions (PDFs and CDFs) of a sub-Weibull, i.e. almost any light- or heavy-tailed, distribution while the samples from it arrive in a stream. The idea is to reduce these problems into estimating the frequency of an \textit{appropriately chosen subset} of the support of a \textit{properly discretised distribution}. We leverage this reduction to compute mergeable summaries of distributions from the stream of samples while requiring only sublinear space relative to the number of observed samples. This allows us to estimate Wasserstein and Total Variation (TV) distances between any two distributions while samples arrive in streams and from multiple sources. Our algorithms significantly improves on the existing methods for distance estimation incurring super-linear time and linear space complexities, and further extend the mergeable summaries framework to continuous distributions with possibly infinite support. Our results are tight with respect to the existing lower bounds for bounded discrete distributions. In addition, we leverage our proposed estimators of Wasserstein and TV distances to tightly audit the fairness and privacy of algorithms. We empirically demonstrate the efficiency of proposed algorithms across synthetic and real-world datasets.
Authors: Chandan Tankala, Dheeraj M. Nagaraj, Anant Raj
Abstract: Gradient flow in the 2-Wasserstein space is widely used to optimize functionals over probability distributions and is typically implemented using an interacting particle system with $n$ particles. Analyzing these algorithms requires showing (a) that the finite-particle system converges and/or (b) that the resultant empirical distribution of the particles closely approximates the optimal distribution (i.e., propagation of chaos). However, establishing efficient sufficient conditions can be challenging, as the finite particle system may produce heavily dependent random variables. In this work, we study the virtual particle stochastic approximation, originally introduced for Stein Variational Gradient Descent. This method can be viewed as a form of stochastic gradient descent in the Wasserstein space and can be implemented efficiently. In popular settings, we demonstrate that our algorithm's output converges to the optimal distribution under conditions similar to those for the infinite particle limit, and it produces i.i.d. samples without the need to explicitly establish propagation of chaos bounds.
Authors: Eshan Mehendale, Abhinav Thorat, Ravi Kolla, Niranjan Pedanekar
Abstract: We introduce KANITE, a framework leveraging Kolmogorov-Arnold Networks (KANs) for Individual Treatment Effect (ITE) estimation under multiple treatments setting in causal inference. By utilizing KAN's unique abilities to learn univariate activation functions as opposed to learning linear weights by Multi-Layer Perceptrons (MLPs), we improve the estimates of ITEs. The KANITE framework comprises two key architectures: 1.Integral Probability Metric (IPM) architecture: This employs an IPM loss in a specialized manner to effectively align towards ITE estimation across multiple treatments. 2. Entropy Balancing (EB) architecture: This uses weights for samples that are learned by optimizing entropy subject to balancing the covariates across treatment groups. Extensive evaluations on benchmark datasets demonstrate that KANITE outperforms state-of-the-art algorithms in both $\epsilon_{\text{PEHE}}$ and $\epsilon_{\text{ATE}}$ metrics. Our experiments highlight the advantages of KANITE in achieving improved causal estimates, emphasizing the potential of KANs to advance causal inference methodologies across diverse application areas.
Authors: George Rapakoulias, Ali Reza Pedram, Panagiotis Tsiotras
Abstract: The Mean-Field Schrodinger Bridge (MFSB) problem is an optimization problem aiming to find the minimum effort control policy to drive a McKean-Vlassov stochastic differential equation from one probability measure to another. In the context of multi-agent control, the objective is to control the configuration of a swarm of identical, interacting cooperative agents, as captured by the time-varying probability measure of their state. Available methods for solving this problem for distributions with continuous support rely either on spatial discretizations of the problem's domain or on approximating optimal solutions using neural networks trained through stochastic optimization schemes. For agents following Linear Time Varying dynamics, and for Gaussian Mixture Model boundary distributions, we propose a highly efficient parameterization to approximate the optimal solutions of the corresponding MFSB in closed form, without any learning step. Our proposed approach consists of a mixture of elementary policies, each solving a Gaussian-to-Gaussian Covariance Steering problem from the components of the initial mixture to the components of the terminal mixture. Leveraging the semidefinite formulation of the Covariance Steering problem, the proposed solver can handle probabilistic constraints on the system's state while maintaining numerical tractability. We illustrate our approach on a variety of numerical examples.
Authors: Xuerui Su, Shufang Xie, Guoqing Liu, Yingce Xia, Renqian Luo, Peiran Jin, Zhiming Ma, Yue Wang, Zun Wang, Yuting Liu
Abstract: Recently, Large Language Models (LLMs) have rapidly evolved, approaching Artificial General Intelligence (AGI) while benefiting from large-scale reinforcement learning to enhance Human Alignment (HA) and Reasoning. Recent reward-based optimization algorithms, such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO) have achieved significant performance on reasoning tasks, whereas preference-based optimization algorithms such as Direct Preference Optimization (DPO) significantly improve the performance of LLMs on human alignment. However, despite the strong performance of reward-based optimization methods in alignment tasks , they remain vulnerable to reward hacking. Furthermore, preference-based algorithms (such as Online DPO) haven't yet matched the performance of reward-based optimization algorithms (like PPO) on reasoning tasks, making their exploration in this specific area still a worthwhile pursuit. Motivated by these challenges, we propose the Trust Region Preference Approximation (TRPA) algorithm, which integrates rule-based optimization with preference-based optimization for reasoning tasks. As a preference-based algorithm, TRPA naturally eliminates the reward hacking issue. TRPA constructs preference levels using predefined rules, forms corresponding preference pairs, and leverages a novel optimization algorithm for RL training with a theoretical monotonic improvement guarantee. Experimental results demonstrate that TRPA not only achieves competitive performance on reasoning tasks but also exhibits robust stability. The code of this paper are released and updating on https://github.com/XueruiSu/Trust-Region-Preference-Approximation.git.
URLs: https://github.com/XueruiSu/Trust-Region-Preference-Approximation.git.
Authors: Gen Li, Li Chen, Cheng Tang, Valdemar \v{S}v\'abensk\'y, Daisuke Deguchi, Takayoshi Yamashita, Atsushi Shimada
Abstract: We explore the use of Large Language Models (LLMs) for automated assessment of open-text student reflections and prediction of academic performance. Traditional methods for evaluating reflections are time-consuming and may not scale effectively in educational settings. In this work, we employ LLMs to transform student reflections into quantitative scores using two assessment strategies (single-agent and multi-agent) and two prompting techniques (zero-shot and few-shot). Our experiments, conducted on a dataset of 5,278 reflections from 377 students over three academic terms, demonstrate that the single-agent with few-shot strategy achieves the highest match rate with human evaluations. Furthermore, models utilizing LLM-assessed reflection scores outperform baselines in both at-risk student identification and grade prediction tasks. These findings suggest that LLMs can effectively automate reflection assessment, reduce educators' workload, and enable timely support for students who may need additional assistance. Our work emphasizes the potential of integrating advanced generative AI technologies into educational practices to enhance student engagement and academic success.
Authors: Ryoma Sato, Shinji Ito
Abstract: While classical formulations of multi-armed bandit problems assume that each arm's reward is independent and stationary, real-world applications often involve non-stationary environments and interdependencies between arms. In particular, selecting one arm may influence the future rewards of other arms, a scenario not adequately captured by existing models such as rotting bandits or restless bandits. To address this limitation, we propose the influential bandit problem, which models inter-arm interactions through an unknown, symmetric, positive semi-definite interaction matrix that governs the dynamics of arm losses. We formally define this problem and establish two regret lower bounds, including a superlinear $\Omega(T^2 / \log^2 T)$ bound for the standard LCB algorithm (loss minimization version of UCB) and an algorithm-independent $\Omega(T)$ bound, which highlight the inherent difficulty of the setting. We then introduce a new algorithm based on a lower confidence bound (LCB) estimator tailored to the structure of the loss dynamics. Under mild assumptions, our algorithm achieves a regret of $O(KT \log T)$, which is nearly optimal in terms of its dependence on the time horizon. The algorithm is simple to implement and computationally efficient. Empirical evaluations on both synthetic and real-world datasets demonstrate the presence of inter-arm influence and confirm the superior performance of our method compared to conventional bandit algorithms.
Authors: Flint Xiaofeng Fan, Cheston Tan, Roger Wattenhofer, Yew-Soon Ong
Abstract: The rise of reinforcement learning (RL) in critical real-world applications demands a fundamental rethinking of privacy in AI systems. Traditional privacy frameworks, designed to protect isolated data points, fall short for sequential decision-making systems where sensitive information emerges from temporal patterns, behavioral strategies, and collaborative dynamics. Modern RL paradigms, such as federated RL (FedRL) and RL with human feedback (RLHF) in large language models (LLMs), exacerbate these challenges by introducing complex, interactive, and context-dependent learning environments that traditional methods do not address. In this position paper, we argue for a new privacy paradigm built on four core principles: multi-scale protection, behavioral pattern protection, collaborative privacy preservation, and context-aware adaptation. These principles expose inherent tensions between privacy, utility, and interpretability that must be navigated as RL systems become more pervasive in high-stakes domains like healthcare, autonomous vehicles, and decision support systems powered by LLMs. To tackle these challenges, we call for the development of new theoretical frameworks, practical mechanisms, and rigorous evaluation methodologies that collectively enable effective privacy protection in sequential decision-making systems.
Authors: Baohao Liao, Hanze Dong, Yuhui Xu, Doyen Sahoo, Christof Monz, Junnan Li, Caiming Xiong
Abstract: Inference-time scaling techniques have significantly bolstered the reasoning capabilities of large language models (LLMs) by harnessing additional computational effort at inference without retraining. Similarly, Chain-of-Thought (CoT) prompting and its extension, Long CoT, improve accuracy by generating rich intermediate reasoning trajectories, but these approaches incur substantial token costs that impede their deployment in latency-sensitive settings. In this work, we first show that truncated CoT, which stops reasoning before completion and directly generates the final answer, often matches full CoT sampling while using dramatically fewer tokens. Building on this insight, we introduce Fractured Sampling, a unified inference-time strategy that interpolates between full CoT and solution-only sampling along three orthogonal axes: (1) the number of reasoning trajectories, (2) the number of final solutions per trajectory, and (3) the depth at which reasoning traces are truncated. Through extensive experiments on five diverse reasoning benchmarks and several model scales, we demonstrate that Fractured Sampling consistently achieves superior accuracy-cost trade-offs, yielding steep log-linear scaling gains in Pass@k versus token budget. Our analysis reveals how to allocate computation across these dimensions to maximize performance, paving the way for more efficient and scalable LLM reasoning. Code is available at https://github.com/BaohaoLiao/frac-cot.
Authors: Guangtao Zheng, Wenqian Ye, Aidong Zhang
Abstract: Deep learning models often achieve high performance by inadvertently learning spurious correlations between targets and non-essential features. For example, an image classifier may identify an object via its background that spuriously correlates with it. This prediction behavior, known as spurious bias, severely degrades model performance on data that lacks the learned spurious correlations. Existing methods on spurious bias mitigation typically require a variety of data groups with spurious correlation annotations called group labels. However, group labels require costly human annotations and often fail to capture subtle spurious biases such as relying on specific pixels for predictions. In this paper, we propose a novel post hoc spurious bias mitigation framework without requiring group labels. Our framework, termed ShortcutProbe, identifies prediction shortcuts that reflect potential non-robustness in predictions in a given model's latent space. The model is then retrained to be invariant to the identified prediction shortcuts for improved robustness. We theoretically analyze the effectiveness of the framework and empirically demonstrate that it is an efficient and practical tool for improving a model's robustness to spurious bias on diverse datasets.
Authors: Nicolas Castanet, Olivier Sigaud, Sylvain Lamprier
Abstract: Goal-Conditioned Reinforcement Learning (GCRL) enables agents to autonomously acquire diverse behaviors, but faces major challenges in visual environments due to high-dimensional, semantically sparse observations. In the online setting, where agents learn representations while exploring, the latent space evolves with the agent's policy, to capture newly discovered areas of the environment. However, without incentivization to maximize state coverage in the representation, classical approaches based on auto-encoders may converge to latent spaces that over-represent a restricted set of states frequently visited by the agent. This is exacerbated in an intrinsic motivation setting, where the agent uses the distribution encoded in the latent space to sample the goals it learns to master. To address this issue, we propose to progressively enforce distributional shifts towards a uniform distribution over the full state space, to ensure a full coverage of skills that can be learned in the environment. We introduce DRAG (Distributionally Robust Auto-Encoding for GCRL), a method that combines the $\beta$-VAE framework with Distributionally Robust Optimization. DRAG leverages an adversarial neural weighter of training states of the VAE, to account for the mismatch between the current data distribution and unseen parts of the environment. This allows the agent to construct semantically meaningful latent spaces beyond its immediate experience. Our approach improves state space coverage and downstream control performance on hard exploration environments such as mazes and robotic control involving walls to bypass, without pre-training nor prior environment knowledge.
Authors: Zhucong Li, Bowei Zhang, Jin Xiao, Zhijian Zhou, Fenglei Cao, Jiaqing Liang, Yuan Qi
Abstract: Large Language Model (LLM)-based agents have demonstrated the ability to improve performance in chemistry-related tasks by selecting appropriate tools. However, their effectiveness remains limited by the inherent prediction errors of chemistry tools. In this paper, we take a step further by exploring how LLMbased agents can, in turn, be leveraged to reduce prediction errors of the tools. To this end, we propose ChemHAS (Chemical Hierarchical Agent Stacking), a simple yet effective method that enhances chemistry tools through optimizing agent-stacking structures from limited data. ChemHAS achieves state-of-the-art performance across four fundamental chemistry tasks, demonstrating that our method can effectively compensate for prediction errors of the tools. Furthermore, we identify and characterize four distinct agent-stacking behaviors, potentially improving interpretability and revealing new possibilities for AI agent applications in scientific research. Our code and dataset are publicly available at https: //anonymous.4open.science/r/ChemHAS-01E4/README.md.
Authors: Yihong Tang, Ao Qu, Xujing Yu, Weipeng Deng, Jun Ma, Jinhua Zhao, Lijun Sun
Abstract: Urban and transportation research has long sought to uncover statistically meaningful relationships between key variables and societal outcomes such as road safety, to generate actionable insights that guide the planning, development, and renewal of urban and transportation systems. However, traditional workflows face several key challenges: (1) reliance on human experts to propose hypotheses, which is time-consuming and prone to confirmation bias; (2) limited interpretability, particularly in deep learning approaches; and (3) underutilization of unstructured data that can encode critical urban context. Given these limitations, we propose a Multimodal Large Language Model (MLLM)-based approach for interpretable hypothesis inference, enabling the automated generation, evaluation, and refinement of hypotheses concerning urban context and road safety outcomes. Our method leverages MLLMs to craft safety-relevant questions for street view images (SVIs), extract interpretable embeddings from their responses, and apply them in regression-based statistical models. UrbanX supports iterative hypothesis testing and refinement, guided by statistical evidence such as coefficient significance, thereby enabling rigorous scientific discovery of previously overlooked correlations between urban design and safety. Experimental evaluations on Manhattan street segments demonstrate that our approach outperforms pretrained deep learning models while offering full interpretability. Beyond road safety, UrbanX can serve as a general-purpose framework for urban scientific discovery, extracting structured insights from unstructured urban data across diverse socioeconomic and environmental outcomes. This approach enhances model trustworthiness for policy applications and establishes a scalable, statistically grounded pathway for interpretable knowledge discovery in urban and transportation studies.
Authors: Adri\`a Molina Rodr\'iguez, Oriol Ramos Terrades, Josep Llad\'os
Abstract: Achieving robustness in recognition systems across diverse domains is crucial for their practical utility. While ample data availability is usually assumed, low-resource languages, such as ancient manuscripts and non-western languages, tend to be kept out of the equations of massive pretraining and foundational techniques due to an under representation. In this work, we aim for building models which can generalize to new distributions of data, such as alphabets, faster than centralized fine-tune strategies. For doing so, we take advantage of the recent advancements in model editing to enhance the incorporation of unseen scripts (low-resource learning). In contrast to state-of-the-art meta-learning, we showcase the effectiveness of domain merging in sparse distributions of data, with agnosticity of its relation to the overall distribution or any other prototyping necessity. Even when using the same exact training data, our experiments showcase significant performance boosts in \textbf{transfer learning} to new alphabets and \textbf{out-of-domain evaluation} in challenging domain shifts, including historical ciphered texts and non-Latin scripts. This research contributes a novel approach into building models that can easily adopt under-represented alphabets and, therefore, enable document recognition to a wider set of contexts and cultures.
Authors: Joshua Barron, Devin White
Abstract: The relationship between memorization and generalization in large language models (LLMs) remains an open area of research, with growing evidence that the two are deeply intertwined. In this work, we investigate this relationship by pre-training a series of capacity-limited Transformer models from scratch on two synthetic character-level tasks designed to separately probe generalization (via arithmetic extrapolation) and memorization (via factual recall). We observe a consistent trade-off: small models extrapolate to unseen arithmetic cases but fail to memorize facts, while larger models memorize but fail to extrapolate. An intermediate-capacity model exhibits a similar shift toward memorization. When trained on both tasks jointly, no model (regardless of size) succeeds at extrapolation. These findings suggest that pre-training may intrinsically favor one learning mode over the other. By isolating these dynamics in a controlled setting, our study offers insight into how model capacity shapes learning behavior and offers broader implications for the design and deployment of small language models.
Authors: Mingkang Wu, Devin White, Evelyn Rose, Vernon Lawhern, Nicholas R Waytowich, Yongcan Cao
Abstract: Reinforcement learning from human feedback (RLHF) has become a key factor in aligning model behavior with users' goals. However, while humans integrate multiple strategies when making decisions, current RLHF approaches often simplify this process by modeling human reasoning through isolated tasks such as classification or regression. In this paper, we propose a novel reinforcement learning (RL) method that mimics human decision-making by jointly considering multiple tasks. Specifically, we leverage human ratings in reward-free environments to infer a reward function, introducing learnable weights that balance the contributions of both classification and regression models. This design captures the inherent uncertainty in human decision-making and allows the model to adaptively emphasize different strategies. We conduct several experiments using synthetic human ratings to validate the effectiveness of the proposed approach. Results show that our method consistently outperforms existing rating-based RL methods, and in some cases, even surpasses traditional RL approaches.
Authors: Yuji Kawamata, Kaoru Kamijo, Masateru Kihira, Akihiro Toyoda, Tomoru Nakayama, Akira Imakura, Tetsuya Sakurai, Yukihiko Okada
Abstract: In recent years, the growing need to leverage sensitive data across institutions has led to increased attention on federated learning (FL), a decentralized machine learning paradigm that enables model training without sharing raw data. However, existing FL-based clustering methods, known as federated clustering, typically assume simple data partitioning scenarios such as horizontal or vertical splits, and cannot handle more complex distributed structures. This study proposes data collaboration clustering (DC-Clustering), a novel federated clustering method that supports clustering over complex data partitioning scenarios where horizontal and vertical splits coexist. In DC-Clustering, each institution shares only intermediate representations instead of raw data, ensuring privacy preservation while enabling collaborative clustering. The method allows flexible selection between k-means and spectral clustering, and achieves final results with a single round of communication with the central server. We conducted extensive experiments using synthetic and open benchmark datasets. The results show that our method achieves clustering performance comparable to centralized clustering where all data are pooled. DC-Clustering addresses an important gap in current FL research by enabling effective knowledge discovery from distributed heterogeneous data. Its practical properties -- privacy preservation, communication efficiency, and flexibility -- make it a promising tool for privacy-sensitive domains such as healthcare and finance.
Authors: Ejafa Bassam, Dawei Zhu, Kaigui Bian
Abstract: Knowledge distillation is a model compression technique in which a compact "student" network is trained to replicate the predictive behavior of a larger "teacher" network. In logit-based knowledge distillation it has become the de facto approach to augment cross-entropy with a distillation term. Typically this term is either a KL divergence-matching marginal probabilities or a correlation-based loss capturing intra- and inter-class relationships but in every case it sits as an add-on to cross-entropy with its own weight that must be carefully tuned. In this paper we adopt a choice-theoretic perspective and recast knowledge distillation under the Plackett-Luce model by interpreting teacher logits as "worth" scores. We introduce Plackett-Luce Distillation (PLD), a weighted list-wise ranking loss in which the teacher model transfers knowledge of its full ranking of classes, weighting each ranked choice by its own confidence. PLD directly optimizes a single teacher-optimal ranking of the true label first, followed by the remaining classes in descending teacher confidence, yielding a convex, translation-invariant surrogate that subsumes weighted cross-entropy. Empirically on standard image classification benchmarks, PLD improves Top-1 accuracy by an average of +0.42% over DIST (arXiv:2205.10536) and +1.04% over KD (arXiv:1503.02531) in homogeneous settings and by +0.48% and +1.09% over DIST and KD, respectively, in heterogeneous settings.
Authors: Weicai Li, Tiejun Lv, Xiyu Zhao, Xin Yuan, Wei Ni
Abstract: Inherent communication noises have the potential to preserve privacy for wireless federated learning (WFL) but have been overlooked in digital communication systems predominantly using floating-point number standards, e.g., IEEE 754, for data storage and transmission. This is due to the potentially catastrophic consequences of bit errors in floating-point numbers, e.g., on the sign or exponent bits. This paper presents a novel channel-native bit-flipping differential privacy (DP) mechanism tailored for WFL, where transmit bits are randomly flipped and communication noises are leveraged, to collectively preserve the privacy of WFL in digital communication systems. The key idea is to interpret the bit perturbation at the transmitter and bit errors caused by communication noises as a bit-flipping DP process. This is achieved by designing a new floating-point-to-fixed-point conversion method that only transmits the bits in the fraction part of model parameters, hence eliminating the need for transmitting the sign and exponent bits and preventing the catastrophic consequence of bit errors. We analyze a new metric to measure the bit-level distance of the model parameters and prove that the proposed mechanism satisfies (\lambda,\epsilon)-R\'enyi DP and does not violate the WFL convergence. Experiments validate privacy and convergence analysis of the proposed mechanism and demonstrate its superiority to the state-of-the-art Gaussian mechanisms that are channel-agnostic and add Gaussian noise for privacy protection.
Authors: Haiyang Guo, Fanhu Zeng, Fei Zhu, Jiayi Wang, Xukai Wang, Jingang Zhou, Hongbo Zhao, Wenzhuo Liu, Shijie Ma, Da-Han Wang, Xu-Yao Zhang, Cheng-Lin Liu
Abstract: The rapid advancement of generative models has enabled modern AI systems to comprehend and produce highly sophisticated content, even achieving human-level performance in specific domains. However, these models remain fundamentally constrained by catastrophic forgetting - a persistent challenge where adapting to new tasks typically leads to significant degradation in performance on previously learned tasks. To address this practical limitation, numerous approaches have been proposed to enhance the adaptability and scalability of generative models in real-world applications. In this work, we present a comprehensive survey of continual learning methods for mainstream generative models, including large language models, multimodal large language models, vision language action models, and diffusion models. Drawing inspiration from the memory mechanisms of the human brain, we systematically categorize these approaches into three paradigms: architecture-based, regularization-based, and replay-based methods, while elucidating their underlying methodologies and motivations. We further analyze continual learning setups for different generative models, including training objectives, benchmarks, and core backbones, offering deeper insights into the field. The project page of this paper is available at https://github.com/Ghy0501/Awesome-Continual-Learning-in-Generative-Models.
URLs: https://github.com/Ghy0501/Awesome-Continual-Learning-in-Generative-Models.
Authors: Daniel Zhengyu Huang, Jiaoyang Huang, Zhengjiang Lin
Abstract: Diffusion probabilistic models generate samples by learning to reverse a noise-injection process that transforms data into noise. Reformulating this reverse process as a deterministic probability flow ordinary differential equation (ODE) enables efficient sampling using high-order solvers, often requiring only $\mathcal{O}(10)$ steps. Since the score function is typically approximated by a neural network, analyzing the interaction between its regularity, approximation error, and numerical integration error is key to understanding the overall sampling accuracy. In this work, we continue our analysis of the convergence properties of the deterministic sampling methods derived from probability flow ODEs [25], focusing on $p$-th order (exponential) Runge-Kutta schemes for any integer $p \geq 1$. Under the assumption that the first and second derivatives of the approximate score function are bounded, we develop $p$-th order (exponential) Runge-Kutta schemes and demonstrate that the total variation distance between the target distribution and the generated data distribution can be bounded above by \begin{align*} O\bigl(d^{\frac{7}{4}}\varepsilon_{\text{score}}^{\frac{1}{2}} +d(dH_{\max})^p\bigr), \end{align*} where $\varepsilon^2_{\text{score}}$ denotes the $L^2$ error in the score function approximation, $d$ is the data dimension and $H_{\max}$ represents the maximum step size used in the solver. We numerically verify the regularity assumption on benchmark datasets, confirming that the first and second derivatives of the approximate score function remain bounded in practice. Our theoretical guarantees hold for general forward processes with arbitrary variance schedules.
Authors: Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti, Christian Kroer
Abstract: We study online decision making problems under resource constraints, where both reward and cost functions are drawn from distributions that may change adversarially over time. We focus on two canonical settings: $(i)$ online resource allocation where rewards and costs are observed before action selection, and $(ii)$ online learning with resource constraints where they are observed after action selection, under full feedback or bandit feedback. It is well known that achieving sublinear regret in these settings is impossible when reward and cost distributions may change arbitrarily over time. To address this challenge, we analyze a framework in which the learner is guided by a spending plan--a sequence prescribing expected resource usage across rounds. We design general (primal-)dual methods that achieve sublinear regret with respect to baselines that follow the spending plan. Crucially, the performance of our algorithms improves when the spending plan ensures a well-balanced distribution of the budget across rounds. We additionally provide a robust variant of our methods to handle worst-case scenarios where the spending plan is highly imbalanced. To conclude, we study the regret of our algorithms when competing against benchmarks that deviate from the prescribed spending plan.
Authors: Yi Wang, Zhenghong Wang, Fan Zhang, Chengling Tang, Chaogui Kang, Di Zhu, Zhongfu Ma, Sijie Ruan, Weiyu Zhang, Yu Zheng, Philip S. Yu, Yu Liu
Abstract: Human activity intensity prediction is a crucial to many location-based services. Although tremendous progress has been made to model dynamic spatiotemporal patterns of human activity, most existing methods, including spatiotemporal graph neural networks (ST-GNNs), overlook physical constraints of spatial interactions and the over-smoothing phenomenon in spatial correlation modeling. To address these limitations, this work proposes a physics-informed deep learning framework, namely Gravity-informed Spatiotemporal Transformer (Gravityformer) by refining transformer attention to integrate the universal law of gravitation and explicitly incorporating constraints from spatial interactions. Specifically, it (1) estimates two spatially explicit mass parameters based on inflow and outflow, (2) models the likelihood of cross-unit interaction using closed-form solutions of spatial interactions to constrain spatial modeling randomness, and (3) utilizes the learned spatial interaction to guide and mitigate the over-smoothing phenomenon in transformer attention matrices. The underlying law of human activity can be explicitly modeled by the proposed adaptive gravity model. Moreover, a parallel spatiotemporal graph convolution transformer structure is proposed for achieving a balance between coupled spatial and temporal learning. Systematic experiments on six real-world large-scale activity datasets demonstrate the quantitative and qualitative superiority of our approach over state-of-the-art benchmarks. Additionally, the learned gravity attention matrix can be disentangled and interpreted based on geographical laws. This work provides a novel insight into integrating physical laws with deep learning for spatiotemporal predictive learning.
Authors: Tatthapong Srikitrungruang, Matthew Lemon, Sina Aghaee Dabaghan Fard, Jaesung Lee, Yuxiao Zhou
Abstract: Accurately estimating spatially heterogeneous elasticity parameters, particularly Young's modulus and Poisson's ratio, from noisy displacement measurements remains significantly challenging in inverse elasticity problems. Existing inverse estimation techniques are often limited by instability, pronounced sensitivity to measurement noise, and difficulty in recovering absolute-scale Young's modulus. This work presents a novel Inverse Elasticity Physics-Informed Neural Network (IE-PINN) specifically designed to robustly reconstruct heterogeneous distributions of elasticity parameters from noisy displacement data based on linear elasticity physics. IE-PINN integrates three distinct neural network architectures dedicated to separately modeling displacement fields, strain fields, and elasticity distributions, thereby significantly enhancing stability and accuracy against measurement noise. Additionally, a two-phase estimation strategy is introduced: the first phase recovers relative spatial distributions of Young's modulus and Poisson's ratio, and the second phase calibrates the absolute scale of Young's modulus using imposed loading boundary conditions. Additional methodological innovations, including positional encoding, sine activation functions, and a sequential pretraining protocol, further enhance the model's performance and robustness. Extensive numerical experiments demonstrate that IE-PINN effectively overcomes critical limitations encountered by existing methods, delivering accurate absolute-scale elasticity estimations even under severe noise conditions. This advancement holds substantial potential for clinical imaging diagnostics and mechanical characterization, where measurements typically encounter substantial noise.
Authors: Parikshit Ram, Kenneth L. Clarkson, Tim Klinger, Shashanka Ubaru, Alexander G. Gray
Abstract: Various forms of sparse attention have been explored to mitigate the quadratic computational and memory cost of the attention mechanism in transformers. We study sparse transformers not through a lens of efficiency but rather in terms of learnability and generalization. Empirically studying a range of attention mechanisms, we find that input-dependent sparse attention models appear to converge faster and generalize better than standard attention models, while input-agnostic sparse attention models show no such benefits -- a phenomenon that is robust across architectural and optimization hyperparameter choices. This can be interpreted as demonstrating that concentrating a model's "semantic focus" with respect to the tokens currently being considered (in the form of input-dependent sparse attention) accelerates learning. We develop a theoretical characterization of the conditions that explain this behavior. We establish a connection between the stability of the standard softmax and the loss function's Lipschitz properties, then show how sparsity affects the stability of the softmax and the subsequent convergence and generalization guarantees resulting from the attention mechanism. This allows us to theoretically establish that input-agnostic sparse attention does not provide any benefits. We also characterize conditions when semantic focus (input-dependent sparse attention) can provide improved guarantees, and we validate that these conditions are in fact met in our empirical evaluations.
Authors: Rohan Gupta, Erik Jenner
Abstract: Latent-space monitors aim to detect undesirable behaviours in large language models by leveraging internal model representations rather than relying solely on black-box outputs. These methods have shown promise in identifying behaviours such as deception and unsafe completions, but a critical open question remains: can LLMs learn to evade such monitors? To study this, we introduce RL-Obfuscation, in which LLMs are finetuned via reinforcement learning to bypass latent-space monitors while maintaining coherent generations. We apply RL-Obfuscation to LLMs ranging from 7B to 14B parameters and evaluate evasion success against a suite of monitors. We find that token-level latent-space monitors are highly vulnerable to this attack. More holistic monitors, such as max-pooling or attention-based probes, remain robust. Moreover, we show that adversarial policies trained to evade a single static monitor generalise to unseen monitors of the same type. Finally, we study how the policy learned by RL bypasses these monitors and find that the model can also learn to repurpose tokens to mean something different internally.
Authors: Gerardo A. Flores, Alyssa H. Smith, Julia A. Fukuyama, Ashia C. Wilson
Abstract: Machine learning-based decision support systems are increasingly deployed in clinical settings, where probabilistic scoring functions are used to inform and prioritize patient management decisions. However, widely used scoring rules, such as accuracy and AUC-ROC, fail to adequately reflect key clinical priorities, including calibration, robustness to distributional shifts, and sensitivity to asymmetric error costs. In this work, we propose a principled yet practical evaluation framework for selecting calibrated thresholded classifiers that explicitly accounts for the uncertainty in class prevalences and domain-specific cost asymmetries often found in clinical settings. Building on the theory of proper scoring rules, particularly the Schervish representation, we derive an adjusted variant of cross-entropy (log score) that averages cost-weighted performance over clinically relevant ranges of class balance. The resulting evaluation is simple to apply, sensitive to clinical deployment conditions, and designed to prioritize models that are both calibrated and robust to real-world variations.
Authors: Jeremy Heng, Valentin De Bortoli, Arnaud Doucet, James Thornton
Abstract: We consider the problem of simulating diffusion bridges, which are diffusion processes that are conditioned to initialize and terminate at two given states. The simulation of diffusion bridges has applications in diverse scientific fields and plays a crucial role in the statistical inference of discretely-observed diffusions. This is known to be a challenging problem that has received much attention in the last two decades. This article contributes to this rich body of literature by presenting a new avenue to obtain diffusion bridge approximations. Our approach is based on a backward time representation of a diffusion bridge, which may be simulated if one can time-reverse the unconditioned diffusion. We introduce a variational formulation to learn this time-reversal with function approximation and rely on a score matching method to circumvent intractability. Another iteration of our proposed methodology approximates the Doob's $h$-transform defining the forward time representation of a diffusion bridge. We discuss algorithmic considerations and extensions, and present numerical results on an Ornstein--Uhlenbeck process, a model from financial econometrics for interest rates, and a model from genetics for cell differentiation and development to illustrate the effectiveness of our approach.
Authors: Mai-Quyen Pham, J\'er\'emy Cohen, Thierry Chonavel
Abstract: Nonnegative Matrix Factorization (NMF) is a fundamental tool in unsupervised learning, widely used for tasks such as dimensionality reduction, feature extraction, representation learning, and topic modeling. Many algorithms have been developed for NMF, including the well-known Multiplicative Updates (MU) algorithm, which belongs to a broader class of majorization-minimization techniques. In this work, we introduce a general second-order optimization framework for NMF under both quadratic and $\beta$-divergence loss functions. This approach, called Second-Order Majorant (SOM), constructs a local quadratic majorization of the loss function by majorizing its Hessian matrix. It includes MU as a special case, while enabling faster variants. In particular, we propose mSOM, a new algorithm within this class that leverages a tighter local approximation to accelerate convergence. We provide a convergence analysis, showing linear convergence for individual factor updates and global convergence to a stationary point for the alternating version, AmSOM algorithm. Numerical experiments on both synthetic and real data sets demonstrate that mSOM consistently outperforms state-of-the-art algorithms across multiple loss functions.
Authors: Matthew A. Price, Jason D. McEwen
Abstract: Many areas of science and engineering encounter data defined on spherical manifolds. Modelling and analysis of spherical data often necessitates spherical harmonic transforms, at high degrees, and increasingly requires efficient computation of gradients for machine learning or other differentiable programming tasks. We develop novel algorithmic structures for accelerated and differentiable computation of generalised Fourier transforms on the sphere $\mathbb{S}^2$ and rotation group $\text{SO}(3)$, i.e. spherical harmonic and Wigner transforms, respectively. We present a recursive algorithm for the calculation of Wigner $d$-functions that is both stable to high harmonic degrees and extremely parallelisable. By tightly coupling this with separable spherical transforms, we obtain algorithms that exhibit an extremely parallelisable structure that is well-suited for the high throughput computing of modern hardware accelerators (e.g. GPUs). We also develop a hybrid automatic and manual differentiation approach so that gradients can be computed efficiently. Our algorithms are implemented within the JAX differentiable programming framework in the S2FFT software code. Numerous samplings of the sphere are supported, including equiangular and HEALPix sampling. Computational errors are at the order of machine precision for spherical samplings that admit a sampling theorem. When benchmarked against alternative C codes we observe up to a 400-fold acceleration. Furthermore, when distributing over multiple GPUs we achieve very close to optimal linear scaling with increasing number of GPUs due to the highly parallelised and balanced nature of our algorithms. Provided access to sufficiently many GPUs our transforms thus exhibit an unprecedented effective linear time complexity.
Authors: Huafu Liao, Alp\'ar R. M\'esz\'aros, Chenchen Mou, Chao Zhou
Abstract: This paper deals with a class of neural SDEs and studies the limiting behavior of the associated sampled optimal control problems as the sample size grows to infinity. The neural SDEs with $N$ samples can be linked to the $N$-particle systems with centralized control. We analyze the Hamilton-Jacobi-Bellman equation corresponding to the $N$-particle system and establish regularity results which are uniform in $N$. The uniform regularity estimates are obtained by the stochastic maximum principle and the analysis of a backward stochastic Riccati equation. Using these uniform regularity results, we show the convergence of the minima of the objective functionals and optimal parameters of the neural SDEs as the sample size $N$ tends to infinity. The limiting objects can be identified with suitable functions defined on the Wasserstein space of Borel probability measures. Furthermore, quantitative convergence rates are also obtained.
Authors: Long Cao, Liwei Ge, Daochi Zhang, Xiang Li, Yao Wang, Rui-Xue Xu, YiJing Yan, Xiao Zheng
Abstract: Reducing computational scaling for simulating non-Markovian dissipative dynamics using artificial neural networks is both a major focus and formidable challenge in open quantum systems. To enable neural quantum states (NQSs), we encode environmental memory in dissipatons (quasiparticles with characteristic lifetimes), yielding the dissipaton-embedded quantum master equation (DQME). The resulting NQS-DQME framework achieves compact representation of many-body correlations and non-Markovian memory. Benchmarking against numerically exact hierarchical equations of motion confirms NQS-DQME maintains comparable accuracy while enhancing scalability and interpretability. This methodology opens new paths to explore non-Markovian open quantum dynamics in previously intractable systems.
Authors: Seonghun Park, Manish Bansal
Abstract: We study submodular optimization in adversarial context, applicable to machine learning problems such as feature selection using data susceptible to uncertainties and attacks. We focus on Stackelberg games between an attacker (or interdictor) and a defender where the attacker aims to minimize the defender's objective of maximizing a $k$-submodular function. We allow uncertainties arising from the success of attacks and inherent data noise, and address challenges due to incomplete knowledge of the probability distribution of random parameters. Specifically, we introduce Distributionally Robust $k$-Submodular Interdiction Problem (DRO $k$-SIP) and Distributionally Risk-Receptive $k$-Submodular Interdiction Problem (DRR $k$-SIP) along with finitely convergent exact algorithms for solving them. When solving the DRO $k$-SIP, the attacker optimizes their expected payoff with respect to the worst-case probability distribution within the ambiguity set, and thereby have robust attack strategies despite distributional ambiguity. In contrast, the DRR $k$-SIP identifies attacker strategies with the best-case probability distribution, and identifies critical vulnerabilities for the defender. The optimal values derived from both DRO $k$-SIP and DRR $k$-SIP offer a confidence interval-like range for the expected value of the defender's objective function, capturing distributional ambiguity. We conduct computational experiments on instances of feature selection and sensor placement problems, using Wisconsin breast cancer data and synthetic data, respectively.
Authors: Pedro Lima Louro, Hugo Redinho, Ricardo Santos, Ricardo Malheiro, Renato Panda, Rui Pedro Paiva
Abstract: The Music Emotion Recognition (MER) field has seen steady developments in recent years, with contributions from feature engineering, machine learning, and deep learning. The landscape has also shifted from audio-centric systems to bimodal ensembles that combine audio and lyrics. However, a lack of public, sizable and quality-controlled bimodal databases has hampered the development and improvement of bimodal audio-lyrics systems. This article proposes three new audio, lyrics, and bimodal MER research datasets, collectively referred to as MERGE, which were created using a semi-automatic approach. To comprehensively assess the proposed datasets and establish a baseline for benchmarking, we conducted several experiments for each modality, using feature engineering, machine learning, and deep learning methodologies. Additionally, we propose and validate fixed train-validation-test splits. The obtained results confirm the viability of the proposed datasets, achieving the best overall result of 81.74\% F1-score for bimodal classification.
Authors: Soroosh Tayebi Arasteh, Mahshad Lotfinia, Keno Bressem, Robert Siepmann, Lisa Adams, Dyke Ferber, Christiane Kuhl, Jakob Nikolas Kather, Sven Nebelung, Daniel Truhn
Abstract: Large language models (LLMs) often generate outdated or inaccurate information based on static training datasets. Retrieval-augmented generation (RAG) mitigates this by integrating outside data sources. While previous RAG systems used pre-assembled, fixed databases with limited flexibility, we have developed Radiology RAG (RadioRAG), an end-to-end framework that retrieves data from authoritative radiologic online sources in real-time. We evaluate the diagnostic accuracy of various LLMs when answering radiology-specific questions with and without access to additional online information via RAG. Using 80 questions from the RSNA Case Collection across radiologic subspecialties and 24 additional expert-curated questions with reference standard answers, LLMs (GPT-3.5-turbo, GPT-4, Mistral-7B, Mixtral-8x7B, and Llama3 [8B and 70B]) were prompted with and without RadioRAG in a zero-shot inference scenario RadioRAG retrieved context-specific information from Radiopaedia in real-time. Accuracy was investigated. Statistical analyses were performed using bootstrapping. The results were further compared with human performance. RadioRAG improved diagnostic accuracy across most LLMs, with relative accuracy increases ranging up to 54% for different LLMs. It matched or exceeded non-RAG models and the human radiologist in question answering across radiologic subspecialties, particularly in breast imaging and emergency radiology. However, the degree of improvement varied among models; GPT-3.5-turbo and Mixtral-8x7B-instruct-v0.1 saw notable gains, while Mistral-7B-instruct-v0.2 showed no improvement, highlighting variability in RadioRAG's effectiveness. LLMs benefit when provided access to domain-specific data beyond their training data. RadioRAG shows potential to improve LLM accuracy and factuality in radiology question answering by integrating real-time domain-specific data.
Authors: Atsuyuki Miyai, Jingkang Yang, Jingyang Zhang, Yifei Ming, Yueqian Lin, Qing Yu, Go Irie, Shafiq Joty, Yixuan Li, Hai Li, Ziwei Liu, Toshihiko Yamasaki, Kiyoharu Aizawa
Abstract: Detecting out-of-distribution (OOD) samples is crucial for ensuring the safety of machine learning systems and has shaped the field of OOD detection. Meanwhile, several other problems are closely related to OOD detection, including anomaly detection (AD), novelty detection (ND), open set recognition (OSR), and outlier detection (OD). To unify these problems, a generalized OOD detection framework was proposed, taxonomically categorizing these five problems. However, Vision Language Models (VLMs) such as CLIP have significantly changed the paradigm and blurred the boundaries between these fields, again confusing researchers. In this survey, we first present a generalized OOD detection v2, encapsulating the evolution of these fields in the VLM era. Our framework reveals that, with some field inactivity and integration, the demanding challenges have become OOD detection and AD. Then, we highlight the significant shift in the definition, problem settings, and benchmarks; we thus feature a comprehensive review of the methodology for OOD detection and related tasks to clarify their relationship to OOD detection. Finally, we explore the advancements in the emerging Large Vision Language Model (LVLM) era, such as GPT-4V. We conclude with open challenges and future directions. The resource is available at https://github.com/AtsuMiyai/Awesome-OOD-VLM.
Authors: Xueying Gu, Qiong Wu, Pingyi Fan, Qiang Fan, Nan Cheng, Wen Chen, Khaled B. Letaief
Abstract: In the Internet of Vehicles (IoV), Federated Learning (FL) provides a privacy-preserving solution by aggregating local models without sharing data. Traditional supervised learning requires image data with labels, but data labeling involves significant manual effort. Federated Self-Supervised Learning (FSSL) utilizes Self-Supervised Learning (SSL) for local training in FL, eliminating the need for labels while protecting privacy. Compared to other SSL methods, Momentum Contrast (MoCo) reduces the demand for computing resources and storage space by creating a dictionary. However, using MoCo in FSSL requires uploading the local dictionary from vehicles to Base Station (BS), which poses a risk of privacy leakage. Simplified Contrast (SimCo) addresses the privacy leakage issue in MoCo-based FSSL by using dual temperature instead of a dictionary to control sample distribution. Additionally, considering the negative impact of motion blur on model aggregation, and based on SimCo, we propose a motion blur-resistant FSSL method, referred to as BFSSL. Furthermore, we address energy consumption and delay in the BFSSL process by proposing a Deep Reinforcement Learning (DRL)-based resource allocation scheme, called DRL-BFSSL. In this scheme, BS allocates the Central Processing Unit (CPU) frequency and transmission power of vehicles to minimize energy consumption and latency, while aggregating received models based on the motion blur level. Simulation results validate the effectiveness of our proposed aggregation and resource allocation methods.
Authors: Mohamed elShehaby, Ashraf Matrawy
Abstract: As network security threats evolve, safeguarding flow-based Machine Learning (ML)-based Network Intrusion Detection Systems (NIDS) from evasion adversarial attacks is crucial. This paper introduces the notion of feature perturb-ability and presents a novel Perturb-ability Score (PS), which quantifies how susceptible NIDS features are to manipulation in the problem-space by an attacker. PS thereby identifies features structurally resistant to evasion attacks in flow-based ML-NIDS due to the semantics of network traffic fields, as these features are constrained by domain-specific limitations and correlations. Consequently, attempts to manipulate such features would likely either compromise the attack's malicious functionality, render the traffic invalid for processing, or potentially both outcomes simultaneously. We introduce and demonstrate the effectiveness of our PS-enabled defenses, PS-guided feature selection and PS-guided feature masking, in enhancing flow-based NIDS resilience. Experimental results across various ML-based NIDS models and public datasets show that discarding or masking highly manipulatable features (high-PS features) can maintain solid detection performance while significantly reducing vulnerability to evasion adversarial attacks. Our findings confirm that PS effectively identifies flow-based NIDS features susceptible to problem-space perturbations. This novel approach leverages problem-space NIDS domain constraints as lightweight universal defense mechanisms against evasion adversarial attacks targeting flow-based ML-NIDS.
Authors: Cui Zhang, Wenjun Zhang, Qiong Wu, Pingyi Fan, Nan Cheng, Wen Chen, Khaled B. Letaief
Abstract: The Internet of Vehicles (IoV) network can address the issue of limited computing resources and data processing capabilities of individual vehicles, but it also brings the risk of privacy leakage to vehicle users. Applying blockchain technology can establish secure data links within the IoV, solving the problems of insufficient computing resources for each vehicle and the security of data transmission over the network. However, with the development of the IoV, the amount of data interaction between multiple vehicles and between vehicles and base stations, roadside units, etc., is continuously increasing. There is a need to further reduce the interaction volume, and intelligent data compression is key to solving this problem. The VIB technique facilitates the training of encoding and decoding models, substantially diminishing the volume of data that needs to be transmitted. This paper introduces an innovative approach that integrates blockchain with VIB, referred to as BVIB, designed to lighten computational workloads and reinforce the security of the network. We first construct a new network framework by separating the encoding and decoding networks to address the computational burden issue, and then propose a new algorithm to enhance the security of IoV networks. We also discuss the impact of the data extraction rate on system latency to determine the most suitable data extraction rate. An experimental framework combining Python and C++ has been established to substantiate the efficacy of our BVIB approach. Comprehensive simulation studies indicate that the BVIB consistently excels in comparison to alternative foundational methodologies.
Authors: Donghee Lee, Hye-Sung Lee, Jaeok Yi
Abstract: Deep neural network architectures often consist of repetitive structural elements. We introduce an approach that reveals these patterns and can be broadly applied to the study of deep learning. Similarly to how a power strip helps untangle and organize complex cable connections, this approach treats neurons as additional degrees of freedom in interactions, simplifying the structure and enhancing the intuitive understanding of interactions within deep neural networks. Furthermore, it reveals the translational symmetry of deep neural networks, which simplifies the application of the renormalization group transformation-a method that effectively analyzes the scaling behavior of the system. By utilizing translational symmetry and renormalization group transformations, we can analyze critical phenomena. This approach may open new avenues for studying deep neural networks using statistical physics.
Authors: Gareth Hardwick, Senwei Liang, Haizhao Yang
Abstract: In this paper, we introduce a new finite expression method (FEX) to solve high-dimensional partial integro-differential equations (PIDEs). This approach builds upon the original FEX and its inherent advantages with new advances: 1) A novel method of parameter grouping is proposed to reduce the number of coefficients in high-dimensional function approximation; 2) A Taylor series approximation method is implemented to significantly improve the computational efficiency and accuracy of the evaluation of the integral terms of PIDEs. The new FEX based method, denoted FEX-PG to indicate the addition of the parameter grouping (PG) step to the algorithm, provides both high accuracy and interpretable numerical solutions, with the outcome being an explicit equation that facilitates intuitive understanding of the underlying solution structures. These features are often absent in traditional methods, such as finite element methods (FEM) and finite difference methods, as well as in deep learning-based approaches. To benchmark our method against recent advances, we apply the new FEX-PG to solve benchmark PIDEs in the literature. In high-dimensional settings, FEX-PG exhibits strong and robust performance, achieving relative errors on the order of single precision machine epsilon.
Authors: Sihyun Yu, Sangkyung Kwak, Huiwon Jang, Jongheon Jeong, Jonathan Huang, Jinwoo Shin, Saining Xie
Abstract: Recent studies have shown that the denoising process in (generative) diffusion models can induce meaningful (discriminative) representations inside the model, though the quality of these representations still lags behind those learned through recent self-supervised learning methods. We argue that one main bottleneck in training large-scale diffusion models for generation lies in effectively learning these representations. Moreover, training can be made easier by incorporating high-quality external visual representations, rather than relying solely on the diffusion models to learn them independently. We study this by introducing a straightforward regularization called REPresentation Alignment (REPA), which aligns the projections of noisy input hidden states in denoising networks with clean image representations obtained from external, pretrained visual encoders. The results are striking: our simple strategy yields significant improvements in both training efficiency and generation quality when applied to popular diffusion and flow-based transformers, such as DiTs and SiTs. For instance, our method can speed up SiT training by over 17.5$\times$, matching the performance (without classifier-free guidance) of a SiT-XL model trained for 7M steps in less than 400K steps. In terms of final generation quality, our approach achieves state-of-the-art results of FID=1.42 using classifier-free guidance with the guidance interval.
Authors: Adrian Ciotinga, YooJung Choi
Abstract: We introduce a novel optimal transport framework for probabilistic circuits (PCs). While it has been shown recently that divergences between distributions represented as certain classes of PCs can be computed tractably, to the best of our knowledge, there is no existing approach to compute the Wasserstein distance between probability distributions given by PCs. We propose a Wasserstein-type distance that restricts the coupling measure of the associated optimal transport problem to be a probabilistic circuit. We then develop an algorithm for computing this distance by solving a series of small linear programs and derive the circuit conditions under which this is tractable. Furthermore, we show that we can easily retrieve the optimal transport plan between the PCs from the solutions to these linear programs. Lastly, we study the empirical Wasserstein distance between a PC and a dataset, and show that we can estimate the PC parameters to minimize this distance through an efficient iterative algorithm.
Authors: \.Ilker I\c{s}{\i}k, Ramazan Gokberk Cinbis, Ebru Aydin Gol
Abstract: Language models lack the notion of interchangeable tokens: symbols that are semantically equivalent yet distinct, such as bound variables in formal logic. This limitation prevents generalization to larger vocabularies and hinders the model's ability to recognize alpha-equivalence, where renaming bound variables preserves meaning. We formalize this machine learning problem and introduce alpha-covariance, a metric for evaluating robustness to such transformations. To tackle this task, we propose a dual-part token embedding strategy: a shared component ensures semantic consistency, while a randomized component maintains token distinguishability. Compared to a baseline that relies on alpha-renaming for data augmentation, our approach demonstrates improved generalization to unseen tokens in linear temporal logic solving, propositional logic assignment prediction, and copying with an extendable vocabulary, while introducing a favorable inductive bias for alpha-equivalence. Our findings establish a foundation for designing language models that can learn interchangeable token representations, a crucial step toward more flexible and systematic reasoning in formal domains. Our code and project page are available at https://necrashter.github.io/interchangeable-token-embeddings
URLs: https://necrashter.github.io/interchangeable-token-embeddings
Authors: Jan Pfister, Julia Wunderle, Andreas Hotho
Abstract: We create two German-only decoder models, LL\"aMmlein 120M and 1B, transparently from scratch and publish them, along with the training data, for the German NLP research community to use. The model training involved several key steps, including extensive data preprocessing, the creation of a custom German tokenizer, the training itself, as well as the evaluation of the final models on various benchmarks. Throughout the training process, multiple checkpoints were saved and analyzed using the SuperGLEBer benchmark to monitor the models' learning dynamics. Compared to state-of-the-art models on the SuperGLEBer benchmark, both LL\"aMmlein models performed competitively, consistently matching or surpassing models with similar parameter sizes. The results show that the models' quality scales with size as expected, but performance improvements on some tasks plateaued early, offering valuable insights into resource allocation for future model development.
Authors: Linshan Hou, Wei Luo, Zhongyun Hua, Songhua Chen, Leo Yu Zhang, Yiming Li
Abstract: Deep neural networks (DNNs) are susceptible to backdoor attacks, where adversaries poison datasets with adversary-specified triggers to implant hidden backdoors, enabling malicious manipulation of model predictions. Dataset purification serves as a proactive defense by removing malicious training samples to prevent backdoor injection at its source. We first reveal that the current advanced purification methods rely on a latent assumption that the backdoor connections between triggers and target labels in backdoor attacks are simpler to learn than the benign features. We demonstrate that this assumption, however, does not always hold, especially in all-to-all (A2A) and untargeted (UT) attacks. As a result, purification methods that analyze the separation between the poisoned and benign samples in the input-output space or the final hidden layer space are less effective. We observe that this separability is not confined to a single layer but varies across different hidden layers. Motivated by this understanding, we propose FLARE, a universal purification method to counter various backdoor attacks. FLARE aggregates abnormal activations from all hidden layers to construct representations for clustering. To enhance separation, FLARE develops an adaptive subspace selection algorithm to isolate the optimal space for dividing an entire dataset into two clusters. FLARE assesses the stability of each cluster and identifies the cluster with higher stability as poisoned. Extensive evaluations on benchmark datasets demonstrate the effectiveness of FLARE against 22 representative backdoor attacks, including all-to-one (A2O), all-to-all (A2A), and untargeted (UT) attacks, and its robustness to adaptive attacks. Codes are available at \href{https://github.com/THUYimingLi/BackdoorBox}{BackdoorBox} and \href{https://github.com/vtu81/backdoor-toolbox}{backdoor-toolbox}.
URLs: https://github.com/THUYimingLi/BackdoorBox, https://github.com/vtu81/backdoor-toolbox
Authors: Peiyan Zhang, Haibo Jin, Leyang Hu, Xinnuo Li, Liying Kang, Man Luo, Yangqiu Song, Haohan Wang
Abstract: Recent advancements in large language models (LLMs) have significantly enhanced the ability of LLM-based systems to perform complex tasks through natural language processing and tool interaction. However, optimizing these LLM-based systems for specific tasks remains challenging, often requiring manual interventions like prompt engineering and hyperparameter tuning. Existing automatic optimization methods, such as textual feedback-based techniques (e.g., TextGrad), tend to focus on immediate feedback, analogous to using immediate derivatives in traditional numerical gradient descent. However, relying solely on such feedback can be limited when the adjustments made in response to this feedback are either too small or fluctuate irregularly, potentially slowing down or even stalling the optimization process. To overcome these challenges, more adaptive methods are needed, especially in situations where the system's response is evolving slowly or unpredictably. In this paper, we introduce REVOLVE, an optimization method that tracks how "R"esponses "EVOLVE" across iterations in LLM systems. By focusing on the evolution of responses over time, REVOLVE enables more stable and effective optimization by making thoughtful, progressive adjustments at each step. Experimental results demonstrate that REVOLVE outperforms competitive baselines, achieving a 7.8% improvement in prompt optimization, a 20.72% gain in solution refinement, and a 29.17% increase in code optimization. Additionally, REVOLVE converges in fewer iterations, resulting in significant computational savings. Beyond its practical contributions, REVOLVE highlights a promising direction, where the rich knowledge from established optimization principles can be leveraged to enhance LLM systems, which paves the way for further advancements in this hybrid domain.
Authors: Jinchao Li, Yuejiao Wang, Junan Li, Jiawen Kang, Bo Zheng, Simon Wong, Brian Mak, Helene Fung, Jean Woo, Man-Wai Mak, Timothy Kwok, Vincent Mok, Xianmin Gong, Xixin Wu, Xunying Liu, Patrick Wong, Helen Meng
Abstract: Early detection of neurocognitive disorders (NCDs) is crucial for timely intervention and disease management. Given that language impairments manifest early in NCD progression, visual-stimulated narrative (VSN)-based analysis offers a promising avenue for NCD detection. Current VSN-based NCD detection methods primarily focus on linguistic microstructures (e.g., pauses, lexical diversity), which are potentially linked to bottom-up (stimulus-driven) cognitive processing. While these features illuminate basic language abilities, the higher-order linguistic macrostructures (e.g., thematic or logical development), which may reflect top-down (concept-driven) cognitive abilities, remain underexplored. These patterns are crucial for NCD detection yet challenging to quantify due to their abstract and complex nature. To bridge this gap, we propose two novel dynamic macrostructural approaches: (1) Dynamic Topic Model (DTM) to track topic evolution over time, and (2) Text-Image Temporal Alignment Network (TITAN) to measure cross-modal consistency between speech and visual stimuli. Experimental results validated the efficiency of proposed approaches in NCD detection, with TITAN achieving superior performance both on the CU-MARVEL-RABBIT corpus (F1 = 0.7238) and the ADReSS corpus (F1 = 0.8889). The feature contribution analysis revealed that macrostructural features (e.g., topic variability, topic change rate, and topic consistency) constituted the most significant contributors in the model's decision pathways, outperforming investigated microstructural features. These findings underscore the critical role of macrostructural patterns in understanding cognitive impairment mechanisms in NCDs.
Authors: Hayder Tirmazi
Abstract: A Bloom filter is a space-efficient probabilistic data structure that represents a set $S$ of elements from a larger universe $U$. This efficiency comes with a trade-off, namely, it allows for a small chance of false positives. When you query the Bloom filter about an element x, the filter will respond 'Yes' if $x \in S$. If $x \notin S$, it may still respond 'Yes' with probability at most $\varepsilon$. We investigate the adversarial robustness and privacy of Bloom filters, addressing open problems across three prominent frameworks: the game-based model of Naor-Oved-Yogev (NOY), the simulator-based model of Filic et. al., and learning-augmented variants. We prove the first formal connection between the Filic and NOY models, showing that Filic correctness implies AB-test resilience. We resolve a longstanding open question by proving that PRF-backed Bloom filters fail the NOY model's stronger BP-test. Finally, we introduce the first private Bloom filters with differential privacy guarantees, including constructions applicable to learned Bloom filters. Our taxonomy organizes the space of robustness and privacy guarantees, clarifying relationships between models and constructions.
Authors: Kiana Asgari, Andrea Montanari, Basil Saeed
Abstract: We consider a general model for high-dimensional empirical risk minimization whereby the data $\mathbf{x}_i$ are $d$-dimensional isotropic Gaussian vectors, the model is parametrized by $\mathbf{\Theta}\in\mathbb{R}^{d\times k}$, and the loss depends on the data via the projection $\mathbf{\Theta}^\mathsf{T}\mathbf{x}_i$. This setting covers as special cases classical statistics methods (e.g. multinomial regression and other generalized linear models), but also two-layer fully connected neural networks with $k$ hidden neurons. We use the Kac-Rice formula from Gaussian process theory to derive a bound on the expected number of local minima of this empirical risk, under the proportional asymptotics in which $n,d\to\infty$, with $n\asymp d$. Via Markov's inequality, this bound allows to determine the positions of these minimizers (with exponential deviation bounds) and hence derive sharp asymptotics on the estimation and prediction error. In this paper, we apply our characterization to convex losses, where high-dimensional asymptotics were not (in general) rigorously established for $k\ge 2$. We show that our approach is tight and allows to prove previously conjectured results. In addition, we characterize the spectrum of the Hessian at the minimizer. A companion paper applies our general result to non-convex examples.
Authors: Zhou Lu, Y. Jennifer Sun, Zhiyu Zhang
Abstract: Focusing on the expert problem in online learning, this paper studies the interpolation of several performance metrics via $\phi$-regret minimization, which measures the total loss of an algorithm by its regret with respect to an arbitrary action modification rule $\phi$. With $d$ experts and $T\gg d$ rounds in total, we present a single algorithm achieving the instance-adaptive $\phi$-regret bound \begin{equation*} \tilde O\left(\min\left\{\sqrt{d-d^{\mathrm{unif}}_\phi+1},\sqrt{d-d^{\mathrm{self}}_\phi}\right\}\cdot\sqrt{T}\right), \end{equation*} where $d^{\mathrm{unif}}_\phi$ is the maximum amount of experts modified identically by $\phi$, and $d^{\mathrm{self}}_\phi$ is the amount of experts that $\phi$ trivially modifies to themselves. By recovering the optimal $O(\sqrt{T\log d})$ external regret bound when $d^{\mathrm{unif}}_\phi=d$, the standard $\tilde O(\sqrt{T})$ internal regret bound when $d^{\mathrm{self}}_\phi=d-1$ and the optimal $\tilde O(\sqrt{dT})$ swap regret bound in the worst case, we improve upon existing algorithms in the intermediate regimes. In addition, the computational complexity of our algorithm matches that of the standard swap-regret minimization algorithm due to (Blum and Mansour, 2007). Technically, building on the well-known reduction from $\phi$-regret minimization to external regret minimization on stochastic matrices, our main idea is to further convert the latter to online linear regression using Haar-wavelet-inspired matrix features. Then, by associating the complexity of each $\phi$ instance with its sparsity under the feature representation, we apply techniques from comparator-adaptive online learning to exploit the sparsity in this regression subroutine.
Authors: Daan Otto, Jannis Kurtz, S. Ilker Birbil
Abstract: The surge of explainable artificial intelligence methods seeks to enhance transparency and explainability in machine learning models. At the same time, there is a growing demand for explaining decisions taken through complex algorithms used in mathematical optimization. However, current explanation methods do not take into account the structure of the underlying optimization problem, leading to unreliable outcomes. In response to this need, we introduce Coherent Local Explanations for Mathematical Optimization (CLEMO). CLEMO provides explanations for multiple components of optimization models, the objective value and decision variables, which are coherent with the underlying model structure. Our sampling-based procedure can provide explanations for the behavior of exact and heuristic solution algorithms. The effectiveness of CLEMO is illustrated by experiments for the shortest path problem, the knapsack problem, and the vehicle routing problem.
Authors: Robyn Larracy, Angkoon Phinyomark, Ala Salehi, Eve MacDonald, Saeed Kazemi, Shikder Shafiul Bashar, Aaron Tabor, Erik Scheme
Abstract: Gait refers to the patterns of limb movement generated during walking, which are unique to each individual due to both physical and behavioral traits. Walking patterns have been widely studied in biometrics, biomechanics, sports, and rehabilitation. While traditional methods rely on video and motion capture, advances in plantar pressure sensing technology now offer deeper insights into gait. However, underfoot pressures during walking remain underexplored due to the lack of large, publicly accessible datasets. To address this, we introduce the UNB StepUP-P150 dataset: a footStep database for gait analysis and recognition using Underfoot Pressure, including data from 150 individuals. This dataset comprises high-resolution plantar pressure data (4 sensors per cm-squared) collected using a 1.2m by 3.6m pressure-sensing walkway. It contains over 200,000 footsteps from participants walking with various speeds (preferred, slow-to-stop, fast, and slow) and footwear conditions (barefoot, standard shoes, and two personal shoes), supporting advancements in biometric gait recognition and presenting new research opportunities in biomechanics and deep learning. UNB StepUP-P150 establishes a new benchmark for plantar pressure-based gait analysis and recognition.
Authors: Joao Marcos Correia Marques, Nils Dengler, Tobias Zaenker, Jesper Mucke, Shenlong Wang, Maren Bennewitz, Kris Hauser
Abstract: Searching for objects in cluttered environments requires selecting efficient viewpoints and manipulation actions to remove occlusions and reduce uncertainty in object locations, shapes, and categories. In this work, we address the problem of manipulation-enhanced semantic mapping, where a robot has to efficiently identify all objects in a cluttered shelf. Although Partially Observable Markov Decision Processes~(POMDPs) are standard for decision-making under uncertainty, representing unstructured interactive worlds remains challenging in this formalism. To tackle this, we define a POMDP whose belief is summarized by a metric-semantic grid map and propose a novel framework that uses neural networks to perform map-space belief updates to reason efficiently and simultaneously about object geometries, locations, categories, occlusions, and manipulation physics. Further, to enable accurate information gain analysis, the learned belief updates should maintain calibrated estimates of uncertainty. Therefore, we propose Calibrated Neural-Accelerated Belief Updates (CNABUs) to learn a belief propagation model that generalizes to novel scenarios and provides confidence-calibrated predictions for unknown areas. Our experiments show that our novel POMDP planner improves map completeness and accuracy over existing methods in challenging simulations and successfully transfers to real-world cluttered shelves in zero-shot fashion.
Authors: Sha Ye, Qiong Wu, Pingyi Fan, Qiang Fan
Abstract: Internet of Vehicles (IoV), as the core of intelligent transportation system, enables comprehensive interconnection between vehicles and their surroundings through multiple communication modes, which is significant for autonomous driving and intelligent traffic management. However, with the emergence of new applications, traditional communication technologies face the problems of scarce spectrum resources and high latency. Semantic communication, which focuses on extracting, transmitting, and recovering some useful semantic information from messages, can reduce redundant data transmission, improve spectrum utilization, and provide innovative solutions to communication challenges in the IoV. This paper systematically reviews state of art of semantic communications in the IoV, elaborates the technical background of IoV and semantic communications, and deeply discusses key technologies of semantic communications in IoV, including semantic information extraction, semantic communication architecture, resource allocation and management, and so on. Through specific case studies, it demonstrates that semantic communications can be effectively employed in the scenarios of traffic environment perception and understanding, intelligent driving decision support, IoV service optimization, and intelligent traffic management. Additionally, it analyzes the current challenges and future research directions. This survey reveals that semantic communications has broad application prospects in IoV, but it is necessary to solve the real existing problems by combining advanced technologies to promote its wide application in IoV and contributing to the development of intelligent transportation system.
Authors: Alexei V. Tkachenko
Abstract: While Landauer's principle sets a fundamental energy limit for irreversible digital computation, we show that Deep Neural Networks (DNNs) implemented on analog physical substrates can operate under markedly different thermodynamic constraints. We distinguish between two classes of analog systems: dynamic and quasi-static. In dynamic systems, energy dissipation arises from neuron resets, with a lower bound governed by Landauer's principle. To analyse a quasi-static analog platform, we construct an explicit mapping of a generic feedforward DNN onto a physical system described by a model Hamiltonian. In this framework, inference can proceed reversibly, with no minimum free energy cost imposed by thermodynamics. We further analyze the training process in quasi-static analog networks and derive a fundamental lower bound on its energy cost, rooted in the interplay between thermal and statistical noise. Our results suggest that while analog implementations can outperform digital ones during inference, the thermodynamic cost of training scales similarly in both paradigms.
Authors: Bhiman Kumar Baghel, Scott M. Jordan, Zheyuan Ryan Shi, Xiang Lorraine Li
Abstract: Large Language Models (LLMs) are widely deployed in downstream tasks, but keeping their knowledge up-to-date via retraining or fine-tuning is often computationally expensive. Model editing provides a more efficient alternative by updating a targeted subset of parameters, which often follows the locate-and-edit paradigm. Despite this efficiency, existing methods are limited: edits may fail to inject knowledge (UnderEdit) or unintentionally disrupt unrelated neighboring knowledge (OverEdit). To address these challenges, we propose two complementary methods: iterative model editing, which applies successive edits to mitigate UnderEdit, and neighbor-assisted model editing, which incorporates neighboring knowledge during editing to reduce OverEdit. Our extensive experiments show that these techniques improve editing performance across multiple LLMs, algorithms, and benchmarks, reducing UnderEdit by up to 38 percentage points and OverEdit by up to 6, while remaining broadly applicable to any locate-and-edit method.
Authors: Zeng Wang, Minghao Shao, Mohammed Nabeel, Prithwish Basu Roy, Likhitha Mankali, Jitendra Bhandari, Ramesh Karri, Ozgur Sinanoglu, Muhammad Shafique, Johann Knechtel
Abstract: Large language models (LLMs) offer significant potential for coding, yet fine-tuning (FT) with curated data is essential for niche languages like Verilog. Using proprietary intellectual property (IP) for FT presents a serious risk, as FT data can be leaked through LLM inference. This leads to a critical dilemma for design houses: seeking to build externally accessible LLMs offering competitive Verilog coding, how can they leverage in-house IP to enhance FT utility while ensuring IP protection? For the first time in the literature, we study this dilemma. Using LLaMA 3.1-8B, we conduct in-house FT on a baseline Verilog dataset (RTLCoder) supplemented with our own in-house IP, which is validated through multiple tape-outs. To rigorously assess IP leakage, we quantify structural similarity (AST/Dolos) and functional equivalence (Synopsys Formality) between generated codes and our in-house IP. We show that our IP can indeed be leaked, confirming the threat. As defense, we evaluate logic locking of Verilog codes (ASSURE). This offers some level of protection, yet reduces the IP's utility for FT and degrades the LLM's performance. Our study shows the need for novel strategies that are both effective and minimally disruptive to FT, an essential effort for enabling design houses to fully utilize their proprietary IP toward LLM-driven Verilog coding.
Authors: Alba M\'arquez-Rodr\'iguez, Miguel \'Angel Mohedano-Munoz, Manuel J. Mar\'in-Jim\'enez, Eduardo Santamar\'ia-Garc\'ia, Giulia Bastianelli, Pedro Jordano, Irene Mendoza
Abstract: Passive Acoustic Monitoring is a key tool for biodiversity conservation, but the large volumes of unsupervised audio it generates present major challenges for extracting meaningful information. Deep Learning offers promising solutions. BirdNET, a widely used bird identification model, has shown success in many study systems but is limited at local scale due to biases in its training data, which focus on specific locations and target sounds rather than entire soundscapes. A key challenge in bird species identification is that many recordings either lack target species or contain overlapping vocalizations, complicating automatic identification. To address these problems, we developed a multi-stage pipeline for automatic bird vocalization identification in Do\~nana National Park (SW Spain), a wetland of high conservation concern. We deployed AudioMoth recorders in three main habitats across nine locations and manually annotated 461 minutes of audio, resulting in 3749 labeled segments spanning 34 classes. We first applied a Bird Song Detector to isolate bird vocalizations using spectrogram-based image processing. Then, species were classified using custom models trained at the local scale. Applying the Bird Song Detector before classification improved species identification, as all models performed better when analyzing only the segments where birds were detected. Specifically, the combination of detector and fine-tuned BirdNET outperformed the baseline without detection. This approach demonstrates the effectiveness of integrating a Bird Song Detector with local classification models. These findings highlight the need to adapt general-purpose tools to specific ecological challenges. Automatically detecting bird species helps track the health of this threatened ecosystem, given birds sensitivity to environmental change, and supports conservation planning to reduce biodiversity loss.
Authors: Panos Tsimpos, Zhi Ren, Jakob Zech, Youssef Marzouk
Abstract: Flow-based methods for sampling and generative modeling use continuous-time dynamical systems to represent a {transport map} that pushes forward a source measure to a target measure. The introduction of a time axis provides considerable design freedom, and a central question is how to exploit this freedom. Though many popular methods seek straight line (i.e., zero acceleration) trajectories, we show here that a specific class of ``curved'' trajectories can significantly improve approximation and learning. In particular, we consider the unit-time interpolation of any given transport map $T$ and seek the schedule $\tau: [0,1] \to [0,1]$ that minimizes the spatial Lipschitz constant of the corresponding velocity field over all times $t \in [0,1]$. This quantity is crucial as it allows for control of the approximation error when the velocity field is learned from data. We show that, for a broad class of source/target measures and transport maps $T$, the \emph{optimal schedule} can be computed in closed form, and that the resulting optimal Lipschitz constant is \emph{exponentially smaller} than that induced by an identity schedule (corresponding to, for instance, the Wasserstein geodesic). Our proof technique relies on the calculus of variations and $\Gamma$-convergence, allowing us to approximate the aforementioned degenerate objective by a family of smooth, tractable problems.
Authors: Zongxia Li, Xiyang Wu, Guangyao Shi, Yubin Qin, Hongyang Du, Tianyi Zhou, Dinesh Manocha, Jordan Lee Boyd-Graber
Abstract: Synthetic video generation has gained significant attention for its realism and broad applications, but remains prone to violations of common sense and physical laws. This highlights the need for reliable abnormality detectors that understand such principles and are robust to hallucinations. To address this, we introduce VideoHallu, a benchmark of over 3,000 video QA pairs built from synthetic videos generated by models like Veo2, Sora, and Kling, paired with expert-crafted counterintuitive QA to evaluate the critical thinking abilities of Multi-modal Large Language Models (MLLMs) on abnormalities that are perceptually obvious to humans but often hallucinated due to language priors. VideoHallu evaluates MLLMs' abnormality detection abilities with examples across alignment, consistency, commonsense, and physics. We benchmark SOTA MLLMs, including GPT-4o, Gemini-2.5-Pro, Qwen2.5-VL, Video-R1, and VideoChat-R1. We observe that these models perform well on many real-world benchmarks like MVBench and MovieChat, but still struggle with basic physics-based and commonsense reasoning in synthetic videos. We further show that post-training with Group Relative Policy Optimization (GRPO), using curriculum learning on datasets combining video QA with counterintuitive commonsense and physics reasoning over real and synthetic videos, improves MLLMs' abnormality detection and critical thinking, demonstrating the value of targeted training for improving their understanding of commonsense and physical laws. Our code is available at https://github.com/zli12321/VideoHallu.git.
Authors: Zihan Shao, Konstantin Pieper, Xiaochuan Tian
Abstract: We propose a novel framework for solving nonlinear PDEs using sparse radial basis function (RBF) networks. Sparsity-promoting regularization is employed to prevent over-parameterization and reduce redundant features. This work is motivated by longstanding challenges in traditional RBF collocation methods, along with the limitations of physics-informed neural networks (PINNs) and Gaussian process (GP) approaches, aiming to blend their respective strengths in a unified framework. The theoretical foundation of our approach lies in the function space of Reproducing Kernel Banach Spaces (RKBS) induced by one-hidden-layer neural networks of possibly infinite width. We prove a representer theorem showing that the sparse optimization problem in the RKBS admits a finite solution and establishes error bounds that offer a foundation for generalizing classical numerical analysis. The algorithmic framework is based on a three-phase algorithm to maintain computational efficiency through adaptive feature selection, second-order optimization, and pruning of inactive neurons. Numerical experiments demonstrate the effectiveness of our method and highlight cases where it offers notable advantages over GP approaches. This work opens new directions for adaptive PDE solvers grounded in rigorous analysis with efficient, learning-inspired implementation.
Authors: Joel Jang, Seonghyeon Ye, Zongyu Lin, Jiannan Xiang, Johan Bjorck, Yu Fang, Fengyuan Hu, Spencer Huang, Kaushil Kundalia, Yen-Chen Lin, Loic Magne, Ajay Mandlekar, Avnish Narayan, You Liang Tan, Guanzhi Wang, Jing Wang, Qi Wang, Yinzhen Xu, Xiaohui Zeng, Kaiyuan Zheng, Ruijie Zheng, Ming-Yu Liu, Luke Zettlemoyer, Dieter Fox, Jan Kautz, Scott Reed, Yuke Zhu, Linxi Fan
Abstract: We introduce DreamGen, a simple yet highly effective 4-stage pipeline for training robot policies that generalize across behaviors and environments through neural trajectories - synthetic robot data generated from video world models. DreamGen leverages state-of-the-art image-to-video generative models, adapting them to the target robot embodiment to produce photorealistic synthetic videos of familiar or novel tasks in diverse environments. Since these models generate only videos, we recover pseudo-action sequences using either a latent action model or an inverse-dynamics model (IDM). Despite its simplicity, DreamGen unlocks strong behavior and environment generalization: a humanoid robot can perform 22 new behaviors in both seen and unseen environments, while requiring teleoperation data from only a single pick-and-place task in one environment. To evaluate the pipeline systematically, we introduce DreamGen Bench, a video generation benchmark that shows a strong correlation between benchmark performance and downstream policy success. Our work establishes a promising new axis for scaling robot learning well beyond manual data collection. Code available at https://github.com/NVIDIA/GR00T-Dreams.
Authors: Zhuoran Duan, Guoshun Nan, Rushan Li, Zijun Wang, Lihua Xiong, Chaoying Yuan, Guorong Liu, Hui Xu, Qimei Cui, Xiaofeng Tao, Tony Q. S. Quek
Abstract: The upcoming 6G will fundamentally reshape mobile networks beyond communications, unlocking a multitude of applications that were once considered unimaginable. Meanwhile, security and resilience are especially highlighted in the 6G design principles. However, safeguarding 6G networks will be quite challenging due to various known and unknown threats from highly heterogeneous networks and diversified security requirements of distinct use cases, calling for a comprehensive re-design of security architecture. This motivates us to propose ES3A (Entire Smart Service-based Security Architecture), a novel security architecture for 6G networks. Specifically, we first discuss six high-level principles of our ES3A that include hierarchy, flexibility, scalability, resilience, endogeny, and trust and privacy. With these goals in mind, we then introduce three guidelines from a deployment perspective, envisioning our ES3A that offers service-based security, end-to-end protection, and smart security automation for 6G networks. Our architecture consists of three layers and three domains. It relies on a two-stage orchestration mechanism to tailor smart security strategies for customized protection in high-dynamic 6G networks, thereby addressing the aforementioned challenges. Finally, we prototype the proposed ES3A on a real-world radio system based on Software-Defined Radio (SDR). Experiments show the effectiveness of our ES3A. We also provide a case to show the superiority of our architecture.
Authors: Junghyun Lee, Yassir Jedra, Alexandre Prouti\`ere, Se-Young Yun
Abstract: We study the problem of clustering $T$ trajectories of length $H$, each generated by one of $K$ unknown ergodic Markov chains over a finite state space of size $S$. The goal is to accurately group trajectories according to their underlying generative model. We begin by deriving an instance-dependent, high-probability lower bound on the clustering error rate, governed by the weighted KL divergence between the transition kernels of the chains. We then present a novel two-stage clustering algorithm. In Stage~I, we apply spectral clustering using a new injective Euclidean embedding for ergodic Markov chains -- a contribution of independent interest that enables sharp concentration results. Stage~II refines the initial clusters via a single step of likelihood-based reassignment. Our method achieves a near-optimal clustering error with high probability, under the conditions $H = \tilde{\Omega}(\gamma_{\mathrm{ps}}^{-1} (S^2 \vee \pi_{\min}^{-1}))$ and $TH = \tilde{\Omega}(\gamma_{\mathrm{ps}}^{-1} S^2 )$, where $\pi_{\min}$ is the minimum stationary probability of a state across the $K$ chains and $\gamma_{\mathrm{ps}}$ is the minimum pseudo-spectral gap. These requirements provide significant improvements, if not at least comparable, to the state-of-the-art guarantee (Kausik et al., 2023), and moreover, our algorithm offers a key practical advantage: unlike existing approach, it requires no prior knowledge of model-specific quantities (e.g., separation between kernels or visitation probabilities). We conclude by discussing the inherent gap between our upper and lower bounds, providing insights into the unique structure of this clustering problem.
Authors: Mahmud Ashraf Shamim, Eric A F Reinhardt, Talal Ahmed Chowdhury, Sergei Gleyzer, Paulo T Araujo
Abstract: Neural Quantum States (NQS) are a class of variational wave functions parametrized by neural networks (NNs) to study quantum many-body systems. In this work, we propose \texttt{SineKAN}, a NQS \textit{ansatz} based on Kolmogorov-Arnold Networks (KANs), to represent quantum mechanical wave functions as nested univariate functions. We show that \texttt{SineKAN} wavefunction with learnable sinusoidal activation functions can capture the ground state energies, fidelities and various correlation functions of the one dimensional Transverse-Field Ising model, Anisotropic Heisenberg model, and Antiferromagnetic $J_{1}-J_{2}$ model with different chain lengths. In our study of the $J_1-J_2$ model with $L=100$ sites, we find that the \texttt{SineKAN} model outperforms several previously explored neural quantum state \textit{ans\"atze}, including Restricted Boltzmann Machines (RBMs), Long Short-Term Memory models (LSTMs), and Feed-Forward Neural Networks (FFNN), when compared to the results obtained from the Density Matrix Renormalization Group (DMRG) algorithm. We find that \texttt{SineKAN} models can be trained to high precisions and accuracies with minimal computational costs.
Authors: Junghyun Lee, Kyoungseok Jang, Kwang-Sung Jun, Milan Vojnovi\'c, Se-Young Yun
Abstract: We present `GL-LowPopArt`, a novel Catoni-style estimator for generalized low-rank trace regression. Building on `LowPopArt` (Jang et al., 2024), it employs a two-stage approach: nuclear norm regularization followed by matrix Catoni estimation. We establish state-of-the-art estimation error bounds, surpassing existing guarantees (Fan et al., 2019; Kang et al., 2022), and reveal a novel experimental design objective, $\mathrm{GL}(\pi)$. The key technical challenge is controlling bias from the nonlinear inverse link function, which we address by our two-stage approach. We prove a *local* minimax lower bound, showing that our `GL-LowPopArt` enjoys instance-wise optimality up to the condition number of the ground-truth Hessian. Applications include generalized linear matrix completion, where `GL-LowPopArt` achieves a state-of-the-art Frobenius error guarantee, and **bilinear dueling bandits**, a novel setting inspired by general preference learning (Zhang et al., 2024). Our analysis of a `GL-LowPopArt`-based explore-then-commit algorithm reveals a new, potentially interesting problem-dependent quantity, along with improved Borda regret bound than vectorization (Wu et al., 2024).
Authors: Dania Herzalla, Willian T. Lunardi, Martin Andreoni
Abstract: Graph-based learning provides a powerful framework for modeling complex relational structures; however, its application within the domain of wireless security remains significantly underexplored. In this work, we introduce the first application of graph-based learning for jamming source localization, addressing the imminent threat of jamming attacks in wireless networks. Unlike geometric optimization techniques that struggle under environmental uncertainties and dense interference, we reformulate the localization as an inductive graph regression task. Our approach integrates structured node representations that encode local and global signal aggregation, ensuring spatial coherence and adaptive signal fusion. To enhance robustness, we incorporate an attention-based \ac{GNN} that adaptively refines neighborhood influence and introduces a confidence-guided estimation mechanism that dynamically balances learned predictions with domain-informed priors. We evaluate our approach under complex \ac{RF} environments with various sampling densities, network topologies, jammer characteristics, and signal propagation conditions, conducting comprehensive ablation studies on graph construction, feature selection, and pooling strategies. Results demonstrate that our novel graph-based learning framework significantly outperforms established localization baselines, particularly in challenging scenarios with sparse and obfuscated signal information. Our code is available at https://github.com/tiiuae/gnn-jamming-source-localization.
URLs: https://github.com/tiiuae/gnn-jamming-source-localization.
Authors: Mengda Ji, Genjiu Xu, Liying Wang
Abstract: This work focuses on the credit assignment problem in cooperative multi-agent reinforcement learning (MARL). Sharing the global advantage among agents often leads to suboptimal policy updates as it fails to account for the distinct contributions of agents. Although numerous methods consider global or individual contributions for credit assignment, a detailed analysis at the coalition level remains lacking in many approaches. This work analyzes the over-updating problem during multi-agent policy updates from a coalition-level perspective. To address this issue, we propose a credit assignment method called Coalitional Rational Advantage Decomposition (CORA). CORA evaluates coalitional advantages via marginal contributions from all possible coalitions and decomposes advantages using the core solution from cooperative game theory, ensuring coalitional rationality. To reduce computational overhead, CORA employs random coalition sampling. Experiments on matrix games, differential games, and multi-agent collaboration benchmarks demonstrate that CORA outperforms strong baselines, particularly in tasks with multiple local optima. These findings highlight the importance of coalition-aware credit assignment for improving MARL performance.
Authors: Haozhen Zhang, Tao Feng, Jiaxuan You
Abstract: The rapid emergence of diverse large language models (LLMs) has spurred the development of LLM routers that assign user queries to the most suitable model. However, existing LLM routers typically perform a single-round, one-to-one mapping (\textit{i.e.}, assigning each query to a single model in isolation), which limits their capability to tackle complex tasks that demand the complementary strengths of multiple LLMs. In this paper, we present \textbf{Router-R1}, a reinforcement learning (RL)-based framework that formulates multi-LLM routing and aggregation as a sequential decision process. Router-R1 instantiates the router itself as a capable LLM, leveraging its reasoning ability to interleave "think" actions (internal deliberation) with "route" actions (dynamic model invocation), and integrates each response into its evolving context. To facilitate learning, we employ a lightweight rule-based reward comprising format rewards, final outcome rewards, and a novel cost reward for optimizing the balance between performance and cost, opening a pathway toward enhancing performance-cost trade-offs via RL. Router-R1 also conditions only on simple model descriptors such as pricing, latency, and example performance, enabling strong generalization to unseen model selection. Experiments on seven general and multi-hop QA benchmarks show that Router-R1 outperforms several strong baselines, achieving superior performance while maintaining robust generalization and cost management.
Authors: Mo\"ise Blanchard, Samory Kpotufe
Abstract: There has been much recent interest in understanding the continuum from adversarial to stochastic settings in online learning, with various frameworks including smoothed settings proposed to bridge this gap. We consider the more general and flexible framework of distributionally constrained adversaries in which instances are drawn from distributions chosen by an adversary within some constrained distribution class [RST11]. Compared to smoothed analysis, we consider general distributional classes which allows for a fine-grained understanding of learning settings between fully stochastic and fully adversarial for which a learner can achieve non-trivial regret. We give a characterization for which distribution classes are learnable in this context against both oblivious and adaptive adversaries, providing insights into the types of interplay between the function class and distributional constraints on adversaries that enable learnability. In particular, our results recover and generalize learnability for known smoothed settings. Further, we show that for several natural function classes including linear classifiers, learning can be achieved without any prior knowledge of the distribution class -- in other words, a learner can simultaneously compete against any constrained adversary within learnable distribution classes.
Authors: Surya Jasper, Minh Luu, Evan Pan, Aakash Tyagi, Michael Quinn, Jiang Hu, David Kebo Houngninou
Abstract: Hardware complexity continues to strain verification resources, motivating the adoption of machine learning (ML) methods to improve debug efficiency. However, ML-assisted debugging critically depends on diverse and scalable bug datasets, which existing manual or automated bug insertion methods fail to reliably produce. We introduce BugGen, a first of its kind, fully autonomous, multi-agent pipeline leveraging Large Language Models (LLMs) to systematically generate, insert, and validate realistic functional bugs in RTL. BugGen partitions modules, selects mutation targets via a closed-loop agentic architecture, and employs iterative refinement and rollback mechanisms to ensure syntactic correctness and functional detectability. Evaluated across five OpenTitan IP blocks, BugGen produced 500 unique bugs with 94% functional accuracy and achieved a throughput of 17.7 validated bugs per hour-over five times faster than typical manual expert insertion. Additionally, BugGen identified 104 previously undetected bugs in OpenTitan regressions, highlighting its utility in exposing verification coverage gaps. Compared against Certitude, BugGen demonstrated over twice the syntactic accuracy, deeper exposure of testbench blind spots, and more functionally meaningful and complex bug scenarios. Furthermore, when these BugGen-generated datasets were employed to train ML-based failure triage models, we achieved high classification accuracy (88.1%-93.2%) across different IP blocks, confirming the practical utility and realism of generated bugs. BugGen thus provides a scalable solution for generating high-quality bug datasets, significantly enhancing verification efficiency and ML-assisted debugging.
Authors: Paulin de Schoulepnikoff, Gorka Mu\~noz-Gil, Hendrik Poulsen Nautrup, Hans J. Briegel
Abstract: Interpretable machine learning is rapidly becoming a crucial tool for scientific discovery. Among existing approaches, variational autoencoders (VAEs) have shown promise in extracting the hidden physical features of some input data, with no supervision nor prior knowledge of the system at study. Yet, the ability of VAEs to create meaningful, interpretable representations relies on their accurate approximation of the underlying probability distribution of their input. When dealing with quantum data, VAEs must hence account for its intrinsic randomness and complex correlations. While VAEs have been previously applied to quantum data, they have often neglected its probabilistic nature, hindering the extraction of meaningful physical descriptors. Here, we demonstrate that two key modifications enable VAEs to learn physically meaningful latent representations: a decoder capable of faithfully reproduce quantum states and a probabilistic loss tailored to this task. Using benchmark quantum spin models, we identify regimes where standard methods fail while the representations learned by our approach remain meaningful and interpretable. Applied to experimental data from Rydberg atom arrays, the model autonomously uncovers the phase structure without access to prior labels, Hamiltonian details, or knowledge of relevant order parameters, highlighting its potential as an unsupervised and interpretable tool for the study of quantum systems.
Authors: Pengfei Zuo, Huimin Lin, Junbo Deng, Nan Zou, Xingkun Yang, Yingyu Diao, Weifeng Gao, Ke Xu, Zhangyu Chen, Shirui Lu, Zhao Qiu, Peiyang Li, Xianyu Chang, Zhengzhong Yu, Fangzheng Miao, Jia Zheng, Ying Li, Yuan Feng, Bei Wang, Zaijian Zong, Mosong Zhou, Wenli Zhou, Houjiang Chen, Xingyu Liao, Yipeng Li, Wenxiao Zhang, Ping Zhu, Yinggang Wang, Chuanjie Xiao, Depeng Liang, Dong Cao, Juncheng Liu, Yongqiang Yang, Xiaolong Bai, Yi Li, Huaguo Xie, Huatao Wu, Zhibin Yu, Lv Chen, Hu Liu, Yujun Ding, Haipei Zhu, Jing Xia, Yi Xiong, Zhou Yu, Heng Liao
Abstract: The rapid evolution of large language models (LLMs), driven by growing parameter scales, adoption of mixture-of-experts (MoE) architectures, and expanding context lengths, imposes unprecedented demands on AI infrastructure. Traditional AI clusters face limitations in compute intensity, memory bandwidth, inter-chip communication, and latency, compounded by variable workloads and strict service-level objectives. Addressing these issues requires fundamentally redesigned hardware-software integration. This paper introduces Huawei CloudMatrix, a next-generation AI datacenter architecture, realized in the production-grade CloudMatrix384 supernode. It integrates 384 Ascend 910C NPUs and 192 Kunpeng CPUs interconnected via an ultra-high-bandwidth Unified Bus (UB) network, enabling direct all-to-all communication and dynamic pooling of resources. These features optimize performance for communication-intensive operations, such as large-scale MoE expert parallelism and distributed key-value cache access. To fully leverage CloudMatrix384, we propose CloudMatrix-Infer, an advanced LLM serving solution incorporating three core innovations: a peer-to-peer serving architecture that independently scales prefill, decode, and caching; a large-scale expert parallelism strategy supporting EP320 via efficient UB-based token dispatch; and hardware-aware optimizations including specialized operators, microbatch-based pipelining, and INT8 quantization. Evaluation with the DeepSeek-R1 model shows CloudMatrix-Infer achieves state-of-the-art efficiency: prefill throughput of 6,688 tokens/s per NPU and decode throughput of 1,943 tokens/s per NPU (<50 ms TPOT). It effectively balances throughput and latency, sustaining 538 tokens/s per NPU even under stringent 15 ms latency constraints, while INT8 quantization maintains model accuracy across benchmarks.
Authors: Kshitij Kavimandan, Angelos Nalmpantis, Emma Beauxis-Aussalet, Robert-Jan Sips
Abstract: Patent images are technical drawings that convey information about a patent's innovation. Patent image retrieval systems aim to search in vast collections and retrieve the most relevant images. Despite recent advances in information retrieval, patent images still pose significant challenges due to their technical intricacies and complex semantic information, requiring efficient fine-tuning for domain adaptation. Current methods neglect patents' hierarchical relationships, such as those defined by the Locarno International Classification (LIC) system, which groups broad categories (e.g., "furnishing") into subclasses (e.g., "seats" and "beds") and further into specific patent designs. In this work, we introduce a hierarchical multi-positive contrastive loss that leverages the LIC's taxonomy to induce such relations in the retrieval process. Our approach assigns multiple positive pairs to each patent image within a batch, with varying similarity scores based on the hierarchical taxonomy. Our experimental analysis with various vision and multimodal models on the DeepPatent2 dataset shows that the proposed method enhances the retrieval results. Notably, our method is effective with low-parameter models, which require fewer computational resources and can be deployed on environments with limited hardware.
Authors: Daniel Anadria, Roel Dobbe, Anastasia Giachanou, Ruurd Kuiper, Richard Bartels, Wouter van Amsterdam, \'I\~nigo Mart\'inez de Rituerto de Troya, Carmen Z\"urcher, Daniel Oberski
Abstract: In this work, we reflect on the data-driven modeling paradigm that is gaining ground in AI-driven automation of patient care. We argue that the repurposing of existing real-world patient datasets for machine learning may not always represent an optimal approach to model development as it could lead to undesirable outcomes in patient care. We reflect on the history of data analysis to explain how the data-driven paradigm rose to popularity, and we envision ways in which systems thinking and clinical domain theory could complement the existing model development approaches in reaching human-centric outcomes. We call for a purpose-driven machine learning paradigm that is grounded in clinical theory and the sociotechnical realities of real-world operational contexts. We argue that understanding the utility of existing patient datasets requires looking in two directions: upstream towards the data generation, and downstream towards the automation objectives. This purpose-driven perspective to AI system development opens up new methodological opportunities and holds promise for AI automation of patient care.
Authors: Giulia Luise, Chin-Wei Huang, Thijs Vogels, Derk P. Kooi, Sebastian Ehlert, Stephanie Lanius, Klaas J. H. Giesbertz, Amir Karton, Deniz Gunceler, Megan Stanley, Wessel P. Bruinsma, Lin Huang, Xinran Wei, Jos\'e Garrido Torres, Abylay Katbashev, B\'alint M\'at\'e, S\'ekou-Oumar Kaba, Roberto Sordillo, Yingrong Chen, David B. Williams-Young, Christopher M. Bishop, Jan Hermann, Rianne van den Berg, Paola Gori-Giorgi
Abstract: Density Functional Theory (DFT) is the most widely used electronic structure method for predicting the properties of molecules and materials. Although DFT is, in principle, an exact reformulation of the Schr\"odinger equation, practical applications rely on approximations to the unknown exchange-correlation (XC) functional. Most existing XC functionals are constructed using a limited set of increasingly complex, hand-crafted features that improve accuracy at the expense of computational efficiency. Yet, no current approximation achieves the accuracy and generality for predictive modeling of laboratory experiments at chemical accuracy -- typically defined as errors below 1 kcal/mol. In this work, we present Skala, a modern deep learning-based XC functional that bypasses expensive hand-designed features by learning representations directly from data. Skala achieves chemical accuracy for atomization energies of small molecules while retaining the computational efficiency typical of semi-local DFT. This performance is enabled by training on an unprecedented volume of high-accuracy reference data generated using computationally intensive wavefunction-based methods. Notably, Skala systematically improves with additional training data covering diverse chemistry. By incorporating a modest amount of additional high-accuracy data tailored to chemistry beyond atomization energies, Skala achieves accuracy competitive with the best-performing hybrid functionals across general main group chemistry, at the cost of semi-local DFT. As the training dataset continues to expand, Skala is poised to further enhance the predictive power of first-principles simulations.
Authors: Mikael M{\o}ller H{\o}gsgaard, Andrea Paudice
Abstract: The Median of Means (MoM) is a mean estimator that has gained popularity in the context of heavy-tailed data. In this work, we analyze its performance in the task of simultaneously estimating the mean of each function in a class $\mathcal{F}$ when the data distribution possesses only the first $p$ moments for $p \in (1,2]$. We prove a new sample complexity bound using a novel symmetrization technique that may be of independent interest. Additionally, we present applications of our result to $k$-means clustering with unbounded inputs and linear regression with general losses, improving upon existing works.