Authors: Ofer Dekel
Abstract: Blockbuster is a framework for AI operator fusion in inference programs. The Blockbuster framework is compatible with any multiprocessor architecture that has a tiered memory hierarchy, including GPUs, multi-core CPUs, and some AI accelerator chips. It includes a graph-based representation for AI workloads, called a block program, which explicitly models how blocks of data move between the memory tiers. It also includes an operator fusion procedure, which is made up of a candidate selection algorithm and a fusion algorithm that fuses each individual candidate - this two-algorithm structure makes Blockbuster especially suitable for large AI programs. The current paper focuses on the fusion algorithm, which is a rule-based technique. While the literature is full of previous rule-based fusion algorithms, what sets our algorithm apart is its direct modeling of data movement between memory tiers, resulting in uniquely powerful fusion results. As a first sanity check, we demonstrate how our algorithm automatically rediscovers the well-known Flash Attention kernel. Then, we demonstrate the real power of our approach by fusing LayerNorm with matrix multiplication and RMSNorm with FNN-SwiGLU - the latter involves fusing three matrix multiplications, a Hadamard product, a reduction, and a few elementwise operations into a single mega-kernel.
Authors: Thomas Wolgast, Astrid Nie{\ss}e
Abstract: Reinforcement learning (RL) algorithms are increasingly used to solve the optimal power flow (OPF) problem. Yet, the question of how to design RL environments to maximize training performance remains unanswered, both for the OPF and the general case. We propose a general approach for automated RL environment design by utilizing multi-objective optimization. For that, we use the hyperparameter optimization (HPO) framework, which allows the reuse of existing HPO algorithms and methods. On five OPF benchmark problems, we demonstrate that our automated design approach consistently outperforms a manually created baseline environment design. Further, we use statistical analyses to determine which environment design decisions are especially important for performance, resulting in multiple novel insights on how RL-OPF environments should be designed. Finally, we discuss the risk of overfitting the environment to the utilized RL algorithm. To the best of our knowledge, this is the first general approach for automated RL environment design.
Authors: Jiafan Li, Jiaqi Zhu, Liang Chang, Yilin Li, Miaomiao Li, Yang Wang, Hongan Wang
Abstract: Nowadays, numerous online platforms can be described as multi-modal heterogeneous networks (MMHNs), such as Douban's movie networks and Amazon's product review networks. Accurately categorizing nodes within these networks is crucial for analyzing the corresponding entities, which requires effective representation learning on nodes. However, existing multi-modal fusion methods often adopt either early fusion strategies which may lose the unique characteristics of individual modalities, or late fusion approaches overlooking the cross-modal guidance in GNN-based information propagation. In this paper, we propose a novel model for node classification in MMHNs, named Heterogeneous Graph Neural Network with Inter-Modal Attention (HGNN-IMA). It learns node representations by capturing the mutual influence of multiple modalities during the information propagation process, within the framework of heterogeneous graph transformer. Specifically, a nested inter-modal attention mechanism is integrated into the inter-node attention to achieve adaptive multi-modal fusion, and modality alignment is also taken into account to encourage the propagation among nodes with consistent similarities across all modalities. Moreover, an attention loss is augmented to mitigate the impact of missing modalities. Extensive experiments validate the superiority of the model in the node classification task, providing an innovative view to handle multi-modal data, especially when accompanied with network structures.
Authors: Minh-Duc Nguyen, Hyung-Jeong Yang, Soo-Hyung Kim, Ji-Eun Shin, Seung-Won Kim
Abstract: The dyadic reaction generation task involves synthesizing responsive facial reactions that align closely with the behaviors of a conversational partner, enhancing the naturalness and effectiveness of human-like interaction simulations. This paper introduces a novel approach, the Latent Behavior Diffusion Model, comprising a context-aware autoencoder and a diffusion-based conditional generator that addresses the challenge of generating diverse and contextually relevant facial reactions from input speaker behaviors. The autoencoder compresses high-dimensional input features, capturing dynamic patterns in listener reactions while condensing complex input data into a concise latent representation, facilitating more expressive and contextually appropriate reaction synthesis. The diffusion-based conditional generator operates on the latent space generated by the autoencoder to predict realistic facial reactions in a non-autoregressive manner. This approach allows for generating diverse facial reactions that reflect subtle variations in conversational cues and emotional states. Experimental results demonstrate the effectiveness of our approach in achieving superior performance in dyadic reaction synthesis tasks compared to existing methods.
Authors: Karahan Sar{\i}ta\c{s}, \c{C}a\u{g}atay Y{\i}ld{\i}z
Abstract: In this reproduction study, we revisit recent claims that self-attention implements kernel principal component analysis (KPCA) (Teo et al., 2024), positing that (i) value vectors $V$ capture the eigenvectors of the Gram matrix of the keys, and (ii) that self-attention projects queries onto the principal component axes of the key matrix $K$ in a feature space. Our analysis reveals three critical inconsistencies: (1) No alignment exists between learned self-attention value vectors and what is proposed in the KPCA perspective, with average similarity metrics (optimal cosine similarity $\leq 0.32$, linear CKA (Centered Kernel Alignment) $\leq 0.11$, kernel CKA $\leq 0.32$) indicating negligible correspondence; (2) Reported decreases in reconstruction loss $J_\text{proj}$, arguably justifying the claim that the self-attention minimizes the projection error of KPCA, are misinterpreted, as the quantities involved differ by orders of magnitude ($\sim\!10^3$); (3) Gram matrix eigenvalue statistics, introduced to justify that $V$ captures the eigenvector of the gram matrix, are irreproducible without undocumented implementation-specific adjustments. Across 10 transformer architectures, we conclude that the KPCA interpretation of self-attention lacks empirical support.
Authors: Alexander Hinterleitner, Thomas Bartz-Beielstein
Abstract: Despite the growing interest in Explainable Artificial Intelligence (XAI), explainability is rarely considered during hyperparameter tuning or neural architecture optimization, where the focus remains primarily on minimizing predictive loss. In this work, we introduce the novel concept of XAI consistency, defined as the agreement among different feature attribution methods, and propose new metrics to quantify it. For the first time, we integrate XAI consistency directly into the hyperparameter tuning objective, creating a multi-objective optimization framework that balances predictive performance with explanation robustness. Implemented within the Sequential Parameter Optimization Toolbox (SPOT), our approach uses both weighted aggregation and desirability-based strategies to guide model selection. Through our proposed framework and supporting tools, we explore the impact of incorporating XAI consistency into the optimization process. This enables us to characterize distinct regions in the architecture configuration space: one region with poor performance and comparatively low interpretability, another with strong predictive performance but weak interpretability due to low \gls{xai} consistency, and a trade-off region that balances both objectives by offering high interpretability alongside competitive performance. Beyond introducing this novel approach, our research provides a foundation for future investigations into whether models from the trade-off zone-balancing performance loss and XAI consistency-exhibit greater robustness by avoiding overfitting to training performance, thereby leading to more reliable predictions on out-of-distribution data.
Authors: Chengmin Zhou, Ville Kyrki, Pasi Fr\"anti, Laura Ruotsalainen
Abstract: Bayesian inference has many advantages in decision making of agents (e.g. robotics/simulative agent) over a regular data-driven black-box neural network: Data-efficiency, generalization, interpretability, and safety where these advantages benefit directly/indirectly from the uncertainty quantification of Bayesian inference. However, there are few comprehensive reviews to summarize the progress of Bayesian inference on reinforcement learning (RL) for decision making to give researchers a systematic understanding. This paper focuses on combining Bayesian inference with RL that nowadays is an important approach in agent decision making. To be exact, this paper discusses the following five topics: 1) Bayesian methods that have potential for agent decision making. First basic Bayesian methods and models (Bayesian rule, Bayesian learning, and Bayesian conjugate models) are discussed followed by variational inference, Bayesian optimization, Bayesian deep learning, Bayesian active learning, Bayesian generative models, Bayesian meta-learning, and lifelong Bayesian learning. 2) Classical combinations of Bayesian methods with model-based RL (with approximation methods), model-free RL, and inverse RL. 3) Latest combinations of potential Bayesian methods with RL. 4) Analytical comparisons of methods that combine Bayesian methods with RL with respect to data-efficiency, generalization, interpretability, and safety. 5) In-depth discussions in six complex problem variants of RL, including unknown reward, partial-observability, multi-agent, multi-task, non-linear non-Gaussian, and hierarchical RL problems and the summary of how Bayesian methods work in the data collection, data processing and policy learning stages of RL to pave the way for better agent decision-making strategies.
Authors: Yuxuan Zhang, Ye Xu, Luciano Sebastian Martinez-Rau, Quynh Nguyen Phuong Vu, Bengt Oelmann, Sebastian Bader
Abstract: Crack segmentation can play a critical role in Structural Health Monitoring (SHM) by enabling accurate identification of crack size and location, which allows to monitor structural damages over time. However, deploying deep learning models for crack segmentation on resource-constrained microcontrollers presents significant challenges due to limited memory, computational power, and energy resources. To address these challenges, this study explores lightweight U-Net architectures tailored for TinyML applications, focusing on three optimization strategies: filter number reduction, network depth reduction, and the use of Depthwise Separable Convolutions (DWConv2D). Our results demonstrate that reducing convolution kernels and network depth significantly reduces RAM and Flash requirement, and inference times, albeit with some accuracy trade-offs. Specifically, by reducing the filer number to 25%, the network depth to four blocks, and utilizing depthwise convolutions, a good compromise between segmentation performance and resource consumption is achieved. This makes the network particularly suitable for low-power TinyML applications. This study not only advances TinyML-based crack segmentation but also provides the possibility for energy-autonomous edge SHM systems.
Authors: Qi Xu, Junyang Zhu, Dongdong Zhou, Hao Chen, Yang Liu, Jiangrong Shen, Qiang Zhang
Abstract: Deep neural networks (DNNs) excel in computer vision tasks, especially, few-shot learning (FSL), which is increasingly important for generalizing from limited examples. However, DNNs are computationally expensive with scalability issues in real world. Spiking Neural Networks (SNNs), with their event-driven nature and low energy consumption, are particularly efficient in processing sparse and dynamic data, though they still encounter difficulties in capturing complex spatiotemporal features and performing accurate cross-class comparisons. To further enhance the performance and efficiency of SNNs in few-shot learning, we propose a few-shot learning framework based on SNNs, which combines a self-feature extractor module and a cross-feature contrastive module to refine feature representation and reduce power consumption. We apply the combination of temporal efficient training loss and InfoNCE loss to optimize the temporal dynamics of spike trains and enhance the discriminative power. Experimental results show that the proposed FSL-SNN significantly improves the classification performance on the neuromorphic dataset N-Omniglot, and also achieves competitive performance to ANNs on static datasets such as CUB and miniImageNet with low power consumption.
Authors: Thomas R. Harvey, Fabian Ruehle, Cristofero S. Fraser-Taliente, James Halverson
Abstract: We present a novel approach to symbolic regression using vision-capable large language models (LLMs) and the ideas behind Google DeepMind's Funsearch. The LLM is given a plot of a univariate function and tasked with proposing an ansatz for that function. The free parameters of the ansatz are fitted using standard numerical optimisers, and a collection of such ans\"atze make up the population of a genetic algorithm. Unlike other symbolic regression techniques, our method does not require the specification of a set of functions to be used in regression, but with appropriate prompt engineering, we can arbitrarily condition the generative step. By using Kolmogorov Arnold Networks (KANs), we demonstrate that ``univariate is all you need'' for symbolic regression, and extend this method to multivariate functions by learning the univariate function on each edge of a trained KAN. The combined expression is then simplified by further processing with a language model.
Authors: Xuechen Zhang, Zijian Huang, Chenshun Ni, Ziyang Xiong, Jiasi Chen, Samet Oymak
Abstract: Recent research enhances language model reasoning by scaling test-time compute via longer chain-of-thought traces. This often improves accuracy but also introduces redundancy and high computational cost, especially for small language models distilled with supervised fine-tuning (SFT). In this work, we propose new algorithms to improve token-efficient reasoning with small-scale models by effectively trading off accuracy and computation. We first show that the post-SFT model fails to determine the optimal stopping point of the reasoning process, resulting in verbose and repetitive outputs. Verbosity also significantly varies across wrong vs correct responses. To address these issues, we propose two solutions: (1) Temperature scaling (TS) to control the stopping point for the thinking phase and thereby trace length, and (2) TLDR: a length-regularized reinforcement learning method based on GRPO that facilitates multi-level trace length control (e.g. short, medium, long reasoning). Experiments on four reasoning benchmarks, MATH500, AMC, AIME24 and OlympiadBench, demonstrate that TS is highly effective compared to s1's budget forcing approach and TLDR significantly improves token efficiency by about 50% with minimal to no accuracy loss over the SFT baseline. Moreover, TLDR also facilitates flexible control over the response length, offering a practical and effective solution for token-efficient reasoning in small models. Ultimately, our work reveals the importance of stopping time control, highlights shortcomings of pure SFT, and provides effective algorithmic recipes.
Authors: H\'eber H. Arcolezi, Mina Alishahi, Adda-Akram Bendoukha, Nesrine Kaaniche
Abstract: Machine learning (ML) algorithms are heavily based on the availability of training data, which, depending on the domain, often includes sensitive information about data providers. This raises critical privacy concerns. Anonymization techniques have emerged as a practical solution to address these issues by generalizing features or suppressing data to make it more difficult to accurately identify individuals. Although recent studies have shown that privacy-enhancing technologies can influence ML predictions across different subgroups, thus affecting fair decision-making, the specific effects of anonymization techniques, such as $k$-anonymity, $\ell$-diversity, and $t$-closeness, on ML fairness remain largely unexplored. In this work, we systematically audit the impact of anonymization techniques on ML fairness, evaluating both individual and group fairness. Our quantitative study reveals that anonymization can degrade group fairness metrics by up to four orders of magnitude. Conversely, similarity-based individual fairness metrics tend to improve under stronger anonymization, largely as a result of increased input homogeneity. By analyzing varying levels of anonymization across diverse privacy settings and data distributions, this study provides critical insights into the trade-offs between privacy, fairness, and utility, offering actionable guidelines for responsible AI development. Our code is publicly available at: https://github.com/hharcolezi/anonymity-impact-fairness.
URLs: https://github.com/hharcolezi/anonymity-impact-fairness.
Authors: Tianyu Zhang, Shen Dong, O. Deniz Kose, Yanning Shen, Yupeng Zhang
Abstract: With the rise of machine learning techniques, ensuring the fairness of decisions made by machine learning algorithms has become of great importance in critical applications. However, measuring fairness often requires full access to the model parameters, which compromises the confidentiality of the models. In this paper, we propose a solution using zero-knowledge proofs, which allows the model owner to convince the public that a machine learning model is fair while preserving the secrecy of the model. To circumvent the efficiency barrier of naively proving machine learning inferences in zero-knowledge, our key innovation is a new approach to measure fairness only with model parameters and some aggregated information of the input, but not on any specific dataset. To achieve this goal, we derive new bounds for the fairness of logistic regression and deep neural network models that are tighter and better reflecting the fairness compared to prior work. Moreover, we develop efficient zero-knowledge proof protocols for common computations involved in measuring fairness, including the spectral norm of matrices, maximum, absolute value, and fixed-point arithmetic. We have fully implemented our system, FairZK, that proves machine learning fairness in zero-knowledge. Experimental results show that FairZK is significantly faster than the naive approach and an existing scheme that use zero-knowledge inferences as a subroutine. The prover time is improved by 3.1x--1789x depending on the size of the model and the dataset. FairZK can scale to a large model with 47 million parameters for the first time, and generates a proof for its fairness in 343 seconds. This is estimated to be 4 orders of magnitude faster than existing schemes, which only scale to small models with hundreds to thousands of parameters.
Authors: Steffen Schotth\"ofer, H. Lexie Yang, Stefan Schnake
Abstract: Deployment of neural networks on resource-constrained devices demands models that are both compact and robust to adversarial inputs. However, compression and adversarial robustness often conflict. In this work, we introduce a dynamical low-rank training scheme enhanced with a novel spectral regularizer that controls the condition number of the low-rank core in each layer. This approach mitigates the sensitivity of compressed models to adversarial perturbations without sacrificing clean accuracy. The method is model- and data-agnostic, computationally efficient, and supports rank adaptivity to automatically compress the network at hand. Extensive experiments across standard architectures, datasets, and adversarial attacks show the regularized networks can achieve over 94% compression while recovering or improving adversarial accuracy relative to uncompressed baselines.
Authors: Chao Feng, Nicolas Huber, Alberto Huertas Celdran, Gerome Bovet, Burkhard Stiller
Abstract: Federated Learning (FL) enables collaborative model training without sharing raw data, preserving participant privacy. Decentralized FL (DFL) eliminates reliance on a central server, mitigating the single point of failure inherent in the traditional FL paradigm, while introducing deployment challenges on resource-constrained devices. To evaluate real-world applicability, this work designs and deploys a physical testbed using edge devices such as Raspberry Pi and Jetson Nano. The testbed is built upon a DFL training platform, NEBULA, and extends it with a power monitoring module to measure energy consumption during training. Experiments across multiple datasets show that model performance is influenced by the communication topology, with denser topologies leading to better outcomes in DFL settings.
Authors: Dong Shu, Xuansheng Wu, Haiyan Zhao, Mengnan Du, Ninghao Liu
Abstract: Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs). However, conventional approaches to analyzing SAEs typically rely solely on input-side activations, without considering the causal influence between each latent feature and the model's output. This work is built on two key hypotheses: (1) activated latents do not contribute equally to the construction of the model's output, and (2) only latents with high causal influence are effective for model steering. To validate these hypotheses, we propose Gradient Sparse Autoencoder (GradSAE), a simple yet effective method that identifies the most influential latents by incorporating output-side gradient information.
Authors: Yuting Cai, Shaohuai Liu, Chao Tian, Le Xie
Abstract: Generative artificial intelligence (AI) models in smart grids have advanced significantly in recent years due to their ability to generate large amounts of synthetic data, which would otherwise be difficult to obtain in the real world due to confidentiality constraints. A key challenge in utilizing such synthetic data is how to assess the data quality produced from such generative models. Traditional Euclidean distance-based metrics only reflect pair-wise relations between two individual samples, and could fail in evaluating quality differences between groups of synthetic datasets. In this work, we propose a novel metric based on the Fr\'{e}chet Distance (FD) estimated between two datasets in a learned feature space. The proposed method evaluates the quality of generation from a distributional perspective. Empirical results demonstrate the superiority of the proposed metric across timescales and models, enhancing the reliability of data-driven decision-making in smart grid operations.
Authors: Alexandre Cotorobai, Jorge Miguel Silva, Jose Luis Oliveira
Abstract: Privacy and regulatory barriers often hinder centralized machine learning solutions, particularly in sectors like healthcare where data cannot be freely shared. Federated learning has emerged as a powerful paradigm to address these concerns; however, existing frameworks primarily support gradient-based models, leaving a gap for more interpretable, tree-based approaches. This paper introduces a federated learning framework for Random Forest classifiers that preserves data privacy and provides robust performance in distributed settings. By leveraging PySyft for secure, privacy-aware computation, our method enables multiple institutions to collaboratively train Random Forest models on locally stored data without exposing sensitive information. The framework supports weighted model averaging to account for varying data distributions, incremental learning to progressively refine models, and local evaluation to assess performance across heterogeneous datasets. Experiments on two real-world healthcare benchmarks demonstrate that the federated approach maintains competitive predictive accuracy - within a maximum 9\% margin of centralized methods - while satisfying stringent privacy requirements. These findings underscore the viability of tree-based federated learning for scenarios where data cannot be centralized due to regulatory, competitive, or technical constraints. The proposed solution addresses a notable gap in existing federated learning libraries, offering an adaptable tool for secure distributed machine learning tasks that demand both transparency and reliable performance. The tool is available at https://github.com/ieeta-pt/fed_rf.
Authors: Willem Diepeveen, Deanna Needell
Abstract: Modern machine learning increasingly leverages the insight that high-dimensional data often lie near low-dimensional, non-linear manifolds, an idea known as the manifold hypothesis. By explicitly modeling the geometric structure of data through learning Riemannian geometry algorithms can achieve improved performance and interpretability in tasks like clustering, dimensionality reduction, and interpolation. In particular, learned pullback geometry has recently undergone transformative developments that now make it scalable to learn and scalable to evaluate, which further opens the door for principled non-linear data analysis and interpretable machine learning. However, there are still steps to be taken when considering real-world multi-modal data. This work focuses on addressing distortions and modeling errors that can arise in the multi-modal setting and proposes to alleviate both challenges through isometrizing the learned Riemannian structure and balancing regularity and expressivity of the diffeomorphism parametrization. We showcase the effectiveness of the synergy of the proposed approaches in several numerical experiments with both synthetic and real data.
Authors: Xinghua Liu, Ming Cao
Abstract: The paper proposes a novel regularization procedure for machine learning. The proposed high-order regularization (HR) provides new insight into regularization, which is widely used to train a neural network that can be utilized to approximate the action-value function in general reinforcement learning problems. The proposed HR method ensures the provable convergence of the approximation algorithm, which makes the much-needed connection between regularization and explainable learning using neural networks. The proposed HR method theoretically demonstrates that regularization can be regarded as an approximation in terms of inverse mapping with explicitly calculable approximation error, and the $L_2$ regularization is a lower-order case of the proposed method. We provide lower and upper bounds for the error of the proposed HR solution, which helps build a reliable model. We also find that regularization with the proposed HR can be regarded as a contraction. We prove that the generalizability of neural networks can be maximized with a proper regularization matrix, and the proposed HR is applicable for neural networks with any mapping matrix. With the theoretical explanation of the extreme learning machine for neural network training and the proposed high-order regularization, one can better interpret the output of the neural network, thus leading to explainable learning. We present a case study based on regularized extreme learning neural networks to demonstrate the application of the proposed HR and give the corresponding incremental HR solution. We verify the performance of the proposed HR method by solving a classic control problem in reinforcement learning. The result demonstrates the superior performance of the method with significant enhancement in the generalizability of the neural network.
Authors: Licheng Zhang, Bach Le, Naveed Akhtar, Siew-Kei Lam, Tuan Ngo
Abstract: Large Language Models (LLMs) have seen rapid advancements in recent years, with models like ChatGPT and DeepSeek, showcasing their remarkable capabilities across diverse domains. While substantial research has been conducted on LLMs in various fields, a comprehensive review focusing on their integration with Computer-Aided Design (CAD) remains notably absent. CAD is the industry standard for 3D modeling and plays a vital role in the design and development of products across different industries. As the complexity of modern designs increases, the potential for LLMs to enhance and streamline CAD workflows presents an exciting frontier. This article presents the first systematic survey exploring the intersection of LLMs and CAD. We begin by outlining the industrial significance of CAD, highlighting the need for AI-driven innovation. Next, we provide a detailed overview of the foundation of LLMs. We also examine both closed-source LLMs as well as publicly available models. The core of this review focuses on the various applications of LLMs in CAD, providing a taxonomy of six key areas where these models are making considerable impact. Finally, we propose several promising future directions for further advancements, which offer vast opportunities for innovation and are poised to shape the future of CAD technology. Github: https://github.com/lichengzhanguom/LLMs-CAD-Survey-Taxonomy
URLs: https://github.com/lichengzhanguom/LLMs-CAD-Survey-Taxonomy
Authors: Brennon Brimhall, Philip Mathew, Neil Fendley, Yinzhi Cao, Matthew Green
Abstract: Machine unlearning methods take a model trained on a dataset and a forget set, then attempt to produce a model as if it had only been trained on the examples not in the forget set. We empirically show that an adversary is able to distinguish between a mirror model (a control model produced by retraining without the data to forget) and a model produced by an unlearning method across representative unlearning methods from the literature. We build distinguishing algorithms based on evaluation scores in the literature (i.e. membership inference scores) and Kullback-Leibler divergence. We propose a strong formal definition for machine unlearning called computational unlearning. Computational unlearning is defined as the inability for an adversary to distinguish between a mirror model and a model produced by an unlearning method. If the adversary cannot guess better than random (except with negligible probability), then we say that an unlearning method achieves computational unlearning. Our computational unlearning definition provides theoretical structure to prove unlearning feasibility results. For example, our computational unlearning definition immediately implies that there are no deterministic computational unlearning methods for entropic learning algorithms. We also explore the relationship between differential privacy (DP)-based unlearning methods and computational unlearning, showing that DP-based approaches can satisfy computational unlearning at the cost of an extreme utility collapse. These results demonstrate that current methodology in the literature fundamentally falls short of achieving computational unlearning. We conclude by identifying several open questions for future work.
Authors: Seyed Mohammad Azimi-Abarghouyi, Carlo Fischione
Abstract: Almost all existing hierarchical federated learning (FL) models are limited to two aggregation layers, restricting scalability and flexibility in complex, large-scale networks. In this work, we propose a Multi-Layer Hierarchical Federated Learning framework (QMLHFL), which appears to be the first study that generalizes hierarchical FL to arbitrary numbers of layers and network architectures through nested aggregation, while employing a layer-specific quantization scheme to meet communication constraints. We develop a comprehensive convergence analysis for QMLHFL and derive a general convergence condition and rate that reveal the effects of key factors, including quantization parameters, hierarchical architecture, and intra-layer iteration counts. Furthermore, we determine the optimal number of intra-layer iterations to maximize the convergence rate while meeting a deadline constraint that accounts for both communication and computation times. Our results show that QMLHFL consistently achieves high learning accuracy, even under high data heterogeneity, and delivers notably improved performance when optimized, compared to using randomly selected values.
Authors: Xiannan Huang, Shuhan Qiu
Abstract: Time series forecasting is critical for many applications, where deep learning-based point prediction models have demonstrated strong performance. However, in practical scenarios, there is also a need to quantify predictive uncertainty through online confidence intervals. Existing confidence interval modeling approaches building upon these deep point prediction models suffer from key limitations: they either require costly retraining, fail to fully leverage the representational strengths of deep models, or lack theoretical guarantees. To address these gaps, we propose a lightweight conformal prediction method that provides valid coverage and shorter interval lengths without retraining. Our approach leverages features extracted from pre-trained point prediction models to fit a residual predictor and construct confidence intervals, further enhanced by an adaptive coverage control mechanism. Theoretically, we prove that our method achieves asymptotic coverage convergence, with error bounds dependent on the feature quality of the underlying point prediction model. Experiments on 12 datasets demonstrate that our method delivers tighter confidence intervals while maintaining desired coverage rates. Code, model and dataset in \href{https://github.com/xiannanhuang/FFDCI}{Github}
Authors: Zhikun Tao, Gang Xiong, He Fang, Zhen Shen, Yunjun Han, Qing-Shan Jia
Abstract: Offline safe reinforcement learning(OSRL) derives constraint-satisfying policies from pre-collected datasets, offers a promising avenue for deploying RL in safety-critical real-world domains such as robotics. However, the majority of existing approaches emphasize only short-term safety, neglecting long-horizon considerations. Consequently, they may violate safety constraints and fail to ensure sustained protection during online deployment. Moreover, the learned policies often struggle to handle states and actions that are not present or out-of-distribution(OOD) from the offline dataset, and exhibit limited sample efficiency. To address these challenges, we propose a novel framework Feasibility-Aware offline Safe Reinforcement Learning with CVAE-based Pessimism (FASP). First, we employ Hamilton-Jacobi (H-J) reachability analysis to generate reliable safety labels, which serve as supervisory signals for training both a conditional variational autoencoder (CVAE) and a safety classifier. This approach not only ensures high sampling efficiency but also provides rigorous long-horizon safety guarantees. Furthermore, we utilize pessimistic estimation methods to estimate the Q-value of reward and cost, which mitigates the extrapolation errors induces by OOD actions, and penalize unsafe actions to enabled the agent to proactively avoid high-risk behaviors. Moreover, we theoretically prove the validity of this pessimistic estimation. Extensive experiments on DSRL benchmarks demonstrate that FASP algorithm achieves competitive performance across multiple experimental tasks, particularly outperforming state-of-the-art algorithms in terms of safety.
Authors: Alex Zhihao Dou, Dongfei Cui, Jun Yan, Weida Wang, Benteng Chen, Haoming Wang, Zeke Xie, Shufei Zhang
Abstract: Although Reinforcement Learning (RL) agents are effective in well-defined environments, they often struggle to generalize their learned policies to dynamic settings due to their reliance on trial-and-error interactions. Recent work has explored applying Large Language Models (LLMs) or Vision Language Models (VLMs) to boost the generalization of RL agents through policy optimization guidance or prior knowledge. However, these approaches often lack seamless coordination between the RL agent and the foundation model, leading to unreasonable decision-making in unfamiliar environments and efficiency bottlenecks. Making full use of the inferential capabilities of foundation models and the rapid response capabilities of RL agents and enhancing the interaction between the two to form a dual system is still a lingering scientific question. To address this problem, we draw inspiration from Kahneman's theory of fast thinking (System 1) and slow thinking (System 2), demonstrating that balancing intuition and deep reasoning can achieve nimble decision-making in a complex world. In this study, we propose a Dual-System Adaptive Decision Framework (DSADF), integrating two complementary modules: System 1, comprising an RL agent and a memory space for fast and intuitive decision making, and System 2, driven by a VLM for deep and analytical reasoning. DSADF facilitates efficient and adaptive decision-making by combining the strengths of both systems. The empirical study in the video game environment: Crafter and Housekeep demonstrates the effectiveness of our proposed method, showing significant improvements in decision abilities for both unseen and known tasks.
Authors: Boshi Gao, Qingjian Ni, Fanbo Ju, Yu Chen, Ziqi Zhao
Abstract: Long-term time series forecasting (LTSF) offers broad utility in practical settings like energy consumption and weather prediction. Accurately predicting long-term changes, however, is demanding due to the intricate temporal patterns and inherent multi-scale variations within time series. This work confronts key issues in LTSF, including the suboptimal use of multi-granularity information, the neglect of channel-specific attributes, and the unique nature of trend and seasonal components, by introducing a proficient MLP-based forecasting framework. Our method adeptly disentangles complex temporal dynamics using clear, concurrent predictions across various scales. These multi-scale forecasts are then skillfully integrated through a system that dynamically assigns importance to information from different granularities, sensitive to individual channel characteristics. To manage the specific features of temporal patterns, a two-pronged structure is utilized to model trend and seasonal elements independently. Experimental results on eight LTSF benchmarks demonstrate that MDMixer improves average MAE performance by 4.64% compared to the recent state-of-the-art MLP-based method (TimeMixer), while achieving an effective balance between training efficiency and model interpretability.
Authors: Dorit Hochbaum, Torpong Nitayanont
Abstract: In many scenarios of binary classification, only positive instances are provided in the training data, leaving the rest of the data unlabeled. This setup, known as positive-unlabeled (PU) learning, is addressed here with a network flow-based method which utilizes pairwise similarities between samples. The method we propose here, 2-HNC, leverages Hochbaum's Normalized Cut (HNC) and the set of solutions it provides by solving a parametric minimum cut problem. The set of solutions, that are nested partitions of the samples into two sets, correspond to varying tradeoff values between the two goals: high intra-similarity inside the sets and low inter-similarity between the two sets. This nested sequence is utilized here to deliver a ranking of unlabeled samples by their likelihood of being negative. Building on this insight, our method, 2-HNC, proceeds in two stages. The first stage generates this ranking without assuming any negative labels, using a problem formulation that is constrained only on positive labeled samples. The second stage augments the positive set with likely-negative samples and recomputes the classification. The final label prediction selects among all generated partitions in both stages, the one that delivers a positive class proportion, closest to a prior estimate of this quantity, which is assumed to be given. Extensive experiments across synthetic and real datasets show that 2-HNC yields strong performance and often surpasses existing state-of-the-art algorithms.
Authors: Lu Dai, Wenxuan Zhu, Xuehui Quan, Renzi Meng, Sheng Cai, Yichen Wang
Abstract: To improve the identification of potential anomaly patterns in complex user behavior, this paper proposes an anomaly detection method based on a deep mixture density network. The method constructs a Gaussian mixture model parameterized by a neural network, enabling conditional probability modeling of user behavior. It effectively captures the multimodal distribution characteristics commonly present in behavioral data. Unlike traditional classifiers that rely on fixed thresholds or a single decision boundary, this approach defines an anomaly scoring function based on probability density using negative log-likelihood. This significantly enhances the model's ability to detect rare and unstructured behaviors. Experiments are conducted on the real-world network user dataset UNSW-NB15. A series of performance comparisons and stability validation experiments are designed. These cover multiple evaluation aspects, including Accuracy, F1- score, AUC, and loss fluctuation. The results show that the proposed method outperforms several advanced neural network architectures in both performance and training stability. This study provides a more expressive and discriminative solution for user behavior modeling and anomaly detection. It strongly promotes the application of deep probabilistic modeling techniques in the fields of network security and intelligent risk control.
Authors: Sisipho Hamlomo, Marcellin Atemkeng
Abstract: Low-rank matrix approximation (LoRMA) is a fundamental tool for compressing high-resolution data matrices by extracting important features while suppressing redundancy. Low-rank methods, such as global singular value decomposition (SVD), apply uniform compression across the entire data matrix, often ignoring important local variations and leading to the loss of fine structural details. To address these limitations, we introduce an adaptive LoRMA, which partitions data matrix into overlapping patches, groups structurally similar patches into several clusters using k-means, and performs SVD within each cluster. We derive the overall compression factor accounting for patch overlap and analyze how patch size influences compression efficiency and computational cost. While the proposed adaptive LoRMA method is applicable to any data exhibiting high local variation, we focus on medical imaging due to its pronounced local variability. We evaluate and compare our adaptive LoRMA against global SVD across four imaging modalities: MRI, ultrasound, CT scan, and chest X-ray. Results demonstrate that adaptive LoRMA effectively preserves structural integrity, edge details, and diagnostic relevance, as measured by peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), mean squared error (MSE), intersection over union (IoU), and edge preservation index (EPI). Adaptive LoRMA significantly minimizes block artifacts and residual errors, particularly in pathological regions, consistently outperforming global SVD in terms of PSNR, SSIM, IoU, EPI, and achieving lower MSE. Adaptive LoRMA prioritizes clinically salient regions while allowing aggressive compression in non-critical regions, optimizing storage efficiency. Although adaptive LoRMA requires higher processing time, its diagnostic fidelity justifies the overhead for high-compression applications.
Authors: Nathanael Tepakbong, Ding-Xuan Zhou, Xiang Zhou
Abstract: We study the classical binary classification problem for hypothesis spaces of Deep Neural Networks (DNNs) with ReLU activation under Tsybakov's low-noise condition with exponent $q>0$, and its limit-case $q\to\infty$ which we refer to as the "hard-margin condition". We show that DNNs which minimize the empirical risk with square loss surrogate and $\ell_p$ penalty can achieve finite-sample excess risk bounds of order $\mathcal{O}\left(n^{-\alpha}\right)$ for arbitrarily large $\alpha>0$ under the hard-margin condition, provided that the regression function $\eta$ is sufficiently smooth. The proof relies on a novel decomposition of the excess risk which might be of independent interest.
Authors: Hang Gao, Wenxuan Huang, Fengge Wu, Junsuo Zhao, Changwen Zheng, Huaping Liu
Abstract: The use of large language models (LLMs) as feature enhancers to optimize node representations, which are then used as inputs for graph neural networks (GNNs), has shown significant potential in graph representation learning. However, the fundamental properties of this approach remain underexplored. To address this issue, we propose conducting a more in-depth analysis of this issue based on the interchange intervention method. First, we construct a synthetic graph dataset with controllable causal relationships, enabling precise manipulation of semantic relationships and causal modeling to provide data for analysis. Using this dataset, we conduct interchange interventions to examine the deeper properties of LLM enhancers and GNNs, uncovering their underlying logic and internal mechanisms. Building on the analytical results, we design a plug-and-play optimization module to improve the information transfer between LLM enhancers and GNNs. Experiments across multiple datasets and models validate the proposed module.
Authors: Jueqing Lu, Yuanyuan Qi, Xiaohao Yang, Shujie Zhou, Lan Du
Abstract: Multimodal learning enhances deep learning models by enabling them to perceive and understand information from multiple data modalities, such as visual and textual inputs. However, most existing approaches assume the availability of all modalities, an assumption that often fails in real-world applications. Recent works have introduced learnable missing-case-aware prompts to mitigate performance degradation caused by missing modalities while reducing the need for extensive model fine-tuning. Building upon the effectiveness of missing-case-aware handling for missing modalities, we propose a novel decoupled prototype-based output head, which leverages missing-case-aware class-wise prototypes tailored for each individual modality. This approach dynamically adapts to different missing modality scenarios and can be seamlessly integrated with existing prompt-based methods. Extensive experiments demonstrate that our proposed output head significantly improves performance across a wide range of missing-modality scenarios and varying missing rates.
Authors: Yinghan Sun, Hongxi Wang, Hua Chen, Wei Zhang
Abstract: Deep reinforcement learning (DRL) has emerged as a powerful framework for solving sequential decision-making problems, achieving remarkable success in a wide range of applications, including game AI, autonomous driving, biomedicine, and large language models. However, the diversity of algorithms and the complexity of theoretical foundations often pose significant challenges for beginners seeking to enter the field. This tutorial aims to provide a concise, intuitive, and practical introduction to DRL, with a particular focus on the Proximal Policy Optimization (PPO) algorithm, which is one of the most widely used and effective DRL methods. To facilitate learning, we organize all algorithms under the Generalized Policy Iteration (GPI) framework, offering readers a unified and systematic perspective. Instead of lengthy theoretical proofs, we emphasize intuitive explanations, illustrative examples, and practical engineering techniques. This work serves as an efficient and accessible guide, helping readers rapidly progress from basic concepts to the implementation of advanced DRL algorithms.
Authors: Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Abstract: State-space models (SSMs), particularly the Mamba architecture, have emerged as powerful alternatives to Transformers for sequence modeling, offering linear-time complexity and competitive performance across diverse tasks. However, their large parameter counts pose significant challenges for deployment in resource-constrained environments. We propose a novel unstructured pruning framework tailored for Mamba models that achieves up to 70\% parameter reduction while retaining over 95\% of the original performance. Our approach integrates three key innovations: (1) a gradient-aware magnitude pruning technique that combines weight magnitude and gradient information to identify less critical parameters, (2) an iterative pruning schedule that gradually increases sparsity to maintain model stability, and (3) a global pruning strategy that optimizes parameter allocation across the entire model. Through extensive experiments on WikiText-103, Long Range Arena, and ETT time-series benchmarks, we demonstrate significant efficiency gains with minimal performance degradation. Our analysis of pruning effects on Mamba's components reveals critical insights into the architecture's redundancy and robustness, enabling practical deployment in resource-constrained settings while broadening Mamba's applicability.
Authors: Shira Vansover-Hager, Tomer Koren, Roi Livni
Abstract: We study the out-of-sample performance of multi-pass stochastic gradient descent (SGD) in the fundamental stochastic convex optimization (SCO) model. While one-pass SGD is known to achieve an optimal $\Theta(1/\sqrt{n})$ excess population loss given a sample of size $n$, much less is understood about the multi-pass version of the algorithm which is widely used in practice. Somewhat surprisingly, we show that in the general non-smooth case of SCO, just a few epochs of SGD can already hurt its out-of-sample performance significantly and lead to overfitting. In particular, using a step size $\eta = \Theta(1/\sqrt{n})$, which gives the optimal rate after one pass, can lead to population loss as large as $\Omega(1)$ after just one additional pass. More generally, we show that the population loss from the second pass onward is of the order $\Theta(1/(\eta T) + \eta \sqrt{T})$, where $T$ is the total number of steps. These results reveal a certain phase-transition in the out-of-sample behavior of SGD after the first epoch, as well as a sharp separation between the rates of overfitting in the smooth and non-smooth cases of SCO. Additionally, we extend our results to with-replacement SGD, proving that the same asymptotic bounds hold after $O(n \log n)$ steps. Finally, we also prove a lower bound of $\Omega(\eta \sqrt{n})$ on the generalization gap of one-pass SGD in dimension $d = \smash{\widetilde O}(n)$, improving on recent results of Koren et al.(2022) and Schliserman et al.(2024).
Authors: Yoonhyuk Choi, Chong-Kwon Kim
Abstract: We introduce SpecSphere, the first dual-pass spectral-spatial GNN that certifies every prediction against both $\ell\_{0}$ edge flips and $\ell\_{\infty}$ feature perturbations, adapts to the full homophily-heterophily spectrum, and surpasses the expressive power of 1-Weisfeiler-Lehman while retaining linear-time complexity. Our model couples a Chebyshev-polynomial spectral branch with an attention-gated spatial branch and fuses their representations through a lightweight MLP trained in a cooperative-adversarial min-max game. We further establish (i) a uniform Chebyshev approximation theorem, (ii) minimax-optimal risk across the homophily-heterophily spectrum, (iii) closed-form robustness certificates, and (iv) universal approximation strictly beyond 1-WL. SpecSphere achieves state-of-the-art node-classification accuracy and delivers tighter certified robustness guarantees on real-world benchmarks. These results demonstrate that high expressivity, heterophily adaptation, and provable robustness can coexist within a single, scalable architecture.
Authors: Haodong Zhao, Peng Peng, Chiyu Chen, Linqing Huang, Gongshen Liu
Abstract: Remote sensing (RS) images are usually produced at an unprecedented scale, yet they are geographically and institutionally distributed, making centralized model training challenging due to data-sharing restrictions and privacy concerns. Federated learning (FL) offers a solution by enabling collaborative model training across decentralized RS data sources without exposing raw data. However, there lacks a realistic federated dataset and benchmark in RS. Prior works typically rely on manually partitioned single dataset, which fail to capture the heterogeneity and scale of real-world RS data, and often use inconsistent experimental setups, hindering fair comparison. To address this gap, we propose a realistic federated RS dataset, termed FedRS. FedRS consists of eight datasets that cover various sensors and resolutions and builds 135 clients, which is representative of realistic operational scenarios. Data for each client come from the same source, exhibiting authentic federated properties such as skewed label distributions, imbalanced client data volumes, and domain heterogeneity across clients. These characteristics reflect practical challenges in federated RS and support evaluation of FL methods at scale. Based on FedRS, we implement 10 baseline FL algorithms and evaluation metrics to construct the comprehensive FedRS-Bench. The experimental results demonstrate that FL can consistently improve model performance over training on isolated data silos, while revealing performance trade-offs of different methods under varying client heterogeneity and availability conditions. We hope FedRS-Bench will accelerate research on large-scale, realistic FL in RS by providing a standardized, rich testbed and facilitating fair comparisons across future works. The source codes and dataset are available at https://fedrs-bench.github.io/.
Authors: Zhenrong Liu, Janne M. J. Huttunen, Mikko Honkala
Abstract: Continual learning (CL) aims to train models that can learn a sequence of tasks without forgetting previously acquired knowledge. A core challenge in CL is balancing stability -- preserving performance on old tasks -- and plasticity -- adapting to new ones. Recently, large pre-trained models have been widely adopted in CL for their ability to support both, offering strong generalization for new tasks and resilience against forgetting. However, their high computational cost at inference time limits their practicality in real-world applications, especially those requiring low latency or energy efficiency. To address this issue, we explore model compression techniques, including pruning and knowledge distillation (KD), and propose two efficient frameworks tailored for class-incremental learning (CIL), a challenging CL setting where task identities are unavailable during inference. The pruning-based framework includes pre- and post-pruning strategies that apply compression at different training stages. The KD-based framework adopts a teacher-student architecture, where a large pre-trained teacher transfers downstream-relevant knowledge to a compact student. Extensive experiments on multiple CIL benchmarks demonstrate that the proposed frameworks achieve a better trade-off between accuracy and inference complexity, consistently outperforming strong baselines. We further analyze the trade-offs between the two frameworks in terms of accuracy and efficiency, offering insights into their use across different scenarios.
Authors: Chang Zong, Yueting Zhuang, Jian Shao, Weiming Lu
Abstract: Detecting anomalous edges in dynamic graphs is an important task in many applications over evolving triple-based data, such as social networks, transaction management, and epidemiology. A major challenge with this task is the absence of structural-temporal coupling information, which decreases the ability of the representation to distinguish anomalies from normal instances. Existing methods focus on handling independent structural and temporal features with embedding models, which ignore the deep interaction between these two types of information. In this paper, we propose a structural-temporal coupling anomaly detection architecture with a dynamic graph transformer model. Specifically, we introduce structural and temporal features from two integration levels to provide anomaly-aware graph evolutionary patterns. Then, a dynamic graph transformer enhanced by two-dimensional positional encoding is implemented to capture both discrimination and contextual consistency signals. Extensive experiments on six datasets demonstrate that our method outperforms current state-of-the-art models. Finally, a case study illustrates the strength of our method when applied to a real-world task.
Authors: Hyunseung Hwang, Andrew Bell, Joao Fonseca, Venetia Pliatsika, Julia Stoyanovich, Steven Euijong Whang
Abstract: Local feature-based explanations are a key component of the XAI toolkit. These explanations compute feature importance values relative to an ``interpretable'' feature representation. In tabular data, feature values themselves are often considered interpretable. This paper examines the impact of data engineering choices on local feature-based explanations. We demonstrate that simple, common data engineering techniques, such as representing age with a histogram or encoding race in a specific way, can manipulate feature importance as determined by popular methods like SHAP. Notably, the sensitivity of explanations to feature representation can be exploited by adversaries to obscure issues like discrimination. While the intuition behind these results is straightforward, their systematic exploration has been lacking. Previous work has focused on adversarial attacks on feature-based explainers by biasing data or manipulating models. To the best of our knowledge, this is the first study demonstrating that explainers can be misled by standard, seemingly innocuous data engineering techniques.
Authors: Alexander Humer, Lukas Grasboeck, Ayech Benjeddou
Abstract: Today, machine learning is ubiquitous, and structural health monitoring (SHM) is no exception. Specifically, we address the problem of impact localization on shell-like structures, where knowledge of impact locations aids in assessing structural integrity. Impacts on thin-walled structures excite Lamb waves, which can be measured with piezoelectric sensors. Their dispersive characteristics make it difficult to detect and localize impacts by conventional methods. In the present contribution, we explore the localization of impacts using neural networks. In particular, we propose to use {recurrent neural networks} (RNNs) to estimate impact positions end-to-end, i.e., directly from {sequential sensor data}. We deal with comparatively long sequences of thousands of samples, since high sampling rate are needed to accurately capture elastic waves. For this reason, the proposed approach builds upon Gated Recurrent Units (GRUs), which are less prone to vanishing gradients as compared to conventional RNNs. Quality and quantity of data are crucial when training neural networks. Often, synthetic data is used, which inevitably introduces a reality gap. Here, by contrast, we train our networks using {physical data from experiments}, which requires automation to handle the large number of experiments needed. For this purpose, a {robot is used to drop steel balls} onto an {aluminum plate} equipped with {piezoceramic sensors}. Our results show remarkable accuracy in estimating impact positions, even with a comparatively small dataset.
Authors: Takashi Nicholas Maeda, Shohei Shimizu, Hidetoshi Matsui
Abstract: This paper proposes a causal discovery method for mixed bivariate data consisting of one continuous and one discrete variable. Existing constraint-based approaches are ineffective in the bivariate setting, as they rely on conditional independence tests that are not suited to bivariate data. Score-based methods either impose strong distributional assumptions or face challenges in fairly comparing causal directions between variables of different types, due to differences in their information content. We introduce a novel approach that determines causal direction by analyzing the monotonicity of the conditional density ratio of the continuous variable, conditioned on different values of the discrete variable. Our theoretical analysis shows that the conditional density ratio exhibits monotonicity when the continuous variable causes the discrete variable, but not in the reverse direction. This property provides a principled basis for comparing causal directions between variables of different types, free from strong distributional assumptions and bias arising from differences in their information content. We demonstrate its effectiveness through experiments on both synthetic and real-world datasets, showing superior accuracy compared to existing methods.
Authors: Mayank Nautiyal, Andreas Hellander, Prashant Singh
Abstract: We present a conditional diffusion model - ConDiSim, for simulation-based inference of complex systems with intractable likelihoods. ConDiSim leverages denoising diffusion probabilistic models to approximate posterior distributions, consisting of a forward process that adds Gaussian noise to parameters, and a reverse process learning to denoise, conditioned on observed data. This approach effectively captures complex dependencies and multi-modalities within posteriors. ConDiSim is evaluated across ten benchmark problems and two real-world test problems, where it demonstrates effective posterior approximation accuracy while maintaining computational efficiency and stability in model training. ConDiSim offers a robust and extensible framework for simulation-based inference, particularly suitable for parameter inference workflows requiring fast inference methods.
Authors: Adel Ammar, Anis Koubaa, Omer Nacar, Wadii Boulila
Abstract: Large language models achieve high task performance yet often hallucinate or rely on outdated knowledge. Retrieval-augmented generation (RAG) addresses these gaps by coupling generation with external search. We analyse how hyperparameters influence speed and quality in RAG systems, covering Chroma and Faiss vector stores, chunking policies, cross-encoder re-ranking, and temperature, and we evaluate six metrics: faithfulness, answer correctness, answer relevancy, context precision, context recall, and answer similarity. Chroma processes queries 13% faster, whereas Faiss yields higher retrieval precision, revealing a clear speed-accuracy trade-off. Naive fixed-length chunking with small windows and minimal overlap outperforms semantic segmentation while remaining the quickest option. Re-ranking provides modest gains in retrieval quality yet increases runtime by roughly a factor of 5, so its usefulness depends on latency constraints. These results help practitioners balance computational cost and accuracy when tuning RAG systems for transparent, up-to-date responses. Finally, we re-evaluate the top configurations with a corrective RAG workflow and show that their advantages persist when the model can iteratively request additional evidence. We obtain a near-perfect context precision (99%), which demonstrates that RAG systems can achieve extremely high retrieval accuracy with the right combination of hyperparameters, with significant implications for applications where retrieval quality directly impacts downstream task performance, such as clinical decision support in healthcare.
Authors: Chetra Mang, Axel TahmasebiMoradi, David Danan, Mouadh Yagoubi
Abstract: Physical models classically involved Partial Differential equations (PDE) and depending of their underlying complexity and the level of accuracy required, and known to be computationally expensive to numerically solve them. Thus, an idea would be to create a surrogate model relying on data generated by such solver. However, training such a model on an imbalanced data have been shown to be a very difficult task. Indeed, if the distribution of input leads to a poor response manifold representation, the model may not learn well and consequently, it may not predict the outcome with acceptable accuracy. In this work, we present an Adaptive Sampling Algorithm for Data Generation (ASADG) involving a physical model. As the initial input data may not accurately represent the response manifold in higher dimension, this algorithm iteratively adds input data into it. At each step the barycenter of each simplicial complex, that the manifold is discretized into, is added as new input data, if a certain threshold is satisfied. We demonstrate the efficiency of the data sampling algorithm in comparison with LHS method for generating more representative input data. To do so, we focus on the construction of a harmonic transport problem metamodel by generating data through a classical solver. By using such algorithm, it is possible to generate the same number of input data as LHS while providing a better representation of the response manifold.
Authors: Adam Ulrich, Jan Kr\v{n}\'avek, Roman \v{S}enke\v{r}\'ik, Zuzana Kom\'inkov\'a Oplatkov\'a, Radek Vala
Abstract: Data mining offers a diverse toolbox for extracting meaningful structures from complex datasets, with anomaly detection emerging as a critical subfield particularly in the context of streaming or real-time data. Within anomaly detection, novelty detection focuses on identifying previously unseen patterns after training solely on regular data. While classic algorithms such as One-Class SVM or Local Outlier Factor (LOF) have been widely applied, they often lack interpretability and scalability. In this work, we explore the Half-Space Tree (HST) algorithm, originally proposed for streaming anomaly detection, and propose a novel theoretical modification to adapt it specifically for novelty detection tasks. Our approach is grounded in the idea that anomalies i.e., novelties tend to appear in the higher leaves of the tree, which are less frequently visited by regular instances. We analytically demonstrate the effectiveness of this approach using probabilistic analysis, expected depth (EXD) calculations, and combinatorial reasoning. A comparative analysis of expected depths between our modified HST and the original Isolation Forest highlights that novelty points are significantly more isolated in our approach. This supports the hypothesis that HSTs, with appropriate structural adaptation, can serve as interpretable and efficient novelty detectors. The paper contributes a theoretical foundation and supporting analysis for this adaptation, setting the stage for further application and experimentation.
Authors: Chetra Mang, Axel TahmasebiMoradi, Mouadh Yagoubi
Abstract: We propose a new methodology for parametric domain decomposition using iterative principal component analysis. Starting with iterative principle component analysis, the high dimension manifold is reduced to the lower dimension manifold. Moreover, two approaches are developed to reconstruct the inverse projector to project from the lower data component to the original one. Afterward, we provide a detailed strategy to decompose the parametric domain based on the low dimension manifold. Finally, numerical examples of harmonic transport problem are given to illustrate the efficiency and effectiveness of the proposed method comparing to the classical meta-models such as neural networks.
Authors: Teng Xiao, Zhen Ge, Sujay Sanghavi, Tian Wang, Julian Katz-Samuels, Marc Versage, Qingjun Cui, Trishul Chilimbi
Abstract: We study the post-training of large language models (LLMs) with human preference data. Recently, direct preference optimization and its variants have shown considerable promise in aligning language models, eliminating the need for reward models and online sampling. Despite these benefits, these methods rely on explicit assumptions about the Bradley-Terry (BT) model, which makes them prone to overfitting and results in suboptimal performance, particularly on reasoning-heavy tasks. To address these challenges, we propose a principled preference fine-tuning algorithm called InfoPO, which effectively and efficiently aligns large language models using preference data. InfoPO eliminates the reliance on the BT model and prevents the likelihood of the chosen response from decreasing. Extensive experiments confirm that InfoPO consistently outperforms established baselines on widely used open benchmarks, particularly in reasoning tasks.
Authors: Hyowon Wi, Jeongwhan Choi, Noseong Park
Abstract: Transformers have demonstrated remarkable performance across diverse domains. The key component of Transformers is self-attention, which learns the relationship between any two tokens in the input sequence. Recent studies have revealed that the self-attention can be understood as a normalized adjacency matrix of a graph. Notably, from the perspective of graph signal processing (GSP), the self-attention can be equivalently defined as a simple graph filter, applying GSP using the value vector as the signal. However, the self-attention is a graph filter defined with only the first order of the polynomial matrix, and acts as a low-pass filter preventing the effective leverage of various frequency information. Consequently, existing self-attention mechanisms are designed in a rather simplified manner. Therefore, we propose a novel method, called \underline{\textbf{A}}ttentive \underline{\textbf{G}}raph \underline{\textbf{F}}ilter (AGF), interpreting the self-attention as learning the graph filter in the singular value domain from the perspective of graph signal processing for directed graphs with the linear complexity w.r.t. the input length $n$, i.e., $\mathcal{O}(nd^2)$. In our experiments, we demonstrate that AGF achieves state-of-the-art performance on various tasks, including Long Range Arena benchmark and time series classification.
Authors: Minsu Kim, Seong-Hyeon Hwang, Steven Euijong Whang
Abstract: In the context of continual learning, acquiring new knowledge while maintaining previous knowledge presents a significant challenge. Existing methods often use experience replay techniques that store a small portion of previous task data for training. In experience replay approaches, data augmentation has emerged as a promising strategy to further improve the model performance by mixing limited previous task data with sufficient current task data. However, we theoretically and empirically analyze that training with mixed samples from random sample pairs may harm the knowledge of previous tasks and cause greater catastrophic forgetting. We then propose GradMix, a robust data augmentation method specifically designed for mitigating catastrophic forgetting in class-incremental learning. GradMix performs gradient-based selective mixup using a class-based criterion that mixes only samples from helpful class pairs and not from detrimental class pairs for reducing catastrophic forgetting. Our experiments on various real datasets show that GradMix outperforms data augmentation baselines in accuracy by minimizing the forgetting of previous knowledge.
Authors: Shan Zhao, Zhitong Xiong, Jie Zhao, Xiao Xiang Zhu
Abstract: Our planet is facing increasingly frequent extreme events, which pose major risks to human lives and ecosystems. Recent advances in machine learning (ML), especially with foundation models (FMs) trained on extensive datasets, excel in extracting features and show promise in disaster management. Nevertheless, these models often inherit biases from training data, challenging their performance over extreme values. To explore the reliability of FM in the context of extreme events, we introduce \textbf{ExE}Bench (\textbf{Ex}treme \textbf{E}arth Benchmark), a collection of seven extreme event categories across floods, wildfires, storms, tropical cyclones, extreme precipitation, heatwaves, and cold waves. The dataset features global coverage, varying data volumes, and diverse data sources with different spatial, temporal, and spectral characteristics. To broaden the real-world impact of FMs, we include multiple challenging ML tasks that are closely aligned with operational needs in extreme events detection, monitoring, and forecasting. ExEBench aims to (1) assess FM generalizability across diverse, high-impact tasks and domains, (2) promote the development of novel ML methods that benefit disaster management, and (3) offer a platform for analyzing the interactions and cascading effects of extreme events to advance our understanding of Earth system, especially under the climate change expected in the decades to come. The dataset and code are public https://github.com/zhaoshan2/EarthExtreme-Bench.
Authors: Wenzhen Yue, Yong Liu, Haoxuan Li, Hao Wang, Xianghua Ying, Ruohao Guo, Bowei Xing, Ji Shi
Abstract: This paper presents $\mathbf{OLinear}$, a $\mathbf{linear}$-based multivariate time series forecasting model that operates in an $\mathbf{o}$rthogonally transformed domain. Recent forecasting models typically adopt the temporal forecast (TF) paradigm, which directly encode and decode time series in the time domain. However, the entangled step-wise dependencies in series data can hinder the performance of TF. To address this, some forecasters conduct encoding and decoding in the transformed domain using fixed, dataset-independent bases (e.g., sine and cosine signals in the Fourier transform). In contrast, we utilize $\mathbf{OrthoTrans}$, a data-adaptive transformation based on an orthogonal matrix that diagonalizes the series' temporal Pearson correlation matrix. This approach enables more effective encoding and decoding in the decorrelated feature domain and can serve as a plug-in module to enhance existing forecasters. To enhance the representation learning for multivariate time series, we introduce a customized linear layer, $\mathbf{NormLin}$, which employs a normalized weight matrix to capture multivariate dependencies. Empirically, the NormLin module shows a surprising performance advantage over multi-head self-attention, while requiring nearly half the FLOPs. Extensive experiments on 24 benchmarks and 140 forecasting tasks demonstrate that OLinear consistently achieves state-of-the-art performance with high efficiency. Notably, as a plug-in replacement for self-attention, the NormLin module consistently enhances Transformer-based forecasters. The code and datasets are available at https://anonymous.4open.science/r/OLinear
Authors: Yaxi Hu, Bernhard Sch\"olkopf, Amartya Sanyal
Abstract: We formalize the problem of online learning-unlearning, where a model is updated sequentially in an online setting while accommodating unlearning requests between updates. After a data point is unlearned, all subsequent outputs must be statistically indistinguishable from those of a model trained without that point. We present two online learner-unlearner (OLU) algorithms, both built upon online gradient descent (OGD). The first, passive OLU, leverages OGD's contractive property and injects noise when unlearning occurs, incurring no additional computation. The second, active OLU, uses an offline unlearning algorithm that shifts the model toward a solution excluding the deleted data. Under standard convexity and smoothness assumptions, both methods achieve regret bounds comparable to those of standard OGD, demonstrating that one can maintain competitive regret bounds while providing unlearning guarantees.
Authors: Xiang Li, Bhavani Thuraisingham, Wenqi Wei
Abstract: Recent legal frameworks have mandated the right to be forgotten, obligating the removal of specific data upon user requests. Machine Unlearning has emerged as a promising solution by selectively removing learned information from machine learning models. This paper presents MUBox, a comprehensive platform designed to evaluate unlearning methods in deep learning. MUBox integrates 23 advanced unlearning techniques, tested across six practical scenarios with 11 diverse evaluation metrics. It allows researchers and practitioners to (1) assess and compare the effectiveness of different machine unlearning methods across various scenarios; (2) examine the impact of current evaluation metrics on unlearning performance; and (3) conduct detailed comparative studies on machine unlearning in a unified framework. Leveraging MUBox, we systematically evaluate these unlearning methods in deep learning and uncover several key insights: (a) Even state-of-the-art unlearning methods, including those published in top-tier venues and winners of unlearning competitions, demonstrate inconsistent effectiveness across diverse scenarios. Prior research has predominantly focused on simplified settings, such as random forgetting and class-wise unlearning, highlighting the need for broader evaluations across more difficult unlearning tasks. (b) Assessing unlearning performance remains a non-trivial problem, as no single evaluation metric can comprehensively capture the effectiveness, efficiency, and preservation of model utility. Our findings emphasize the necessity of employing multiple metrics to achieve a balanced and holistic assessment of unlearning methods. (c) In the context of depoisoning, our evaluation reveals significant variability in the effectiveness of existing approaches, which is highly dependent on the specific type of poisoning attacks.
Authors: Amirhossein Javaheri, Daniel P. Palomar
Abstract: There are various approaches to graph learning for data clustering, incorporating different spectral and structural constraints through diverse graph structures. Some methods rely on bipartite graph models, where nodes are divided into two classes: centers and members. These models typically require access to data for the center nodes in addition to observations from the member nodes. However, such additional data may not always be available in many practical scenarios. Moreover, popular Gaussian models for graph learning have demonstrated limited effectiveness in modeling data with heavy-tailed distributions, which are common in financial markets. In this paper, we propose a clustering method based on a bipartite graph model that addresses these challenges. First, it can infer clusters from incomplete data without requiring information about the center nodes. Second, it is designed to effectively handle heavy-tailed data. Numerical experiments using real financial data validate the efficiency of the proposed method for data clustering.
Authors: Sarmad Mehrdad, Avadesh Meduri, Ludovic Righetti
Abstract: We present an iterative inverse reinforcement learning algorithm to infer optimal cost functions in continuous spaces. Based on a popular maximum entropy criteria, our approach iteratively finds a weight improvement step and proposes a method to find an appropriate step size that ensures learned cost function features remain similar to the demonstrated trajectory features. In contrast to similar approaches, our algorithm can individually tune the effectiveness of each observation for the partition function and does not need a large sample set, enabling faster learning. We generate sample trajectories by solving an optimal control problem instead of random sampling, leading to more informative trajectories. The performance of our method is compared to two state of the art algorithms to demonstrate its benefits in several simulated environments.
Authors: Shuai Han, Mehdi Dastani, Shihan Wang
Abstract: Training cooperative agents in sparse-reward scenarios poses significant challenges for multi-agent reinforcement learning (MARL). Without clear feedback on actions at each step in sparse-reward setting, previous methods struggle with precise credit assignment among agents and effective exploration. In this paper, we introduce a novel method to deal with both credit assignment and exploration problems in reward-sparse domains. Accordingly, we propose an algorithm that calculates the Influence Scope of Agents (ISA) on states by taking specific value of the dimensions/attributes of states that can be influenced by individual agents. The mutual dependence between agents' actions and state attributes are then used to calculate the credit assignment and to delimit the exploration space for each individual agent. We then evaluate ISA in a variety of sparse-reward multi-agent scenarios. The results show that our method significantly outperforms the state-of-art baselines.
Authors: Frederico Vicente, Cl\'audia Soares, Du\v{s}an Jakoveti\'c
Abstract: Federated Learning (FL) enables distributed machine learning training while preserving privacy, representing a paradigm shift for data-sensitive and decentralized environments. Despite its rapid advancements, FL remains a complex and multifaceted field, requiring a structured understanding of its methodologies, challenges, and applications. In this survey, we introduce a meta-framework perspective, conceptualising FL as a composition of modular components that systematically address core aspects such as communication, optimisation, security, and privacy. We provide a historical contextualisation of FL, tracing its evolution from distributed optimisation to modern distributed learning paradigms. Additionally, we propose a novel taxonomy distinguishing Aggregation from Alignment, introducing the concept of alignment as a fundamental operator alongside aggregation. To bridge theory with practice, we explore available FL frameworks in Python, facilitating real-world implementation. Finally, we systematise key challenges across FL sub-fields, providing insights into open research questions throughout the meta-framework modules. By structuring FL within a meta-framework of modular components and emphasising the dual role of Aggregation and Alignment, this survey provides a holistic and adaptable foundation for understanding and advancing FL research and deployment.
Authors: Hangwei Zhang, Zhimu Huang, Yan Wang
Abstract: Kolmogorov-Arnold Networks (KANs) have recently shown promise for solving partial differential equations (PDEs). Yet their original formulation is computationally and memory intensive, motivating the introduction of Chebyshev Type-I-based KANs (Chebyshev1KANs). Although Chebyshev1KANs have outperformed the vanilla KANs architecture, our rigorous theoretical analysis reveals that they still suffer from rank collapse, ultimately limiting their expressive capacity. To overcome these limitations, we enhance Chebyshev1KANs by integrating wavelet-activated MLPs with learnable parameters and an internal attention mechanism. We prove that this design preserves a full-rank Jacobian and is capable of approximating solutions to PDEs of arbitrary order. Furthermore, to alleviate the loss instability and imbalance introduced by the Chebyshev polynomial basis, we externally incorporate a Residual Gradient Attention (RGA) mechanism that dynamically re-weights individual loss terms according to their gradient norms and residual magnitudes. By jointly leveraging internal and external attention, we present AC-PKAN, a novel architecture that constitutes an enhancement to weakly supervised Physics-Informed Neural Networks (PINNs) and extends the expressive power of KANs. Experimental results from nine benchmark tasks across three domains show that AC-PKAN consistently outperforms or matches state-of-the-art models such as PINNsFormer, establishing it as a highly effective tool for solving complex real-world engineering problems in zero-data or data-sparse regimes. The code will be made publicly available upon acceptance.
Authors: Yang Su, Na Yan, Yansha Deng, Robert Schober
Abstract: Large language models (LLMs) hosted on cloud servers alleviate the computational and storage burdens on local devices but raise privacy concerns due to sensitive data transmission and require substantial communication bandwidth, which is challenging in constrained environments. In contrast, small language models (SLMs) running locally enhance privacy but suffer from limited performance on complex tasks. To balance computational cost, performance, and privacy protection under bandwidth constraints, we propose a privacy-aware wireless collaborative mixture of experts (PWC-MoE) framework. Specifically, PWC-MoE employs a sparse privacy-aware gating network to dynamically route sensitive tokens to privacy experts located on local clients, while non-sensitive tokens are routed to non-privacy experts located at the remote base station. To achieve computational efficiency, the gating network ensures that each token is dynamically routed to and processed by only one expert. To enhance scalability and prevent overloading of specific experts, we introduce a group-wise load-balancing mechanism for the gating network that evenly distributes sensitive tokens among privacy experts and non-sensitive tokens among non-privacy experts. To adapt to bandwidth constraints while preserving model performance, we propose a bandwidth-adaptive and importance-aware token offloading scheme. This scheme incorporates an importance predictor to evaluate the importance scores of non-sensitive tokens, prioritizing the most important tokens for transmission to the base station based on their predicted importance and the available bandwidth. Experiments demonstrate that the PWC-MoE framework effectively preserves privacy and maintains high performance even in bandwidth-constrained environments, offering a practical solution for deploying LLMs in privacy-sensitive and bandwidth-limited scenarios.
Authors: Fangyuan Yu
Abstract: We prove theoretically that generalization improves not only through data scaling but also by compressing internal representations. To operationalize this insight, we introduce the Information Bottleneck Language Modeling (IBLM) objective, which reframes language modeling as a constrained optimization problem: minimizing representation entropy subject to optimal prediction performance. Empirically, we observe an emergent memorization-compression cycle during LLM pretraining, evidenced by oscillation positive/negative gradient alignment between cross-entropy and Matrix-Based Entropy (MBE), a measure of representation entropy. This pattern closely mirrors the predictive-compressive trade-off prescribed by IBLM and also parallels the biological alternation between awake learning and sleep consolidation. Motivated by this observation, we propose Gated Phase Transition (GAPT), a training algorithm that adaptively switches between memorization and compression phases. When applied to GPT-2 pretraining on FineWeb dataset, GAPT reduces MBE by 50% and improves cross-entropy by 4.8%. GAPT improves OOD generalizatino by 35% in a pretraining task on arithmetic multiplication. In a setting designed to simulate catastrophic forgetting, GAPT reduces interference by compressing and separating representations, achieving a 97% improvement in separation - paralleling the functional role of sleep consolidation.
Authors: Mingjun Pan, Guanquan Lin, You-Wei Luo, Bin Zhu, Zhien Dai, Lijun Sun, Chun Yuan
Abstract: Reinforcement Learning (RL) has emerged as a powerful tool for neural combinatorial optimization, enabling models to learn heuristics that solve complex problems without requiring expert knowledge. Despite significant progress, existing RL approaches face challenges such as diminishing reward signals and inefficient exploration in vast combinatorial action spaces, leading to inefficiency. In this paper, we propose Preference Optimization, a novel method that transforms quantitative reward signals into qualitative preference signals via statistical comparison modeling, emphasizing the superiority among sampled solutions. Methodologically, by reparameterizing the reward function in terms of policy and utilizing preference models, we formulate an entropy-regularized RL objective that aligns the policy directly with preferences while avoiding intractable computations. Furthermore, we integrate local search techniques into the fine-tuning rather than post-processing to generate high-quality preference pairs, helping the policy escape local optima. Empirical results on various benchmarks, such as the Traveling Salesman Problem (TSP), the Capacitated Vehicle Routing Problem (CVRP) and the Flexible Flow Shop Problem (FFSP), demonstrate that our method significantly outperforms existing RL algorithms, achieving superior convergence efficiency and solution quality.
Authors: James Giroux, Cristiano Fanelli
Abstract: We present a (proto) Foundation Model for Nuclear Physics, capable of operating on low-level detector inputs from Imaging Cherenkov Detectors at the future Electron Ion Collider. To address limitations in existing next-token prediction approaches-namely resolution loss from VQ-VAE tokenization and lack of conditional generation-we propose three key innovations: (i) separate vocabularies for discrete spatial features and continuous variates, combined via Causal Multi-Head Cross-Attention (CMHCA), (ii) continuous kinematic conditioning through prepended context embeddings, and (iii) scalable and simple, high-resolution continuous variate tokenization without joint vocabulary inflation. Our model enables fast, high-fidelity generation of pixel and time sequences for Cherenkov photons, validated through closure tests in the High Performance DIRC. We also show our model generalizes to reconstruction tasks such as pion and kaon identification, in which we show its ability to leverage fine-tuning.
Authors: Abdolmehdi Behroozi, Chaopeng Shen and, Daniel Kifer
Abstract: Parametric differential equations of the form du/dt = f(u, x, t, p) are fundamental in science and engineering. While deep learning frameworks such as the Fourier Neural Operator (FNO) can efficiently approximate solutions, they struggle with inverse problems, sensitivity estimation (du/dp), and concept drift. We address these limitations by introducing a sensitivity-based regularization strategy, called Sensitivity-Constrained Fourier Neural Operators (SC-FNO). SC-FNO achieves high accuracy in predicting solution paths and consistently outperforms standard FNO and FNO with physics-informed regularization. It improves performance in parameter inversion tasks, scales to high-dimensional parameter spaces (tested with up to 82 parameters), and reduces both data and training requirements. These gains are achieved with a modest increase in training time (30% to 130% per epoch) and generalize across various types of differential equations and neural operators. Code and selected experiments are available at: https://github.com/AMBehroozi/SC_Neural_Operators
Authors: Fanyu Meng, Ziwen Kan, Shahbaz Rezaei, Zhaodan Kong, Xin Chen, Xin Liu
Abstract: Explainability in time series models is crucial for fostering trust, facilitating debugging, and ensuring interpretability in real-world applications. In this work, we introduce Implet, a novel post-hoc explainer that generates accurate and concise subsequence-level explanations for time series models. Our approach identifies critical temporal segments that significantly contribute to the model's predictions, providing enhanced interpretability beyond traditional feature-attribution methods. Based on it, we propose a cohort-based (group-level) explanation framework designed to further improve the conciseness and interpretability of our explanations. We evaluate Implet on several standard time-series classification benchmarks, demonstrating its effectiveness in improving interpretability. The code is available at https://github.com/LbzSteven/implet
Authors: Suhan Guo, Jiahong Deng, Mengjun Yi, Furao Shen, Jian Zhao
Abstract: Attention-based architectures have achieved superior performance in multivariate time series forecasting but are computationally expensive. Techniques such as patching and adaptive masking have been developed to reduce their sizes and latencies. In this work, we propose a structured pruning method, SPAT ($\textbf{S}$ensitivity $\textbf{P}$runer for $\textbf{At}$tention), which selectively removes redundant attention mechanisms and yields highly effective models. Different from previous approaches, SPAT aims to remove the entire attention module, which reduces the risk of overfitting and enables speed-up without demanding specialized hardware. We propose a dynamic sensitivity metric, $\textbf{S}$ensitivity $\textbf{E}$nhanced $\textbf{N}$ormalized $\textbf{D}$ispersion (SEND) that measures the importance of each attention module during the pre-training phase. Experiments on multivariate datasets demonstrate that SPAT-pruned models achieve reductions of 2.842% in MSE, 1.996% in MAE, and 35.274% in FLOPs. Furthermore, SPAT-pruned models outperform existing lightweight, Mamba-based and LLM-based SOTA methods in both standard and zero-shot inference, highlighting the importance of retaining only the most effective attention mechanisms. We have made our code publicly available https://anonymous.4open.science/r/SPAT-6042.
Authors: Junghoon Justin Park, Jiook Cha, Samuel Yen-Chi Chen, Huan-Hsin Tseng, Shinjae Yoo
Abstract: Quantum Machine Learning (QML) holds significant promise for solving computational challenges across diverse domains. However, its practical deployment is constrained by the limitations of noisy intermediate-scale quantum (NISQ) devices, including noise, limited scalability, and trainability issues in variational quantum circuits (VQCs). We introduce the multi-chip ensemble VQC framework, which partitions high-dimensional computations across smaller quantum chips to enhance scalability, trainability, and noise resilience. We show that this approach mitigates barren plateaus, reduces quantum error bias and variance, and maintains robust generalization through controlled entanglement. Designed to align with current and emerging quantum hardware, the framework demonstrates strong potential for enabling scalable QML on near-term devices, as validated by experiments on standard benchmark datasets (MNIST, FashionMNIST, CIFAR-10) and real world dataset (PhysioNet EEG).
Authors: Shanda Li, Tanya Marwah, Junhong Shen, Weiwei Sun, Andrej Risteski, Yiming Yang, Ameet Talwalkar
Abstract: Partial differential equations (PDEs) are fundamental to modeling physical systems, yet solving them remains a complex challenge. Traditional numerical solvers rely on expert knowledge to implement and are computationally expensive, while neural-network-based solvers require large training datasets and often lack interpretability. In this work, we frame PDE solving as a code generation task and introduce CodePDE, the first inference framework for generating PDE solvers using large language models (LLMs). Leveraging advanced inference-time algorithms and scaling strategies, CodePDE unlocks critical capacities of LLM for PDE solving: reasoning, debugging, selfrefinement, and test-time scaling -- all without task-specific tuning. CodePDE achieves superhuman performance across a range of representative PDE problems. We also present a systematic empirical analysis of LLM generated solvers, analyzing their accuracy, efficiency, and numerical scheme choices. Our findings highlight the promise and the current limitations of LLMs in PDE solving, offering a new perspective on solver design and opportunities for future model development. Our code is available at https://github.com/LithiumDA/CodePDE.
Authors: Lakshit Arora, Sanjay Surendranath Girija, Shashank Kapoor, Aman Raj, Dipen Pradhan, Ankit Shetgaonkar
Abstract: Artificial Intelligence (AI) is rapidly expanding and integrating more into daily life to automate tasks, guide decision making, and enhance efficiency. However, complex AI models, which make decisions without providing clear explanations (known as the "black-box problem"), currently restrict trust and widespread adoption of AI. Explainable Artificial Intelligence (XAI) has emerged to address the black-box problem of making AI systems more interpretable and transparent so stakeholders can trust, verify, and act upon AI-based outcomes. Researchers have developed various techniques to foster XAI in the Software Development Lifecycle. However, there are gaps in applying XAI techniques in the Software Engineering phases. Literature review shows that 68% of XAI in Software Engineering research is focused on maintenance as opposed to 8% on software management and requirements. In this paper, we present a comprehensive survey of the applications of XAI methods such as concept-based explanations, Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), rule extraction, attention mechanisms, counterfactual explanations, and example-based explanations to the different phases of the Software Development Life Cycle (SDLC), including requirements elicitation, design and development, testing and deployment, and evolution. To the best of our knowledge, this paper presents the first comprehensive survey of XAI techniques for every phase of the Software Development Life Cycle (SDLC). This survey aims to promote explainable AI in Software Engineering and facilitate the practical application of complex AI models in AI-driven software development.
Authors: M. J. Nadjafi Arani, S. Sorgun, M. Mirzargar
Abstract: This study conducts a Quantitative Structure Property Relationship (QSPR) analysis to explore the correlation between the physical properties of drug molecules and their topological indices using machine learning techniques. While prior studies in drug design have focused on degree-based topological indices, this work analyzes a dataset of 166 drug molecules by computing degree-distance-based topological indices, incorporating vertex-edge weightings with respect to different six atomic properties (atomic number, atomic radius, atomic mass, density, electronegativity, ionization). Both linear models (Linear Regression, Lasso, and Ridge Regression) and nonlinear approaches (Random Forest, XGBoost, and Neural Networks) were employed to predict molecular properties. The results demonstrate the effectiveness of these indices in predicting specific physicochemical properties and underscore the practical relevance of computational methods in molecular property estimation. The study provides an innovative perspective on integrating topological indices with machine learning to enhance predictive accuracy, highlighting their potential application in drug discovery and development processes. This predictive may also explain that establishing a reliable relationship between topological indices and physical properties enables chemists to gain preliminary insights into molecular behavior before conducting experimental analyses, thereby optimizing resource utilization in cheminformatics research.
Authors: Hoang Tran, Zezhong Zhang, Feng Bao, Dan Lu, Guannan Zhang
Abstract: We propose a hybrid generative model for efficient sampling of high-dimensional, multimodal probability distributions for Bayesian inference. Traditional Monte Carlo methods, such as the Metropolis-Hastings and Langevin Monte Carlo sampling methods, are effective for sampling from single-mode distributions in high-dimensional spaces. However, these methods struggle to produce samples with the correct proportions for each mode in multimodal distributions, especially for distributions with well separated modes. To address the challenges posed by multimodality, we adopt a divide-and-conquer strategy. We start by minimizing the energy function with initial guesses uniformly distributed within the prior domain to identify all the modes of the energy function. Then, we train a classifier to segment the domain corresponding to each mode. After the domain decomposition, we train a diffusion-model-assisted generative model for each identified mode within its support. Once each mode is characterized, we employ bridge sampling to estimate the normalizing constant, allowing us to directly adjust the ratios between the modes. Our numerical examples demonstrate that the proposed framework can effectively handle multimodal distributions with varying mode shapes in up to 100 dimensions. An application to Bayesian inverse problem for partial differential equations is also provided.
Authors: Michael Pichat, William Pogrund, Paloma Pichat, Judicael Poumay, Armanouche Gasparian, Samuel Demarchi, Martin Corbet, Alois Georgeon, Michael Veillet-Guillem
Abstract: The polysemantic nature of synthetic neurons in artificial intelligence language models is currently understood as the result of a necessary superposition of distributed features within the latent space. We propose an alternative approach, geometrically defining a neuron in layer n as a categorical vector space with a non-orthogonal basis, composed of categorical sub-dimensions extracted from preceding neurons in layer n-1. This categorical vector space is structured by the activation space of each neuron and enables, via an intra-neuronal attention process, the identification and utilization of a critical categorical zone for the efficiency of the language model - more homogeneous and located at the intersection of these different categorical sub-dimensions.
Authors: Maria-Lamprini A. Bartsioka, Ioannis A. Bartsiokas, Panagiotis K. Gkonis, Dimitra I. Kaklamani, Iakovos S. Venieris
Abstract: Advanced fifth generation (5G) and beyond (B5G) communication networks have revolutionized wireless technologies, supporting ultra-high data rates, low latency, and massive connectivity. However, they also introduce vulnerabilities, particularly in decentralized Industrial Internet of Things (IIoT) environments. Traditional cryptographic methods struggle with scalability and complexity, leading researchers to explore Artificial Intelligence (AI)-driven physical layer techniques for secure communications. In this context, this paper focuses on the utilization of Machine and Deep Learning (ML/DL) techniques to tackle with the common problem of eavesdropping detection. To this end, a simulated industrial B5G heterogeneous wireless network is used to evaluate the performance of various ML/DL models, including Random Forests (RF), Deep Convolutional Neural Networks (DCNN), and Long Short-Term Memory (LSTM) networks. These models classify users as either legitimate or malicious ones based on channel state information (CSI), position data, and transmission power. According to the presented numerical results, DCNN and RF models achieve a detection accuracy approaching 100\% in identifying eavesdroppers with zero false alarms. In general, this work underlines the great potential of combining AI and Physical Layer Security (PLS) for next-generation wireless networks in order to address evolving security threats.
Authors: Junhe Zhang, Wanli Ni, Pengwei Wang, Dongyu Wang
Abstract: The proliferation of intelligent applications at the wireless edge, alongside the exponential growth of multimodal data, poses challenges for deploying multimodal large models (MLMs) in resource-constrained networks. These constraints manifest as limited bandwidth, computational capacity, and stringent latency requirements, particularly under low signal-to-noise ratio (SNR) conditions. To overcome these limitations, we propose a token communication paradigm that facilitates the decentralized deployment of MLMs across user devices and edge infrastructure (e.g., base stations). In this paradigm, task-relevant tokens are extracted from multimodal inputs and serve as the primary medium for communication between distributed model components. To align semantics and optimize transmission efficiency, we propose a dual-pronged approach: 1) We design a contrastive split fine-tuning method to project heterogeneous modalities into a shared feature space, enabling seamless interaction between model components while preserving modal-specific semantics. 2) We employ a lightweight compression technique to reduce the size of transmitted tokens, minimizing bandwidth consumption without sacrificing task-critical information. The proposed framework integrates collaborative fine-tuning of both the foundation model and multimodal transceivers, ensuring that token generation and utilization are tailored to specific downstream tasks. Simulation experiments conducted under different SNR conditions demonstrate that our method results in a $13.7\%$ improvement in test accuracy. Furthermore, our approach exhibits quicker convergence rates, even with reduced token lengths, highlighting the promise of token communication for facilitating more scalable and resilient MLM implementations in practical multiuser networks.
Authors: HsiaoYuan Hsu, Yuxin Peng
Abstract: In poster design, content-aware layout generation is crucial for automatically arranging visual-textual elements on the given image. With limited training data, existing work focused on image-centric enhancement. However, this neglects the diversity of layouts and fails to cope with shape-variant elements or diverse design intents in generalized settings. To this end, we proposed a layout-centric approach that leverages layout knowledge implicit in large language models (LLMs) to create posters for omnifarious purposes, hence the name PosterO. Specifically, it structures layouts from datasets as trees in SVG language by universal shape, design intent vectorization, and hierarchical node representation. Then, it applies LLMs during inference to predict new layout trees by in-context learning with intent-aligned example selection. After layout trees are generated, we can seamlessly realize them into poster designs by editing the chat with LLMs. Extensive experimental results have demonstrated that PosterO can generate visually appealing layouts for given images, achieving new state-of-the-art performance across various benchmarks. To further explore PosterO's abilities under the generalized settings, we built PStylish7, the first dataset with multi-purpose posters and various-shaped elements, further offering a challenging test for advanced research.
Authors: Ali Senol, Garima Agrawal, Huan Liu
Abstract: Detecting fake interactions in digital communication platforms remains a challenging and insufficiently addressed problem. These interactions may appear as harmless spam or escalate into sophisticated scam attempts, making it difficult to flag malicious intent early. Traditional detection methods often rely on static anomaly detection techniques that fail to adapt to dynamic conversational shifts. One key limitation is the misinterpretation of benign topic transitions referred to as concept drift as fraudulent behavior, leading to either false alarms or missed threats. We propose a two stage detection framework that first identifies suspicious conversations using a tailored ensemble classification model. To improve the reliability of detection, we incorporate a concept drift analysis step using a One Class Drift Detector (OCDD) to isolate conversational shifts within flagged dialogues. When drift is detected, a large language model (LLM) assesses whether the shift indicates fraudulent manipulation or a legitimate topic change. In cases where no drift is found, the behavior is inferred to be spam like. We validate our framework using a dataset of social engineering chat scenarios and demonstrate its practical advantages in improving both accuracy and interpretability for real time fraud detection. To contextualize the trade offs, we compare our modular approach against a Dual LLM baseline that performs detection and judgment using different language models.
Authors: Daniel Franzen, Jan Disselhoff, David Hartmann
Abstract: The Abstraction and Reasoning Corpus (ARC-AGI) poses a significant challenge for large language models (LLMs), exposing limitations in their abstract reasoning abilities. In this work, we leverage task-specific data augmentations throughout the training, generation, and scoring phases, and employ a depth-first search algorithm to generate diverse, high-probability candidate solutions. Furthermore, we utilize the LLM not only as a generator but also as a scorer, using its output probabilities to select the most promising solutions. Our method achieves a score of 71.6% (286.5/400 solved tasks) on the public ARC-AGI evaluation set, demonstrating state-of-the-art performance among publicly available approaches. While concurrent closed-source work has reported higher scores, our method distinguishes itself through its transparency, reproducibility, and remarkably low inference cost, averaging only around 2ct per task on readily available hardware (we assume a price of 36ct/hour for a Nvidia 4090 GPU).
Authors: Harry Dong, Bilge Acun, Beidi Chen, Yuejie Chi
Abstract: Due to long generations, large language model (LLM) math reasoning demands significant computational resources and time. While many existing efficient inference methods have been developed with excellent performance preservation on language tasks, they often severely degrade math performance. In this paper, we propose Caprese, a low-cost distillation method to recover lost capabilities from deploying efficient inference methods, focused primarily in feedforward blocks. With original weights unperturbed, roughly 1% of additional parameters, and only 20K synthetic training samples, we are able to recover much if not all of the math capabilities lost from efficient inference for thinking LLMs and without harm to language tasks for instruct LLMs. Moreover, Caprese slashes the number of active parameters (~2B cut for Gemma 2 9B and Llama 3.1 8B) and integrates cleanly into existing model layers to reduce latency (>11% reduction to generate 2048 tokens with Qwen 2.5 14B) while encouraging response brevity.
Authors: Qian Xu, Lei Zhang, Yixiao Liu
Abstract: Connected Autonomous Vehicles (CAVs) operate in dynamic, open, and multi-domain networks, rendering them vulnerable to various threats. Trust Management Systems (TMS) systematically organize essential steps in the trust mechanism, identifying malicious nodes against internal threats and external threats, as well as ensuring reliable decision-making for more cooperative tasks. Recent advances in machine learning (ML) offer significant potential to enhance TMS, especially for the strict requirements of CAVs, such as CAV nodes moving at varying speeds, and opportunistic and intermittent network behavior. Those features distinguish ML-based TMS from social networks, static IoT, and Social IoT. This survey proposes a novel three-layer ML-based TMS framework for CAVs in the vehicle-road-cloud integration system, i.e., trust data layer, trust calculation layer and trust incentive layer. A six-dimensional taxonomy of objectives is proposed. Furthermore, the principles of ML methods for each module in each layer are analyzed. Then, recent studies are categorized based on traffic scenarios that are against the proposed objectives. Finally, future directions are suggested, addressing the open issues and meeting the research trend. We maintain an active repository that contains up-to-date literature and open-source projects at https://github.com/octoberzzzzz/ML-based-TMS-CAV-Survey.
URLs: https://github.com/octoberzzzzz/ML-based-TMS-CAV-Survey.
Authors: S. E Emedem, I. E Onyenwe, E. G Onyedinma
Abstract: Named Entity Recognition NER is very crucial for various natural language processing applications, including information extraction, machine translation, and sentiment analysis. Despite the ever-increasing interest in African languages within computational linguistics, existing NER systems focus mainly on English, European, and a few other global languages, leaving a significant gap for under-resourced languages. This research presents the development of a WAZOBIA-NER system tailored for the three most prominent Nigerian languages: Hausa, Yoruba, and Igbo. This research begins with a comprehensive compilation of annotated datasets for each language, addressing data scarcity and linguistic diversity challenges. Exploring the state-of-the-art machine learning technique, Conditional Random Fields (CRF) and deep learning models such as Bidirectional Long Short-Term Memory (BiLSTM), Bidirectional Encoder Representation from Transformers (Bert) and fine-tune with a Recurrent Neural Network (RNN), the study evaluates the effectiveness of these approaches in recognizing three entities: persons, organizations, and locations. The system utilizes optical character recognition (OCR) technology to convert textual images into machine-readable text, thereby enabling the Wazobia system to accept both input text and textual images for extraction purposes. The system achieved a performance of 0.9511 in precision, 0.9400 in recall, 0.9564 in F1-score, and 0.9301 in accuracy. The model's evaluation was conducted across three languages, with precision, recall, F1-score, and accuracy as key assessment metrics. The Wazobia-NER system demonstrates that it is feasible to build robust NER tools for under-resourced African languages using current NLP frameworks and transfer learning.
Authors: Lei Lei (Sherman), Kan Zheng (Sherman), Jie Mei (Sherman), Xuemin (Sherman), Shen
Abstract: The vision of sixth-generation (6G) wireless networks paves the way for the seamless integration of digital twins into vehicular networks, giving rise to a Vehicular Digital Twin Network (VDTN). The large amount of computing resources as well as the massive amount of spatial-temporal data in Digital Twin (DT) domain can be utilized to enhance the communication and control performance of Internet of Vehicle (IoV) systems. In this article, we first propose the architecture of VDTN, emphasizing key modules that center on functions related to the joint optimization of control and communication. We then delve into the intricacies of the multitimescale decision process inherent in joint optimization in VDTN, specifically investigating the dynamic interplay between control and communication. To facilitate the joint optimization, we define two Value of Information (VoI) concepts rooted in control performance. Subsequently, utilizing VoI as a bridge between control and communication, we introduce a novel joint optimization framework, which involves iterative processing of two Deep Reinforcement Learning (DRL) modules corresponding to control and communication to derive the optimal policy. Finally, we conduct simulations of the proposed framework applied to a platoon scenario to demonstrate its effectiveness in ensu
Authors: Zhenzhou Jin, Li You, Xudong Li, Zhen Gao, Yuanwei Liu, Xiang-Gen Xia, Xiqi Gao
Abstract: Accurate channel state information (CSI) acquisition for massive multiple-input multiple-output (MIMO) systems is essential for future mobile communication networks. Channel fingerprint (CF), also referred to as channel knowledge map, is a key enabler for intelligent environment-aware communication and can facilitate CSI acquisition. However, due to the cost limitations of practical sensing nodes and test vehicles, the resulting CF is typically coarse-grained, making it insufficient for wireless transceiver design. In this work, we introduce the concept of CF twins and design a conditional generative diffusion model (CGDM) with strong implicit prior learning capabilities as the computational core of the CF twin to establish the connection between coarse- and fine-grained CFs. Specifically, we employ a variational inference technique to derive the evidence lower bound (ELBO) for the log-marginal distribution of the observed fine-grained CF conditioned on the coarse-grained CF, enabling the CGDM to learn the complicated distribution of the target data. During the denoising neural network optimization, the coarse-grained CF is introduced as side information to accurately guide the conditioned generation of the CGDM. To make the proposed CGDM lightweight, we further leverage the additivity of network layers and introduce a one-shot pruning approach along with a multi-objective knowledge distillation technique. Experimental results show that the proposed approach exhibits significant improvement in reconstruction performance compared to the baselines. Additionally, zero-shot testing on reconstruction tasks with different magnification factors further demonstrates the scalability and generalization ability of the proposed approach.
Authors: Zhenzhou Jin, Li You, Xiang-Gen Xia, Xiqi Gao
Abstract: The paradigm shift from environment-unaware communication to intelligent environment-aware communication is expected to facilitate the acquisition of channel state information for future wireless communications. Channel Fingerprint (CF), as an emerging enabling technology for environment-aware communication, provides channel-related knowledge for potential locations within the target communication area. However, due to the limited availability of practical devices for sensing environmental information and measuring channel-related knowledge, most of the acquired environmental information and CF are coarse-grained, insufficient to guide the design of wireless transmissions. To address this, this paper proposes a deep conditional generative learning approach, namely a customized conditional generative diffusion model (CDiff). The proposed CDiff simultaneously refines environmental information and CF, reconstructing a fine-grained CF that incorporates environmental information, referred to as EnvCF, from its coarse-grained counterpart. Experimental results show that the proposed approach significantly improves the performance of EnvCF construction compared to the baselines.
Authors: Erwin Daniel L\'opez Zapata, Cheng Tang, Valdemar \v{S}v\'abensk\'y, Fumiya Okubo, Atsushi Shimada
Abstract: Educational e-book platforms provide valuable information to teachers and researchers through two main sources: reading activity data and reading content data. While reading activity data is commonly used to analyze learning strategies and predict low-performing students, reading content data is often overlooked in these analyses. To address this gap, this study proposes LECTOR (Lecture slides and Topic Relationships), a model that summarizes information from reading content in a format that can be easily integrated with reading activity data. Our first experiment compared LECTOR to representative Natural Language Processing (NLP) models in extracting key information from 2,255 lecture slides, showing an average improvement of 5% in F1-score. These results were further validated through a human evaluation involving 28 students, which showed an average improvement of 21% in F1-score over a model predominantly used in current educational tools. Our second experiment compared reading preferences extracted by LECTOR with traditional reading activity data in predicting low-performing students using 600,712 logs from 218 students. The results showed a tendency to improve the predictive performance by integrating LECTOR. Finally, we proposed examples showing the potential application of the reading preferences extracted by LECTOR in designing personalized interventions for students.
Authors: Ruikun Hou, Babette B\"uhler, Tim F\"utterer, Efe Bozkir, Peter Gerjets, Ulrich Trautwein, Enkelejda Kasneci
Abstract: Classroom discourse is an essential vehicle through which teaching and learning take place. Assessing different characteristics of discursive practices and linking them to student learning achievement enhances the understanding of teaching quality. Traditional assessments rely on manual coding of classroom observation protocols, which is time-consuming and costly. Despite many studies utilizing AI techniques to analyze classroom discourse at the utterance level, investigations into the evaluation of discursive practices throughout an entire lesson segment remain limited. To address this gap, our study proposes a novel text-centered multimodal fusion architecture to assess the quality of three discourse components grounded in the Global Teaching InSights (GTI) observation protocol: Nature of Discourse, Questioning, and Explanations. First, we employ attention mechanisms to capture inter- and intra-modal interactions from transcript, audio, and video streams. Second, a multi-task learning approach is adopted to jointly predict the quality scores of the three components. Third, we formulate the task as an ordinal classification problem to account for rating level order. The effectiveness of these designed elements is demonstrated through an ablation study on the GTI Germany dataset containing 92 videotaped math lessons. Our results highlight the dominant role of text modality in approaching this task. Integrating acoustic features enhances the model's consistency with human ratings, achieving an overall Quadratic Weighted Kappa score of 0.384, comparable to human inter-rater reliability (0.326). Our study lays the groundwork for the future development of automated discourse quality assessment to support teacher professional development through timely feedback on multidimensional discourse practices.
Authors: Geunho Choi, Changhwan Lee, Jieun Kim, Insoo Ye, Keeyoung Jung, Inchul Park
Abstract: Microstructure often dictates materials performance, yet it is rarely treated as an explicit design variable because microstructure is hard to quantify, predict, and optimize. Here, we introduce an image centric, closed-loop framework that makes microstructural morphology into a controllable objective and demonstrate its use case with Li- and Mn-rich layered oxide cathode precursors. This work presents an integrated, AI driven framework for the predictive design and optimization of lithium-ion battery cathode precursor synthesis. This framework integrates a diffusion-based image generation model, a quantitative image analysis pipeline, and a particle swarm optimization (PSO) algorithm. By extracting key morphological descriptors such as texture, sphericity, and median particle size (D50) from SEM images, the platform accurately predicts SEM like morphologies resulting from specific coprecipitation conditions, including reaction time-, solution concentration-, and pH-dependent structural changes. Optimization then pinpoints synthesis parameters that yield user defined target morphologies, as experimentally validated by the close agreement between predicted and synthesized structures. This framework offers a practical strategy for data driven materials design, enabling both forward prediction and inverse design of synthesis conditions and paving the way toward autonomous, image guided microstructure engineering.
Authors: Linus Stuhlmann, Michael Alexander Saxer, Jonathan F\"urst
Abstract: Biomedical question-answering (QA) systems require effective retrieval and generation components to ensure accuracy, efficiency, and scalability. This study systematically examines a Retrieval-Augmented Generation (RAG) system for biomedical QA, evaluating retrieval strategies and response time trade-offs. We first assess state-of-the-art retrieval methods, including BM25, BioBERT, MedCPT, and a hybrid approach, alongside common data stores such as Elasticsearch, MongoDB, and FAISS, on a ~10% subset of PubMed (2.4M documents) to measure indexing efficiency, retrieval latency, and retriever performance in the end-to-end RAG system. Based on these insights, we deploy the final RAG system on the full 24M PubMed corpus, comparing different retrievers' impact on overall performance. Evaluations of the retrieval depth show that retrieving 50 documents with BM25 before reranking with MedCPT optimally balances accuracy (0.90), recall (0.90), and response time (1.91s). BM25 retrieval time remains stable (82ms), while MedCPT incurs the main computational cost. These results highlight previously not well-known trade-offs in retrieval depth, efficiency, and scalability for biomedical QA. With open-source code, the system is fully reproducible and extensible.
Authors: Daoze Zhang, Zhijian Bao, Sihang Du, Zhiyi Zhao, Kuangling Zhang, Dezheng Bao, Yang Yang
Abstract: Peer review is a critical component of scientific progress in the fields like AI, but the rapid increase in submission volume has strained the reviewing system, which inevitably leads to reviewer shortages and declines review quality. Besides the growing research popularity, another key factor in this overload is the repeated resubmission of substandard manuscripts, largely due to the lack of effective tools for authors to self-evaluate their work before submission. Large Language Models (LLMs) show great promise in assisting both authors and reviewers, and their performance is fundamentally limited by the quality of the peer review data. However, existing peer review datasets face three major limitations: (1) limited data diversity, (2) inconsistent and low-quality data due to the use of revised rather than initial submissions, and (3) insufficient support for tasks involving rebuttal and reviewer-author interactions. To address these challenges, we introduce the largest consistency-ensured peer review and rebuttal dataset named Re^2, which comprises 19,926 initial submissions, 70,668 review comments, and 53,818 rebuttals from 24 conferences and 21 workshops on OpenReview. Moreover, the rebuttal and discussion stage is framed as a multi-turn conversation paradigm to support both traditional static review tasks and dynamic interactive LLM assistants, providing more practical guidance for authors to refine their manuscripts and helping alleviate the growing review burden. Our data and code are available in https://anonymous.4open.science/r/ReviewBench_anon/.
Authors: Changyu Liu, Yuling Jiao, Junhui Wang, Jian Huang
Abstract: Distributionally robust optimization has become a powerful tool for prediction and decision-making under model uncertainty. By focusing on the local worst-case risk, it enhances robustness by identifying the most unfavorable distribution within a predefined ambiguity set. While extensive research has been conducted in parametric settings, studies on nonparametric frameworks remain limited. This paper studies the generalization properties of Wasserstein distributionally robust nonparametric estimators, with particular attention to the impact of model misspecification, where non-negligible discrepancies between the estimation function space and target function can impair generalization performance. We establish non-asymptotic error bounds for the excess local worst-case risk by analyzing the regularization effects induced by distributional perturbations and employing feedforward neural networks with Lipschitz constraints. These bounds illustrate how uncertainty levels and neural network structures influence generalization performance and are applicable to both Lipschitz and quadratic loss functions. Furthermore, we investigate the Lagrangian relaxation of the local worst-case risk and derive corresponding non-asymptotic error bounds for these estimators. The robustness of the proposed estimator is evaluated through simulation studies and illustrated with an application to the MNIST dataset.
Authors: Max Peter Ronecker, Matthew Foutter, Amine Elhafsi, Daniele Gammelli, Ihor Barakaiev, Marco Pavone, Daniel Watzenig
Abstract: Semantic anomalies are contextually invalid or unusual combinations of familiar visual elements that can cause undefined behavior and failures in system-level reasoning for autonomous systems. This work explores semantic anomaly detection by leveraging the semantic priors of state-of-the-art vision foundation models, operating directly on the image. We propose a framework that compares local vision embeddings from runtime images to a database of nominal scenarios in which the autonomous system is deemed safe and performant. In this work, we consider two variants of the proposed framework: one using raw grid-based embeddings, and another leveraging instance segmentation for object-centric representations. To further improve robustness, we introduce a simple filtering mechanism to suppress false positives. Our evaluations on CARLA-simulated anomalies show that the instance-based method with filtering achieves performance comparable to GPT-4o, while providing precise anomaly localization. These results highlight the potential utility of vision embeddings from foundation models for real-time anomaly detection in autonomous systems.
Authors: Dominik Baumann, Krzysztof Kowalczyk, Cristian R. Rojas, Koen Tiels, Pawel Wachel
Abstract: Applying machine learning methods to physical systems that are supposed to act in the real world requires providing safety guarantees. However, methods that include such guarantees often come at a high computational cost, making them inapplicable to large datasets and embedded devices with low computational power. In this paper, we propose CoLSafe, a computationally lightweight safe learning algorithm whose computational complexity grows sublinearly with the number of data points. We derive both safety and optimality guarantees and showcase the effectiveness of our algorithm on a seven-degrees-of-freedom robot arm.
Authors: Seyed Bagher Hashemi Natanzi, Zhicong Zhu, Bo Tang
Abstract: Adaptive beam switching in 6G networks is challenged by high frequencies, mobility, and blockage. We propose an Online Learning framework using Deep Reinforcement Learning (DRL) with an enhanced state representation (velocity and blockage history), a GRU architecture, and prioritized experience replay for real-time beam optimization. Validated via Nvidia Sionna under time-correlated blockage, our approach significantly enhances resilience in SNR, throughput, and accuracy compared to a conventional heuristic. Furthermore, the enhanced DRL agent outperforms a reactive Multi-Armed Bandit (MAB) baseline by leveraging temporal dependencies, achieving lower performance variability. This demonstrates the benefits of memory and prioritized learning for robust 6G beam management, while confirming MAB as a strong baseline.
Authors: Yutong Liu, Feng Xiao, Ziyue Zhang, Yongbin Yu, Cheng Huang, Fan Gao, Xiangxiang Wang, Ma-bao Ban, Manping Fan, Thupten Tsering, Cheng Huang, Gadeng Luosang, Renzeng Duojie, Nyima Tashi
Abstract: Multi-level Tibetan spelling correction addresses errors at both the character and syllable levels within a unified model. Existing methods focus mainly on single-level correction and lack effective integration of both levels. Moreover, there are no open-source datasets or augmentation methods tailored for this task in Tibetan. To tackle this, we propose a data augmentation approach using unlabeled text to generate multi-level corruptions, and introduce TiSpell, a semi-masked model capable of correcting both character- and syllable-level errors. Although syllable-level correction is more challenging due to its reliance on global context, our semi-masked strategy simplifies this process. We synthesize nine types of corruptions on clean sentences to create a robust training set. Experiments on both simulated and real-world data demonstrate that TiSpell, trained on our dataset, outperforms baseline models and matches the performance of state-of-the-art approaches, confirming its effectiveness.
Authors: Olivia Holguin, Rachel Donati, Seyed bagher Hashemi Natanzi, Bo Tang
Abstract: Mobile jammers pose a critical threat to 5G networks, particularly in military communications. We propose an intelligent anti-jamming framework that integrates Multiple Signal Classification (MUSIC) for high-resolution Direction-of-Arrival (DoA) estimation, Minimum Variance Distortionless Response (MVDR) beamforming for adaptive interference suppression, and machine learning (ML) to enhance DoA prediction for mobile jammers. Extensive simulations in a realistic highway scenario demonstrate that our hybrid approach achieves an average Signal-to-Noise Ratio (SNR) improvement of 9.58 dB (maximum 11.08 dB) and up to 99.8% DoA estimation accuracy. The framework's computational efficiency and adaptability to dynamic jammer mobility patterns outperform conventional anti-jamming techniques, making it a robust solution for securing 5G communications in contested environments.
Authors: Kourosh Shahnazari, Seyed Moein Ayyoubzadeh
Abstract: This study formalizes a computational model to simulate classical Persian poets' dynamics of influence through constructing a multi-dimensional similarity network. Using a rigorously curated dataset based on Ganjoor's corpus, we draw upon semantic, lexical, stylistic, thematic, and metrical features to demarcate each poet's corpus. Each is contained within weighted similarity matrices, which are then appended to generate an aggregate graph showing poet-to-poet influence. Further network investigation is carried out to identify key poets, style hubs, and bridging poets by calculating degree, closeness, betweenness, eigenvector, and Katz centrality measures. Further, for typological insight, we use the Louvain community detection algorithm to demarcate clusters of poets sharing both style and theme coherence, which correspond closely to acknowledged schools of literature like Sabk-e Hindi, Sabk-e Khorasani, and the Bazgasht-e Adabi phenomenon. Our findings provide a new data-driven view of Persian literature distinguished between canonical significance and interextual influence, thus highlighting relatively lesser-known figures who hold great structural significance. Combining computational linguistics with literary study, this paper produces an interpretable and scalable model for poetic tradition, enabling retrospective reflection as well as forward-looking research within digital humanities.
Authors: Rabia Yasa Kostas, Kahraman Kostas
Abstract: Indoor positioning systems (IPSs) are increasingly vital for location-based services in complex multi-storey environments. This study proposes a novel graph-based approach for floor separation using Wi-Fi fingerprint trajectories, addressing the challenge of vertical localization in indoor settings. We construct a graph where nodes represent Wi-Fi fingerprints, and edges are weighted by signal similarity and contextual transitions. Node2Vec is employed to generate low-dimensional embeddings, which are subsequently clustered using K-means to identify distinct floors. Evaluated on the Huawei University Challenge 2021 dataset, our method outperforms traditional community detection algorithms, achieving an accuracy of 68.97%, an F1- score of 61.99%, and an Adjusted Rand Index of 57.19%. By publicly releasing the preprocessed dataset and implementation code, this work contributes to advancing research in indoor positioning. The proposed approach demonstrates robustness to signal noise and architectural complexities, offering a scalable solution for floor-level localization.
Authors: Zitong Li, Aparna Chandramowlishwaran
Abstract: Sparse attention is a core building block in many leading neural network models, from graph-structured learning to sparse sequence modeling. It can be decomposed into a sequence of three sparse matrix operations (3S): sampled dense-dense matrix multiplication (SDDMM), softmax normalization, and sparse matrix multiplication (SpMM). Efficiently executing the 3S computational pattern on modern GPUs remains challenging due to (a) the mismatch between unstructured sparsity and tensor cores optimized for dense operations, and (b) the high cost of data movement. Previous works have optimized these sparse operations individually or addressed one of these challenges. This paper introduces Fused3S, the first fused 3S algorithm that jointly maximizes tensor core utilization and minimizes data movement. Across real-world graph datasets, Fused3S achieves $1.6- 16.3\times$ and $1.5-14\times$ speedup over state-of-the-art on H100 and A30 GPUs. Furthermore, integrating Fused3S into Graph Transformer inference accelerates end-to-end performance by $1.05-5.36\times$, consistently outperforming all 3S baselines across diverse datasets (single and batched graphs) and GPU architectures.
Authors: Luu Tung Hai, Thinh D. Le, Zhicheng Ding, Qing Tian, Truong-Son Hy
Abstract: Point cloud processing has gained significant attention due to its critical role in applications such as autonomous driving and 3D object recognition. However, deploying high-performance models like Point Transformer V3 in resource-constrained environments remains challenging due to their high computational and memory demands. This work introduces a novel distillation framework that leverages topology-aware representations and gradient-guided knowledge distillation to effectively transfer knowledge from a high-capacity teacher to a lightweight student model. Our approach captures the underlying geometric structures of point clouds while selectively guiding the student model's learning process through gradient-based feature alignment. Experimental results in the Nuscenes, SemanticKITTI, and Waymo datasets demonstrate that the proposed method achieves competitive performance, with an approximately 16x reduction in model size and a nearly 1.9x decrease in inference time compared to its teacher model. Notably, on NuScenes, our method achieves state-of-the-art performance among knowledge distillation techniques trained solely on LiDAR data, surpassing prior knowledge distillation baselines in segmentation performance. Our implementation is available publicly at: https://github.com/HySonLab/PointDistill
Authors: Mingjian Jiang, Yangjun Ruan, Luis Lastras, Pavan Kapanipathi, Tatsunori Hashimoto
Abstract: Recent advances in language model (LM) agents have demonstrated significant potential for automating complex real-world tasks. To make progress on these difficult tasks, LM agent architectures have become increasingly complex, often incorporating multi-step retrieval tools, multiple agents, and scaffolding adapted to the underlying LM. In this work, we investigate whether all of this complexity is necessary, or if parts of these scaffolds can be removed on challenging tasks like SWE-bench. We show that in the case of SWE-bench, simply putting the entire environment into the context of a long context language model (LCLM) and properly prompting the model makes it competitive with carefully tuned, complex agent scaffolds. We show that a Gemini-1.5-Pro model without any scaffolding or tools achieves 38% on SWE-Bench-Verified, comparable with approaches using carefully tuned agent scaffolds (32%). While the unscaffolded approach with Gemini-1.5-Pro falls short of the strongest agentic architectures, we demonstrate that the more capable Gemini-2.5-Pro using the same unscaffolded approach directly attains a 50.8% solve rate. Additionally, a two-stage approach combining Gemini-1.5-Pro with Claude-3.7 achieves a competitive 48.6% solve rate.
Authors: Soham Bonnerjee, Sayar Karmakar, Wei Biao Wu
Abstract: Federated Learning has gained traction in privacy-sensitive collaborative environments, with local SGD emerging as a key optimization method in decentralized settings. While its convergence properties are well-studied, asymptotic statistical guarantees beyond convergence remain limited. In this paper, we present two generalized Gaussian approximation results for local SGD and explore their implications. First, we prove a Berry-Esseen theorem for the final local SGD iterates, enabling valid multiplier bootstrap procedures. Second, motivated by robustness considerations, we introduce two distinct time-uniform Gaussian approximations for the entire trajectory of local SGD. The time-uniform approximations support Gaussian bootstrap-based tests for detecting adversarial attacks. Extensive simulations are provided to support our theoretical results.
Authors: Changshuai Wei, Phuc Nguyen, Benjamin Zelditch, Joyce Chen
Abstract: The standard A/B testing approaches are mostly based on t-test in large scale industry applications. These standard approaches however suffers from low statistical power in business settings, due to nature of small sample-size or non-Gaussian distribution or return-on-investment (ROI) consideration. In this paper, we propose several approaches to addresses these challenges: (i) regression adjustment, generalized estimating equation, Man-Whitney U and Zero-Trimmed U that addresses each of these issues separately, and (ii) a novel doubly robust generalized U that handles ROI consideration, distribution robustness and small samples in one framework. We provide theoretical results on asymptotic normality and efficiency bounds, together with insights on the efficiency gain from theoretical analysis. We further conduct comprehensive simulation studies and apply the methods to multiple real A/B tests.
Authors: Tobias Schnabel, Kiran Tomlinson, Adith Swaminathan, Jennifer Neville
Abstract: Despite their many successes, transformer-based large language models (LLMs) continue to struggle with tasks that require complex reasoning over large parts of their input. We argue that these failures arise due to capacity limits on the accurate flow of information within LLMs. To formalize this issue, we introduce the bounded attention prefix oracle (BAPO) model, a new computational framework that models bandwidth constraints on attention heads, the mechanism for internal communication in LLMs. We show that several important reasoning problems like graph reachability require high communication bandwidth for BAPOs to solve; we call these problems BAPO-hard. Our experiments corroborate our theoretical predictions: GPT-4, Claude, and Gemini succeed on BAPO-easy tasks and fail even on relatively small BAPO-hard tasks. BAPOs also reveal another benefit of chain of thought (CoT): we prove that breaking down a task using CoT can turn any BAPO-hard problem into a BAPO-easy one. Our results offer principled explanations for key LLM failures and suggest directions for architectures and inference methods that mitigate bandwidth limits.
Authors: Ninh Pham, Rasmus Pagh
Abstract: Approximation of non-linear kernels using random feature maps has become a powerful technique for scaling kernel methods to large datasets. We propose \textit{Tensor Sketch}, an efficient random feature map for approximating polynomial kernels. Given $n$ training samples in $\R^d$ Tensor Sketch computes low-dimensional embeddings in $\R^D$ in time $\BO{n(d+D \log{D})}$ making it well-suited for high-dimensional and large-scale settings. We provide theoretical guarantees on the approximation error, ensuring the fidelity of the resulting kernel function estimates. We also discuss extensions and highlight applications where Tensor Sketch serves as a central computational tool.
Authors: Sunday Oyinlola Ogundoyin, Muhammad Ikram, Hassan Jameel Asghar, Benjamin Zi Hao Zhao, Dali Kaafar
Abstract: Millions of users leverage generative pretrained transformer (GPT)-based language models developed by leading model providers for a wide range of tasks. To support enhanced user interaction and customization, many platforms-such as OpenAI-now enable developers to create and publish tailored model instances, known as custom GPTs, via dedicated repositories or application stores. These custom GPTs empower users to browse and interact with specialized applications designed to meet specific needs. However, as custom GPTs see growing adoption, concerns regarding their security vulnerabilities have intensified. Existing research on these vulnerabilities remains largely theoretical, often lacking empirical, large-scale, and statistically rigorous assessments of associated risks. In this study, we analyze 14,904 custom GPTs to assess their susceptibility to seven exploitable threats, such as roleplay-based attacks, system prompt leakage, phishing content generation, and malicious code synthesis, across various categories and popularity tiers within the OpenAI marketplace. We introduce a multi-metric ranking system to examine the relationship between a custom GPT's popularity and its associated security risks. Our findings reveal that over 95% of custom GPTs lack adequate security protections. The most prevalent vulnerabilities include roleplay-based vulnerabilities (96.51%), system prompt leakage (92.20%), and phishing (91.22%). Furthermore, we demonstrate that OpenAI's foundational models exhibit inherent security weaknesses, which are often inherited or amplified in custom GPTs. These results highlight the urgent need for enhanced security measures and stricter content moderation to ensure the safe deployment of GPT-based applications.
Authors: Jiaxiang Li, Junwei Feng, Jie Luo, Bowen Jiang, Xiangyu Zheng, Jian Lv, Keith Butler, Hanyu Liu, Congwei Xie, Yu Xie, Yanming Ma
Abstract: Understanding multicomponent complex material systems is essential for design of advanced materials for a wide range of technological applications. While state-of-the-art crystal structure prediction (CSP) methods effectively identify new structures and assess phase stability, they face fundamental limitations when applied to complex systems. This challenge stems from the combinatorial explosion of atomic configurations and the vast stoichiometric space, both of which contribute to computational demands that rapidly exceed practical feasibility. In this work, we propose a flexible and automated workflow to build a highly generalizable and data-efficient machine learning potential (MLP), effectively unlocking the full potential of CSP algorithms. The workflow is validated on both Mg-Ca-H ternary and Be-P-N-O quaternary systems, demonstrating substantial machine learning acceleration in high-throughput structural optimization and enabling the efficient identification of promising compounds. These results underscore the effectiveness of our approach in exploring complex material systems and accelerating the discovery of new multicomponent materials.
Authors: Zachary Novack, Zach Evans, Zack Zukowski, Josiah Taylor, CJ Carr, Julian Parker, Adnan Al-Sinan, Gian Marco Iodice, Julian McAuley, Taylor Berg-Kirkpatrick, Jordi Pons
Abstract: Text-to-audio systems, while increasingly performant, are slow at inference time, thus making their latency unpractical for many creative applications. We present Adversarial Relativistic-Contrastive (ARC) post-training, the first adversarial acceleration algorithm for diffusion/flow models not based on distillation. While past adversarial post-training methods have struggled to compare against their expensive distillation counterparts, ARC post-training is a simple procedure that (1) extends a recent relativistic adversarial formulation to diffusion/flow post-training and (2) combines it with a novel contrastive discriminator objective to encourage better prompt adherence. We pair ARC post-training with a number optimizations to Stable Audio Open and build a model capable of generating $\approx$12s of 44.1kHz stereo audio in $\approx$75ms on an H100, and $\approx$7s on a mobile edge-device, the fastest text-to-audio model to our knowledge.
Authors: Lhuqita Fazry, Valentino Vito
Abstract: Raindrop removal is a challenging task in image processing. Removing raindrops while relying solely on a single image further increases the difficulty of the task. Common approaches include the detection of raindrop regions in the image, followed by performing a background restoration process conditioned on those regions. While various methods can be applied for the detection step, the most common architecture used for background restoration is the Generative Adversarial Network (GAN). Recent advances in the use of diffusion models have led to state-of-the-art image inpainting techniques. In this paper, we introduce a novel technique for raindrop removal from a single image using diffusion-based image inpainting.
Authors: Jinming Hu, Hassan Nawaz, Yuting Rui, Lijie Chi, Arif Ullah, Pavlo O. Dral
Abstract: We have developed Aitomia - a platform powered by AI to assist in performing AI-driven atomistic and quantum chemical (QC) simulations. This intelligent assistant platform is equipped with chatbots and AI agents to help experts and guide non-experts in setting up and running the atomistic simulations, monitoring their computation status, analyzing the simulation results, and summarizing them for the user in text and graphical forms. We achieve these goals by exploiting fine-tuned open-source large language models (LLMs), rule-based agents, and a retrieval-augmented generation (RAG) system. Aitomia leverages the versatility of our MLatom ecosystem for AI-enhanced computational chemistry. This intelligent assistant is going to be integrated into the Aitomistic Hub and XACS online computing services, with some functionality already publicly available as described at http://mlatom.com/aitomia. Aitomia is expected to lower the barrier to performing atomistic simulations, accelerating research and development in the relevant fields.
Authors: Wangxuan Fan, Siqi Li, Doudou Zhou, Yohei Okada, Chuan Hong, Molei Liu, Nan Liu
Abstract: Explainable artificial intelligence (XAI) is essential for trustworthy machine learning (ML), particularly in high-stakes domains such as healthcare and finance. Shapley value (SV) methods provide a principled framework for feature attribution in complex models but incur high computational costs, limiting their scalability in high-dimensional settings. We propose Stochastic Iterative Momentum for Shapley Value Approximation (SIM-Shapley), a stable and efficient SV approximation method inspired by stochastic optimization. We analyze variance theoretically, prove linear $Q$-convergence, and demonstrate improved empirical stability and low bias in practice on real-world datasets. In our numerical experiments, SIM-Shapley reduces computation time by up to 85% relative to state-of-the-art baselines while maintaining comparable feature attribution quality. Beyond feature attribution, our stochastic mini-batch iterative framework extends naturally to a broader class of sample average approximation problems, offering a new avenue for improving computational efficiency with stability guarantees. Code is publicly available at https://github.com/nliulab/SIM-Shapley.
Authors: Ben Shaw, Sasidhar Kunapuli, Abram Magner, Kevin R. Moon
Abstract: Symmetry-informed machine learning can exhibit advantages over machine learning which fails to account for symmetry. Additionally, recent attention has been given to continuous symmetry discovery using vector fields which serve as infinitesimal generators for Lie group symmetries. In this paper, we extend the notion of non-affine symmetry discovery to functions defined by neural networks. We further extend work in this area by introducing symmetry enforcement of smooth models using vector fields. Finally, we extend work on symmetry discovery using vector fields by providing both theoretical and experimental material on the restriction of the symmetry search space to infinitesimal isometries.
Authors: Benjamin Westrich
Abstract: Advanced Metering Infrastructure (AMI) data from smart electric and gas meters enables valuable insights for utilities and consumers, but also raises significant privacy concerns. In California, regulatory decisions (CPUC D.11-07-056 and D.11-08-045) mandate strict privacy protections for customer energy usage data, guided by the Fair Information Practice Principles (FIPPs). We comprehensively explore solutions drawn from data anonymization, privacy-preserving machine learning (differential privacy and federated learning), synthetic data generation, and cryptographic techniques (secure multiparty computation, homomorphic encryption). This allows advanced analytics, including machine learning models, statistical and econometric analysis on energy consumption data, to be performed without compromising individual privacy. We evaluate each technique's theoretical foundations, effectiveness, and trade-offs in the context of utility data analytics, and we propose an integrated architecture that combines these methods to meet real-world needs. The proposed hybrid architecture is designed to ensure compliance with California's privacy rules and FIPPs while enabling useful analytics, from forecasting and personalized insights to academic research and econometrics, while strictly protecting individual privacy. Mathematical definitions and derivations are provided where appropriate to demonstrate privacy guarantees and utility implications rigorously. We include comparative evaluations of the techniques, an architecture diagram, and flowcharts to illustrate how they work together in practice. The result is a blueprint for utility data scientists and engineers to implement privacy-by-design in AMI data handling, supporting both data-driven innovation and strict regulatory compliance.
Authors: Yanbin Wei, Xuehao Wang, Zhan Zhuang, Yang Chen, Shuhao Chen, Yulong Zhang, Yu Zhang, James Kwok
Abstract: Message-passing graph neural networks (MPNNs) and structural features (SFs) are cornerstones for the link prediction task. However, as a common and intuitive mode of understanding, the potential of visual perception has been overlooked in the MPNN community. For the first time, we equip MPNNs with vision structural awareness by proposing an effective framework called Graph Vision Network (GVN), along with a more efficient variant (E-GVN). Extensive empirical results demonstrate that with the proposed frameworks, GVN consistently benefits from the vision enhancement across seven link prediction datasets, including challenging large-scale graphs. Such improvements are compatible with existing state-of-the-art (SOTA) methods and GVNs achieve new SOTA results, thereby underscoring a promising novel direction for link prediction.
Authors: Libin Zhu, Damek Davis, Dmitriy Drusvyatskiy, Maryam Fazel
Abstract: The impressive practical performance of neural networks is often attributed to their ability to learn low-dimensional data representations and hierarchical structure directly from data. In this work, we argue that these two phenomena are not unique to neural networks, and can be elicited from classical kernel methods. Namely, we show that the derivative of the kernel predictor can detect the influential coordinates with low sample complexity. Moreover, by iteratively using the derivatives to reweight the data and retrain kernel machines, one is able to efficiently learn hierarchical polynomials with finite leap complexity. Numerical experiments illustrate the developed theory.
Authors: Honna Shinichi, Akira Matsui
Abstract: Artwork research has long relied on human sensibility and subjective judgment, but recent developments in machine learning have enabled the quantitative assessment of features that humans could not discover. In Western paintings, comprehensive analyses have been conducted from various perspectives in conjunction with large databases, but such extensive analysis has not been sufficiently conducted for Eastern paintings. Then, we focus on Ukiyo-e, a traditional Japanese art form, as a case study of Eastern paintings, and conduct a quantitative analysis of creativity in works of art using 11,000 high-resolution images. This involves using the concept of calculating creativity from networks to analyze both the creativity of the artwork and that of the artists. As a result, In terms of Ukiyo-e as a whole, it was found that the creativity of its appearance has declined with the maturation of culture, but in terms of style, it has become more segmented with the maturation of culture and has maintained a high level of creativity. This not only provides new insights into the study of Ukiyo-e but also shows how Ukiyo-e has evolved within the ongoing cultural history, playing a culturally significant role in the analysis of Eastern art.
Authors: Huiyun Jiang, Zhuang Yang
Abstract: Recent studies have shown the great potential of diffusion models in improving reinforcement learning (RL) by modeling complex policies, expressing a high degree of multi-modality, and efficiently handling high-dimensional continuous control tasks. However, there is currently limited research on how to optimize diffusion-based polices (e.g., Diffusion Policy) fast and stably. In this paper, we propose an Adam-based Diffusion Policy Optimization (ADPO), a fast algorithmic framework containing best practices for fine-tuning diffusion-based polices in robotic control tasks using the adaptive gradient descent method in RL. Adaptive gradient method is less studied in training RL, let alone diffusion-based policies. We confirm that ADPO outperforms other diffusion-based RL methods in terms of overall effectiveness for fine-tuning on standard robotic tasks. Concretely, we conduct extensive experiments on standard robotic control tasks to test ADPO, where, particularly, six popular diffusion-based RL methods are provided as benchmark methods. Experimental results show that ADPO acquires better or comparable performance than the baseline methods. Finally, we systematically analyze the sensitivity of multiple hyperparameters in standard robotics tasks, providing guidance for subsequent practical applications. Our video demonstrations are released in https://github.com/Timeless-lab/ADPO.git.
Authors: Sofia Ek, Dave Zachariah
Abstract: Learning beneficial treatment allocations for a patient population is an important problem in precision medicine. Many treatments come with adverse side effects that are not commensurable with their potential benefits. Patients who do not receive benefits after such treatments are thereby subjected to unnecessary harm. This is a `treatment risk' that we aim to control when learning beneficial allocations. The constrained learning problem is challenged by the fact that the treatment risk is not in general identifiable using either randomized trial or observational data. We propose a certifiable learning method that controls the treatment risk with finite samples in the partially identified setting. The method is illustrated using both simulated and real data.
Authors: Mirco Theile, Andres R. Zapata Rodriguez, Marco Caccamo, Alberto L. Sangiovanni-Vincentelli
Abstract: Unmanned Aerial Vehicle (UAV) Coverage Path Planning (CPP) is critical for applications such as precision agriculture and search and rescue. While traditional methods rely on discrete grid-based representations, real-world UAV operations require power-efficient continuous motion planning. We formulate the UAV CPP problem in a continuous environment, minimizing power consumption while ensuring complete coverage. Our approach models the environment with variable-size axis-aligned rectangles and UAV motion with curvature-constrained B\'ezier curves. We train a reinforcement learning agent using an action-mapping-based Soft Actor-Critic (AM-SAC) algorithm employing a self-adaptive curriculum. Experiments on both procedurally generated and hand-crafted scenarios demonstrate the effectiveness of our method in learning energy-efficient coverage strategies.
Authors: Gijs Vermari\"en, Serena Viti, Johannes Heyl, Francesco Fontani
Abstract: Context. The outer Milky Way has a lower metallicity than our solar neighbourhood, but still many molecules are detected in the region. Molecular line ratios can serve as probes to better understand the chemistry and physics in these regions. Aims. We use interpretable machine learning to study 9 different molecular ratios, helping us understand the forward connection between the physics of these environments and the carbon and oxygen chemistries. Methods. Using a large grid of astrochemical models generated using UCLCHEM, we study the properties of molecular clouds of low oxygen and carbon initial abundance. We first try to understand the line ratios using a classical analysis. We then move on to using interpretable machine learning, namely Shapley Additive Explanations (SHAP), to understand the higher order dependencies of the ratios over the entire parameter grid. Lastly we use the Uniform Manifold Approximation and Projection technique (UMAP) as a reduction method to create intuitive groupings of models. Results. We find that the parameter space is well covered by the line ratios, allowing us to investigate all input parameters. SHAP analysis shows that the temperature and density are the most important features, but the carbon and oxygen abundances are important in parts of the parameter space. Lastly, we find that we can group different types of ratios using UMAP. Conclusions. We show the chosen ratios are mostly sensitive to changes in the carbon initial abundance, together with the temperature and density. Especially the CN/HCN and HNC/HCN ratio are shown to be sensitive to the initial carbon abundance, making them excellent probes for this parameter. Out of the ratios, only CS/SO shows a sensitivity to the oxygen abundance.
Authors: Mehran Sarmadi, Morteza Alikhani, Erfan Zinvandi, Zahra Pourbahman
Abstract: Recent advancements in text embedding have significantly improved natural language understanding across many languages, yet Persian remains notably underrepresented in large-scale embedding research. In this paper, we present Hakim, a novel state-of-the-art Persian text embedding model that achieves a 8.5% performance improvement over existing approaches on the FaMTEB benchmark, outperforming all previously developed Persian language models. As part of this work, we introduce three new datasets - Corpesia, Pairsia-sup, and Pairsia-unsup - to support supervised and unsupervised training scenarios. Additionally, Hakim is designed for applications in chatbots and retrieval-augmented generation (RAG) systems, particularly addressing retrieval tasks that require incorporating message history within these systems. We also propose a new baseline model built on the BERT architecture. Our language model consistently achieves higher accuracy across various Persian NLP tasks, while the RetroMAE-based model proves particularly effective for textual information retrieval applications. Together, these contributions establish a new foundation for advancing Persian language understanding.
Authors: Miguel Arana-Catania, Weisi Guo
Abstract: Causal understanding is important in many disciplines of science and engineering, where we seek to understand how different factors in the system causally affect an experiment or situation and pave a pathway towards creating effective or optimising existing models. Examples of use cases are autonomous exploration and modelling of unknown environments or assessing key variables in optimising large complex systems. In this paper, we analyse a Reinforcement Learning approach called Causal Curiosity, which aims to estimate as accurately and efficiently as possible, without directly measuring them, the value of factors that causally determine the dynamics of a system. Whilst the idea presents a pathway forward, measurement accuracy is the foundation of methodology effectiveness. Focusing on the current causal curiosity's robotic manipulator, we present for the first time a measurement accuracy analysis of the future potentials and current limitations of this technique and an analysis of its sensitivity and confounding factor disentanglement capability - crucial for causal analysis. As a result of our work, we promote proposals for an improved and efficient design of Causal Curiosity methods to be applied to real-world complex scenarios.
Authors: Lata Pangtey, Anukriti Bhatnagar, Shubhi Bansal, Shahid Shafi Dar, Nagendra Kumar
Abstract: Stance detection is essential for understanding subjective content across various platforms such as social media, news articles, and online reviews. Recent advances in Large Language Models (LLMs) have revolutionized stance detection by introducing novel capabilities in contextual understanding, cross-domain generalization, and multimodal analysis. Despite these progressions, existing surveys often lack comprehensive coverage of approaches that specifically leverage LLMs for stance detection. To bridge this critical gap, our review article conducts a systematic analysis of stance detection, comprehensively examining recent advancements of LLMs transforming the field, including foundational concepts, methodologies, datasets, applications, and emerging challenges. We present a novel taxonomy for LLM-based stance detection approaches, structured along three key dimensions: 1) learning methods, including supervised, unsupervised, few-shot, and zero-shot; 2) data modalities, such as unimodal, multimodal, and hybrid; and 3) target relationships, encompassing in-target, cross-target, and multi-target scenarios. Furthermore, we discuss the evaluation techniques and analyze benchmark datasets and performance trends, highlighting the strengths and limitations of different architectures. Key applications in misinformation detection, political analysis, public health monitoring, and social media moderation are discussed. Finally, we identify critical challenges such as implicit stance expression, cultural biases, and computational constraints, while outlining promising future directions, including explainable stance reasoning, low-resource adaptation, and real-time deployment frameworks. Our survey highlights emerging trends, open challenges, and future directions to guide researchers and practitioners in developing next-generation stance detection systems powered by large language models.
Authors: Nicholas Attolino, Alessio Capitanelli, Fulvio Mastrogiovanni
Abstract: PDDL-based symbolic task planning remains pivotal for robot autonomy yet struggles with dynamic human-robot collaboration due to scalability, re-planning demands, and delayed plan availability. Although a few neurosymbolic frameworks have previously leveraged LLMs such as GPT-3 to address these challenges, reliance on closed-source, remote models with limited context introduced critical constraints: third-party dependency, inconsistent response times, restricted plan length and complexity, and multi-domain scalability issues. We present Gideon, a novel framework that enables the transition to modern, smaller, local LLMs with extended context length. Gideon integrates a novel problem generator to systematically generate large-scale datasets of realistic domain-problem-plan tuples for any domain, and adapts neurosymbolic planning for local LLMs, enabling on-device execution and extended context for multi-domain support. Preliminary experiments in single-domain scenarios performed on Qwen-2.5 1.5B and trained on 8k-32k samples, demonstrate a valid plan percentage of 66.1% (32k model) and show that the figure can be further scaled through additional data. Multi-domain tests on 16k samples yield an even higher 70.6% planning validity rate, proving extensibility across domains and signaling that data variety can have a positive effect on learning efficiency. Although long-horizon planning and reduced model size make Gideon training much less efficient than baseline models based on larger LLMs, the results are still significant considering that the trained model is about 120x smaller than baseline and that significant advantages can be achieved in inference efficiency, scalability, and multi-domain adaptability, all critical factors in human-robot collaboration. Training inefficiency can be mitigated by Gideon's streamlined data generation pipeline.
Authors: Majd Abdallah, Sigve Nakken, Mariska Bierkens, Johanna Galvis, Alexis Groppi, Slim Karkar, Lana Meiqari, Maria Alexandra Rujano, Steve Canham, Rodrigo Dienstmann, Remond Fijneman, Eivind Hovig, Gerrit Meijer, Macha Nikolski
Abstract: Patient recruitment remains a major bottleneck in clinical trials, calling for scalable and automated solutions. We present TrialMatchAI, an AI-powered recommendation system that automates patient-to-trial matching by processing heterogeneous clinical data, including structured records and unstructured physician notes. Built on fine-tuned, open-source large language models (LLMs) within a retrieval-augmented generation framework, TrialMatchAI ensures transparency and reproducibility and maintains a lightweight deployment footprint suitable for clinical environments. The system normalizes biomedical entities, retrieves relevant trials using a hybrid search strategy combining lexical and semantic similarity, re-ranks results, and performs criterion-level eligibility assessments using medical Chain-of-Thought reasoning. This pipeline delivers explainable outputs with traceable decision rationales. In real-world validation, 92 percent of oncology patients had at least one relevant trial retrieved within the top 20 recommendations. Evaluation across synthetic and real clinical datasets confirmed state-of-the-art performance, with expert assessment validating over 90 percent accuracy in criterion-level eligibility classification, particularly excelling in biomarker-driven matches. Designed for modularity and privacy, TrialMatchAI supports Phenopackets-standardized data, enables secure local deployment, and allows seamless replacement of LLM components as more advanced models emerge. By enhancing efficiency and interpretability and offering lightweight, open-source deployment, TrialMatchAI provides a scalable solution for AI-driven clinical trial matching in precision medicine.
Authors: Yifan Li, Alan W Pang, Jo Woon Chong
Abstract: Inhalation injuries face a challenge in clinical diagnosis and grading due to the limitations of traditional methods, such as Abbreviated Injury Score (AIS), which rely on subjective assessments and show weak correlations with clinical outcomes. This study introduces a novel deep learning-based framework for grading inhalation injuries using bronchoscopy images with the duration of mechanical ventilation as an objective metric. To address the scarcity of medical imaging data, we propose enhanced StarGAN, a generative model that integrates Patch Loss and SSIM Loss to improve synthetic images' quality and clinical relevance. The augmented dataset generated by enhanced StarGAN significantly improved classification performance when evaluated using the Swin Transformer, achieving an accuracy of 77.78%, an 11.11% improvement over the original dataset. Image quality was assessed using the Fr\'echet Inception Distance (FID), where Enhanced StarGAN achieved the lowest FID of 30.06, outperforming baseline models. Burn surgeons confirmed the realism and clinical relevance of the generated images, particularly the preservation of bronchial structures and color distribution. These results highlight the potential of enhanced StarGAN in addressing data limitations and improving classification accuracy for inhalation injury grading.
Authors: Yanhao Zhang, Zhihan Zhu, Yong Xia
Abstract: The recovery of block-sparse signals with unknown structural patterns remains a fundamental challenge in structured sparse signal reconstruction. By proposing a variance transformation framework, this paper unifies existing pattern-based block sparse Bayesian learning methods, and introduces a novel space power prior based on undirected graph models to adaptively capture the unknown patterns of block-sparse signals. By combining the EM algorithm with high-order equation root-solving, we develop a new structured sparse Bayesian learning method, SPP-SBL, which effectively addresses the open problem of space coupling parameter estimation in pattern-based methods. We further demonstrate that learning the relative values of space coupling parameters is key to capturing unknown block-sparse patterns and improving recovery accuracy. Experiments validate that SPP-SBL successfully recovers various challenging structured sparse signals (e.g., chain-structured signals and multi-pattern sparse signals) and real-world multi-modal structured sparse signals (images, audio), showing significant advantages in recovery accuracy across multiple metrics.
Authors: Chenru Duan, Aditya Nandy, Sizhan Liu, Yuanqi Du, Liu He, Yi Qu, Haojun Jia, Jin-Hu Dou
Abstract: Metal-organic frameworks (MOFs) marry inorganic nodes, organic edges, and topological nets into programmable porous crystals, yet their astronomical design space defies brute-force synthesis. Generative modeling holds ultimate promise, but existing models either recycle known building blocks or are restricted to small unit cells. We introduce Building-Block-Aware MOF Diffusion (BBA MOF Diffusion), an SE(3)-equivariant diffusion model that learns 3D all-atom representations of individual building blocks, encoding crystallographic topological nets explicitly. Trained on the CoRE-MOF database, BBA MOF Diffusion readily samples MOFs with unit cells containing 1000 atoms with great geometric validity, novelty, and diversity mirroring experimental databases. Its native building-block representation produces unprecedented metal nodes and organic edges, expanding accessible chemical space by orders of magnitude. One high-scoring [Zn(1,4-TDC)(EtOH)2] MOF predicted by the model was synthesized, where powder X-ray diffraction, thermogravimetric analysis, and N2 sorption confirm its structural fidelity. BBA-Diff thus furnishes a practical pathway to synthesizable and high-performing MOFs.
Authors: Linna Xu, Yongli Zhu
Abstract: This paper presents a modified model predictive control (MPC) framework for real-time power system operation. The framework incorporates a diffusion model tailored for time series generation to enhance the accuracy of the load forecasting module used in the system operation. In the absence of explicit state transition law, a model-identification procedure is leveraged to derive the system dynamics, thereby eliminating a barrier when applying MPC to a renewables-dominated power system. Case study results on an industry park system and the IEEE 30-bus system demonstrate that using the diffusion model to augment the training dataset significantly improves load-forecasting accuracy, and the inferred system dynamics are applicable to the real-time grid operation with solar and wind.
Authors: Yifu Yuan, Haiqin Cui, Yibin Chen, Zibin Dong, Fei Ni, Longxin Kou, Jinyi Liu, Pengyi Li, Yan Zheng, Jianye Hao
Abstract: Achieving generalization in robotic manipulation remains a critical challenge, particularly for unseen scenarios and novel tasks. Current Vision-Language-Action (VLA) models, while building on top of general Vision-Language Models (VLMs), still fall short of achieving robust zero-shot performance due to the scarcity and heterogeneity prevalent in embodied datasets. To address these limitations, we propose FSD (From Seeing to Doing), a novel vision-language model that generates intermediate representations through spatial relationship reasoning, providing fine-grained guidance for robotic manipulation. Our approach combines a hierarchical data pipeline for training with a self-consistency mechanism that aligns spatial coordinates with visual signals. Through extensive experiments, we comprehensively validated FSD's capabilities in both "seeing" and "doing," achieving outstanding performance across 8 benchmarks for general spatial reasoning and embodied reference abilities, as well as on our proposed more challenging benchmark VABench. We also verified zero-shot capabilities in robot manipulation, demonstrating significant performance improvements over baseline methods in both SimplerEnv and real robot settings. Experimental results show that FSD achieves 54.1% success rate in SimplerEnv and 72% success rate across 8 real-world tasks, outperforming the strongest baseline by 30%.
Authors: Haroon Wahab, Hassan Ugail, Irfan Mehmood
Abstract: Recent proliferation of generative AI tools for visual content creation-particularly in the context of visual artworks-has raised serious concerns about copyright infringement and forgery. The large-scale datasets used to train these models often contain a mixture of copyrighted and non-copyrighted artworks. Given the tendency of generative models to memorize training patterns, they are susceptible to varying degrees of copyright violation. Building on the recently proposed DeepfakeArt Challenge benchmark, this work introduces DFA-CON, a contrastive learning framework designed to detect copyright-infringing or forged AI-generated art. DFA-CON learns a discriminative representation space, posing affinity among original artworks and their forged counterparts within a contrastive learning framework. The model is trained across multiple attack types, including inpainting, style transfer, adversarial perturbation, and cutmix. Evaluation results demonstrate robust detection performance across most attack types, outperforming recent pretrained foundation models. Code and model checkpoints will be released publicly upon acceptance.
Authors: Barak Pinkovich, Boaz Matalon, Ehud Rivlin, Hector Rotstein
Abstract: This paper presents a Multi-Elevation Semantic Segmentation Image (MESSI) dataset comprising 2525 images taken by a drone flying over dense urban environments. MESSI is unique in two main features. First, it contains images from various altitudes, allowing us to investigate the effect of depth on semantic segmentation. Second, it includes images taken from several different urban regions (at different altitudes). This is important since the variety covers the visual richness captured by a drone's 3D flight, performing horizontal and vertical maneuvers. MESSI contains images annotated with location, orientation, and the camera's intrinsic parameters and can be used to train a deep neural network for semantic segmentation or other applications of interest (e.g., localization, navigation, and tracking). This paper describes the dataset and provides annotation details. It also explains how semantic segmentation was performed using several neural network models and shows several relevant statistics. MESSI will be published in the public domain to serve as an evaluation benchmark for semantic segmentation using images captured by a drone or similar vehicle flying over a dense urban environment.
Authors: Sebastian Billaudelle, Laura Kriener, Filippo Moro, Tristan Torchet, Melika Payvand
Abstract: Recurrent neural networks (RNNs) have been a long-standing candidate for processing of temporal sequence data, especially in memory-constrained systems that one may find in embedded edge computing environments. Recent advances in training paradigms have now inspired new generations of efficient RNNs. We introduce a streamlined and hardware-compatible architecture based on minimal gated recurrent units (GRUs), and an accompanying efficient mixed-signal hardware implementation of the model. The proposed design leverages switched-capacitor circuits not only for in-memory computation (IMC), but also for the gated state updates. The mixed-signal cores rely solely on commodity circuits consisting of metal capacitors, transmission gates, and a clocked comparator, thus greatly facilitating scaling and transfer to other technology nodes. We benchmark the performance of our architecture on time series data, introducing all constraints required for a direct mapping to the hardware system. The direct compatibility is verified in mixed-signal simulations, reproducing data recorded from the software-only network model.
Authors: Wenqi Zeng, Shuqi Zhou, Yuan Yao, Chunlai Chen
Abstract: Single-molecule fluorescence assays enable high-resolution analysis of biomolecular dynamics, but traditional analysis pipelines are labor-intensive and rely on users' experience, limiting scalability and reproducibility. Recent deep learning models have automated aspects of data processing, yet many still require manual thresholds, complex architectures, or extensive labeled data. Therefore, we present DASH, a fully streamlined architecture for trace classification, state assignment, and automatic sorting that requires no user input. DASH demonstrates robust performance across users and experimental conditions both in equilibrium and non-equilibrium systems such as Cas12a-mediated DNA cleavage. This paper proposes a novel strategy for the automatic and detailed sorting of single-molecule fluorescence events. The dynamic cleavage process of Cas12a is used as an example to provide a comprehensive analysis. This approach is crucial for studying biokinetic structural changes at the single-molecule level.
Authors: Ines Ortega-Fernandez, Marta Sestelo
Abstract: Nowadays, Neural Networks are considered one of the most effective methods for various tasks such as anomaly detection, computer-aided disease detection, or natural language processing. However, these networks suffer from the ``black-box'' problem which makes it difficult to understand how they make decisions. In order to solve this issue, an R package called neuralGAM is introduced. This package implements a Neural Network topology based on Generalized Additive Models, allowing to fit an independent Neural Network to estimate the contribution of each feature to the output variable, yielding a highly accurate and interpretable Deep Learning model. The neuralGAM package provides a flexible framework for training Generalized Additive Neural Networks, which does not impose any restrictions on the Neural Network architecture. We illustrate the use of the neuralGAM package in both synthetic and real data examples.
Authors: Yifan Li, Myeongjun Kim, Yanjing Jin, Peter Ho, Jo Woon Chong
Abstract: Keratoconus (KC) is a progressive corneal disorder characterized by localized thinning and protrusion, leading to visual distortion. While Placido disc-based topography remains a standard in clinical diagnostics, its dependence on specialized equipment limits accessibility. In this paper, we propose a portable, smartphone-based diagnostic framework that captures corneal reflections of a Placido disc displayed on a phone screen and applies a two-stage detection pipeline, then validate on 3D-printed emulated eyeball models that simulate normal, moderate, and severe KC stages based on anterior chamber depth (ACD). The first step of the two-stage detection pipeline is classifying different stages of KC with features including height and width of extracted reflections using weighted support vector machine (WSVM). It achieves a maximum accuracy of 92.93%, and maintains over 90% accuracy across multiple smartphone models, including the Galaxy Z Flip 3, iPhone 15 Pro, and iPhone 16 Pro. For the second step, we visualize the KC-affected protrusion regions on the corneas with color maps based on inter-disc distance, that provides an intuitive representation of disease severity and localization. Moreover, we validate the ability of the extracted features to differentiate between KC stages with ANOVA and Omega Squared, with significant p-values (e.g., $p < 10^{-6}$) and large effect sizes ($\\omega^2$ up to 0.8398) among classes.
Authors: Dvir Cohen, Lin Burg, Sviatoslav Pykhnivskyi, Hagit Gur, Stanislav Kovynov, Olga Atzmon, Gilad Barkan
Abstract: Retrieval-Augmented Generation (RAG) is a cornerstone of modern question answering (QA) systems, enabling grounded answers based on external knowledge. Although recent progress has been driven by open-domain datasets, enterprise QA systems need datasets that mirror the concrete, domain-specific issues users raise in day-to-day support scenarios. Critically, evaluating end-to-end RAG systems requires benchmarks comprising not only question--answer pairs but also the specific knowledge base (KB) snapshot from which answers were derived. To address this need, we introduce WixQA, a benchmark suite featuring QA datasets precisely grounded in the released KB corpus, enabling holistic evaluation of retrieval and generation components. WixQA includes three distinct QA datasets derived from Wix.com customer support interactions and grounded in a snapshot of the public Wix Help Center KB: (i) WixQA-ExpertWritten, 200 real user queries with expert-authored, multi-step answers; (ii) WixQA-Simulated, 200 expert-validated QA pairs distilled from user dialogues; and (iii) WixQA-Synthetic, 6,222 LLM-generated QA pairs, with one pair systematically derived from each article in the knowledge base. We release the KB snapshot alongside the datasets under MIT license and provide comprehensive baseline results, forming a unique benchmark for evaluating enterprise RAG systems in realistic enterprise environments.
Authors: Chen Wu, Yin Song
Abstract: We present MegaBeam-Mistral-7B, a language model that supports 512K-token context length. Our work addresses practical limitations in long-context training, supporting real-world tasks such as compliance monitoring and verification. Evaluated on three long-context benchmarks, our 7B-parameter model demonstrates superior in-context learning performance on HELMET and robust retrieval and tracing capability on RULER. It is currently the only open model to achieve competitive long-range reasoning on BABILong at 512K context length without RAG or targeted fine-tuning. Released as fully open source under the Apache 2.0 license, the model has been downloaded over 100,000 times on Hugging Face. Model available at: https://huggingface.co/aws-prototyping/MegaBeam-Mistral-7B-512k
URLs: https://huggingface.co/aws-prototyping/MegaBeam-Mistral-7B-512k
Authors: Marcus Buckmann, Quynh Anh Nguyen, Edward Hill
Abstract: We investigate whether the hidden states of large language models (LLMs) can be used to estimate and impute economic and financial statistics. Focusing on county-level (e.g. unemployment) and firm-level (e.g. total assets) variables, we show that a simple linear model trained on the hidden states of open-source LLMs outperforms the models' text outputs. This suggests that hidden states capture richer economic information than the responses of the LLMs reveal directly. A learning curve analysis indicates that only a few dozen labelled examples are sufficient for training. We also propose a transfer learning method that improves estimation accuracy without requiring any labelled data for the target variable. Finally, we demonstrate the practical utility of hidden-state representations in super-resolution and data imputation tasks.
Authors: Stefania Scheurer, Philipp Reiser, Tim Br\"unnette, Wolfgang Nowak, Anneli Guthke, Paul-Christian B\"urkner
Abstract: Bayesian inference typically relies on a large number of model evaluations to estimate posterior distributions. Established methods like Markov Chain Monte Carlo (MCMC) and Amortized Bayesian Inference (ABI) can become computationally challenging. While ABI enables fast inference after training, generating sufficient training data still requires thousands of model simulations, which is infeasible for expensive models. Surrogate models offer a solution by providing approximate simulations at a lower computational cost, allowing the generation of large data sets for training. However, the introduced approximation errors and uncertainties can lead to overconfident posterior estimates. To address this, we propose Uncertainty-Aware Surrogate-based Amortized Bayesian Inference (UA-SABI) - a framework that combines surrogate modeling and ABI while explicitly quantifying and propagating surrogate uncertainties through the inference pipeline. Our experiments show that this approach enables reliable, fast, and repeated Bayesian inference for computationally expensive models, even under tight time constraints.
Authors: Changqi He, Shuhan Zhang, Liguo Zhang, Jiajun Miao
Abstract: Computer-aided design (CAD) is a way to digitally create 2D drawings and 3D models of real-world products. Traditional CAD typically relies on hand-drawing by experts or modifications of existing library files, which doesn't allow for rapid personalization. With the emergence of generative artificial intelligence, convenient and efficient personalized CAD generation has become possible. However, existing generative methods typically produce outputs that lack interactive editability and geometric annotations, limiting their practical applications in manufacturing. To enable interactive generative CAD, we propose CAD-Coder, a framework that transforms natural language instructions into CAD script codes, which can be executed in Python environments to generate human-editable CAD files (.Dxf). To facilitate the generation of editable CAD sketches with annotation information, we construct a comprehensive dataset comprising 29,130 Dxf files with their corresponding script codes, where each sketch preserves both editability and geometric annotations. We evaluate CAD-Coder on various 2D/3D CAD generation tasks against existing methods, demonstrating superior interactive capabilities while uniquely providing editable sketches with geometric annotations.
Authors: Antonio \'Alvarez-L\'opez, Marcos Matabuena
Abstract: Modeling the continuous--time dynamics of probability distributions from time--dependent data samples is a fundamental problem in many fields, including digital health. The aim is to analyze how the distribution of a biomarker, such as glucose, evolves over time and how these changes may reflect the progression of chronic diseases such as diabetes. In this paper, we propose a novel probabilistic model based on a mixture of Gaussian distributions to capture how samples from a continuous-time stochastic process evolve over the time. To model potential distribution shifts over time, we introduce a time-dependent function parameterized by a Neural Ordinary Differential Equation (Neural ODE) and estimate it non--parametrically using the Maximum Mean Discrepancy (MMD). The proposed model is highly interpretable, detects subtle temporal shifts, and remains computationally efficient. Through simulation studies, we show that it performs competitively in terms of estimation accuracy against state-of-the-art, less interpretable methods such as normalized gradient--flows and non--parameteric kernel density estimators. Finally, we demonstrate the utility of our method on digital clinical--trial data, showing how the interventions alters the time-dependent distribution of glucose levels and enabling a rigorous comparison of control and treatment groups from novel mathematical and clinical perspectives.
Authors: Ibrahim Elsharkawy, Yonatan Kahn
Abstract: Estimating physical parameters from data is a crucial application of machine learning (ML) in the physical sciences. However, systematic uncertainties, such as detector miscalibration, induce data distribution distortions that can erode statistical precision. In both high-energy physics (HEP) and broader ML contexts, achieving uncertainty-aware parameter estimation under these domain shifts remains an open problem. In this work, we address this challenge of uncertainty-aware parameter estimation for a broad set of tasks critical for HEP. We introduce a novel approach based on Contrastive Normalizing Flows (CNFs), which achieves top performance on the HiggsML Uncertainty Challenge dataset. Building on the insight that a binary classifier can approximate the model parameter likelihood ratio, we address the practical limitations of expressivity and the high cost of simulating high-dimensional parameter grids by embedding data and parameters in a learned CNF mapping. This mapping yields a tunable contrastive distribution that enables robust classification under shifted data distributions. Through a combination of theoretical analysis and empirical evaluations, we demonstrate that CNFs, when coupled with a classifier and established frequentist techniques, provide principled parameter estimation and uncertainty quantification through classification that is robust to data distribution distortions.
Authors: Saurabh Dash, Yiyang Nan, John Dang, Arash Ahmadian, Shivalika Singh, Madeline Smith, Bharat Venkitesh, Vlad Shmyhlo, Viraat Aryabumi, Walter Beller-Morales, Jeremy Pekmez, Jason Ozuzu, Pierre Richemond, Acyr Locatelli, Nick Frosst, Phil Blunsom, Aidan Gomez, Ivan Zhang, Marzieh Fadaee, Manoj Govindassamy, Sudip Roy, Matthias Gall\'e, Beyza Ermis, Ahmet \"Ust\"un, Sara Hooker
Abstract: Building multimodal language models is fundamentally challenging: it requires aligning vision and language modalities, curating high-quality instruction data, and avoiding the degradation of existing text-only capabilities once vision is introduced. These difficulties are further magnified in the multilingual setting, where the need for multimodal data in different languages exacerbates existing data scarcity, machine translation often distorts meaning, and catastrophic forgetting is more pronounced. To address the aforementioned challenges, we introduce novel techniques spanning both data and modeling. First, we develop a synthetic annotation framework that curates high-quality, diverse multilingual multimodal instruction data, enabling Aya Vision models to produce natural, human-preferred responses to multimodal inputs across many languages. Complementing this, we propose a cross-modal model merging technique that mitigates catastrophic forgetting, effectively preserving text-only capabilities while simultaneously enhancing multimodal generative performance. Aya-Vision-8B achieves best-in-class performance compared to strong multimodal models such as Qwen-2.5-VL-7B, Pixtral-12B, and even much larger Llama-3.2-90B-Vision. We further scale this approach with Aya-Vision-32B, which outperforms models more than twice its size, such as Molmo-72B and LLaMA-3.2-90B-Vision. Our work advances multilingual progress on the multi-modal frontier, and provides insights into techniques that effectively bend the need for compute while delivering extremely high performance.
Authors: Jeff Guo, V\'ictor Sabanza-Gil, Zlatko Jon\v{c}ev, Jeremy S. Luterbacher, Philippe Schwaller
Abstract: Synthesizability in small molecule generative design remains a bottleneck. Existing works that do consider synthesizability can output predicted synthesis routes for generated molecules. However, there has been minimal attention in addressing the ease of synthesis and enabling flexibility to incorporate desired reaction constraints. In this work, we propose a small molecule generative design framework that enables steerable and granular synthesizability control. Generated molecules satisfy arbitrary multi-parameter optimization objectives with predicted synthesis routes containing pre-defined allowed reactions, while optionally avoiding others. One can also enforce that all reactions belong to a pre-defined set. We show the capability to mix-and-match these reaction constraints across the most common medicinal chemistry transformations. Next, we show how our framework can be used to valorize industrial byproducts towards de novo optimized molecules. Going further, we demonstrate how granular control over synthesizability constraints can loosely mimic virtual screening of ultra-large make-on-demand libraries. Using only a single GPU, we generate and dock 15k molecules to identify promising candidates in Freedom 4.0 constituting 142B make-on-demand molecules (assessing only 0.00001% of the library). Generated molecules satisfying the reaction constraints have > 90% exact match rate. Lastly, we benchmark our framework against recent synthesizability-constrained generative models and demonstrate the highest sample efficiency even when imposing the additional constraint that all molecules must be synthesizable from a single reaction type. The main theme is demonstrating that a pre-trained generalist molecular generative model can be incentivized to generate property-optimized small molecules under challenging synthesizability constraints through reinforcement learning.
Authors: Abhineet Agarwal, Michael Xiao, Rebecca Barter, Omer Ronen, Boyu Fan, Bin Yu
Abstract: As machine learning (ML) models are increasingly deployed in high-stakes domains, trustworthy uncertainty quantification (UQ) is critical for ensuring the safety and reliability of these models. Traditional UQ methods rely on specifying a true generative model and are not robust to misspecification. On the other hand, conformal inference allows for arbitrary ML models but does not consider model selection, which leads to large interval sizes. We tackle these drawbacks by proposing a UQ method based on the predictability, computability, and stability (PCS) framework for veridical data science proposed by Yu and Kumbier. Specifically, PCS-UQ addresses model selection by using a prediction check to screen out unsuitable models. PCS-UQ then fits these screened algorithms across multiple bootstraps to assess inter-sample variability and algorithmic instability, enabling more reliable uncertainty estimates. Further, we propose a novel calibration scheme that improves local adaptivity of our prediction sets. Experiments across $17$ regression and $6$ classification datasets show that PCS-UQ achieves the desired coverage and reduces width over conformal approaches by $\approx 20\%$. Further, our local analysis shows PCS-UQ often achieves target coverage across subgroups while conformal methods fail to do so. For large deep-learning models, we propose computationally efficient approximation schemes that avoid the expensive multiple bootstrap trainings of PCS-UQ. Across three computer vision benchmarks, PCS-UQ reduces prediction set size over conformal methods by $20\%$. Theoretically, we show a modified PCS-UQ algorithm is a form of split conformal inference and achieves the desired coverage with exchangeable data.
Authors: Volodymyr Kuleshov, Shachi Deshpande
Abstract: Accurate probabilistic predictions can be characterized by two properties -- calibration and sharpness. However, standard maximum likelihood training yields models that are poorly calibrated and thus inaccurate -- a 90% confidence interval typically does not contain the true outcome 90% of the time. This paper argues that calibration is important in practice and is easy to maintain by performing low-dimensional density estimation. We introduce a simple training procedure based on recalibration that yields calibrated models without sacrificing overall performance; unlike previous approaches, ours ensures the most general property of distribution calibration and applies to any model, including neural networks. We formally prove the correctness of our procedure assuming that we can estimate densities in low dimensions and we establish uniform convergence bounds. Our results yield empirical performance improvements on linear and deep Bayesian models and suggest that calibration should be increasingly leveraged across machine learning. We release a library that implements our methods along with a blog post here: https://shachideshpande.github.io/blog-distribution-calibration/.
URLs: https://shachideshpande.github.io/blog-distribution-calibration/.
Authors: Han-Dong Lim, Donghwan Lee
Abstract: The goal of this paper is to investigate distributed temporal difference (TD) learning for a networked multi-agent Markov decision process. The proposed approach is based on distributed optimization algorithms, which can be interpreted as primal-dual Ordinary differential equation (ODE) dynamics subject to null-space constraints. Based on the exponential convergence behavior of the primal-dual ODE dynamics subject to null-space constraints, we examine the behavior of the final iterate in various distributed TD-learning scenarios, considering both constant and diminishing step-sizes and incorporating both i.i.d. and Markovian observation models. Unlike existing methods, the proposed algorithm does not require the assumption that the underlying communication network structure is characterized by a doubly stochastic matrix.
Authors: Nathan Justin, Sina Aghaei, Andr\'es G\'omez, Phebe Vayanos
Abstract: We consider the problem of learning classification trees that are robust to distribution shifts between training and testing/deployment data. This problem arises frequently in high stakes settings such as public health and social work where data is often collected using self-reported surveys which are highly sensitive to e.g., the framing of the questions, the time when and place where the survey is conducted, and the level of comfort the interviewee has in sharing information with the interviewer. We propose a method for learning optimal robust classification trees based on mixed-integer robust optimization technology. In particular, we demonstrate that the problem of learning an optimal robust tree can be cast as a single-stage mixed-integer robust optimization problem with a highly nonlinear and discontinuous objective. We reformulate this problem equivalently as a two-stage linear robust optimization problem for which we devise a tailored solution procedure based on constraint generation. We evaluate the performance of our approach on numerous publicly available datasets, and compare the performance to a regularized, non-robust optimal tree. We show an increase of up to 12.48% in worst-case accuracy and of up to 4.85% in average-case accuracy across several datasets and distribution shifts from using our robust solution in comparison to the non-robust one.
Authors: Yan Lin, Jilin Hu, Shengnan Guo, Bin Yang, Christian S. Jensen, Youfang Lin, Huaiyu Wan
Abstract: Vehicle movement is frequently captured in the form of GPS trajectories, i.e., sequences of timestamped GPS locations. Such data is widely used for various tasks such as travel-time estimation, trajectory recovery, and trajectory prediction. A universal vehicle trajectory model could be applied to different tasks, removing the need to maintain multiple specialized models, thereby reducing computational and storage costs. However, creating such a model is challenging when the integrity of trajectory features is compromised, i.e., in scenarios where only partial features are available or the trajectories are sparse. To address these challenges, we propose the Universal Vehicle Trajectory Model (UVTM), which can effectively adapt to different tasks without excessive retraining. UVTM incorporates two specialized designs. First, it divides trajectory features into three distinct domains. Each domain can be masked and generated independently to accommodate tasks with only partially available features. Second, UVTM is pre-trained by reconstructing dense, feature-complete trajectories from sparse, feature-incomplete counterparts, enabling strong performance even when the integrity of trajectory features is compromised. Experiments involving four representative trajectory-related tasks on three real-world vehicle trajectory datasets provide insight into the performance of UVTM and offer evidence that it is capable of meeting its objectives.
Authors: David Yevick
Abstract: A general procedure for introducing parametric, learned, nonlinearity into activation functions is found to enhance the accuracy of representative neural networks without requiring significant additional computational resources. Examples are given based on the standard rectified linear unit (ReLU) as well as several other frequently employed activation functions. The associated accuracy improvement is quantified both in the context of the MNIST digit data set and a convolutional neural network (CNN) benchmark example.
Authors: Jessica N. Howard, Ro Jefferson, Anindita Maiti, Zohar Ringel
Abstract: Separating relevant and irrelevant information is key to any modeling process or scientific inquiry. Theoretical physics offers a powerful tool for achieving this in the form of the renormalization group (RG). Here we demonstrate a practical approach to performing Wilsonian RG in the context of Gaussian Process (GP) Regression. We systematically integrate out the unlearnable modes of the GP kernel, thereby obtaining an RG flow of the GP in which the data sets the IR scale. In simple cases, this results in a universal flow of the ridge parameter, which becomes input-dependent in the richer scenario in which non-Gaussianities are included. In addition to being analytically tractable, this approach goes beyond structural analogies between RG and neural networks by providing a natural connection between RG flow and learnable vs. unlearnable modes. Studying such flows may improve our understanding of feature learning in deep neural networks, and enable us to identify potential universality classes in these models.
Authors: Iv\'an Matas, Carmen Serrano, Francisca Silva, Amalia Serrano, Tom\'as Toledo-Pastrana, Bego\~na Acha
Abstract: An AI tool has been developed to provide interpretable support for the diagnosis of BCC via teledermatology, thus speeding up referrals and optimizing resource utilization. The interpretability is provided in two ways: on the one hand, the main BCC dermoscopic patterns are found in the image to justify the BCC/Non BCC classification. Secondly, based on the common visual XAI Grad-CAM, a clinically inspired visual explanation is developed where the relevant features for diagnosis are located. Since there is no established ground truth for BCC dermoscopic features, a standard reference is inferred from the diagnosis of four dermatologists using an Expectation Maximization (EM) based algorithm. The results demonstrate significant improvements in classification accuracy and interpretability, positioning this approach as a valuable tool for early BCC detection and referral to dermatologists. The BCC/non-BCC classification achieved an accuracy rate of 90%. For Clinically-inspired XAI results, the detection of BCC patterns useful to clinicians reaches 99% accuracy. As for the Clinically-inspired Visual XAI results, the mean of the Grad-CAM normalized value within the manually segmented clinical features is 0.57, while outside this region it is 0.16. This indicates that the model struggles to accurately identify the regions of the BCC patterns. These results prove the ability of the AI tool to provide a useful explanation.
Authors: Taehyun Cho, Seungyub Han, Seokhun Ju, Dohyeong Kim, Kyungjae Lee, Jungwoo Lee
Abstract: Distributional reinforcement learning improves performance by capturing environmental stochasticity, but a comprehensive theoretical understanding of its effectiveness remains elusive. In addition, the intractable element of the infinite dimensionality of distributions has been overlooked. In this paper, we present a regret analysis of distributional reinforcement learning with general value function approximation in a finite episodic Markov decision process setting. We first introduce a key notion of $\textit{Bellman unbiasedness}$ which is essential for exactly learnable and provably efficient distributional updates in an online manner. Among all types of statistical functionals for representing infinite-dimensional return distributions, our theoretical results demonstrate that only moment functionals can exactly capture the statistical information. Secondly, we propose a provably efficient algorithm, $\texttt{SF-LSVI}$, that achieves a tight regret bound of $\tilde{O}(d_E H^{\frac{3}{2}}\sqrt{K})$ where $H$ is the horizon, $K$ is the number of episodes, and $d_E$ is the eluder dimension of a function class.
Authors: Mengjian Hua, Mathieu Lauri\`ere, Eric Vanden-Eijnden
Abstract: We present a novel on-policy algorithm for solving stochastic optimal control (SOC) problems. By leveraging the Girsanov theorem, our method directly computes on-policy gradients of the SOC objective without expensive backpropagation through stochastic differential equations or adjoint problem solutions. This approach significantly accelerates the optimization of neural network control policies while scaling efficiently to high-dimensional problems and long time horizons. We evaluate our method on classical SOC benchmarks as well as applications to sampling from unnormalized distributions via Schr\"odinger-F\"ollmer processes and fine-tuning pre-trained diffusion models. Experimental results demonstrate substantial improvements in both computational speed and memory efficiency compared to existing approaches.
Authors: Tyler Sours, Shivang Agarwal, Marc Cormier, Jordan Crivelli-Decker, Steffen Ridderbusch, Stephen L. Glazier, Connor P. Aiken, Aayush R. Singh, Ang Xiao, Omar Allam
Abstract: Predicting the end-of-life (EOL) of lithium-ion batteries across different manufacturers presents significant challenges due to variations in electrode materials, manufacturing processes, cell formats, and a lack of generally available data. Methods that construct features solely on voltage-capacity profile data typically fail to generalize across cell chemistries. This study introduces a methodology that combines traditional voltage-capacity features with Direct Current Internal Resistance (DCIR) measurements, enabling more accurate and generalizable EOL predictions. The use of early-cycle DCIR data captures critical degradation mechanisms related to internal resistance growth, enhancing model robustness. Models are shown to successfully predict the number of cycles to EOL for unseen manufacturers of varied electrode composition with a mean absolute error (MAE) of 150 cycles. This cross-manufacturer generalizability reduces the need for extensive new data collection and retraining, enabling manufacturers to optimize new battery designs using existing datasets. Additionally, a novel DCIR-compatible dataset is released as part of ongoing efforts to enrich the growing ecosystem of cycling data and accelerate battery materials development.
Authors: Arham Khan, Robert Underwood, Carlo Siebenschuh, Yadu Babuji, Aswathy Ajith, Kyle Hippe, Ozan Gokdemir, Alexander Brace, Kyle Chard, Ian Foster
Abstract: Deduplication is a major focus for assembling and curating training datasets for large language models (LLM) -- detecting and eliminating additional instances of the same content -- in large collections of technical documents. Unrestrained, duplicates in the training dataset increase training costs and lead to undesirable properties such as memorization in trained models or cheating on evaluation. Contemporary approaches to document-level deduplication are often extremely expensive in both runtime and memory. We propose LSHBloom, an extension to MinhashLSH, which replaces the expensive LSHIndex with lightweight Bloom filters. LSHBloom demonstrates the same deduplication performance as MinhashLSH with only a marginal increase in false positives (as low as 1e-5 in our experiments); demonstrates competitive runtime (270\% faster than MinhashLSH on peS2o); and, crucially, uses just 0.6\% of the disk space required by MinhashLSH to deduplicate peS2o. We demonstrate that this space advantage scales with increased dataset size -- at the extreme scale of several billion documents, LSHBloom promises a 250\% speedup and a 54$\times$ space advantage over traditional MinHashLSH scaling deduplication of text datasets to many billions of documents.
Authors: Rui Li, Marcus Klasson, Arno Solin, Martin Trapp
Abstract: The rising interest in Bayesian deep learning (BDL) has led to a plethora of methods for estimating the posterior distribution. However, efficient computation of inferences, such as predictions, has been largely overlooked with Monte Carlo integration remaining the standard. In this work we examine streamlining prediction in BDL through a single forward pass without sampling. For this we use local linearisation on activation functions and local Gaussian approximations at linear layers. Thus allowing us to analytically compute an approximation to the posterior predictive distribution. We showcase our approach for both MLP and transformers, such as ViT and GPT-2, and assess its performance on regression and classification tasks. Open-source library: https://github.com/AaltoML/SUQ
Authors: Muhammad Sohail Ibrahim, Muhammad Usman, Jeong-A Lee
Abstract: Convolutional Neural Networks (CNNs) are crucial in various applications, but their deployment on resource-constrained edge devices poses challenges. This study presents the Sum-of-Products (SOP) units for convolution, which utilize low-latency left-to-right bit-serial arithmetic to minimize response time and enhance overall performance. The study proposes a methodology for fusing multiple convolution layers to reduce off-chip memory communication and increase overall performance. An effective mechanism detects and skips inefficient convolutions after ReLU layers, minimizing power consumption without compromising accuracy. Furthermore, efficient tile movement guarantees uniform access to the fusion pyramid. An analysis demonstrates the utile stride strategy improves operational intensity. Two designs cater to varied demands: one focuses on minimal response time for mission-critical applications, and another focuses on resource-constrained devices with comparable latency. This approach notably reduced redundant computations, improving the efficiency of CNN deployment on edge devices.
Authors: Zhongtian Ma, Qiaosheng Zhang, Bocheng Zhou, Yexin Zhang, Shuyue Hu, Zhen Wang
Abstract: Despite the growing popularity of graph attention mechanisms, their theoretical understanding remains limited. This paper aims to explore the conditions under which these mechanisms are effective in node classification tasks through the lens of Contextual Stochastic Block Models (CSBMs). Our theoretical analysis reveals that incorporating graph attention mechanisms is \emph{not universally beneficial}. Specifically, by appropriately defining \emph{structure noise} and \emph{feature noise} in graphs, we show that graph attention mechanisms can enhance classification performance when structure noise exceeds feature noise. Conversely, when feature noise predominates, simpler graph convolution operations are more effective. Furthermore, we examine the over-smoothing phenomenon and show that, in the high signal-to-noise ratio (SNR) regime, graph convolutional networks suffer from over-smoothing, whereas graph attention mechanisms can effectively resolve this issue. Building on these insights, we propose a novel multi-layer Graph Attention Network (GAT) architecture that significantly outperforms single-layer GATs in achieving \emph{perfect node classification} in CSBMs, relaxing the SNR requirement from $ \omega(\sqrt{\log n}) $ to $ \omega(\sqrt{\log n} / \sqrt[3]{n}) $. To our knowledge, this is the first study to delineate the conditions for perfect node classification using multi-layer GATs. Our theoretical contributions are corroborated by extensive experiments on both synthetic and real-world datasets, highlighting the practical implications of our findings.
Authors: Xingwu Sun, Shuaipeng Li, Ruobing Xie, Weidong Han, Kan Wu, Zhen Yang, Yixing Li, An Wang, Shuai Li, Jinbao Xue, Yu Cheng, Yangyu Tao, Zhanhui Kang, Chengzhong Xu, Di Wang, Jie Jiang
Abstract: Low-precision training is considered an effective strategy for reducing both training and downstream inference costs. Previous scaling laws for precision mainly focus on integer quantization, which pay less attention to the constituents in floating-point (FP) quantization, and thus cannot well fit the LLM losses in this scenario. In contrast, while FP quantization training is more commonly implemented in production, it's research has been relatively superficial. In this paper, we thoroughly explore the effects of FP quantization targets, exponent bits, mantissa bits, and the calculation granularity of the scaling factor in FP quantization training performance of LLM models. In addition to an accurate FP quantization unified scaling law, we also provide valuable suggestions for the community: (1) Exponent bits contribute slightly more to the model performance than mantissa bits. We provide the optimal exponent-mantissa bit ratio for different bit numbers, which is available for future reference by hardware manufacturers; (2) We discover the formation of the critical data size in low-precision LLM training. Too much training data exceeding the critical data size will inversely bring in degradation of LLM performance; (3) The optimal FP quantization precision is directly proportional to the computational power, but within a wide computational power range. We estimate that the best cost-performance precision should lie between 4-8 bits.
Authors: Baojun Che, Yifan Chen, Zhenghao Huan, Daniel Zhengyu Huang, Weijie Wang
Abstract: This paper is concerned with the approximation of probability distributions known up to normalization constants, with a focus on Bayesian inference for large-scale inverse problems in scientific computing. In this context, key challenges include costly repeated evaluations of forward models, multimodality, and inaccessible gradients for the forward model. To address them, we develop a variational inference framework that combines Fisher-Rao natural gradient with specialized quadrature rules to enable derivative free updates of Gaussian mixture variational families. The resulting method, termed Derivative Free Gaussian Mixture Variational Inference (DF-GMVI), guarantees covariance positivity and affine invariance, offering a stable and efficient framework for approximating complex posterior distributions. The effectiveness of DF-GMVI is demonstrated through numerical experiments on challenging scenarios, including distributions with multiple modes, infinitely many modes, and curved modes in spaces with up to 100 dimensions. The method's practicality is further demonstrated in a large-scale application, where it successfully recovers the initial conditions of the Navier-Stokes equations from solution data at positive times.
Authors: Jiadong Lou, Xu Yuan, Rui Zhang, Xingliang Yuan, Neil Gong, Nian-Feng Tzeng
Abstract: Graph neural networks (GNNs) have exhibited superior performance in various classification tasks on graph-structured data. However, they encounter the potential vulnerability from the link stealing attacks, which can infer the presence of a link between two nodes via measuring the similarity of its incident nodes' prediction vectors produced by a GNN model. Such attacks pose severe security and privacy threats to the training graph used in GNN models. In this work, we propose a novel solution, called Graph Link Disguise (GRID), to defend against link stealing attacks with the formal guarantee of GNN model utility for retaining prediction accuracy. The key idea of GRID is to add carefully crafted noises to the nodes' prediction vectors for disguising adjacent nodes as n-hop indirect neighboring nodes. We take into account the graph topology and select only a subset of nodes (called core nodes) covering all links for adding noises, which can avert the noises offset and have the further advantages of reducing both the distortion loss and the computation cost. Our crafted noises can ensure 1) the noisy prediction vectors of any two adjacent nodes have their similarity level like that of two non-adjacent nodes and 2) the model prediction is unchanged to ensure zero utility loss. Extensive experiments on five datasets are conducted to show the effectiveness of our proposed GRID solution against different representative link-stealing attacks under transductive settings and inductive settings respectively, as well as two influence-based attacks. Meanwhile, it achieves a much better privacy-utility trade-off than existing methods when extended to GNNs.
Authors: Shuaiqun Pan, Diederick Vermetten, Manuel L\'opez-Ib\'a\~nez, Thomas B\"ack, Hao Wang
Abstract: Surrogate models provide efficient alternatives to computationally demanding real world processes but often require large datasets for effective training. A promising solution to this limitation is the transfer of pre-trained surrogate models to new tasks. Previous studies have investigated the transfer of differentiable and non-differentiable surrogate models, typically assuming an affine transformation between the source and target functions. This paper extends previous research by addressing a broader range of transformations, including linear and nonlinear variations. Specifically, we consider the combination of an unknown input warping, such as one modeled by the beta cumulative distribution function, with an unspecified affine transformation. Our approach achieves transfer learning by employing a limited number of data points from the target task to optimize these transformations, minimizing empirical loss on the transfer dataset. We validate the proposed method on the widely used Black-Box Optimization Benchmark (BBOB) testbed and a real-world transfer learning task from the automobile industry. The results underscore the significant advantages of the approach, revealing that the transferred surrogate significantly outperforms both the original surrogate and the one built from scratch using the transfer dataset, particularly in data-scarce scenarios.
Authors: Yunke Wang, Yanxi Li, Chang Xu
Abstract: AI Scaling has traditionally been synonymous with Scaling Up, which builds larger and more powerful models. However, the growing demand for efficiency, adaptability, and collaboration across diverse applications necessitates a broader perspective. This position paper presents a holistic framework for AI scaling, encompassing Scaling Up, Scaling Down, and Scaling Out. It argues that while Scaling Up of models faces inherent bottlenecks, the future trajectory of AI scaling lies in Scaling Down and Scaling Out. These paradigms address critical technical and societal challenges, such as reducing carbon footprint, ensuring equitable access, and enhancing cross-domain collaboration. We explore transformative applications in healthcare, smart manufacturing, and content creation, demonstrating how AI Scaling can enable breakthroughs in efficiency, personalization, and global connectivity. Additionally, we highlight key challenges, including balancing model complexity with interpretability, managing resource constraints, and fostering ethical development. By synthesizing these approaches, we propose a unified roadmap that redefines the future of AI research and application, paving the way for advancements toward Artificial General Intelligence (AGI).
Authors: Panqi Chen, Lei Cheng, Jianlong Li, Weichang Li, Weiqing Liu, Jiang Bian, Shikai Fang
Abstract: Tensor decomposition is a fundamental tool for analyzing multi-dimensional data by learning low-rank factors to represent high-order interactions. While recent works on temporal tensor decomposition have made significant progress by incorporating continuous timestamps in latent factors, they still struggle with general tensor data with continuous indexes not only in the temporal mode but also in other modes, such as spatial coordinates in climate data. Moreover, the challenge of self-adapting model complexity is largely unexplored in functional temporal tensor models, with existing methods being inapplicable in this setting. To address these limitations, we propose functional \underline{C}omplexity-\underline{A}daptive \underline{T}emporal \underline{T}ensor d\underline{E}composition (\textsc{Catte}). Our approach encodes continuous spatial indexes as learnable Fourier features and employs neural ODEs in latent space to learn the temporal trajectories of factors. To enable automatic adaptation of model complexity, we introduce a sparsity-inducing prior over the factor trajectories. We develop an efficient variational inference scheme with an analytical evidence lower bound, enabling sampling-free optimization. Through extensive experiments on both synthetic and real-world datasets, we demonstrate that \textsc{Catte} not only reveals the underlying ranks of functional temporal tensors but also significantly outperforms existing methods in prediction performance and robustness against noise.
Authors: Florian Beier, Moritz Piening, Robert Beinert, Gabriele Steidl
Abstract: We propose a new approach for unsupervised alignment of heterogeneous datasets, which maps data from two different domains without any known correspondences to a common metric space. Our method is based on an unbalanced optimal transport problem with Gromov-Wasserstein marginal penalization. It can be seen as a counterpart to the recently introduced joint multidimensional scaling method. We prove that there exists a minimizer of our functional and that for penalization parameters going to infinity, the corresponding sequence of minimizers converges to a minimizer of the so-called embedded Wasserstein distance. Our model can be reformulated as a quadratic, multi-marginal, unbalanced optimal transport problem, for which a bi-convex relaxation admits a numerical solver via block-coordinate descent. We provide numerical examples for joint embeddings in Euclidean as well as non-Euclidean spaces.
Authors: Chae-Won Lee, Jong-Seok Lee
Abstract: In recent studies of emotional EEG classification, connectivity matrices have been successfully employed as input to convolutional neural networks (CNNs), which can effectively consider inter-regional interaction patterns in EEG. However, we find that such an approach has a limitation that important patterns in connectivity matrices may be lost during the convolutional operations in CNNs. To resolve this issue, we propose and validate an idea to upscale the connectivity matrices to strengthen the local patterns. Experimental results demonstrate that this simple idea can significantly enhance the classification performance.
Authors: Weiyang Kong, Kaiqi Wu, Sen Zhang, Yubao Liu
Abstract: Traffic flow forecasting is a critical spatio-temporal data mining task with wide-ranging applications in intelligent route planning and dynamic traffic management. Recent advancements in deep learning, particularly through Graph Neural Networks (GNNs), have significantly enhanced the accuracy of these forecasts by capturing complex spatio-temporal dynamics. However, the scalability of GNNs remains a challenge due to their exponential growth in model complexity with increasing nodes in the graph. Existing methods to address this issue, including sparsification, decomposition, and kernel-based approaches, either do not fully resolve the complexity issue or risk compromising predictive accuracy. This paper introduces GraphSparseNet (GSNet), a novel framework designed to improve both the scalability and accuracy of GNN-based traffic forecasting models. GraphSparseNet is comprised of two core modules: the Feature Extractor and the Relational Compressor. These modules operate with linear time and space complexity, thereby reducing the overall computational complexity of the model to a linear scale. Our extensive experiments on multiple real-world datasets demonstrate that GraphSparseNet not only significantly reduces training time by 3.51x compared to state-of-the-art linear models but also maintains high predictive performance.
Authors: Yanzhou Pan, Huawei Lin, Yide Ran, Jiamin Chen, Xiaodong Yu, Weijie Zhao, Denghui Zhang, Zhaozhuo Xu
Abstract: Large Language Models (LLMs) heavily rely on high-quality training data, making data valuation crucial for optimizing model performance, especially when working within a limited budget. In this work, we aim to offer a third-party data valuation approach that benefits both data providers and model developers. We introduce a linearized future influence kernel (LinFiK), which assesses the value of individual data samples in improving LLM performance during training. We further propose ALinFiK, a learning strategy to approximate LinFiK, enabling scalable data valuation. Our comprehensive evaluations demonstrate that this approach surpasses existing baselines in effectiveness and efficiency, demonstrating significant scalability advantages as LLM parameters increase.
Authors: Teng Pang, Bingzheng Wang, Guoqiang Wu, Yilong Yin
Abstract: Offline preference-based reinforcement learning (PbRL) mitigates the need for reward definition, aligning with human preferences via preference-driven reward feedback without interacting with the environment. However, the effectiveness of preference-driven reward functions depends on the modeling ability of the learning model, which current MLP-based and Transformer-based methods may fail to adequately provide. To alleviate the failure of the reward function caused by insufficient modeling, we propose a novel preference-based reward acquisition method: Diffusion Preference-based Reward (DPR). Unlike previous methods using Bradley-Terry models for trajectory preferences, we use diffusion models to directly model preference distributions for state-action pairs, allowing rewards to be discriminatively obtained from these distributions. In addition, considering the particularity of preference data that only know the internal relationships of paired trajectories, we further propose Conditional Diffusion Preference-based Reward (C-DPR), which leverages relative preference information to enhance the construction of the diffusion model. We apply the above methods to existing offline reinforcement learning algorithms and a series of experiment results demonstrate that the diffusion-based reward acquisition approach outperforms previous MLP-based and Transformer-based methods.
Authors: Maximilian Kirsch, Jakob Wernicke, Pawan Datta, Christine Preisach
Abstract: Climate change has increased the vulnerability of forests to insect-related damage, resulting in widespread forest loss in Central Europe and highlighting the need for effective, continuous monitoring systems. Remote sensing based forest health monitoring, oftentimes, relies on supervised machine learning algorithms that require labeled training data. Monitoring temporal patterns through time series analysis offers a potential alternative for earlier detection of disturbance but requires substantial storage resources. This study investigates the potential of a Deep Learning algorithm based on a Long Short Term Memory (LSTM) Autoencoder for the detection of anomalies in forest health (e.g. bark beetle outbreaks), utilizing Sentinel-2 time series data. This approach is an alternative to supervised machine learning methods, avoiding the necessity for labeled training data. Furthermore, it is more memory-efficient than other time series analysis approaches, as a robust model can be created using only a 26-week-long time series as input. In this study, we monitored pure stands of spruce in Thuringia, Germany, over a 7-year period from 2018 to the end of 2024. Our best model achieved a detection accuracy of 87% on test data and was able to detect 61% of all anomalies at a very early stage (more than a month before visible signs of forest degradation). Compared to another widely used time series break detection algorithm - BFAST (Breaks For Additive Season and Trend), our approach consistently detected higher percentage of anomalies at an earlier stage. These findings suggest that LSTM-based Autoencoders could provide a promising, resource-efficient approach to forest health monitoring, enabling more timely responses to emerging threats.
Authors: Daniel Mayfrank, Mehmet Velioglu, Alexander Mitsos, Manuel Dahmen
Abstract: Reinforcement learning (RL) can be used to tune data-driven (economic) nonlinear model predictive controllers ((e)NMPCs) for optimal performance in a specific control task by optimizing the dynamic model or parameters in the policy's objective function or constraints, such as state bounds. However, the sample efficiency of RL is crucial, and to improve it, we combine a model-based RL algorithm with our published method that turns Koopman (e)NMPCs into automatically differentiable policies. We apply our approach to an eNMPC case study of a continuous stirred-tank reactor (CSTR) model from the literature. The approach outperforms benchmark methods, i.e., data-driven eNMPCs using models based on system identification without further RL tuning of the resulting policy, and neural network controllers trained with model-based RL, by achieving superior control performance and higher sample efficiency. Furthermore, utilizing partial prior knowledge about the system dynamics via physics-informed learning further increases sample efficiency.
Authors: Shriyank Somvanshi, Md Monzurul Islam, Mahmuda Sultana Mimi, Sazzad Bin Bashar Polock, Gaurab Chhetri, Subasish Das
Abstract: Recent advancements in sequence modeling have led to the emergence of Structured State Space Models (SSMs) as an efficient alternative to Recurrent Neural Networks (RNNs) and Transformers, addressing challenges in long-range dependency modeling and computational efficiency. While RNNs suffer from vanishing gradients and sequential inefficiencies, and Transformers face quadratic complexity, SSMs leverage structured recurrence and state-space representations to achieve superior long-sequence processing with linear or near-linear complexity. This survey provides a comprehensive review of SSMs, tracing their evolution from the foundational S4 model to its successors like Mamba, Simplified Structured State Space Sequence Model (S5), and Jamba, highlighting their improvements in computational efficiency, memory optimization, and inference speed. By comparing SSMs with traditional sequence models across domains such as natural language processing (NLP), speech recognition, vision, and time-series forecasting, we demonstrate their advantages in handling long-range dependencies while reducing computational overhead. Despite their potential, challenges remain in areas such as training optimization, hybrid modeling, and interpretability. This survey serves as a structured guide for researchers and practitioners, detailing the advancements, trade-offs, and future directions of SSM-based architectures in AI and deep learning.
Authors: William Claster, Suhas KM, Dhairya Gundechia
Abstract: We propose Adaptive Integrated Layered Attention (AILA), a neural network architecture that combines dense skip connections with different mechanisms for adaptive feature reuse across network layers. We evaluate AILA on three challenging tasks: price forecasting for various commodities and indices (S&P 500, Gold, US dollar Futures, Coffee, Wheat), image recognition using the CIFAR-10 dataset, and sentiment analysis on the IMDB movie review dataset. In all cases, AILA matches strong deep learning baselines (LSTMs, Transformers, and ResNets), achieving it at a fraction of the training and inference time. Notably, we implement and test two versions of the model - AILA-Architecture 1, which uses simple linear layers as the connection mechanism between layers, and AILA-Architecture 2, which implements an attention mechanism to selectively focus on outputs from previous layers. Both architectures are applied in a single-task learning setting, with each model trained separately for individual tasks. Results confirm that AILA's adaptive inter-layer connections yield robust gains by flexibly reusing pertinent features at multiple network depths. The AILA approach thus presents an extension to existing architectures, improving long-range sequence modeling, image recognition with optimised computational speed, and SOTA classification performance in practice.
Authors: Bingxu Wang, Min Ge, Kunzhi Cai, Yuqi Zhang, Zeyi Zhou, Wenjiao Li, Yachong Guo, Wei Wang, Qing Zhou
Abstract: Postoperative delirium (POD), a severe neuropsychiatric complication affecting nearly 50% of high-risk surgical patients, is defined as an acute disorder of attention and cognition, It remains significantly underdiagnosed in the intensive care units (ICUs) due to subjective monitoring methods. Early and accurate diagnosis of POD is critical and achievable. Here, we propose a POD prediction framework comprising a Transformer representation model followed by traditional machine learning algorithms. Our approaches utilizes multi-modal physiological data, including amplitude-integrated electroencephalography (aEEG), vital signs, electrocardiographic monitor data as well as hemodynamic parameters. We curated the first multi-modal POD dataset encompassing two patient types and evaluated the various Transformer architectures for representation learning. Empirical results indicate a consistent improvements of sensitivity and Youden index in patient TYPE I using Transformer representations, particularly our fusion adaptation of Pathformer. By enabling effective delirium diagnosis from postoperative day 1 to 3, our extensive experimental findings emphasize the potential of multi-modal physiological data and highlight the necessity of representation learning via multi-modal Transformer architecture in clinical diagnosis.
Authors: Jiaqi He, Xiangwen Luo, Yiping Wang
Abstract: At the current stage, deep learning-based methods have demonstrated excellent capabilities in evaluating aerodynamic performance, significantly reducing the time and cost required for traditional computational fluid dynamics (CFD) simulations. However, when faced with the task of processing extremely complex three-dimensional (3D) vehicle models, the lack of large-scale datasets and training resources, coupled with the inherent diversity and complexity of the geometry of different vehicle models, means that the prediction accuracy and versatility of these networks are still not up to the level required for current production. In view of the remarkable success of Transformer models in the field of natural language processing and their strong potential in the field of image processing, this study innovatively proposes a point cloud learning framework called DrivAer Transformer (DAT). The DAT structure uses the DrivAerNet++ dataset, which contains high-fidelity CFD data of industrial-standard 3D vehicle shapes. enabling accurate estimation of air drag directly from 3D meshes, thus avoiding the limitations of traditional methods such as 2D image rendering or signed distance fields (SDF). DAT enables fast and accurate drag prediction, driving the evolution of the aerodynamic evaluation process and laying the critical foundation for introducing a data-driven approach to automotive design. The framework is expected to accelerate the vehicle design process and improve development efficiency.
Authors: Lucas Maisonnave, Cyril Moineau, Olivier Bichler, Fabrice Rastello
Abstract: Large language models (LLMs) have become pivotal in artificial intelligence, demonstrating strong capabilities in reasoning, understanding, and generating data. However, their deployment on edge devices is hindered by their substantial size, often reaching several billion parameters. Quantization is a widely used method to reduce memory usage and inference time, however LLMs present unique challenges due to the prevalence of outliers in their activations. In this work, we leverage the theoretical advantages of Hadamard matrices over random rotation matrices to push the boundaries of quantization in LLMs. We demonstrate that Hadamard matrices are more effective in reducing outliers, which are a significant obstacle in achieving low-bit quantization. Our method based on a gradual binary search enables 3-bit quantization for weights, activations, and key-value (KV) caches, resulting in a 40% increase in accuracy on common benchmarks compared to SoTA methods. We extend the use of rotation matrices to support non-power-of-2 embedding dimensions, similar to the Qwen architecture, by employing the Paley algorithm. We theoretically demonstrates the superiority of Hadamard matrices in reducing outliers.We achieved 3-bit quantization for weights, activations, and KV cache, significantly enhancing model performance. Our experimental results on multiple models family like Mistral, LLaMA, and Qwen demonstrate the effectiveness of our approach, outperforming existing methods and enabling practical 3-bit quantization.
Authors: Till Rossner, Ziteng Li, Jonas Balke, Nikoo Salehfard, Tom Seifert, Ming Tang
Abstract: AI-driven drug response prediction holds great promise for advancing personalized cancer treatment. However, the inherent heterogenity of cancer and high cost of data generation make accurate prediction challenging. In this study, we investigate whether incorporating the pretrained foundation model scGPT can enhance the performance of existing drug response prediction frameworks. Our approach builds on the DeepCDR framework, which encodes drug representations from graph structures and cell representations from multi-omics profiles. We adapt this framework by leveraging scGPT to generate enriched cell representations using its pretrained knowledge to compensate for limited amount of data. We evaluate our modified framework using IC$_{50}$ values on Pearson correlation coefficient (PCC) and a leave-one-drug out validation strategy, comparing it against the original DeepCDR framework and a prior scFoundation-based approach. scGPT not only outperforms previous approaches but also exhibits greater training stability, highlighting the value of leveraging scGPT-derived knowledge in this domain.
Authors: Yazan Otoum, Arghavan Asad, Amiya Nayak
Abstract: The rapid expansion of IoT ecosystems introduces severe challenges in scalability, security, and real-time decision-making. Traditional centralized architectures struggle with latency, privacy concerns, and excessive resource consumption, making them unsuitable for modern large-scale IoT deployments. This paper presents a novel Federated Learning-driven Large Language Model (FL-LLM) framework, designed to enhance IoT system intelligence while ensuring data privacy and computational efficiency. The framework integrates Generative IoT (GIoT) models with a Gradient Sensing Federated Strategy (GSFS), dynamically optimizing model updates based on real-time network conditions. By leveraging a hybrid edge-cloud processing architecture, our approach balances intelligence, scalability, and security in distributed IoT environments. Evaluations on the IoT-23 dataset demonstrate that our framework improves model accuracy, reduces response latency, and enhances energy efficiency, outperforming traditional FL techniques (i.e., FedAvg, FedOpt). These findings highlight the potential of integrating LLM-powered federated learning into large-scale IoT ecosystems, paving the way for more secure, scalable, and adaptive IoT management solutions.
Authors: Mohammad Vahid Jamali, Hamid Saber, Jung Hyun Bae
Abstract: Meta federated learning (FL) is a personalized variant of FL, where multiple agents collaborate on training an initial shared model without exchanging raw data samples. The initial model should be trained in a way that current or new agents can easily adapt it to their local datasets after one or a few fine-tuning steps, thus improving the model personalization. Conventional meta FL approaches minimize the average loss of agents on the local models obtained after one step of fine-tuning. In practice, agents may need to apply several fine-tuning steps to adapt the global model to their local data, especially under highly heterogeneous data distributions across agents. To this end, we present a generalized framework for the meta FL by minimizing the average loss of agents on their local model after any arbitrary number $\nu$ of fine-tuning steps. For this generalized framework, we present a variant of the well-known federated averaging (FedAvg) algorithm and conduct a comprehensive theoretical convergence analysis to characterize the convergence speed as well as behavior of the meta loss functions in both the exact and approximated cases. Our experiments on real-world datasets demonstrate superior accuracy and faster convergence for the proposed scheme compared to conventional approaches.
Authors: Kodai Hirata, Tsuyoshi Okita
Abstract: This paper proposes a method MTL-Swin-Unet which is multi-task learning using transformers for classification and semantic segmentation. For spurious-correlation problems, this method allows us to enhance the image representation with two other image representations: representation obtained by semantic segmentation and representation obtained by image reconstruction. In our experiments, the proposed method outperformed in F-value measure than other classifiers when the test data included slices from the same patient (no covariate shift). Similarly, when the test data did not include slices from the same patient (covariate shift setting), the proposed method outperformed in AUC measure.
Authors: Qi Cheng, Licheng Liu, Yao Zhang, Mu Hong, Shiyuan Luo, Zhenong Jin, Yiqun Xie, Xiaowei Jia
Abstract: Agricultural monitoring is critical for ensuring food security, maintaining sustainable farming practices, informing policies on mitigating food shortage, and managing greenhouse gas emissions. Traditional process-based physical models are often designed and implemented for specific situations, and their parameters could also be highly uncertain. In contrast, data-driven models often use black-box structures and does not explicitly model the inter-dependence between different ecological variables. As a result, they require extensive training data and lack generalizability to different tasks with data distribution shifts and inconsistent observed variables. To address the need for more universal models, we propose a knowledge-guided encoder-decoder model, which can predict key crop variables by leveraging knowledge of underlying processes from multiple physical models. The proposed method also integrates a language model to process complex and inconsistent inputs and also utilizes it to implement a model selection mechanism for selectively combining the knowledge from different physical models. Our evaluations on predicting carbon and nitrogen fluxes for multiple sites demonstrate the effectiveness and robustness of the proposed model under various scenarios.
Authors: Taehyun Cho, Seokhun Ju, Seungyub Han, Dohyeong Kim, Kyungjae Lee, Jungwoo Lee
Abstract: To design rewards that align with human goals, Reinforcement Learning from Human Feedback (RLHF) has emerged as a prominent technique for learning reward functions from human preferences and optimizing policies via reinforcement learning algorithms. However, existing RLHF methods often misinterpret trajectories as being generated by an optimal policy, causing inaccurate likelihood estimation and suboptimal learning. Inspired by Direct Preference Optimization framework which directly learns optimal policy without explicit reward, we propose policy-labeled preference learning (PPL), to resolve likelihood mismatch issues by modeling human preferences with regret, which reflects behavior policy information. We also provide a contrastive KL regularization, derived from regret-based principles, to enhance RLHF in sequential decision making. Experiments in high-dimensional continuous control tasks demonstrate PPL's significant improvements in offline RLHF performance and its effectiveness in online settings.
Authors: Xiyuan Wei, Ming Lin, Fanjiang Ye, Fengguang Song, Liangliang Cao, My T. Thai, Tianbao Yang
Abstract: This paper formalizes an emerging learning paradigm that uses a trained model as a reference to guide and enhance the training of a target model through strategic data selection or weighting, named $\textbf{model steering}$. While ad-hoc methods have been used in various contexts, including the training of large foundation models, its underlying principles remain insufficiently understood, leading to sub-optimal performance. In this work, we propose a theory-driven framework for model steering called $\textbf{DRRho risk minimization}$, which is rooted in Distributionally Robust Optimization (DRO). Through a generalization analysis, we provide theoretical insights into why this approach improves generalization and data efficiency compared to training without a reference model. To the best of our knowledge, this is the first time such theoretical insights are provided for the new learning paradigm, which significantly enhance our understanding and practice of model steering. Building on these insights and the connection between contrastive learning and DRO, we introduce a novel method for Contrastive Language-Image Pretraining (CLIP) with a reference model, termed DRRho-CLIP. Extensive experiments validate the theoretical insights, reveal a superior scaling law compared to CLIP without a reference model, and demonstrate its strength over existing heuristic approaches.
Authors: Abhijit Gupta
Abstract: Commodity price volatility creates economic challenges, necessitating accurate multi-horizon forecasting. Predicting prices for commodities like copper and crude oil is complicated by diverse interacting factors (macroeconomic, supply/demand, geopolitical, etc.). Current models often lack transparency, limiting strategic use. This paper presents a Regularized Sparse Autoencoder (RSAE), a deep learning framework for simultaneous multi-horizon commodity price prediction and discovery of interpretable latent market drivers. The RSAE forecasts prices at multiple horizons (e.g., 1-day, 1-week, 1-month) using multivariate time series. Crucially, L1 regularization ($\|\mathbf{z}\|_1$) on its latent vector $\mathbf{z}$ enforces sparsity, promoting parsimonious explanations of market dynamics through learned factors representing underlying drivers (e.g., demand, supply shocks). Drawing from energy-based models and sparse coding, the RSAE optimizes predictive accuracy while learning sparse representations. Evaluated on historical Copper and Crude Oil data with numerous indicators, our findings indicate the RSAE offers competitive multi-horizon forecasting accuracy and data-driven insights into price dynamics via its interpretable latent space, a key advantage over traditional black-box approaches.
Authors: Gregoire Fournier, Sourav Medya
Abstract: Graph neural networks (GNNs) have been widely used in various domains such as social networks, molecular biology, or recommendation systems. Concurrently, different explanations methods of GNNs have arisen to complement its black-box nature. Explanations of the GNNs' predictions can be categorized into two types--factual and counterfactual. Given a GNN trained on binary classification into ''accept'' and ''reject'' classes, a global counterfactual explanation consists in generating a small set of ''accept'' graphs relevant to all of the input ''reject'' graphs. The transformation of a ''reject'' graph into an ''accept'' graph is called a recourse. A common recourse explanation is a small set of recourse, from which every ''reject'' graph can be turned into an ''accept'' graph. Although local counterfactual explanations have been studied extensively, the problem of finding common recourse for global counterfactual explanation remains unexplored, particularly for GNNs. In this paper, we formalize the common recourse explanation problem, and design an effective algorithm, COMRECGC, to solve it. We benchmark our algorithm against strong baselines on four different real-world graphs datasets and demonstrate the superior performance of COMRECGC against the competitors. We also compare the common recourse explanations to the graph counterfactual explanation, showing that common recourse explanations are either comparable or superior, making them worth considering for applications such as drug discovery or computational biology.
Authors: Neil De La Fuente, Maria Pilligua, Daniel Vidal, Albin Soutiff, Cecilia Curreli, Daniel Cremers, Andrey Barsky
Abstract: Continual learning (CL) aims to learn a sequence of tasks without forgetting prior knowledge, but gradient updates for a new task often overwrite the weights learned earlier, causing catastrophic forgetting (CF). We propose Prototype-Augmented Hypernetworks (PAH), a framework where a single hypernetwork, conditioned on learnable task prototypes, dynamically generates task-specific classifier heads on demand. To mitigate forgetting, PAH combines cross-entropy with dual distillation losses, one to align logits and another to align prototypes, ensuring stable feature representations across tasks. Evaluations on Split-CIFAR100 and TinyImageNet demonstrate that PAH achieves state-of-the-art performance, reaching 74.5 % and 63.7 % accuracy with only 1.7 % and 4.4 % forgetting, respectively, surpassing prior methods without storing samples or heads.
Authors: Yihe Zhou, Shunyu Liu, Yunpeng Qing, Kaixuan Chen, Tongya Zheng, Jie Song, Mingli Song
Abstract: Centralized Training with Decentralized Execution (CTDE) has recently emerged as a popular framework for cooperative Multi-Agent Reinforcement Learning (MARL), where agents can use additional global state information to guide training in a centralized way and make their own decisions only based on decentralized local policies. Despite the encouraging results achieved, CTDE makes an independence assumption on agent policies, which limits agents to adopt global cooperative information from each other during centralized training. Therefore, we argue that existing CTDE methods cannot fully utilize global information for training, leading to an inefficient joint-policy exploration and even suboptimal results. In this paper, we introduce a novel Centralized Advising and Decentralized Pruning (CADP) framework for multi-agent reinforcement learning, that not only enables an efficacious message exchange among agents during training but also guarantees the independent policies for execution. Firstly, CADP endows agents the explicit communication channel to seek and take advices from different agents for more centralized training. To further ensure the decentralized execution, we propose a smooth model pruning mechanism to progressively constraint the agent communication into a closed one without degradation in agent cooperation capability. Empirical evaluations on StarCraft II micromanagement and Google Research Football benchmarks demonstrate that the proposed framework achieves superior performance compared with the state-of-the-art counterparts. Our code will be made publicly available.
Authors: Akifumi Okuno, Shotaro Yagishita
Abstract: In this study, we tackle the challenge of outlier-robust predictive modeling using highly expressive neural networks. Our approach integrates two key components: (1) a transformed trimmed loss (TTL), a computationally efficient variant of the classical trimmed loss, and (2) higher-order variation regularization (HOVR), which imposes smoothness constraints on the prediction function. While traditional robust statistics typically assume low-complexity models such as linear and kernel models, applying TTL alone to modern neural networks may fail to ensure robustness, as their high expressive power allows them to fit both inliers and outliers, even when a robust loss is used. To address this, we revisit the traditional notion of breakdown point and adapt it to the nonlinear function setting, introducing a regularization scheme via HOVR that controls the model's capacity and suppresses overfitting to outliers. We theoretically establish that our training procedure retains a high functional breakdown point, thereby ensuring robustness to outlier contamination. We develop a stochastic optimization algorithm tailored to this framework and provide a theoretical guarantee of its convergence.
Authors: Meiyi Zhu, Caili Guo, Chunyan Feng, Osvaldo Simeone
Abstract: In a membership inference attack (MIA), an attacker exploits the overconfidence exhibited by typical machine learning models to determine whether a specific data point was used to train a target model. In this paper, we analyze the performance of the likelihood ratio attack (LiRA) within an information-theoretical framework that allows the investigation of the impact of the aleatoric uncertainty in the true data generation process, of the epistemic uncertainty caused by a limited training data set, and of the calibration level of the target model. We compare three different settings, in which the attacker receives decreasingly informative feedback from the target model: confidence vector (CV) disclosure, in which the output probability vector is released; true label confidence (TLC) disclosure, in which only the probability assigned to the true label is made available by the model; and decision set (DS) disclosure, in which an adaptive prediction set is produced as in conformal prediction. We derive bounds on the advantage of an MIA adversary with the aim of offering insights into the impact of uncertainty and calibration on the effectiveness of MIAs. Simulation results demonstrate that the derived analytical bounds predict well the effectiveness of MIAs.
Authors: Orlando A. Mendible, Jonathan K. Whitmer, Yamil J. Col\'on
Abstract: Machine learning force fields (MLFFs) promise to accurately describe the potential energy surface of molecules at the ab initio level of theory with improved computational efficiency. Within MLFFs, equivariant graph neural networks (EQNNs) have shown great promise in accuracy and performance and are the focus of this work. The capability of EQNNs to recover free energy surfaces (FES) remains to be thoroughly investigated. In this work, we investigate the impact of collective variables (CVs) distribution within the training data on the accuracy of EQNNs predicting the FES of butane and alanine dipeptide (ADP). A generalizable workflow is presented in which training configurations are generated with classical molecular dynamics simulations, and energies and forces are obtained with ab initio calculations. We evaluate how bond and angle constraints in the training data influence the accuracy of EQNN force fields in reproducing the FES of the molecules at both classical and ab initio levels of theory. Results indicate that the model's accuracy is unaffected by the distribution of sampled CVs during training, given that the training data includes configurations from characteristic regions of the system's FES. However, when the training data is obtained from classical simulations, the EQNN struggles to extrapolate the free energy for configurations with high free energy. In contrast, models trained with the same configurations on ab initio data show improved extrapolation accuracy. The findings underscore the difficulties in creating a comprehensive training dataset for EQNNs to predict FESs and highlight the importance of prior knowledge of the system's FES.
Authors: Kota Kondo, Claudius T. Tewari, Andrea Tagliabue, Jesus Tordesillas, Parker C. Lusk, Mason B. Peterson, Jonathan P. How
Abstract: In decentralized multiagent trajectory planners, agents need to communicate and exchange their positions to generate collision-free trajectories. However, due to localization errors/uncertainties, trajectory deconfliction can fail even if trajectories are perfectly shared between agents. To address this issue, we first present PARM and PARM*, perception-aware, decentralized, asynchronous multiagent trajectory planners that enable a team of agents to navigate uncertain environments while deconflicting trajectories and avoiding obstacles using perception information. PARM* differs from PARM as it is less conservative, using more computation to find closer-to-optimal solutions. While these methods achieve state-of-the-art performance, they suffer from high computational costs as they need to solve large optimization problems onboard, making it difficult for agents to replan at high rates. To overcome this challenge, we present our second key contribution, PRIMER, a learning-based planner trained with imitation learning (IL) using PARM* as the expert demonstrator. PRIMER leverages the low computational requirements at deployment of neural networks and achieves a computation speed up to 5500 times faster than optimization-based approaches.
Authors: Koki Chinzei, Shinichiro Yamano, Quoc Hoan Tran, Yasuhiro Endo, Hirotaka Oshima
Abstract: Quantum neural networks (QNNs) require an efficient training algorithm to achieve practical quantum advantages. A promising approach is gradient-based optimization, where gradients are estimated by quantum measurements. However, QNNs currently lack general quantum algorithms for efficiently measuring gradients, which limits their scalability. To elucidate the fundamental limits and potentials of efficient gradient estimation, we rigorously prove a trade-off between gradient measurement efficiency (the mean number of simultaneously measurable gradient components) and expressivity in deep QNNs. This trade-off indicates that more expressive QNNs require higher measurement costs per parameter for gradient estimation, while reducing QNN expressivity to suit a given task can increase gradient measurement efficiency. We further propose a general QNN ansatz called the stabilizer-logical product ansatz (SLPA), which achieves the trade-off upper bound by exploiting the symmetric structure of the quantum circuit. Numerical experiments show that the SLPA drastically reduces the sample complexity needed for training while maintaining accuracy and trainability compared to well-designed circuits based on the parameter-shift method.
Authors: Nicola Muca Cirone, Jad Hamdan, Cristopher Salvi
Abstract: We present a unified approach to studying certain non-linear random matrix ensembles and associated random neural networks at initialization. This begins with a novel series expansion for neural networks which generalizes Fa\'a di Bruno's formula to an arbitrary number of compositions. The role of monomials is played by random multilinear maps indexed by directed graphs, whose edges correspond to random matrices. Crucially, this expansion linearizes the effect of the activation functions, allowing for the direct application of Wick's principle and the genus expansion technique. As an application, we prove several results about neural networks with random weights. We first give a new proof of the fact that they converge to Gaussian processes as their width tends to infinity. Secondly, we quantify the rate of convergence of the Neural Tangent Kernel to its deterministic limit in Frobenius norm. Finally, we compute the moments of the limiting spectral distribution of the Jacobian (only the first two of which were previously known), expressing them as sums over non-crossing partitions. All of these results are then generalised to the case of neural networks with sparse and non-Gaussian weights, under moment assumptions.
Authors: Jinghan Yao, Sam Ade Jacobs, Masahiro Tanaka, Olatunji Ruwase, Hari Subramoni, Dhabaleswar K. Panda
Abstract: Large Language Models (LLMs) with long context capabilities are integral to complex tasks in natural language processing and computational biology, such as text generation and protein sequence analysis. However, training LLMs directly on extremely long contexts demands considerable GPU resources and increased memory, leading to higher costs and greater complexity. Alternative approaches that introduce long context capabilities via downstream finetuning or adaptations impose significant design limitations. In this paper, we propose Fully Pipelined Distributed Transformer (FPDT) for efficiently training long-context LLMs with extreme hardware efficiency. For GPT and Llama models, we achieve a 16x increase in sequence length that can be trained on the same hardware compared to current state-of-the-art solutions. With our dedicated sequence chunk pipeline design, we can now train 8B LLM with 2 million sequence length on only 4 GPUs, while also maintaining over 55% of MFU. Our proposed FPDT is agnostic to existing training techniques and is proven to work efficiently across different LLM models.
Authors: Federico Barbero, Alex Vitvitskyi, Christos Perivolaropoulos, Razvan Pascanu, Petar Veli\v{c}kovi\'c
Abstract: Positional Encodings (PEs) are a critical component of Transformer-based Large Language Models (LLMs), providing the attention mechanism with important sequence-position information. One of the most popular types of encoding used today in LLMs are Rotary Positional Encodings (RoPE), that rotate the queries and keys based on their relative distance. A common belief is that RoPE is useful because it helps to decay token dependency as relative distance increases. In this work, we argue that this is unlikely to be the core reason. We study the internals of a trained Gemma 7B model to understand how RoPE is being used at a mechanical level. We find that Gemma learns to use RoPE to construct robust "positional" attention patterns by exploiting the highest frequencies. We also find that, in general, Gemma greatly prefers to use the lowest frequencies of RoPE, which we suspect are used to carry semantic information. We mathematically prove interesting behaviours of RoPE and conduct experiments to verify our findings, proposing a modification of RoPE that fixes some highlighted issues and improves performance. We believe that this work represents an interesting step in better understanding PEs in LLMs, which we believe holds crucial value for scaling LLMs to large sizes and context lengths.
Authors: Kanan Gupta, Stephan Wojtowytsch
Abstract: While momentum-based optimization algorithms are commonly used in the notoriously non-convex optimization problems of deep learning, their analysis has historically been restricted to the convex and strongly convex setting. In this article, we partially close this gap between theory and practice and demonstrate that virtually identical guarantees can be obtained in optimization problems with a `benign' non-convexity. We show that these weaker geometric assumptions are well justified in overparametrized deep learning, at least locally. Variations of this result are obtained for a continuous time model of Nesterov's accelerated gradient descent algorithm (NAG), the classical discrete time version of NAG, and versions of NAG with stochastic gradient estimates with purely additive noise and with noise that exhibits both additive and multiplicative scaling.
Authors: Adel Javanmard, Jingwei Ji, Renyuan Xu
Abstract: We study the dynamic pricing problem faced by a broker seeking to learn prices for a large number of credit market securities, such as corporate bonds, government bonds, loans, and other credit-related securities. A major challenge in pricing these securities stems from their infrequent trading and the lack of transparency in over-the-counter (OTC) markets, which leads to insufficient data for individual pricing. Nevertheless, many securities share structural similarities that can be exploited. Moreover, brokers often place small "probing" orders to infer competitors' pricing behavior. Leveraging these insights, we propose a multi-task dynamic pricing framework that leverages the shared structure across securities to enhance pricing accuracy. In the OTC market, a broker wins a quote by offering a more competitive price than rivals. The broker's goal is to learn winning prices while minimizing expected regret against a clairvoyant benchmark. We model each security using a $d$-dimensional feature vector and assume a linear contextual model for the competitor's pricing of the yield, with parameters unknown a priori. We propose the Two-Stage Multi-Task (TSMT) algorithm: first, an unregularized MLE over pooled data to obtain a coarse parameter estimate; second, a regularized MLE on individual securities to refine the parameters. We show that the TSMT achieves a regret bounded by $\tilde{O} ( \delta_{\max} \sqrt{T M d} + M d ) $, outperforming both fully individual and fully pooled baselines, where $M$ is the number of securities and $\delta_{\max}$ quantifies their heterogeneity.
Authors: Rodrigo Carmo Terin
Abstract: Physics-informed neural networks (PINNs) are employed to solve the Dyson--Schwinger equations of quantum electrodynamics (QED) in Euclidean space, with a focus on the non-perturbative generation of the fermion's dynamical mass function in the Landau gauge. By inserting the integral equation directly into the loss function, our PINN framework enables a single neural network to learn a continuous and differentiable representation of the mass function over a spectrum of momenta. Also, we benchmark our approach against a traditional numerical algorithm showing the main differences among them. Our novel strategy, which is expected to be extended to other quantum field theories, is the first step towards forefront applications of machine learning in high-level theoretical physics.
Authors: Niklas Hanselmann, Simon Doll, Marius Cordts, Hendrik P. A. Lensch, Andreas Geiger
Abstract: To handle the complexities of real-world traffic, learning planners for self-driving from data is a promising direction. While recent approaches have shown great progress, they typically assume a setting in which the ground-truth world state is available as input. However, when deployed, planning needs to be robust to the long-tail of errors incurred by a noisy perception system, which is often neglected in evaluation. To address this, previous work has proposed drawing adversarial samples from a perception error model (PEM) mimicking the noise characteristics of a target object detector. However, these methods use simple PEMs that fail to accurately capture all failure modes of detection. In this paper, we present EMPERROR, a novel transformer-based generative PEM, apply it to stress-test an imitation learning (IL)-based planner and show that it imitates modern detectors more faithfully than previous work. Furthermore, it is able to produce realistic noisy inputs that increase the planner's collision rate by up to 85%, demonstrating its utility as a valuable tool for a more complete evaluation of self-driving planners.
Authors: Hanieh Shojaei Miandashti, Qianqian Zou, Claus Brenner
Abstract: Reliable deep learning models require not only accurate predictions but also well-calibrated confidence estimates to ensure dependable uncertainty estimation. This is crucial in safety-critical applications like autonomous driving, which depend on rapid and precise semantic segmentation of LiDAR point clouds for real-time 3D scene understanding. In this work, we introduce a sampling-free approach for estimating well-calibrated confidence values for classification tasks, achieving alignment with true classification accuracy and significantly reducing inference time compared to sampling-based methods. Our evaluation using the Adaptive Calibration Error (ACE) metric for LiDAR semantic segmentation shows that our approach maintains well-calibrated confidence values while achieving increased processing speed compared to a sampling baseline. Additionally, reliability diagrams reveal that our method produces underconfidence rather than overconfident predictions, an advantage for safety-critical applications. Our sampling-free approach offers well-calibrated and time-efficient predictions for LiDAR scene semantic segmentation.
Authors: Mary Paterson, James Moor, Luisa Cutillo
Abstract: Cases of laryngeal cancer are predicted to rise significantly in the coming years. Current diagnostic pathways are inefficient, putting undue stress on both patients and the medical system. Artificial intelligence offers a promising solution by enabling non-invasive detection of laryngeal cancer from patient voice, which could help prioritise referrals more effectively. A major barrier in this field is the lack of reproducible methods. Our work addresses this challenge by introducing a benchmark suite comprising 36 models trained and evaluated on open-source datasets. These models classify patients with benign and malignant voice pathologies. All models are accessible in a public repository, providing a foundation for future research. We evaluate three algorithms and three audio feature sets, including both audio-only inputs and multimodal inputs incorporating demographic and symptom data. Our best model achieves a balanced accuracy of 83.7%, sensitivity of 84.0%, specificity of 83.3%, and AUROC of 91.8%.
Authors: Wenqi Zhang, Hang Zhang, Xin Li, Jiashuo Sun, Yongliang Shen, Weiming Lu, Deli Zhao, Yueting Zhuang, Lidong Bing
Abstract: Compared to image-text pair data, interleaved corpora enable Vision-Language Models (VLMs) to understand the world more naturally like humans. However, such existing datasets are crawled from webpage, facing challenges like low knowledge density, loose image-text relations, and poor logical coherence between images. On the other hand, the internet hosts vast instructional videos (e.g., online geometry courses) that are widely used by humans to learn foundational subjects, yet these valuable resources remain underexplored in VLM training. In this paper, we introduce a high-quality \textbf{multimodal textbook} corpus with richer foundational knowledge for VLM pretraining. It collects over 2.5 years of instructional videos, totaling 22,000 class hours. We first use an LLM-proposed taxonomy to systematically gather instructional videos. Then we progressively extract and refine visual (keyframes), audio (ASR), and textual knowledge (OCR) from the videos, and organize as an image-text interleaved corpus based on temporal order. Compared to its counterparts, our video-centric textbook offers more coherent context, richer knowledge, and better image-text alignment. Experiments demonstrate its superb pretraining performance, particularly in knowledge- and reasoning-intensive tasks like ScienceQA and MathVista. Moreover, VLMs pre-trained on our textbook exhibit outstanding interleaved context awareness, leveraging visual and textual cues in their few-shot context for task solving. Our code are available at https://github.com/DAMO-NLP-SG/multimodal_textbook.
Authors: Liam A. Kruse, Alexandros E. Tzikas, Harrison Delecki, Mansur M. Arief, Mykel J. Kochenderfer
Abstract: Importance sampling is a rare event simulation technique used in Monte Carlo simulations to bias the sampling distribution towards the rare event of interest. By assigning appropriate weights to sampled points, importance sampling allows for more efficient estimation of rare events or tails of distributions. However, importance sampling can fail when the proposal distribution does not effectively cover the target distribution. In this work, we propose a method for more efficient sampling by updating the proposal distribution in the latent space of a normalizing flow. Normalizing flows learn an invertible mapping from a target distribution to a simpler latent distribution. The latent space can be more easily explored during the search for a proposal distribution, and samples from the proposal distribution are recovered in the space of the target distribution via the invertible mapping. We empirically validate our methodology on simulated robotics applications such as autonomous racing and aircraft ground collision avoidance.
Authors: Oleg Sautenkov, Yasheerah Yaqoot, Artem Lykov, Muhammad Ahsan Mustafa, Grik Tadevosyan, Aibek Akhmetkazy, Miguel Altamirano Cabrera, Mikhail Martynov, Sausar Karaf, Dzmitry Tsetserukou
Abstract: The UAV-VLA (Visual-Language-Action) system is a tool designed to facilitate communication with aerial robots. By integrating satellite imagery processing with the Visual Language Model (VLM) and the powerful capabilities of GPT, UAV-VLA enables users to generate general flight paths-and-action plans through simple text requests. This system leverages the rich contextual information provided by satellite images, allowing for enhanced decision-making and mission planning. The combination of visual analysis by VLM and natural language processing by GPT can provide the user with the path-and-action set, making aerial operations more efficient and accessible. The newly developed method showed the difference in the length of the created trajectory in 22% and the mean error in finding the objects of interest on a map in 34.22 m by Euclidean distance in the K-Nearest Neighbors (KNN) approach.
Authors: Kevin Fu, Shalin Anand Jain, Pierce Howell, Harish Ravichandar
Abstract: Recent advances have enabled heterogeneous multi-robot teams to learn complex and effective coordination skills. However, existing neural architectures that support heterogeneous teaming tend to force a trade-off between expressivity and efficiency. Shared-parameter designs prioritize sample efficiency by enabling a single network to be shared across all or a pre-specified subset of robots (via input augmentations), but tend to limit behavioral diversity. In contrast, recent designs employ a separate policy for each robot, enabling greater diversity and expressivity at the cost of efficiency and generalization. Our key insight is that such tradeoffs can be avoided by viewing these design choices as ends of a broad spectrum. Inspired by recent work in transfer and meta learning, and building on prior work in multi-robot task allocation, we propose Capability-Aware Shared Hypernetworks (CASH), a soft weight sharing architecture that uses hypernetworks to efficiently learn a flexible shared policy that dynamically adapts to each robot post-training. By explicitly encoding the impact of robot capabilities (e.g., speed and payload) on collective behavior, CASH enables zero-shot generalization to unseen robots or team compositions. Our experiments involve multiple heterogeneous tasks, three learning paradigms (imitation learning, value-based, and policy-gradient RL), and SOTA multi-robot simulation (JaxMARL) and hardware (Robotarium) platforms. Across all conditions, we find that CASH generates appropriately-diverse behaviors and consistently outperforms baseline architectures in terms of performance and sample efficiency during both training and zero-shot generalization, all with 60%-80% fewer learnable parameters.
Authors: Sara Abdali, Can Goksen, Saeed Amizadeh, Julie E. Maybee, Kazuhito Koishida
Abstract: Investigating NLP through a philosophical lens has recently caught researcher's eyes as it connects computational methods with classical schools of philosophy. This paper introduces a philosophical approach inspired by the \textit{Hegelian Dialectic} for LLMs' \textit{self-reflection}, utilizing a self-dialectical approach to emulate internal critiques and then synthesize new ideas by resolving the opposing points of view. Moreover, this paper investigates the effect of LLMs' temperature for generation by establishing a dynamic annealing approach, which promotes the creativity in the early stages and gradually refines it by focusing on the nuances, as well as a fixed-temperature strategy for generation. We assess the effectiveness of our proposed method in generating novel ideas and in improving the reasoning abilities of LLMs during problem-solving. Moreover, we implement a Multi-Agent Majority Voting (MAMV) strategy to assess the validity and novelty of the generated ideas, which proves useful in the absence of domain experts. Our experiments demonstrate promising results in generating ideas and enhancing problem-solving performance.
Authors: Yutong Yin, Zhaoran Wang
Abstract: Humans exhibit remarkable compositional reasoning by integrating knowledge from various sources. For example, if someone learns ( B = f(A) ) from one source and ( C = g(B) ) from another, they can deduce ( C=g(B)=g(f(A)) ) even without encountering ( ABC ) together, showcasing the generalization ability of human intelligence. In this paper, we introduce a synthetic learning task, "FTCT" (Fragmented at Training, Chained at Testing), to validate the potential of Transformers in replicating this skill and interpret its inner mechanism. In the training phase, data consist of separated knowledge fragments from an overall causal graph. During testing, Transformers must infer complete causal graph traces by integrating these fragments. Our findings demonstrate that few-shot Chain-of-Thought prompting enables Transformers to perform compositional reasoning on FTCT by revealing correct combinations of fragments, even if such combinations were absent in the training data. Furthermore, the emergence of compositional reasoning ability is strongly correlated with the model complexity and training-testing data similarity. We propose, both theoretically and empirically, that Transformers learn an underlying generalizable program from training, enabling effective compositional reasoning during testing.
Authors: Shuai Chen, Yong Zu, Zhixi Feng, Shuyuan Yang, Mengchang Li
Abstract: The growing scarcity of spectrum resources and rapid proliferation of wireless devices make efficient radio network management critical. While deep learning-enhanced Cognitive Radio Technology (CRT) provides promising solutions for tasks such as radio signal classification (RSC), denoising, and spectrum allocation, existing DL-based CRT frameworks are typically task-specific and lack scalability in diverse real-world applications. This limitation naturally leads to the exploration of Large Language Models (LLMs), whose exceptional cross-domain generalization capabilities offer new potential for advancing CRT. To bridge this gap, we propose RadioLLM, a novel framework that integrates Hybrid Prompt and Token Reprogramming (HPTR) for combining radio signal features with expert knowledge, and a Frequency-Attuned Fusion (FAF) module for enhanced high-frequency feature modeling. Extensive evaluations on multiple benchmark datasets demonstrate that RadioLLM achieves superior performance compared to existing baselines in the majority of testing scenarios.
Authors: Shuanghao Bai, Wanqi Zhou, Pengxiang Ding, Wei Zhao, Donglin Wang, Badong Chen
Abstract: Behavior Cloning (BC) is a widely adopted visual imitation learning method in robot manipulation. Current BC approaches often enhance generalization by leveraging large datasets and incorporating additional visual and textual modalities to capture more diverse information. However, these methods overlook whether the learned representations contain redundant information and lack a solid theoretical foundation to guide the learning process. To address these limitations, we adopt an information-theoretic perspective and introduce mutual information to quantify and mitigate redundancy in latent representations. Building on this, we incorporate the Information Bottleneck (IB) principle into BC, which extends the idea of reducing redundancy by providing a structured framework for compressing irrelevant information while preserving task-relevant features. This work presents the first comprehensive study on redundancy in latent representations across various methods, backbones, and experimental settings, while extending the generalizability of the IB to BC. Extensive experiments and analyses on the CortexBench and LIBERO benchmarks demonstrate significant performance improvements with IB, underscoring the importance of reducing input data redundancy and highlighting its practical value for more practical applications. Project Page: https://baishuanghao.github.io/BC-IB.github.io.
Authors: Dylan Waldner, Risto Miikkulainen
Abstract: As AI models grow in power and generality, understanding how agents learn and make decisions in complex environments is critical to promoting ethical behavior. This study introduces the Odyssey, a lightweight, adaptive text based adventure game, providing a scalable framework for exploring AI ethics and safety. The Odyssey examines the ethical implications of implementing biological drives, specifically, self preservation, into three different agents. A Bayesian agent optimized with NEAT, a Bayesian agent optimized with stochastic variational inference, and a GPT 4o agent. The agents select actions at each scenario to survive, adapting to increasingly challenging scenarios. Post simulation analysis evaluates the ethical scores of the agent decisions, uncovering the tradeoffs it navigates to survive. Specifically, analysis finds that when danger increases, agents ethical behavior becomes unpredictable. Surprisingly, the GPT 4o agent outperformed the Bayesian models in both survival and ethical consistency, challenging assumptions about traditional probabilistic methods and raising a new challenge to understand the mechanisms of LLMs' probabilistic reasoning.
Authors: Ioannis Levi, Konstantinos Kyritsis, Vasileios Papapanagiotou, Georgios Tsakiridis, Anastasios Delopoulos
Abstract: Accurate monitoring of eating behavior is crucial for managing obesity and eating disorders such as bulimia nervosa. At the same time, existing methods rely on multiple and/or specialized sensors, greatly harming adherence and ultimately, the quality and continuity of data. This paper introduces a novel approach for estimating the weight of a bite, from a commercial smartwatch. Our publicly-available dataset contains smartwatch inertial data from ten participants, with manually annotated start and end times of each bite along with their corresponding weights from a smart scale, under semi-controlled conditions. The proposed method combines extracted behavioral features such as the time required to load the utensil with food, with statistical features of inertial signals, that serve as input to a Support Vector Regression model to estimate bite weights. Under a leave-one-subject-out cross-validation scheme, our approach achieves a mean absolute error (MAE) of 3.99 grams per bite. To contextualize this performance, we introduce the improvement metric, that measures the relative MAE difference compared to a baseline model. Our method demonstrates a 17.41% improvement, while the adapted state-of-the art method shows a -28.89% performance against that same baseline. The results presented in this work establish the feasibility of extracting meaningful bite weight estimates from commercial smartwatch inertial sensors alone, laying the groundwork for future accessible, non-invasive dietary monitoring systems.
Authors: Anh-Tien Nguyen, Duy Minh Ho Nguyen, Nghiem Tuong Diep, Trung Quoc Nguyen, Nhat Ho, Jacqueline Michelle Metsch, Miriam Cindy Maurer, Daniel Sonntag, Hanibal Bohnenberger, Anne-Christin Hauschild
Abstract: Whole slide pathology image classification presents challenges due to gigapixel image sizes and limited annotation labels, hindering model generalization. This paper introduces a prompt learning method to adapt large vision-language models for few-shot pathology classification. We first extend the Prov-GigaPath vision foundation model, pre-trained on 1.3 billion pathology image tiles, into a vision-language model by adding adaptors and aligning it with medical text encoders via contrastive learning on 923K image-text pairs. The model is then used to extract visual features and text embeddings from few-shot annotations and fine-tunes with learnable prompt embeddings. Unlike prior methods that combine prompts with frozen features using prefix embeddings or self-attention, we propose multi-granular attention that compares interactions between learnable prompts with individual image patches and groups of them. This approach improves the model's ability to capture both fine-grained details and broader context, enhancing its recognition of complex patterns across sub-regions. To further improve accuracy, we leverage (unbalanced) optimal transport-based visual-text distance to secure model robustness by mitigating perturbations that might occur during the data augmentation process. Empirical experiments on lung, kidney, and breast pathology modalities validate the effectiveness of our approach; thereby, we surpass several of the latest competitors and consistently improve performance across diverse architectures, including CLIP, PLIP, and Prov-GigaPath integrated PLIP. We release our implementations and pre-trained models at this MGPATH.
Authors: Nikolaos Dionelis, Nicolas Long\'ep\'e, Alessandra Feliciotti, Mattia Marconcini, Devis Peressutti, Nika Oman Kadunc, JaeWan Park, Hagai Raja Sinulingga, Steve Andreas Immanuel, Ba Tran, Caroline Arnold
Abstract: Estimating the construction year of buildings is of great importance for sustainability. Sustainable buildings minimize energy consumption and are a key part of responsible and sustainable urban planning and development to effectively combat climate change. By using Artificial Intelligence (AI) and recently proposed powerful Transformer models, we are able to estimate the construction epoch of buildings from a multi-modal dataset. In this paper, we introduce a new benchmark multi-modal dataset, i.e. the Map your City Dataset (MyCD), containing top-view Very High Resolution (VHR) images, Earth Observation (EO) multi-spectral data from the Copernicus Sentinel-2 satellite constellation, and street-view images in many different cities in Europe that are co-localized with respect to the building under study and labelled with the construction epoch. We assess EO generalization performance on new/ previously unseen cities that have been held-out from training and appear only during inference. In this work, we present the community-based data challenge we organized based on MyCD. The AI4EO Challenge ESA MapYourCity was opened in 2024 for 4 months. In this paper, we present the Top-4 performing models of the challenge, and the evaluation results. During inference, the performance of the models using: i) both all three input modalities, and ii) only the two top-view modalities, i.e. without the street-view ground images, is examined. The evaluation results in this work show that the models to estimate the construction year of buildings are effective and can achieve good performance on this difficult important real-world task, even when inference is on previously unseen cities, as well as even when using only the two top-view modalities (i.e. VHR and Sentinel-2) during inference.
Authors: Yang Peng, Kaicheng Jin, Liangyu Zhang, Zhihua Zhang
Abstract: In this paper, we study the finite-sample statistical rates of distributional temporal difference (TD) learning with linear function approximation. The aim of distributional TD learning is to estimate the return distribution of a discounted Markov decision process for a given policy {\pi}. Previous works on statistical analysis of distributional TD learning mainly focus on the tabular case. In contrast, we first consider the linear function approximation setting and derive sharp finite-sample rates. Our theoretical results demonstrate that the sample complexity of linear distributional TD learning matches that of classic linear TD learning. This implies that, with linear function approximation, learning the full distribution of the return from streaming data is no more difficult than learning its expectation (value function). To derive tight sample complexity bounds, we conduct a fine-grained analysis of the linear-categorical Bellman equation and employ the exponential stability arguments for products of random matrices. Our results provide new insights into the statistical efficiency of distributional reinforcement learning algorithms.
Authors: Run He, Di Fang, Yicheng Xu, Yawen Cui, Ming Li, Cen Chen, Ziqian Zeng, Huiping Zhuang
Abstract: Exemplar-Free Class-Incremental Learning (EFCIL) aims to sequentially learn from distinct categories without retaining exemplars but easily suffers from catastrophic forgetting of learned knowledge. While existing EFCIL methods leverage knowledge distillation to alleviate forgetting, they still face two critical challenges: semantic shift and decision bias. Specifically, the embeddings of old tasks shift in the embedding space after learning new tasks, and the classifier becomes biased towards new tasks due to training solely with new data, hindering the balance between old and new knowledge. To address these issues, we propose the Dual-Projection Shift Estimation and Classifier Reconstruction (DPCR) approach for EFCIL. DPCR effectively estimates semantic shift through a dual-projection, which combines a learnable transformation with a row-space projection to capture both task-wise and category-wise shifts. Furthermore, to mitigate decision bias, DPCR employs ridge regression to reformulate a classifier reconstruction process. This reconstruction exploits previous in covariance and prototype of each class after calibration with estimated shift, thereby reducing decision bias. Extensive experiments demonstrate that, on various datasets, DPCR effectively balances old and new tasks, outperforming state-of-the-art EFCIL methods. Our codes are available at https://github.com/RHe502/ICML25-DPCR.
Authors: Mohini Anand, Xavier Tricoche
Abstract: Understanding the complex myocardial architecture is critical for diagnosing and treating heart disease. However, existing methods often struggle to accurately capture this intricate structure from Diffusion Tensor Imaging (DTI) data, particularly due to the lack of ground truth labels and the ambiguous, intertwined nature of fiber trajectories. We present a novel deep learning framework for unsupervised clustering of myocardial fibers, providing a data-driven approach to identifying distinct fiber bundles. We uniquely combine a Bidirectional Long Short-Term Memory network to capture local sequential information along fibers, with a Transformer autoencoder to learn global shape features, with pointwise incorporation of essential anatomical context. Clustering these representations using a density-based algorithm identifies 33 to 62 robust clusters, successfully capturing the subtle distinctions in fiber trajectories with varying levels of granularity. Our framework offers a new, flexible, and quantitative way to analyze myocardial structure, achieving a level of delineation that, to our knowledge, has not been previously achieved, with potential applications in improving surgical planning, characterizing disease-related remodeling, and ultimately, advancing personalized cardiac care.
Authors: Chao Gao, Liren Shan, Vaidehi Srinivas, Aravindan Vijayaraghavan
Abstract: We study the problem of learning a high-density region of an arbitrary distribution over $\mathbb{R}^d$. Given a target coverage parameter $\delta$, and sample access to an arbitrary distribution $D$, we want to output a confidence set $S \subset \mathbb{R}^d$ such that $S$ achieves $\delta$ coverage of $D$, i.e., $\mathbb{P}_{y \sim D} \left[ y \in S \right] \ge \delta$, and the volume of $S$ is as small as possible. This is a central problem in high-dimensional statistics with applications in finding confidence sets, uncertainty quantification, and support estimation. In the most general setting, this problem is statistically intractable, so we restrict our attention to competing with sets from a concept class $C$ with bounded VC-dimension. An algorithm is competitive with class $C$ if, given samples from an arbitrary distribution $D$, it outputs in polynomial time a set that achieves $\delta$ coverage of $D$, and whose volume is competitive with the smallest set in $C$ with the required coverage $\delta$. This problem is computationally challenging even in the basic setting when $C$ is the set of all Euclidean balls. Existing algorithms based on coresets find in polynomial time a ball whose volume is $\exp(\tilde{O}( d/ \log d))$-factor competitive with the volume of the best ball. Our main result is an algorithm that finds a confidence set whose volume is $\exp(\tilde{O}(d^{1/2}))$ factor competitive with the optimal ball having the desired coverage. The algorithm is improper (it outputs an ellipsoid). Combined with our computational intractability result for proper learning balls within an $\exp(\tilde{O}(d^{1-o(1)}))$ approximation factor in volume, our results provide an interesting separation between proper and (improper) learning of confidence sets.
Authors: Julian Cremer, Ross Irwin, Alessandro Tibo, Jon Paul Janet, Simon Olsson, Djork-Arn\'e Clevert
Abstract: We introduce FLOWR, a novel structure-based framework for the generation and optimization of three-dimensional ligands. FLOWR integrates continuous and categorical flow matching with equivariant optimal transport, enhanced by an efficient protein pocket conditioning. Alongside FLOWR, we present SPINDR, a thoroughly curated dataset comprising ligand-pocket co-crystal complexes specifically designed to address existing data quality issues. Empirical evaluations demonstrate that FLOWR surpasses current state-of-the-art diffusion- and flow-based methods in terms of PoseBusters-validity, pose accuracy, and interaction recovery, while offering a significant inference speedup, achieving up to 70-fold faster performance. In addition, we introduce FLOWR:multi, a highly accurate multi-purpose model allowing for the targeted sampling of novel ligands that adhere to predefined interaction profiles and chemical substructures for fragment-based design without the need of re-training or any re-sampling strategies
Authors: Ole-Christian Galbo Engstr{\o}m, Michela Albano-Gaglio, Erik Schou Dreier, Yamine Bouzembrak, Maria Font-i-Furnols, Puneet Mishra, Kim Steenstrup Pedersen
Abstract: Current approaches to chemical map generation from hyperspectral images are based on models such as partial least squares (PLS) regression, generating pixel-wise predictions that do not consider spatial context and suffer from a high degree of noise. This study proposes an end-to-end deep learning approach using a modified version of U-Net and a custom loss function to directly obtain chemical maps from hyperspectral images, skipping all intermediate steps required for traditional pixel-wise analysis. We compare the U-Net with the traditional PLS regression on a real dataset of pork belly samples with associated mean fat reference values. The U-Net obtains a test set root mean squared error of between 9% and 13% lower than that of PLS regression on the task of mean fat prediction. At the same time, U-Net generates fine detail chemical maps where 99.91% of the variance is spatially correlated. Conversely, only 2.53% of the variance in the PLS-generated chemical maps is spatially correlated, indicating that each pixel-wise prediction is largely independent of neighboring pixels. Additionally, while the PLS-generated chemical maps contain predictions far beyond the physically possible range of 0-100%, U-Net learns to stay inside this range. Thus, the findings of this study indicate that U-Net is superior to PLS for chemical map generation.
Authors: Md Fahimuzzman Sohan, A. H. Abdul Hafez, Raid Alzubi
Abstract: Cattle lameness is often caused by hoof injuries or interdigital dermatitis, leads to pain and significantly impacts essential physiological activities such as walking, feeding, and drinking. This study presents a deep learning-based model for detecting cattle lameness, sickness, or gait abnormalities using publicly available video data. The dataset consists of 50 unique videos from 40 individual cattle, recorded from various angles in both indoor and outdoor environments. Half of the dataset represents naturally walking (normal/non-lame) cattle, while the other half consists of cattle exhibiting gait abnormalities (lame). To enhance model robustness and generalizability, data augmentation was applied to the training data. The pre-processed videos were then classified using two deep learning models: ConvLSTM2D and 3D CNN. A comparative analysis of the results demonstrates strong classification performance. Specifically, the 3D CNN model achieved a video-level classification accuracy of 90%, with precision, recall, and f1-score of 90.9%, 90.9%, and 90.91% respectively. The ConvLSTM2D model exhibited a slightly lower accuracy of 85%. This study highlights the effectiveness of directly applying classification models to learn spatiotemporal features from video data, offering an alternative to traditional multi-stage approaches that typically involve object detection, pose estimation, and feature extraction. Besides, the findings demonstrate that the proposed deep learning models, particularly the 3D CNN, effectively classify and detect lameness in cattle while simplifying the processing pipeline.
Authors: Gionni Marchetti
Abstract: We present a machine learning analysis of circular dichroism spectra of globular proteins from the SP175 database, using the optimal transport-based $1$-Wasserstein distance $\mathcal{W}_1$ (with order $p=1$) and the manifold learning algorithm $t$-SNE. Our results demonstrate that $\mathcal{W}_1$ is consistent with both Euclidean and Manhattan metrics while exhibiting robustness to noise. On the other hand, $t$-SNE uncovers meaningful structure in the high-dimensional data. The clustering in the $t$-SNE embedding is primarily determined by proteins with distinct secondary structure compositions: one cluster predominantly contains $\beta$-rich proteins, while the other consists mainly of proteins with mixed $\alpha/\beta$ and $\alpha$-helical content.
Authors: Yazan Otoum, Arghavan Asad, Amiya Nayak
Abstract: The increasing complexity and scale of the Internet of Things (IoT) have made security a critical concern. This paper presents a novel Large Language Model (LLM)-based framework for comprehensive threat detection and prevention in IoT environments. The system integrates lightweight LLMs fine-tuned on IoT-specific datasets (IoT-23, TON_IoT) for real-time anomaly detection and automated, context-aware mitigation strategies optimized for resource-constrained devices. A modular Docker-based deployment enables scalable and reproducible evaluation across diverse network conditions. Experimental results in simulated IoT environments demonstrate significant improvements in detection accuracy, response latency, and resource efficiency over traditional security methods. The proposed framework highlights the potential of LLM-driven, autonomous security solutions for future IoT ecosystems.
Authors: Yazan Otoum, Arghavan Asad, Ishtiaq Ahmad
Abstract: The proliferation of connected vehicles within the Internet of Vehicles (IoV) ecosystem presents critical challenges in ensuring scalable, real-time, and privacy-preserving traffic management. Existing centralized IoV solutions often suffer from high latency, limited scalability, and reliance on proprietary Artificial Intelligence (AI) models, creating significant barriers to widespread deployment, particularly in dynamic and privacy-sensitive environments. Meanwhile, integrating Large Language Models (LLMs) in vehicular systems remains underexplored, especially concerning prompt optimization and effective utilization in federated contexts. To address these challenges, we propose the Federated Prompt-Optimized Traffic Transformer (FPoTT), a novel framework that leverages open-source LLMs for predictive IoV management. FPoTT introduces a dynamic prompt optimization mechanism that iteratively refines textual prompts to enhance trajectory prediction. The architecture employs a dual-layer federated learning paradigm, combining lightweight edge models for real-time inference with cloud-based LLMs to retain global intelligence. A Transformer-driven synthetic data generator is incorporated to augment training with diverse, high-fidelity traffic scenarios in the Next Generation Simulation (NGSIM) format. Extensive evaluations demonstrate that FPoTT, utilizing EleutherAI Pythia-1B, achieves 99.86% prediction accuracy on real-world data while maintaining high performance on synthetic datasets. These results underscore the potential of open-source LLMs in enabling secure, adaptive, and scalable IoV management, offering a promising alternative to proprietary solutions in smart mobility ecosystems.
Authors: Kilian Tscharke, Maximilian Wendlinger, Sebastian Issel, Pascal Debus
Abstract: Anomaly Detection (AD) is critical in data analysis, particularly within the domain of IT security. In recent years, Machine Learning (ML) algorithms have emerged as a powerful tool for AD in large-scale data. In this study, we explore the potential of quantum ML approaches, specifically quantum kernel methods, for the application to robust AD. We build upon previous work on Quantum Support Vector Regression (QSVR) for semisupervised AD by conducting a comprehensive benchmark on IBM quantum hardware using eleven datasets. Our results demonstrate that QSVR achieves strong classification performance and even outperforms the noiseless simulation on two of these datasets. Moreover, we investigate the influence of - in the NISQ-era inevitable - quantum noise on the performance of the QSVR. Our findings reveal that the model exhibits robustness to depolarizing, phase damping, phase flip, and bit flip noise, while amplitude damping and miscalibration noise prove to be more disruptive. Finally, we explore the domain of Quantum Adversarial Machine Learning and demonstrate that QSVR is highly vulnerable to adversarial attacks and that noise does not improve the adversarial robustness of the model.
Authors: Sharvi Endait, Ruturaj Ghatage, Aditya Kulkarni, Rajlaxmi Patil, Raviraj Joshi
Abstract: The rapid progress in question-answering (QA) systems has predominantly benefited high-resource languages, leaving Indic languages largely underrepresented despite their vast native speaker base. In this paper, we present IndicSQuAD, a comprehensive multi-lingual extractive QA dataset covering nine major Indic languages, systematically derived from the SQuAD dataset. Building on previous work with MahaSQuAD for Marathi, our approach adapts and extends translation techniques to maintain high linguistic fidelity and accurate answer-span alignment across diverse languages. IndicSQuAD comprises extensive training, validation, and test sets for each language, providing a robust foundation for model development. We evaluate baseline performances using language-specific monolingual BERT models and the multilingual MuRIL-BERT. The results indicate some challenges inherent in low-resource settings. Moreover, our experiments suggest potential directions for future work, including expanding to additional languages, developing domain-specific datasets, and incorporating multimodal data. The dataset and models are publicly shared at https://github.com/l3cube-pune/indic-nlp
Authors: Srecharan Selvam
Abstract: Automating leaf manipulation in agricultural settings faces significant challenges, including the variability of plant morphologies and deformable leaves. We propose a novel hybrid geometric-neural approach for autonomous leaf grasping that combines traditional computer vision with neural networks through self-supervised learning. Our method integrates YOLOv8 for instance segmentation and RAFT-Stereo for 3D depth estimation to build rich leaf representations, which feed into both a geometric feature scoring pipeline and a neural refinement module (GraspPointCNN). The key innovation is our confidence-weighted fusion mechanism that dynamically balances the contribution of each approach based on prediction certainty. Our self-supervised framework uses the geometric pipeline as an expert teacher to automatically generate training data. Experiments demonstrate that our approach achieves an 88.0% success rate in controlled environments and 84.7% in real greenhouse conditions, significantly outperforming both purely geometric (75.3%) and neural (60.2%) methods. This work establishes a new paradigm for agricultural robotics where domain expertise is seamlessly integrated with machine learning capabilities, providing a foundation for fully automated crop monitoring systems.
Authors: Asif Rahman, Veljko Cvetkovic, Kathleen Reece, Aidan Walters, Yasir Hassan, Aneesh Tummeti, Bryan Torres, Denise Cooney, Margaret Ellis, Dimitrios S. Nikolopoulos
Abstract: Large language models (LLMs) have transformed software development through code generation capabilities, yet their effectiveness for high-performance computing (HPC) remains limited. HPC code requires specialized optimizations for parallelism, memory efficiency, and architecture-specific considerations that general-purpose LLMs often overlook. We present MARCO (Multi-Agent Reactive Code Optimizer), a novel framework that enhances LLM-generated code for HPC through a specialized multi-agent architecture. MARCO employs separate agents for code generation and performance evaluation, connected by a feedback loop that progressively refines optimizations. A key innovation is MARCO's web-search component that retrieves real-time optimization techniques from recent conference proceedings and research publications, bridging the knowledge gap in pre-trained LLMs. Our extensive evaluation on the LeetCode 75 problem set demonstrates that MARCO achieves a 14.6% average runtime reduction compared to Claude 3.5 Sonnet alone, while the integration of the web-search component yields a 30.9% performance improvement over the base MARCO system. These results highlight the potential of multi-agent systems to address the specialized requirements of high-performance code generation, offering a cost-effective alternative to domain-specific model fine-tuning.
Authors: Shan Yu, Jiarong Xing, Yifan Qiao, Mingyuan Ma, Yangmin Li, Yang Wang, Shuo Yang, Zhiqiang Xie, Shiyi Cao, Ke Bao, Ion Stoica, Harry Xu, Ying Sheng
Abstract: Serving large language models (LLMs) is expensive, especially for providers hosting many models, making cost reduction essential. The unique workload patterns of serving multiple LLMs (i.e., multi-LLM serving) create new opportunities and challenges for this task. The long-tail popularity of models and their long idle periods present opportunities to improve utilization through GPU sharing. However, existing GPU sharing systems lack the ability to adjust their resource allocation and sharing policies at runtime, making them ineffective at meeting latency service-level objectives (SLOs) under rapidly fluctuating workloads. This paper presents Prism, a multi-LLM serving system that unleashes the full potential of GPU sharing to achieve both cost efficiency and SLO attainment. At its core, Prism tackles a key limitation of existing systems$\unicode{x2014}$the lack of $\textit{cross-model memory coordination}$, which is essential for flexibly sharing GPU memory across models under dynamic workloads. Prism achieves this with two key designs. First, it supports on-demand memory allocation by dynamically mapping physical to virtual memory pages, allowing flexible memory redistribution among models that space- and time-share a GPU. Second, it improves memory efficiency through a two-level scheduling policy that dynamically adjusts sharing strategies based on models' runtime demands. Evaluations on real-world traces show that Prism achieves more than $2\times$ cost savings and $3.3\times$ SLO attainment compared to state-of-the-art systems.
Authors: Hongyi Chen, Yunchao Yao, Yufei Ye, Zhixuan Xu, Homanga Bharadhwaj, Jiashun Wang, Shubham Tulsiani, Zackory Erickson, Jeffrey Ichnowski
Abstract: Functional grasp is essential for enabling dexterous multi-finger robot hands to manipulate objects effectively. However, most prior work either focuses on power grasping, which simply involves holding an object still, or relies on costly teleoperated robot demonstrations to teach robots how to grasp each object functionally. Instead, we propose extracting human grasp information from web images since they depict natural and functional object interactions, thereby bypassing the need for curated demonstrations. We reconstruct human hand-object interaction (HOI) 3D meshes from RGB images, retarget the human hand to multi-finger robot hands, and align the noisy object mesh with its accurate 3D shape. We show that these relatively low-quality HOI data from inexpensive web sources can effectively train a functional grasping model. To further expand the grasp dataset for seen and unseen objects, we use the initially-trained grasping policy with web data in the IsaacGym simulator to generate physically feasible grasps while preserving functionality. We train the grasping model on 10 object categories and evaluate it on 9 unseen objects, including challenging items such as syringes, pens, spray bottles, and tongs, which are underrepresented in existing datasets. The model trained on the web HOI dataset, achieving a 75.8% success rate on seen objects and 61.8% across all objects in simulation, with a 6.7% improvement in success rate and a 1.8x increase in functionality ratings over baselines. Simulator-augmented data further boosts performance from 61.8% to 83.4%. The sim-to-real transfer to the LEAP Hand achieves a 85% success rate. Project website is at: https://web2grasp.github.io/.
Authors: Kalyan Nakka, Jimmy Dani, Ausmit Mondal, Nitesh Saxena
Abstract: The growing adoption of Large Language Models (LLMs) has influenced the development of their lighter counterparts-Small Language Models (SLMs)-to enable on-device deployment across smartphones and edge devices. These SLMs offer enhanced privacy, reduced latency, server-free functionality, and improved user experience. However, due to resource constraints of on-device environment, SLMs undergo size optimization through compression techniques like quantization, which can inadvertently introduce fairness, ethical and privacy risks. Critically, quantized SLMs may respond to harmful queries directly, without requiring adversarial manipulation, raising significant safety and trust concerns. To address this, we propose LiteLMGuard (LLMG), an on-device prompt guard that provides real-time, prompt-level defense for quantized SLMs. Additionally, our prompt guard is designed to be model-agnostic such that it can be seamlessly integrated with any SLM, operating independently of underlying architectures. Our LLMG formalizes prompt filtering as a deep learning (DL)-based prompt answerability classification task, leveraging semantic understanding to determine whether a query should be answered by any SLM. Using our curated dataset, Answerable-or-Not, we trained and fine-tuned several DL models and selected ELECTRA as the candidate, with 97.75% answerability classification accuracy. Our safety effectiveness evaluations demonstrate that LLMG defends against over 87% of harmful prompts, including both direct instruction and jailbreak attack strategies. We further showcase its ability to mitigate the Open Knowledge Attacks, where compromised SLMs provide unsafe responses without adversarial prompting. In terms of prompt filtering effectiveness, LLMG achieves near state-of-the-art filtering accuracy of 94%, with an average latency of 135 ms, incurring negligible overhead for users.
Authors: Olaf Wysocki, Benedikt Schwab, Manoj Kumar Biswanath, Michael Greza, Qilin Zhang, Jingwei Zhu, Thomas Froech, Medhini Heeramaglore, Ihab Hijazi, Khaoula Kanna, Mathias Pechinger, Zhaiyu Chen, Yao Sun, Alejandro Rueda Segura, Ziyang Xu, Omar AbdelGafar, Mansour Mehranfar, Chandan Yeshwanth, Yueh-Cheng Liu, Hadi Yazdi, Jiapan Wang, Stefan Auer, Katharina Anders, Klaus Bogenberger, Andre Borrmann, Angela Dai, Ludwig Hoegner, Christoph Holst, Thomas H. Kolbe, Ferdinand Ludwig, Matthias Nie{\ss}ner, Frank Petzold, Xiao Xiang Zhu, Boris Jutzi
Abstract: Urban Digital Twins (UDTs) have become essential for managing cities and integrating complex, heterogeneous data from diverse sources. Creating UDTs involves challenges at multiple process stages, including acquiring accurate 3D source data, reconstructing high-fidelity 3D models, maintaining models' updates, and ensuring seamless interoperability to downstream tasks. Current datasets are usually limited to one part of the processing chain, hampering comprehensive UDTs validation. To address these challenges, we introduce the first comprehensive multimodal Urban Digital Twin benchmark dataset: TUM2TWIN. This dataset includes georeferenced, semantically aligned 3D models and networks along with various terrestrial, mobile, aerial, and satellite observations boasting 32 data subsets over roughly 100,000 $m^2$ and currently 767 GB of data. By ensuring georeferenced indoor-outdoor acquisition, high accuracy, and multimodal data integration, the benchmark supports robust analysis of sensors and the development of advanced reconstruction methods. Additionally, we explore downstream tasks demonstrating the potential of TUM2TWIN, including novel view synthesis of NeRF and Gaussian Splatting, solar potential analysis, point cloud semantic segmentation, and LoD3 building reconstruction. We are convinced this contribution lays a foundation for overcoming current limitations in UDT creation, fostering new research directions and practical solutions for smarter, data-driven urban environments. The project is available under: https://tum2t.win
URLs: https://tum2t.win
Authors: Arun S. Maiya
Abstract: We present OnPrem$.$LLM, a Python-based toolkit for applying large language models (LLMs) to sensitive, non-public data in offline or restricted environments. The system is designed for privacy-preserving use cases and provides prebuilt pipelines for document processing and storage, retrieval-augmented generation (RAG), information extraction, summarization, classification, and prompt/output processing with minimal configuration. OnPrem$.$LLM supports multiple LLM backends -- including llama$.$cpp, Ollama, vLLM, and Hugging Face Transformers -- with quantized model support, GPU acceleration, and seamless backend switching. Although designed for fully local execution, OnPrem$.$LLM also supports integration with a wide range of cloud LLM providers when permitted, enabling hybrid deployments that balance performance with data control. A no-code web interface extends accessibility to non-technical users.