Authors: Jun-Peng Jiang, Si-Yang Liu, Hao-Run Cai, Qile Zhou, Han-Jia Ye
Abstract: Tabular data, structured as rows and columns, is among the most prevalent data types in machine learning classification and regression applications. Models for learning from tabular data have continuously evolved, with Deep Neural Networks (DNNs) recently demonstrating promising results through their capability of representation learning. In this survey, we systematically introduce the field of tabular representation learning, covering the background, challenges, and benchmarks, along with the pros and cons of using DNNs. We organize existing methods into three main categories according to their generalization capabilities: specialized, transferable, and general models. Specialized models focus on tasks where training and evaluation occur within the same data distribution. We introduce a hierarchical taxonomy for specialized models based on the key aspects of tabular data -- features, samples, and objectives -- and delve into detailed strategies for obtaining high-quality feature- and sample-level representations. Transferable models are pre-trained on one or more datasets and subsequently fine-tuned on downstream tasks, leveraging knowledge acquired from homogeneous or heterogeneous sources, or even cross-modalities such as vision and language. General models, also known as tabular foundation models, extend this concept further, allowing direct application to downstream tasks without fine-tuning. We group these general models based on the strategies used to adapt across heterogeneous datasets. Additionally, we explore ensemble methods, which integrate the strengths of multiple tabular models. Finally, we discuss representative extensions of tabular learning, including open-environment tabular machine learning, multimodal learning with tabular data, and tabular understanding. More information can be found in the following repository: https://github.com/LAMDA-Tabular/Tabular-Survey.
Authors: Chiung-Yi Tseng, Junhao Song, Ziqian Bi, Tianyang Wang, Chia Xin Liang, Ming Liu
Abstract: In the era of data-driven intelligence, the paradox of data abundance and annotation scarcity has emerged as a critical bottleneck in the advancement of machine learning. This paper gives a detailed overview of Active Learning (AL), which is a strategy in machine learning that helps models achieve better performance using fewer labeled examples. It introduces the basic concepts of AL and discusses how it is used in various fields such as computer vision, natural language processing, transfer learning, and real-world applications. The paper focuses on important research topics such as uncertainty estimation, handling of class imbalance, domain adaptation, fairness, and the creation of strong evaluation metrics and benchmarks. It also shows that learning methods inspired by humans and guided by questions can improve data efficiency and help models learn more effectively. In addition, this paper talks about current challenges in the field, including the need to rebuild trust, ensure reproducibility, and deal with inconsistent methodologies. It points out that AL often gives better results than passive learning, especially when good evaluation measures are used. This work aims to be useful for both researchers and practitioners by providing key insights and proposing directions for future progress in active learning.
Authors: Max Hartman, Lav Varshney
Abstract: Joint Embedding Predictive Architectures (JEPA) have emerged as a powerful framework for learning general-purpose representations. However, these models often lack interpretability and suffer from inefficiencies due to dense embedding representations. We propose SparseJEPA, an extension that integrates sparse representation learning into the JEPA framework to enhance the quality of learned representations. SparseJEPA employs a penalty method that encourages latent space variables to be shared among data features with strong semantic relationships, while maintaining predictive performance. We demonstrate the effectiveness of SparseJEPA by training on the CIFAR-100 dataset and pre-training a lightweight Vision Transformer. The improved embeddings are utilized in linear-probe transfer learning for both image classification and low-level tasks, showcasing the architecture's versatility across different transfer tasks. Furthermore, we provide a theoretical proof that demonstrates that the grouping mechanism enhances representation quality. This was done by displaying that grouping reduces Multiinformation among latent-variables, including proofing the Data Processing Inequality for Multiinformation. Our results indicate that incorporating sparsity not only refines the latent space but also facilitates the learning of more meaningful and interpretable representations. In further work, hope to further extend this method by finding new ways to leverage the grouping mechanism through object-centric representation learning.
Authors: Yue Shi, Liangxiu Han, Xin Zhang, Tam Sobeih, Thomas Gaiser, Nguyen Huu Thuy, Dominik Behrend, Amit Kumar Srivastava, Krishnagopal Halder, Frank Ewert
Abstract: Process-based models (PBMs) and deep learning (DL) are two key approaches in agricultural modelling, each offering distinct advantages and limitations. PBMs provide mechanistic insights based on physical and biological principles, ensuring interpretability and scientific rigour. However, they often struggle with scalability, parameterisation, and adaptation to heterogeneous environments. In contrast, DL models excel at capturing complex, nonlinear patterns from large datasets but may suffer from limited interpretability, high computational demands, and overfitting in data-scarce scenarios. This study presents a systematic review of PBMs, DL models, and hybrid PBM-DL frameworks, highlighting their applications in agricultural and environmental modelling. We classify hybrid PBM-DL approaches into DL-informed PBMs, where neural networks refine process-based models, and PBM-informed DL, where physical constraints guide deep learning predictions. Additionally, we conduct a case study on crop dry biomass prediction, comparing hybrid models against standalone PBMs and DL models under varying data quality, sample sizes, and spatial conditions. The results demonstrate that hybrid models consistently outperform traditional PBMs and DL models, offering greater robustness to noisy data and improved generalisation across unseen locations. Finally, we discuss key challenges, including model interpretability, scalability, and data requirements, alongside actionable recommendations for advancing hybrid modelling in agriculture. By integrating domain knowledge with AI-driven approaches, this study contributes to the development of scalable, interpretable, and reproducible agricultural models that support data-driven decision-making for sustainable agriculture.
Authors: Xiao Zhang, Yaoyao Ding, Yang Hu, Gennady Pekhimenko
Abstract: Deep learning (DL) workloads mainly run on accelerators like GPUs. Recent DL quantization techniques demand a new matrix multiplication operator with mixed input data types, further complicating GPU optimization. Prior high-level compilers like Triton lack the expressiveness to implement key optimizations like fine-grained data pipelines and hardware-friendly memory layouts for these operators, while low-level programming models, such as Hidet, Graphene, and CUTLASS, require significant programming efforts. To balance expressiveness with engineering effort, we propose Hexcute, a tile-based programming language that exposes shared memory and register abstractions to enable fine-grained optimization for these operators. Additionally, Hexcute leverages task mapping to schedule the GPU program, and to reduce programming efforts, it automates layout and task mapping synthesis with a novel type-inference-based algorithm. Our evaluation shows that Hexcute generalizes to a wide range of DL operators, achieves 1.7-11.28$\times$ speedup over existing DL compilers for mixed-type operators, and brings up to 2.91$\times$ speedup in the end-to-end evaluation.
Authors: Rene Pilz, Johannes Schneider
Abstract: This paper explores the idea of using phonemes as a textual representation within a conventional multilingual simultaneous speech-to-speech translation pipeline, as opposed to the traditional reliance on text-based language representations. To investigate this, we trained an open-source sequence-to-sequence model on the WMT17 dataset in two formats: one using standard textual representation and the other employing phonemic representation. The performance of both approaches was assessed using the BLEU metric. Our findings shows that the phonemic approach provides comparable quality but offers several advantages, including lower resource requirements or better suitability for low-resource languages.
Authors: L\'eandre Eberhard, Nirek Sharma, Filipp Shelobolin, Aalok Ganesh Shanbhag
Abstract: As machine learning increasingly influences critical domains such as credit underwriting, public policy, and talent acquisition, ensuring compliance with fairness constraints is both a legal and ethical imperative. This paper introduces a novel framework for fairness adjustments that applies to diverse machine learning tasks, including regression and classification, and accommodates a wide range of fairness metrics. Unlike traditional approaches categorized as pre-processing, in-processing, or post-processing, our method adapts in-processing techniques for use as a post-processing step. By decoupling fairness adjustments from the model training process, our framework preserves model performance on average while enabling greater flexibility in model development. Key advantages include eliminating the need for custom loss functions, enabling fairness tuning using different datasets, accommodating proprietary models as black-box systems, and providing interpretable insights into the fairness adjustments. We demonstrate the effectiveness of this approach by comparing it to Adversarial Debiasing, showing that our framework achieves a comparable fairness/accuracy tradeoff on real-world datasets.
Authors: Tina Behzad, Mithilesh Kumar Singh, Anthony J. Ripa, Klaus Mueller
Abstract: The issue of fairness in decision-making is a critical one, especially given the variety of stakeholder demands for differing and mutually incompatible versions of fairness. Adopting a strategic interaction of perspectives provides an alternative to enforcing a singular standard of fairness. We present a web-based software application, FairPlay, that enables multiple stakeholders to debias datasets collaboratively. With FairPlay, users can negotiate and arrive at a mutually acceptable outcome without a universally agreed-upon theory of fairness. In the absence of such a tool, reaching a consensus would be highly challenging due to the lack of a systematic negotiation process and the inability to modify and observe changes. We have conducted user studies that demonstrate the success of FairPlay, as users could reach a consensus within about five rounds of gameplay, illustrating the application's potential for enhancing fairness in AI systems.
Authors: Junn Yong Loo, Michelle Adeline, Julia Kaiwen Lau, Fang Yu Leong, Hwa Hui Tew, Arghya Pal, Vishnu Monn Baskaran, Chee-Ming Ting, Rapha\"el C. -W. Phan
Abstract: Energy-based models (EBMs) are a powerful class of probabilistic generative models due to their flexibility and interpretability. However, relationships between potential flows and explicit EBMs remain underexplored, while contrastive divergence training via implicit Markov chain Monte Carlo (MCMC) sampling is often unstable and expensive in high-dimensional settings. In this paper, we propose Variational Potential Flow Bayes (VPFB), a new energy-based generative framework that eliminates the need for implicit MCMC sampling and does not rely on auxiliary networks or cooperative training. VPFB learns an energy-parameterized potential flow by constructing a flow-driven density homotopy that is matched to the data distribution through a variational loss minimizing the Kullback-Leibler divergence between the flow-driven and marginal homotopies. This principled formulation enables robust and efficient generative modeling while preserving the interpretability of EBMs. Experimental results on image generation, interpolation, out-of-distribution detection, and compositional generation confirm the effectiveness of VPFB, showing that our method performs competitively with existing approaches in terms of sample quality and versatility across diverse generative modeling tasks.
Authors: Magnus Sieverding, Nathan Steffen, Kelly Cohen
Abstract: This paper presents a performance benchmarking study of a Gradient-Optimized Fuzzy Inference System (GF) classifier against several state-of-the-art machine learning models, including Random Forest, XGBoost, Logistic Regression, Support Vector Machines, and Neural Networks. The evaluation was conducted across five datasets from the UCI Machine Learning Repository, each chosen for their diversity in input types, class distributions, and classification complexity. Unlike traditional Fuzzy Inference Systems that rely on derivative-free optimization methods, the GF leverages gradient descent to significantly improving training efficiency and predictive performance. Results demonstrate that the GF model achieved competitive, and in several cases superior, classification accuracy while maintaining high precision and exceptionally low training times. In particular, the GF exhibited strong consistency across folds and datasets, underscoring its robustness in handling noisy data and variable feature sets. These findings support the potential of gradient optimized fuzzy systems as interpretable, efficient, and adaptable alternatives to more complex deep learning models in supervised learning tasks.
Authors: Abdesslem Layeb
Abstract: In this paper, we introduce a novel data transformation framework based on Opposition-Based Learning (OBL) to boost the performance of traditional classification algorithms. Originally developed to accelerate convergence in optimization tasks, OBL is leveraged here to generate synthetic opposite samples that replace the acutely training data and improve decision boundary formation. We explore three OBL variants; Global OBL, Class-Wise OBL, and Localized Class-Wise OBL; and integrate them with several widely used classifiers, including K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Logistic Regression (LR), and Decision Tree (DT). Extensive experiments conducted on 26 heterogeneous and high-dimensional datasets demonstrate that OBL-enhanced classifiers consistently outperform their standard counterparts in terms of accuracy and F1-score, frequently achieving near-perfect or perfect classification. Furthermore, OBL contributes to improved computational efficiency, particularly in SVM and LR. These findings underscore the potential of OBL as a lightweight yet powerful data transformation strategy for enhancing classification performance, especially in complex or sparse learning environments.
Authors: Ryan Koo, Ian Yang, Vipul Raheja, Mingyi Hong, Kwang-Sung Jun, Dongyeop Kang
Abstract: Current reinforcement learning from human feedback (RLHF) pipelines for large language model (LLM) alignment typically assign scalar rewards to sequences, using the final token as a surrogate indicator for the quality of the entire sequence. However, this leads to sparse feedback and suboptimal token-level credit assignment. In this work, we frame reward shaping as an optimization problem focused on token-level credit assignment. We propose a reward-shaping function leveraging explainability methods such as SHAP and LIME to estimate per-token rewards from the reward model. To learn parameters of this shaping function, we employ a bilevel optimization framework that integrates Bayesian Optimization and policy training to handle noise from the token reward estimates. Our experiments show that achieving a better balance of token-level reward attribution leads to performance improvements over baselines on downstream tasks and finds an optimal policy faster during training. Furthermore, we show theoretically that explainability methods that are feature additive attribution functions maintain the optimal policy as the original reward.
Authors: Jannis Born, Filip Skogh, Kahn Rhrissorrakrai, Filippo Utro, Nico Wagner, Aleksandros Sobczyk
Abstract: At the core of the Transformer, the Softmax normalizes the attention matrix to be right stochastic. Previous research has shown that this often destabilizes training and that enforcing the attention matrix to be doubly stochastic (through Sinkhorn's algorithm) consistently improves performance across different tasks, domains and Transformer flavors. However, Sinkhorn's algorithm is iterative, approximative, non-parametric and thus inflexible w.r.t. the obtained doubly stochastic matrix (DSM). Recently, it has been proven that DSMs can be obtained with a parametric quantum circuit, yielding a novel quantum inductive bias for DSMs with no known classical analogue. Motivated by this, we demonstrate the feasibility of a hybrid classical-quantum doubly stochastic Transformer (QDSFormer) that replaces the Softmax in the self-attention layer with a variational quantum circuit. We study the expressive power of the circuit and find that it yields more diverse DSMs that better preserve information than classical operators. Across multiple small-scale object recognition tasks, we find that our QDSFormer consistently surpasses both a standard Vision Transformer and other doubly stochastic Transformers. Beyond the established Sinkformer, this comparison includes a novel quantum-inspired doubly stochastic Transformer (based on QR decomposition) that can be of independent interest. The QDSFormer also shows improved training stability and lower performance variation suggesting that it may mitigate the notoriously unstable training of ViTs on small-scale data.
Authors: Abhishek Jana, Moeumu Uili, James Atherton, Mark O'Brien, Joe Wood, Leandra Brickson
Abstract: This paper presents an automated one-shot bird call classification pipeline designed for rare species absent from large publicly available classifiers like BirdNET and Perch. While these models excel at detecting common birds with abundant training data, they lack options for species with only 1-3 known recordings-a critical limitation for conservationists monitoring the last remaining individuals of endangered birds. To address this, we leverage the embedding space of large bird classification networks and develop a classifier using cosine similarity, combined with filtering and denoising preprocessing techniques, to optimize detection with minimal training data. We evaluate various embedding spaces using clustering metrics and validate our approach in both a simulated scenario with Xeno-Canto recordings and a real-world test on the critically endangered tooth-billed pigeon (Didunculus strigirostris), which has no existing classifiers and only three confirmed recordings. The final model achieved 1.0 recall and 0.95 accuracy in detecting tooth-billed pigeon calls, making it practical for use in the field. This open-source system provides a practical tool for conservationists seeking to detect and monitor rare species on the brink of extinction.
Authors: Neha Hulkund, Alaa Maalouf, Levi Cai, Daniel Yang, Tsun-Hsuan Wang, Abigail O'Neil, Timm Haucke, Sandeep Mukherjee, Vikram Ramaswamy, Judy Hansen Shen, Gabriel Tseng, Mike Walmsley, Daniela Rus, Ken Goldberg, Hannah Kerner, Irene Chen, Yogesh Girdhar, Sara Beery
Abstract: In many real-world machine learning (ML) applications (e.g. detecting broken bones in x-ray images, detecting species in camera traps), in practice models need to perform well on specific deployments (e.g. a specific hospital, a specific national park) rather than the domain broadly. However, deployments often have imbalanced, unique data distributions. Discrepancy between the training distribution and the deployment distribution can lead to suboptimal performance, highlighting the need to select deployment-specialized subsets from the available training data. We formalize dataset subset selection for specialization (DS3): given a training set drawn from a general distribution and a (potentially unlabeled) query set drawn from the desired deployment-specific distribution, the goal is to select a subset of the training data that optimizes deployment performance. We introduce DataS^3; the first dataset and benchmark designed specifically for the DS3 problem. DataS^3 encompasses diverse real-world application domains, each with a set of distinct deployments to specialize in. We conduct a comprehensive study evaluating algorithms from various families--including coresets, data filtering, and data curation--on DataS^3, and find that general-distribution methods consistently fail on deployment-specific tasks. Additionally, we demonstrate the existence of manually curated (deployment-specific) expert subsets that outperform training on all available data with accuracy gains up to 51.3 percent. Our benchmark highlights the critical role of tailored dataset curation in enhancing performance and training efficiency on deployment-specific distributions, which we posit will only become more important as global, public datasets become available across domains and ML models are deployed in the real world.
Authors: Jaya Narain, Amrit Romana, Vikramjit Mitra, Colin Lea, Shirley Ren
Abstract: Speech and voice conditions can alter the acoustic properties of speech, which could impact the performance of paralinguistic models for affect for people with atypical speech. We evaluate publicly available models for recognizing categorical and dimensional affect from speech on a dataset of atypical speech, comparing results to datasets of typical speech. We investigate three dimensions of speech atypicality: intelligibility, which is related to pronounciation; monopitch, which is related to prosody, and harshness, which is related to voice quality. We look at (1) distributional trends of categorical affect predictions within the dataset, (2) distributional comparisons of categorical affect predictions to similar datasets of typical speech, and (3) correlation strengths between text and speech predictions for spontaneous speech for valence and arousal. We find that the output of affect models is significantly impacted by the presence and degree of speech atypicalities. For instance, the percentage of speech predicted as sad is significantly higher for all types and grades of atypical speech when compared to similar typical speech datasets. In a preliminary investigation on improving robustness for atypical speech, we find that fine-tuning models on pseudo-labeled atypical speech data improves performance on atypical speech without impacting performance on typical speech. Our results emphasize the need for broader training and evaluation datasets for speech emotion models, and for modeling approaches that are robust to voice and speech differences.
Authors: Kisung You
Abstract: Cosine similarity has become a standard metric for comparing embeddings in modern machine learning. Its scale-invariance and alignment with model training objectives have contributed to its widespread adoption. However, recent studies have revealed important limitations, particularly when embedding norms carry meaningful semantic information. This informal article offers a reflective and selective examination of the evolution, strengths, and limitations of cosine similarity. We highlight why it performs well in many settings, where it tends to break down, and how emerging alternatives are beginning to address its blind spots. We hope to offer a mix of conceptual clarity and practical perspective, especially for quantitative scientists who think about embeddings not just as vectors, but as geometric and philosophical objects.
Authors: Mao Wang, Tao Wu, Xingping Xian, Shaojie Qiao, Weina Niu, Canyixing Cui
Abstract: Graphs effectively characterize relational data, driving graph representation learning methods that uncover underlying predictive information. As state-of-the-art approaches, Graph Neural Networks (GNNs) enable end-to-end learning for diverse tasks. Recent disentangled graph representation learning enhances interpretability by decoupling independent factors in graph data. However, existing methods often implicitly and coarsely characterize graph structures, limiting structural pattern analysis within the graph. This paper proposes the Graph Optimal Matching Kernel Convolutional Network (GOMKCN) to address this limitation. We view graphs as node-centric subgraphs, where each subgraph acts as a structural factor encoding position-specific information. This transforms graph prediction into structural pattern recognition. Inspired by CNNs, GOMKCN introduces the Graph Optimal Matching Kernel (GOMK) as a convolutional operator, computing similarities between subgraphs and learnable graph filters. Mathematically, GOMK maps subgraphs and filters into a Hilbert space, representing graphs as point sets. Disentangled representations emerge from projecting subgraphs onto task-optimized filters, which adaptively capture relevant structural patterns via gradient descent. Crucially, GOMK incorporates local correspondences in similarity measurement, resolving the trade-off between differentiability and accuracy in graph kernels. Experiments validate that GOMKCN achieves superior accuracy and interpretability in graph pattern mining and prediction. The framework advances the theoretical foundation for disentangled graph representation learning.
Authors: Neharika Jali, Eshika Pathak, Pranay Sharma, Guannan Qu, Gauri Joshi
Abstract: We consider the problem of non-stationary reinforcement learning (RL) in the infinite-horizon average-reward setting. We model it by a Markov Decision Process with time-varying rewards and transition probabilities, with a variation budget of $\Delta_T$. Existing non-stationary RL algorithms focus on model-based and model-free value-based methods. Policy-based methods despite their flexibility in practice are not theoretically well understood in non-stationary RL. We propose and analyze the first model-free policy-based algorithm, Non-Stationary Natural Actor-Critic (NS-NAC), a policy gradient method with a restart based exploration for change and a novel interpretation of learning rates as adapting factors. Further, we present a bandit-over-RL based parameter-free algorithm BORL-NS-NAC that does not require prior knowledge of the variation budget $\Delta_T$. We present a dynamic regret of $\tilde{\mathscr O}(|S|^{1/2}|A|^{1/2}\Delta_T^{1/6}T^{5/6})$ for both algorithms, where $T$ is the time horizon, and $|S|$, $|A|$ are the sizes of the state and action spaces. The regret analysis leverages a novel adaptation of the Lyapunov function analysis of NAC to dynamic environments and characterizes the effects of simultaneous updates in policy, value function estimate and changes in the environment.
Authors: Andrew Ilyas, Logan Engstrom
Abstract: The goal of predictive data attribution is to estimate how adding or removing a given set of training datapoints will affect model predictions. In convex settings, this goal is straightforward (i.e., via the infinitesimal jackknife). In large-scale (non-convex) settings, however, existing methods are far less successful -- current methods' estimates often only weakly correlate with ground truth. In this work, we present a new data attribution method (MAGIC) that combines classical methods and recent advances in metadifferentiation to (nearly) optimally estimate the effect of adding or removing training data on model predictions.
Authors: Ruixiang Zhang, Shuangfei Zhai, Yizhe Zhang, James Thornton, Zijing Ou, Joshua Susskind, Navdeep Jaitly
Abstract: Discrete diffusion is a promising framework for modeling and generating discrete data. In this work, we present Target Concrete Score Matching (TCSM), a novel and versatile objective for training and fine-tuning discrete diffusion models. TCSM provides a general framework with broad applicability. It supports pre-training discrete diffusion models directly from data samples, and many existing discrete diffusion approaches naturally emerge as special cases of our more general TCSM framework. Furthermore, the same TCSM objective extends to post-training of discrete diffusion models, including fine-tuning using reward functions or preference data, and distillation of knowledge from pre-trained autoregressive models. These new capabilities stem from the core idea of TCSM, estimating the concrete score of the target distribution, which resides in the original (clean) data space. This allows seamless integration with reward functions and pre-trained models, which inherently only operate in the clean data space rather than the noisy intermediate spaces of diffusion processes. Our experiments on language modeling tasks demonstrate that TCSM matches or surpasses current methods. Additionally, TCSM is versatile, applicable to both pre-training and post-training scenarios, offering greater flexibility and sample efficiency.
Authors: Ziran Liang, Rui An, Wenqi Fan, Yanghui Rao, Yuxuan Liang
Abstract: As time evolves, data within specific domains exhibit predictability that motivates time series forecasting to predict future trends from historical data. However, current deep forecasting methods can achieve promising performance but generally lack interpretability, hindering trustworthiness and practical deployment in safety-critical applications such as auto-driving and healthcare. In this paper, we propose a novel interpretable model, iTFKAN, for credible time series forecasting. iTFKAN enables further exploration of model decision rationales and underlying data patterns due to its interpretability achieved through model symbolization. Besides, iTFKAN develops two strategies, prior knowledge injection, and time-frequency synergy learning, to effectively guide model learning under complex intertwined time series data. Extensive experimental results demonstrated that iTFKAN can achieve promising forecasting performance while simultaneously possessing high interpretive capabilities.
Authors: Charlie Hou, Mei-Yu Wang, Yige Zhu, Daniel Lazar, Giulia Fanti
Abstract: In practical settings, differentially private Federated learning (DP-FL) is the dominant method for training models from private, on-device client data. Recent work has suggested that DP-FL may be enhanced or outperformed by methods that use DP synthetic data (Wu et al., 2024; Hou et al., 2024). The primary algorithms for generating DP synthetic data for FL applications require careful prompt engineering based on public information and/or iterative private client feedback. Our key insight is that the private client feedback collected by prior DP synthetic data methods (Hou et al., 2024; Xie et al., 2024) can be viewed as a preference ranking. Our algorithm, Preference Optimization for Private Client Data (POPri) harnesses client feedback using preference optimization algorithms such as Direct Preference Optimization (DPO) to fine-tune LLMs to generate high-quality DP synthetic data. To evaluate POPri, we release LargeFedBench, a new federated text benchmark for uncontaminated LLM evaluations on federated client data. POPri substantially improves the utility of DP synthetic data relative to prior work on LargeFedBench datasets and an existing benchmark from Xie et al. (2024). POPri closes the gap between next-token prediction accuracy in the fully-private and non-private settings by up to 68%, compared to 52% for prior synthetic data methods, and 10% for state-of-the-art DP federated learning methods. The code and data are available at https://github.com/meiyuw/POPri.
Authors: Jeesuk Shin, Cheolwoong Kim, Sunwoong Yang, Minseo Lee, Sung Joong Kim, Joongoo Jeon
Abstract: Severe accidents (SAs) in nuclear power plants have been analyzed using thermal-hydraulic (TH) system codes such as MELCOR and MAAP. These codes efficiently simulate the progression of SAs, while they still have inherent limitations due to their inconsistent finite difference schemes. The use of empirical schemes incorporating both implicit and explicit formulations inherently induces unidirectional coupling in multi-physics analyses. The objective of this study is to develop a novel numerical method for TH system codes using physics-informed neural network (PINN). They have shown strength in solving multi-physics due to the innate feature of neural networks-automatic differentiation. We propose a node-assigned PINN (NA-PINN) that is suitable for the control volume approach-based system codes. NA-PINN addresses the issue of spatial governing equation variation by assigning an individual network to each nodalization of the system code, such that spatial information is excluded from both the input and output domains, and each subnetwork learns to approximate a purely temporal solution. In this phase, we evaluated the accuracy of the PINN methods for the hydrodynamic module. In the 6 water tank simulation, PINN and NA-PINN showed maximum absolute errors of 1.678 and 0.007, respectively. It should be noted that only NA-PINN demonstrated acceptable accuracy. To the best of the authors' knowledge, this is the first study to successfully implement a system code using PINN. Our future work involves extending NA-PINN to a multi-physics solver and developing it in a surrogate manner.
Authors: Rubing Yang, Pratik Chaudhari
Abstract: We derive a differential equation that governs the evolution of the generalization gap when a deep network is trained by gradient descent. This differential equation is controlled by two quantities, a contraction factor that brings together trajectories corresponding to slightly different datasets, and a perturbation factor that accounts for them training on different datasets. We analyze this differential equation to compute an ``effective Gram matrix'' that characterizes the generalization gap after training in terms of the alignment between this Gram matrix and a certain initial ``residual''. Empirical evaluations on image classification datasets indicate that this analysis can predict the test loss accurately. Further, at any point during training, the residual predominantly lies in the subspace of the effective Gram matrix with the smallest eigenvalues. This indicates that the training process is benign, i.e., it does not lead to significant deterioration of the generalization gap (which is zero at initialization). The alignment between the effective Gram matrix and the residual is different for different datasets and architectures. The match/mismatch of the data and the architecture is primarily responsible for good/bad generalization.
Authors: Seungyoon Choi, Sein Kim, Hongseok Kang, Wonjoong Kim, Chanyoung Park
Abstract: Traditional user modeling (UM) approaches have primarily focused on designing models for a single specific task, but they face limitations in generalization and adaptability across various tasks. Recognizing these challenges, recent studies have shifted towards continual learning (CL)-based universal user representation learning aiming to develop a single model capable of handling multiple tasks. Despite advancements, existing methods are in fact evaluated under an unrealistic scenario that does not consider the passage of time as tasks progress, which overlooks newly emerged items that may change the item distribution of previous tasks. In this paper, we introduce a practical evaluation scenario on which CL-based universal user representation learning approaches should be evaluated, which takes into account the passage of time as tasks progress. Then, we propose a novel framework Dynamic Time-aware continual user representation learner, named DITTO, designed to alleviate catastrophic forgetting despite continuous shifts in item distribution, while also allowing the knowledge acquired from previous tasks to adapt to the current shifted item distribution. Through our extensive experiments, we demonstrate the superiority of DITTO over state-of-the-art methods under a practical evaluation scenario. Our source code is available at https://github.com/seungyoon-Choi/DITTO_official.
Authors: Ruxue Shi, Yili Wang, Mengnan Du, Xu Shen, Xin Wang
Abstract: Tabular data remains one of the most prevalent and critical data formats across diverse real-world applications. However, its effective use in machine learning (ML) is often constrained by challenges such as data scarcity, privacy concerns, and class imbalance. Synthetic data generation has emerged as a promising solution, leveraging generative models to learn the distribution of real datasets and produce high-fidelity, privacy-preserving samples. Various generative paradigms have been explored, including energy-based models (EBMs), variational autoencoders (VAEs), generative adversarial networks (GANs), large language models (LLMs), and diffusion models. While several surveys have investigated synthetic tabular data generation, most focus on narrow subdomains or specific generative methods, such as GANs, diffusion models, or privacy-preserving techniques. This limited scope often results in fragmented insights, lacking a comprehensive synthesis that bridges diverse approaches. In particular, recent advances driven by LLMs and diffusion-based models remain underexplored. This gap hinders a holistic understanding of the field`s evolution, methodological interplay, and open challenges. To address this, our survey provides a unified and systematic review of synthetic tabular data generation. Our contributions are threefold: (1) we propose a comprehensive taxonomy that organizes existing methods into traditional approaches, diffusion-based methods, and LLM-based models, and provide an in-depth comparative analysis; (2) we detail the complete pipeline for synthetic tabular data generation, including data synthesis, post-processing, and evaluation; (3) we identify major challenges, explore real-world applications, and outline open research questions and future directions to guide future work in this rapidly evolving area.
Authors: Mohammad Mahdi Abedi, David Pardo, Tariq Alkhalifah
Abstract: Physics-Informed Neural Networks (PINNs) have shown promise in solving partial differential equations (PDEs), including the frequency-domain Helmholtz equation. However, standard training of PINNs using gradient descent (GD) suffers from slow convergence and instability, particularly for high-frequency wavefields. For scattered acoustic wavefield simulation based on Helmholtz equation, we derive a hybrid optimization framework that accelerates training convergence by embedding a least-squares (LS) solver directly into the GD loss function. This formulation enables optimal updates for the linear output layer. Our method is applicable with or without perfectly matched layers (PML), and we provide practical tensor-based implementations for both scenarios. Numerical experiments on benchmark velocity models demonstrate that our approach achieves faster convergence, higher accuracy, and improved stability compared to conventional PINN training. In particular, our results show that the LS-enhanced method converges rapidly even in cases where standard GD-based training fails. The LS solver operates on a small normal matrix, ensuring minimal computational overhead and making the method scalable for large-scale wavefield simulations.
Authors: Adam Izdebski, Jan Olszewski, Pankhil Gawade, Krzysztof Koras, Serra Korkmaz, Valentin Rauscher, Jakub M. Tomczak, Ewa Szczurek
Abstract: Modeling the joint distribution of the data samples and their properties allows to construct a single model for both data generation and property prediction, with synergistic capabilities reaching beyond purely generative or predictive models. However, training joint models presents daunting architectural and optimization challenges. Here, we propose Hyformer, a transformer-based joint model that successfully blends the generative and predictive functionalities, using an alternating attention mask together with a unified pre-training scheme. We show that Hyformer rivals other joint models, as well as state-of-the-art molecule generation and property prediction models. Additionally, we show the benefits of joint modeling in downstream tasks of molecular representation learning, hit identification and antimicrobial peptide design.
Authors: Ignacio Peis, Batuhan Koyuncu, Isabel Valera, Jes Frellsen
Abstract: We introduce a novel generative framework for functions by integrating Implicit Neural Representations (INRs) and Transformer-based hypernetworks into latent variable models. Unlike prior approaches that rely on MLP-based hypernetworks with scalability limitations, our method employs a Transformer-based decoder to generate INR parameters from latent variables, addressing both representation capacity and computational efficiency. Our framework extends latent diffusion models (LDMs) to INR generation by replacing standard decoders with a Transformer-based hypernetwork, which can be trained either from scratch or via hyper-transforming-a strategy that fine-tunes only the decoder while freezing the pre-trained latent space. This enables efficient adaptation of existing generative models to INR-based representations without requiring full retraining.
Authors: Xiaofei Wu, Rongmei Liang
Abstract: In large-scale supervised learning, penalized logistic regression (PLR) effectively addresses the overfitting problem by introducing regularization terms yet its performance still depends on efficient variable selection strategies. This paper theoretically demonstrates that label noise stemming from manual labeling, which is solely related to classification difficulty, represents a type of beneficial noise for variable selection in PLR. This benefit is reflected in a more accurate estimation of the selected non-zero coefficients when compared with the case where only truth labels are used. Under large-scale settings, the sample size for PLR can become very large, making it infeasible to store on a single machine. In such cases, distributed computing methods are required to handle PLR model with manual labeling. This paper presents a partition-insensitive parallel algorithm founded on the ADMM (alternating direction method of multipliers) algorithm to address PLR by incorporating manual labeling. The partition insensitivity of the proposed algorithm refers to the fact that the solutions obtained by the algorithm will not change with the distributed storage of data. In addition, the algorithm has global convergence and a sublinear convergence rate. Experimental results indicate that, as compared with traditional variable selection classification techniques, the PLR with manually-labeled noisy data achieves higher estimation and classification accuracy across multiple large-scale datasets.
Authors: Leo Henry, Thomas Neele, Mohammad Mousavi, Matteo Sammartino
Abstract: Active automata learning infers automaton models of systems from behavioral observations, a technique successfully applied to a wide range of domains. Compositional approaches for concurrent systems have recently emerged. We take a significant step beyond available results, including those by the authors, and develop a general technique for compositional learning of a synchronizing parallel system with an unknown decomposition. Our approach automatically refines the global alphabet into component alphabets while learning the component models. We develop a theoretical treatment of distributions of alphabets, i.e., sets of possibly overlapping component alphabets. We characterize counter-examples that reveal inconsistencies with global observations, and show how to systematically update the distribution to restore consistency. We present a compositional learning algorithm implementing these ideas, where learning counterexamples precisely correspond to distribution counterexamples under well-defined conditions. We provide an implementation, called CoalA, using the state-of-the-art active learning library LearnLib. Our experiments show that in more than 630 subject systems, CoalA delivers orders of magnitude improvements (up to five orders) in membership queries and in systems with significant concurrency, it also achieves better scalability in the number of equivalence queries.
Authors: Haoran Gu, Handing Wang, Yi Mei, Mengjie Zhang, Yaochu Jin
Abstract: Aligning large language models with multiple human expectations and values is crucial for ensuring that they adequately serve a variety of user needs. To this end, offline multiobjective alignment algorithms such as the Rewards-in-Context algorithm have shown strong performance and efficiency. However, inappropriate preference representations and training with imbalanced reward scores limit the performance of such algorithms. In this work, we introduce ParetoHqD that addresses the above issues by representing human preferences as preference directions in the objective space and regarding data near the Pareto front as ''high-quality'' data. For each preference, ParetoHqD follows a two-stage supervised fine-tuning process, where each stage uses an individual Pareto high-quality training set that best matches its preference direction. The experimental results have demonstrated the superiority of ParetoHqD over five baselines on two multiobjective alignment tasks.
Authors: Haoran Chen, Jiapeng Liu, Jiafan Wang, Wenjun Shi
Abstract: Traditional Partial Least Squares Regression (PLSR) models frequently underperform when handling data characterized by uneven categories. To address the issue, this paper proposes a Data Augmentation Partial Least Squares Regression (DAPLSR) model via manifold optimization. The DAPLSR model introduces the Synthetic Minority Over-sampling Technique (SMOTE) to increase the number of samples and utilizes the Value Difference Metric (VDM) to select the nearest neighbor samples that closely resemble the original samples for generating synthetic samples. In solving the model, in order to obtain a more accurate numerical solution for PLSR, this paper proposes a manifold optimization method that uses the geometric properties of the constraint space to improve model degradation and optimization. Comprehensive experiments show that the proposed DAPLSR model achieves superior classification performance and outstanding evaluation metrics on various datasets, significantly outperforming existing methods.
Authors: Zhaohan Daniel Guo, Bernardo Avila Pires, Khimya Khetarpal, Dale Schuurmans, Bo Dai
Abstract: Labeling data is often very time consuming and expensive, leaving us with a majority of unlabeled data. Self-supervised representation learning methods such as SimCLR (Chen et al., 2020) or BYOL (Grill et al., 2020) have been very successful at learning meaningful latent representations from unlabeled image data, resulting in much more general and transferable representations for downstream tasks. Broadly, self-supervised methods fall into two types: 1) Contrastive methods, such as SimCLR; and 2) Non-Contrastive methods, such as BYOL. Contrastive methods are generally trying to maximize mutual information between related data points, so they need to compare every data point to every other data point, resulting in high variance, and thus requiring large batch sizes to work well. Non-contrastive methods like BYOL have much lower variance as they do not need to make pairwise comparisons, but are much trickier to implement as they have the possibility of collapsing to a constant vector. In this paper, we aim to develop a self-supervised objective that combines the strength of both types. We start with a particular contrastive method called the Spectral Contrastive Loss (HaoChen et al., 2021; Lu et al., 2024), and we convert it into a more general non-contrastive form; this removes the pairwise comparisons resulting in lower variance, but keeps the mutual information formulation of the contrastive method preventing collapse. We call our new objective the Mutual Information Non-Contrastive (MINC) loss. We test MINC by learning image representations on ImageNet (similar to SimCLR and BYOL) and show that it consistently improves upon the Spectral Contrastive loss baseline.
Authors: Shuyue Wei, Yongxin Tong, Zimu Zhou, Tianran He, Yi Xu
Abstract: Federated learning paradigm to utilize datasets across multiple data providers. In FL, cross-silo data providers often hesitate to share their high-quality dataset unless their data value can be fairly assessed. Shapley value (SV) has been advocated as the standard metric for data valuation in FL due to its desirable properties. However, the computational overhead of SV is prohibitive in practice, as it inherently requires training and evaluating an FL model across an exponential number of dataset combinations. Furthermore, existing solutions fail to achieve high accuracy and efficiency, making practical use of SV still out of reach, because they ignore choosing suitable computation scheme for approximation framework and overlook the property of utility function in FL. We first propose a unified stratified-sampling framework for two widely-used schemes. Then, we analyze and choose the more promising scheme under the FL linear regression assumption. After that, we identify a phenomenon termed key combinations, where only limited dataset combinations have a high-impact on final data value. Building on these insights, we propose a practical approximation algorithm, IPSS, which strategically selects high-impact dataset combinations rather than evaluating all possible combinations, thus substantially reducing time cost with minor approximation error. Furthermore, we conduct extensive evaluations on the FL benchmark datasets to demonstrate that our proposed algorithm outperforms a series of representative baselines in terms of efficiency and effectiveness.
Authors: Youngmi Hur, Hyojae Lim, Mikyoung Lim
Abstract: In this paper, we develop a wavelet-based theoretical framework for analyzing the universal approximation capabilities of neural networks over a wide range of activation functions. Leveraging wavelet frame theory on the spaces of homogeneous type, we derive sufficient conditions on activation functions to ensure that the associated neural network approximates any functions in the given space, along with an error estimate. These sufficient conditions accommodate a variety of smooth activation functions, including those that exhibit oscillatory behavior. Furthermore, by considering the $L^2$-distance between smooth and non-smooth activation functions, we establish a generalized approximation result that is applicable to non-smooth activations, with the error explicitly controlled by this distance. This provides increased flexibility in the design of network architectures.
Authors: Ceren Yildirim, Kamer Kaya, Sinan Yildirim, Erkay Savas
Abstract: We propose a new framework for Bayesian estimation of differential privacy, incorporating evidence from multiple membership inference attacks (MIA). Bayesian estimation is carried out via a Markov chain Monte Carlo (MCMC) algorithm, named MCMC-DP-Est, which provides an estimate of the full posterior distribution of the privacy parameter (e.g., instead of just credible intervals). Critically, the proposed method does not assume that privacy auditing is performed with the most powerful attack on the worst-case (dataset, challenge point) pair, which is typically unrealistic. Instead, MCMC-DP-Est jointly estimates the strengths of MIAs used and the privacy of the training algorithm, yielding a more cautious privacy analysis. We also present an economical way to generate measurements for the performance of an MIA that is to be used by the MCMC method to estimate privacy. We present the use of the methods with numerical examples with both artificial and real data.
Authors: Wenxuan Li, Hang Zhao, Zhiyuan Yu, Yu Du, Qin Zou, Ruizhen Hu, Kai Xu
Abstract: While non-prehensile manipulation (e.g., controlled pushing/poking) constitutes a foundational robotic skill, its learning remains challenging due to the high sensitivity to complex physical interactions involving friction and restitution. To achieve robust policy learning and generalization, we opt to learn a world model of the 3D rigid body dynamics involved in non-prehensile manipulations and use it for model-based reinforcement learning. We propose PIN-WM, a Physics-INformed World Model that enables efficient end-to-end identification of a 3D rigid body dynamical system from visual observations. Adopting differentiable physics simulation, PIN-WM can be learned with only few-shot and task-agnostic physical interaction trajectories. Further, PIN-WM is learned with observational loss induced by Gaussian Splatting without needing state estimation. To bridge Sim2Real gaps, we turn the learned PIN-WM into a group of Digital Cousins via physics-aware randomizations which perturb physics and rendering parameters to generate diverse and meaningful variations of the PIN-WM. Extensive evaluations on both simulation and real-world tests demonstrate that PIN-WM, enhanced with physics-aware digital cousins, facilitates learning robust non-prehensile manipulation skills with Sim2Real transfer, surpassing the Real2Sim2Real state-of-the-arts.
Authors: Shiyin Tan, Jaeeon Park, Dongyuan Li, Renhe Jiang, Manabu Okumura
Abstract: In the field of multi-document summarization (MDS), transformer-based models have demonstrated remarkable success, yet they suffer an input length limitation. Current methods apply truncation after the retrieval process to fit the context length; however, they heavily depend on manually well-crafted queries, which are impractical to create for each document set for MDS. Additionally, these methods retrieve information at a coarse granularity, leading to the inclusion of irrelevant content. To address these issues, we propose a novel retrieval-based framework that integrates query selection and document ranking and shortening into a unified process. Our approach identifies the most salient elementary discourse units (EDUs) from input documents and utilizes them as latent queries. These queries guide the document ranking by calculating relevance scores. Instead of traditional truncation, our approach filters out irrelevant EDUs to fit the context length, ensuring that only critical information is preserved for summarization. We evaluate our framework on multiple MDS datasets, demonstrating consistent improvements in ROUGE metrics while confirming its scalability and flexibility across diverse model architectures. Additionally, we validate its effectiveness through an in-depth analysis, emphasizing its ability to dynamically select appropriate queries and accurately rank documents based on their relevance scores. These results demonstrate that our framework effectively addresses context-length constraints, establishing it as a robust and reliable solution for MDS.
Authors: Yanan Zhao, Feng Ji, Kai Zhao, Xuhao Li, Qiyu Kang, Wenfei Liang, Yahya Alkhatib, Xingchao Jian, Wee Peng Tay
Abstract: Graph Contrastive Learning (GCL) has recently made progress as an unsupervised graph representation learning paradigm. GCL approaches can be categorized into augmentation-based and augmentation-free methods. The former relies on complex data augmentations, while the latter depends on encoders that can generate distinct views of the same input. Both approaches may require negative samples for training. In this paper, we introduce a novel augmentation-free GCL framework based on graph neural diffusion models. Specifically, we utilize learnable encoders governed by Fractional Differential Equations (FDE). Each FDE is characterized by an order parameter of the differential operator. We demonstrate that varying these parameters allows us to produce learnable encoders that generate diverse views, capturing either local or global information, for contrastive learning. Our model does not require negative samples for training and is applicable to both homophilic and heterophilic datasets. We demonstrate its effectiveness across various datasets, achieving state-of-the-art performance.
Authors: Owain Parry, Phil McMinn
Abstract: The Quantum Approximate Optimization Algorithm (QAOA) is a promising variational algorithm for solving combinatorial optimization problems on near-term devices. However, as the number of layers in a QAOA circuit increases, which is correlated with the quality of the solution, the number of parameters to optimize grows linearly. This results in more iterations required by the classical optimizer, which results in an increasing computational burden as more circuit executions are needed. To mitigate this issue, we introduce QAOA-PCA, a novel reparameterization technique that employs Principal Component Analysis (PCA) to reduce the dimensionality of the QAOA parameter space. By extracting principal components from optimized parameters of smaller problem instances, QAOA-PCA facilitates efficient optimization with fewer parameters on larger instances. Our empirical evaluation on the prominent MaxCut problem demonstrates that QAOA-PCA consistently requires fewer iterations than standard QAOA, achieving substantial efficiency gains. While this comes at the cost of a slight reduction in approximation ratio compared to QAOA with the same number of layers, QAOA-PCA almost always outperforms standard QAOA when matched by parameter count. QAOA-PCA strikes a favorable balance between efficiency and performance, reducing optimization overhead without significantly compromising solution quality.
Authors: Edison Mucllari, Aswin Raghavan, Zachary Alan Daniels
Abstract: Many applications of computer vision require the ability to adapt to novel data distributions after deployment. Adaptation requires algorithms capable of continual learning (CL). Continual learners must be plastic to adapt to novel tasks while minimizing forgetting of previous tasks.However, CL opens up avenues for noise to enter the training pipeline and disrupt the CL. This work focuses on label noise and instance noise in the context of class-incremental learning (CIL), where new classes are added to a classifier over time, and there is no access to external data from past classes. We aim to understand the sensitivity of CL methods that work by replaying items from a memory constructed using the idea of Coresets. We derive a new bound for the robustness of such a method to uncorrelated instance noise under a general additive noise threat model, revealing several insights. Putting the theory into practice, we create two continual learning algorithms to construct noise-tolerant replay buffers. We empirically compare the effectiveness of prior memory-based continual learners and the proposed algorithms under label and uncorrelated instance noise on five diverse datasets. We show that existing memory-based CL are not robust whereas the proposed methods exhibit significant improvements in maximizing classification accuracy and minimizing forgetting in the noisy CIL setting.
Authors: Andrea N\'ovoa, Luca Magri
Abstract: We propose an online learning framework for forecasting nonlinear spatio-temporal signals (fields). The method integrates (i) dimensionality reduction, here, a simple proper orthogonal decomposition (POD) projection; (ii) a generalized autoregressive model to forecast reduced dynamics, here, a reservoir computer; (iii) online adaptation to update the reservoir computer (the model), here, ensemble sequential data assimilation.We demonstrate the framework on a wake past a cylinder governed by the Navier-Stokes equations, exploring the assimilation of full flow fields (projected onto POD modes) and sparse sensors. Three scenarios are examined: a na\"ive physical state estimation; a two-fold estimation of physical and reservoir states; and a three-fold estimation that also adjusts the model parameters. The two-fold strategy significantly improves ensemble convergence and reduces reconstruction error compared to the na\"ive approach. The three-fold approach enables robust online training of partially-trained reservoir computers, overcoming limitations of a priori training. By unifying data-driven reduced order modelling with Bayesian data assimilation, this work opens new opportunities for scalable online model learning for nonlinear time series forecasting.
Authors: Muhammad Khalifa, Rishabh Agarwal, Lajanugen Logeswaran, Jaekyeom Kim, Hao Peng, Moontae Lee, Honglak Lee, Lu Wang
Abstract: Step-by-step verifiers -- also known as process reward models (PRMs) -- are a key ingredient for test-time scaling. PRMs require step-level supervision, making them expensive to train. This work aims to build data-efficient PRMs as verbalized step-wise reward models that verify every step in the solution by generating a verification chain-of-thought (CoT). We propose ThinkPRM, a long CoT verifier fine-tuned on orders of magnitude fewer process labels than those required by discriminative PRMs. Our approach capitalizes on the inherent reasoning abilities of long CoT models, and outperforms LLM-as-a-Judge and discriminative verifiers -- using only 1% of the process labels in PRM800K -- across several challenging benchmarks. Specifically, ThinkPRM beats the baselines on ProcessBench, MATH-500, and AIME '24 under best-of-N selection and reward-guided search. In an out-of-domain evaluation on a subset of GPQA-Diamond and LiveCodeBench, our PRM surpasses discriminative verifiers trained on the full PRM800K by 8% and 4.5%, respectively. Lastly, under the same token budget, ThinkPRM scales up verification compute more effectively compared to LLM-as-a-Judge, outperforming it by 7.2% on a subset of ProcessBench. Our work highlights the value of generative, long CoT PRMs that can scale test-time compute for verification while requiring minimal supervision for training. Our code, data, and models will be released at https://github.com/mukhal/thinkprm.
Authors: Frederik L. Dennig, Nina Geyer, Daniela Blumberg, Yannick Metz, Daniel A. Keim
Abstract: Recently, neural networks have gained attention for creating parametric and invertible multidimensional data projections. Parametric projections allow for embedding previously unseen data without recomputing the projection as a whole, while invertible projections enable the generation of new data points. However, these properties have never been explored simultaneously for arbitrary projection methods. We evaluate three autoencoder (AE) architectures for creating parametric and invertible projections. Based on a given projection, we train AEs to learn a mapping into 2D space and an inverse mapping into the original space. We perform a quantitative and qualitative comparison on four datasets of varying dimensionality and pattern complexity using t-SNE. Our results indicate that AEs with a customized loss function can create smoother parametric and inverse projections than feed-forward neural networks while giving users control over the strength of the smoothing effect.
Authors: Yilin Zhai, Hongyuan Shi, Chao Zhan, Qing Wang, Zaijin You, Nan Wang
Abstract: Accurate wave height prediction is critical for maritime safety and coastal resilience, yet conventional physics-based models and traditional machine learning methods face challenges in computational efficiency and nonlinear dynamics modeling. This study introduces Chronos, the first implementation of a large language model (LLM)-powered temporal architecture (Chronos) optimized for wave forecasting. Through advanced temporal pattern recognition applied to historical wave data from three strategically chosen marine zones in the Northwest Pacific basin, our framework achieves multimodal improvements: (1) 14.3% reduction in training time with 2.5x faster inference speed compared to PatchTST baselines, achieving 0.575 mean absolute scaled error (MASE) units; (2) superior short-term forecasting (1-24h) across comprehensive metrics; (3) sustained predictive leadership in extended-range forecasts (1-120h); and (4) demonstrated zero-shot capability maintaining median performance (rank 4/12) against specialized operational models. This LLM-enhanced temporal modeling paradigm establishes a new standard in wave prediction, offering both computationally efficient solutions and a transferable framework for complex geophysical systems modeling.
Authors: Panagiotis Kakosimos, Alireza Nemat Saberi, Luca Peretti
Abstract: This study explores alternative framework configurations for adapting thermal machine learning (ML) models for power converters by combining transfer learning (TL) and federated learning (FL) in a piecewise manner. This approach inherently addresses challenges such as varying operating conditions, data sharing limitations, and security implications. The framework starts with a base model that is incrementally adapted by multiple clients via adapting three state-of-the-art domain adaptation techniques: Fine-tuning, Transfer Component Analysis (TCA), and Deep Domain Adaptation (DDA). The Flower framework is employed for FL, using Federated Averaging for aggregation. Validation with field data demonstrates that fine-tuning offers a straightforward TL approach with high accuracy, making it suitable for practical applications. Benchmarking results reveal a comprehensive comparison of these methods, showcasing their respective strengths and weaknesses when applied in different scenarios. Locally hosted FL enhances performance when data aggregation is not feasible, while cloud-based FL becomes more practical with a significant increase in the number of clients, addressing scalability and connectivity challenges.
Authors: Mirian Hipolito Garcia, Camille Couturier, Daniel Madrigal Diaz, Ankur Mallick, Anastasios Kyrillidis, Robert Sim, Victor Ruhle, Saravan Rajmohan
Abstract: We study whether Large Language Models (LLMs) inherently capture domain-specific nuances in natural language. Our experiments probe the domain sensitivity of LLMs by examining their ability to distinguish queries from different domains using hidden states generated during the prefill phase. We reveal latent domain-related trajectories that indicate the model's internal recognition of query domains. We also study the robustness of these domain representations to variations in prompt styles and sources. Our approach leverages these representations for model selection, mapping the LLM that best matches the domain trace of the input query (i.e., the model with the highest performance on similar traces). Our findings show that LLMs can differentiate queries for related domains, and that the fine-tuned model is not always the most accurate. Unlike previous work, our interpretations apply to both closed and open-ended generative tasks
Authors: Julian Bedei, Murray McBain, Charles Robert Koch, Jakob Andert, David Gordon
Abstract: Reinforcement Learning (RL) and Machine Learning Integrated Model Predictive Control (ML-MPC) are promising approaches for optimizing hydrogen-diesel dual-fuel engine control, as they can effectively control multiple-input multiple-output systems and nonlinear processes. ML-MPC is advantageous for providing safe and optimal controls, ensuring the engine operates within predefined safety limits. In contrast, RL is distinguished by its adaptability to changing conditions through its learning-based approach. However, the practical implementation of either method alone poses challenges. RL requires high variance in control inputs during early learning phases, which can pose risks to the system by potentially executing unsafe actions, leading to mechanical damage. Conversely, ML-MPC relies on an accurate system model to generate optimal control inputs and has limited adaptability to system drifts, such as injector aging, which naturally occur in engine applications. To address these limitations, this study proposes a hybrid RL and ML-MPC approach that uses an ML-MPC framework while incorporating an RL agent to dynamically adjust the ML-MPC load tracking reference in response to changes in the environment. At the same time, the ML-MPC ensures that actions stay safe throughout the RL agent's exploration. To evaluate the effectiveness of this approach, fuel pressure is deliberately varied to introduce a model-plant mismatch between the ML-MPC and the engine test bench. The result of this mismatch is a root mean square error (RMSE) in indicated mean effective pressure of 0.57 bar when running the ML-MPC. The experimental results demonstrate that RL successfully adapts to changing boundary conditions by altering the tracking reference while ML-MPC ensures safe control inputs. The quantitative improvement in load tracking by implementing RL is an RSME of 0.44 bar.
Authors: Shaden Alshammari, John Hershey, Axel Feldmann, William T. Freeman, Mark Hamilton
Abstract: As the field of representation learning grows, there has been a proliferation of different loss functions to solve different classes of problems. We introduce a single information-theoretic equation that generalizes a large collection of modern loss functions in machine learning. In particular, we introduce a framework that shows that several broad classes of machine learning methods are precisely minimizing an integrated KL divergence between two conditional distributions: the supervisory and learned representations. This viewpoint exposes a hidden information geometry underlying clustering, spectral methods, dimensionality reduction, contrastive learning, and supervised learning. This framework enables the development of new loss functions by combining successful techniques from across the literature. We not only present a wide array of proofs, connecting over 23 different approaches, but we also leverage these theoretical results to create state-of-the-art unsupervised image classifiers that achieve a +8% improvement over the prior state-of-the-art on unsupervised classification on ImageNet-1K. We also demonstrate that I-Con can be used to derive principled debiasing methods which improve contrastive representation learners.
Authors: Arthur Buzelin, Pedro Robles Dutenhefner, Turi Rezende, Luisa G. Porfirio, Pedro Bento, Yan Aquino, Jose Fernandes, Caio Santana, Gabriela Miana, Gisele L. Pappa, Antonio Ribeiro, Wagner Meira Jr
Abstract: Cardiovascular diseases remain the leading cause of global mortality, emphasizing the critical need for efficient diagnostic tools such as electrocardiograms (ECGs). Recent advancements in deep learning, particularly transformers, have revolutionized ECG analysis by capturing detailed waveform features as well as global rhythm patterns. However, traditional transformers struggle to effectively capture local morphological features that are critical for accurate ECG interpretation. We propose a novel Local-Global Attention ECG model (LGA-ECG) to address this limitation, integrating convolutional inductive biases with global self-attention mechanisms. Our approach extracts queries by averaging embeddings obtained from overlapping convolutional windows, enabling fine-grained morphological analysis, while simultaneously modeling global context through attention to keys and values derived from the entire sequence. Experiments conducted on the CODE-15 dataset demonstrate that LGA-ECG outperforms state-of-the-art models and ablation studies validate the effectiveness of the local-global attention strategy. By capturing the hierarchical temporal dependencies and morphological patterns in ECG signals, this new design showcases its potential for clinical deployment with robust automated ECG classification.
Authors: Tianning Feng (Department of Computer Science, Emory University, Atlanta, GA, USA), Junting Ni (Department of Computer Science, Emory University, Atlanta, GA, USA), Ezequiel Gleichgerrcht (Department of Neurology, Emory University, Atlanta, GA, USA), Wei Jin (Department of Computer Science, Emory University, Atlanta, GA, USA)
Abstract: We present SeizureFormer, a Transformer-based model for long-term seizure risk forecasting using interictal epileptiform activity (IEA) surrogate biomarkers and long episode (LE) biomarkers from responsive neurostimulation (RNS) systems. Unlike raw scalp EEG-based models, SeizureFormer leverages structured, clinically relevant features and integrates CNN-based patch embedding, multi-head self-attention, and squeeze-and-excitation blocks to model both short-term dynamics and long-term seizure cycles. Tested across five patients and multiple prediction windows (1 to 14 days), SeizureFormer achieved state-of-the-art performance with mean ROC AUC of 79.44 percent and mean PR AUC of 76.29 percent. Compared to statistical, machine learning, and deep learning baselines, it demonstrates enhanced generalizability and seizure risk forecasting performance under class imbalance. This work supports future clinical integration of interpretable and robust seizure forecasting tools for personalized epilepsy management.
Authors: Eloi Lindas, Yannig Goude, Philippe Ciais
Abstract: Accurate prediction of non-dispatchable renewable energy sources is essential for grid stability and price prediction. Regional power supply forecasts are usually indirect through a bottom-up approach of plant-level forecasts, incorporate lagged power values, and do not use the potential of spatially resolved data. This study presents a comprehensive methodology for predicting solar and wind power production at country scale in France using machine learning models trained with spatially explicit weather data combined with spatial information about production sites capacity. A dataset is built spanning from 2012 to 2023, using daily power production data from RTE (the national grid operator) as the target variable, with daily weather data from ERA5, production sites capacity and location, and electricity prices as input features. Three modeling approaches are explored to handle spatially resolved weather data: spatial averaging over the country, dimension reduction through principal component analysis, and a computer vision architecture to exploit complex spatial relationships. The study benchmarks state-of-the-art machine learning models as well as hyperparameter tuning approaches based on cross-validation methods on daily power production data. Results indicate that cross-validation tailored to time series is best suited to reach low error. We found that neural networks tend to outperform traditional tree-based models, which face challenges in extrapolation due to the increasing renewable capacity over time. Model performance ranges from 4% to 10% in nRMSE for midterm horizon, achieving similar error metrics to local models established at a single-plant level, highlighting the potential of these methods for regional power supply forecasting.
Authors: Lei Kang, Xuanshuo Fu, Javier Vazquez-Corral, Ernest Valveny, Dimosthenis Karatzas
Abstract: Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, highlighting the critical need for efficient and accurate diagnostic tools. Electrocardiograms (ECGs) are indispensable in diagnosing various heart conditions; however, their manual interpretation is time-consuming and error-prone. In this paper, we propose xLSTM-ECG, a novel approach that leverages an extended Long Short-Term Memory (xLSTM) network for multi-label classification of ECG signals, using the PTB-XL dataset. To the best of our knowledge, this work represents the first design and application of xLSTM modules specifically adapted for multi-label ECG classification. Our method employs a Short-Time Fourier Transform (STFT) to convert time-series ECG waveforms into the frequency domain, thereby enhancing feature extraction. The xLSTM architecture is specifically tailored to address the complexities of 12-lead ECG recordings by capturing both local and global signal features. Comprehensive experiments on the PTB-XL dataset reveal that our model achieves strong multi-label classification performance, while additional tests on the Georgia 12-Lead dataset underscore its robustness and efficiency. This approach significantly improves ECG classification accuracy, thereby advancing clinical diagnostics and patient care. The code will be publicly available upon acceptance.
Authors: Yibo Jacky Zhang, Sanmi Koyejo
Abstract: Fields offer a versatile approach for describing complex systems composed of interacting and dynamic components. In particular, some of these dynamical and stochastic systems may exhibit goal-directed behaviors aimed at achieving specific objectives, which we refer to as $\textit{intelligent fields}$. However, due to their inherent complexity, it remains challenging to develop a formal theoretical description of such systems and to effectively translate these descriptions into practical applications. In this paper, we propose three fundamental principles -- complete configuration, locality, and purposefulness -- to establish a theoretical framework for understanding intelligent fields. Moreover, we explore methodologies for designing such fields from the perspective of artificial intelligence applications. This initial investigation aims to lay the groundwork for future theoretical developments and practical advances in understanding and harnessing the potential of such objective-driven dynamical stochastic fields.
Authors: Muhammad Rafsan Kabir, Rafeed Mohammad Sultan, Fuad Rahman, Mohammad Ruhul Amin, Sifat Momen, Nabeel Mohammed, Shafin Rahman
Abstract: Natural Language Processing (NLP) and computational linguistic techniques are increasingly being applied across various domains, yet their use in legal and regulatory tasks remains limited. To address this gap, we develop an efficient bilingual question-answering framework for regulatory documents, specifically the Bangladesh Police Gazettes, which contain both English and Bangla text. Our approach employs modern Retrieval Augmented Generation (RAG) pipelines to enhance information retrieval and response generation. In addition to conventional RAG pipelines, we propose an advanced RAG-based approach that improves retrieval performance, leading to more precise answers. This system enables efficient searching for specific government legal notices, making legal information more accessible. We evaluate both our proposed and conventional RAG systems on a diverse test set on Bangladesh Police Gazettes, demonstrating that our approach consistently outperforms existing methods across all evaluation metrics.
Authors: Stanley Mugisha, Rashid Kisitu, Florence Tushabe
Abstract: Integrating deep learning applications into agricultural IoT systems faces a serious challenge of balancing the high accuracy of Vision Transformers (ViTs) with the efficiency demands of resource-constrained edge devices. Large transformer models like the Swin Transformers excel in plant disease classification by capturing global-local dependencies. However, their computational complexity (34.1 GFLOPs) limits applications and renders them impractical for real-time on-device inference. Lightweight models such as MobileNetV3 and TinyML would be suitable for on-device inference but lack the required spatial reasoning for fine-grained disease detection. To bridge this gap, we propose a hybrid knowledge distillation framework that synergistically transfers logit and attention knowledge from a Swin Transformer teacher to a MobileNetV3 student model. Our method includes the introduction of adaptive attention alignment to resolve cross-architecture mismatch (resolution, channels) and a dual-loss function optimizing both class probabilities and spatial focus. On the lantVillage-Tomato dataset (18,160 images), the distilled MobileNetV3 attains 92.4% accuracy relative to 95.9% for Swin-L but at an 95% reduction on PC and < 82% in inference latency on IoT devices. (23ms on PC CPU and 86ms/image on smartphone CPUs). Key innovations include IoT-centric validation metrics (13 MB memory, 0.22 GFLOPs) and dynamic resolution-matching attention maps. Comparative experiments show significant improvements over standalone CNNs and prior distillation methods, with a 3.5% accuracy gain over MobileNetV3 baselines. Significantly, this work advances real-time, energy-efficient crop monitoring in precision agriculture and demonstrates how we can attain ViT-level diagnostic precision on edge devices. Code and models will be made available for replication after acceptance.
Authors: Junwei Liao, Muning Wen, Jun Wang, Weinan Zhang
Abstract: LLM-based Multi-Agent Systems have demonstrated remarkable capabilities in addressing complex, agentic tasks requiring multifaceted reasoning and collaboration, from generating high-quality presentation slides to conducting sophisticated scientific research. Meanwhile, RL has been widely recognized for its effectiveness in enhancing agent intelligence, but limited research has investigated the fine-tuning of LaMAS using foundational RL techniques. Moreover, the direct application of MARL methodologies to LaMAS introduces significant challenges, stemming from the unique characteristics and mechanisms inherent to LaMAS. To address these challenges, this article presents a comprehensive study of LLM-based MARL and proposes a novel paradigm termed Multi-Agent Reinforcement Fine-Tuning (MARFT). We introduce a universal algorithmic framework tailored for LaMAS, outlining the conceptual foundations, key distinctions, and practical implementation strategies. We begin by reviewing the evolution from RL to Reinforcement Fine-Tuning, setting the stage for a parallel analysis in the multi-agent domain. In the context of LaMAS, we elucidate critical differences between MARL and MARFT. These differences motivate a transition toward a novel, LaMAS-oriented formulation of RFT. Central to this work is the presentation of a robust and scalable MARFT framework. We detail the core algorithm and provide a complete, open-source implementation to facilitate adoption and further research. The latter sections of the paper explore real-world application perspectives and opening challenges in MARFT. By bridging theoretical underpinnings with practical methodologies, this work aims to serve as a roadmap for researchers seeking to advance MARFT toward resilient and adaptive solutions in agentic systems. Our implementation of the proposed framework is publicly available at: https://github.com/jwliao-ai/MARFT.
Authors: Pengju Ren, Ri-gui Zhou, Yaochong Li
Abstract: Raman spectroscopy serves as a powerful and reliable tool for analyzing the chemical information of substances. The integration of Raman spectroscopy with deep learning methods enables rapid qualitative and quantitative analysis of materials. Most existing approaches adopt supervised learning methods. Although supervised learning has achieved satisfactory accuracy in spectral analysis, it is still constrained by costly and limited well-annotated spectral datasets for training. When spectral annotation is challenging or the amount of annotated data is insufficient, the performance of supervised learning in spectral material identification declines. In order to address the challenge of feature extraction from unannotated spectra, we propose a self-supervised learning paradigm for Raman Spectroscopy based on a Masked AutoEncoder, termed SMAE. SMAE does not require any spectral annotations during pre-training. By randomly masking and then reconstructing the spectral information, the model learns essential spectral features. The reconstructed spectra exhibit certain denoising properties, improving the signal-to-noise ratio (SNR) by more than twofold. Utilizing the network weights obtained from masked pre-training, SMAE achieves clustering accuracy of over 80% for 30 classes of isolated bacteria in a pathogenic bacterial dataset, demonstrating significant improvements compared to classical unsupervised methods and other state-of-the-art deep clustering methods. After fine-tuning the network with a limited amount of annotated data, SMAE achieves an identification accuracy of 83.90% on the test set, presenting competitive performance against the supervised ResNet (83.40%).
Authors: Samuel Yen-Chi Chen, Zhiding Liang
Abstract: Recent advancements in quantum computing (QC) and machine learning (ML) have fueled significant research efforts aimed at integrating these two transformative technologies. Quantum machine learning (QML), an emerging interdisciplinary field, leverages quantum principles to enhance the performance of ML algorithms. Concurrently, the exploration of systematic and automated approaches for designing high-performance quantum circuit architectures for QML tasks has gained prominence, as these methods empower researchers outside the quantum computing domain to effectively utilize quantum-enhanced tools. This tutorial will provide an in-depth overview of recent breakthroughs in both areas, highlighting their potential to expand the application landscape of QML across diverse fields.
Authors: Jasper G\"otting, Pedro Medeiros, Jon G Sanders, Nathaniel Li, Long Phan, Karam Elabd, Lennart Justen, Dan Hendrycks, Seth Donoughe
Abstract: We present the Virology Capabilities Test (VCT), a large language model (LLM) benchmark that measures the capability to troubleshoot complex virology laboratory protocols. Constructed from the inputs of dozens of PhD-level expert virologists, VCT consists of $322$ multimodal questions covering fundamental, tacit, and visual knowledge that is essential for practical work in virology laboratories. VCT is difficult: expert virologists with access to the internet score an average of $22.1\%$ on questions specifically in their sub-areas of expertise. However, the most performant LLM, OpenAI's o3, reaches $43.8\%$ accuracy, outperforming $94\%$ of expert virologists even within their sub-areas of specialization. The ability to provide expert-level virology troubleshooting is inherently dual-use: it is useful for beneficial research, but it can also be misused. Therefore, the fact that publicly available models outperform virologists on VCT raises pressing governance considerations. We propose that the capability of LLMs to provide expert-level troubleshooting of dual-use virology work should be integrated into existing frameworks for handling dual-use technologies in the life sciences.
Authors: Hangxu Liu, Yaojie Sun, Yu Wang
Abstract: In recent years, non-intrusive load monitoring (NILM) technology has attracted much attention in the related research field by virtue of its unique advantage of utilizing single meter data to achieve accurate decomposition of device-level energy consumption. Cutting-edge methods based on machine learning and deep learning have achieved remarkable results in load decomposition accuracy by fusing time-frequency domain features. However, these methods generally suffer from high computational costs and huge memory requirements, which become the main obstacles for their deployment on resource-constrained microcontroller units (MCUs). To address these challenges, this study proposes an innovative Dynamic Time Warping (DTW) algorithm in the time-frequency domain and systematically compares and analyzes the performance of six machine learning techniques in home electricity scenarios. Through complete experimental validation on edge MCUs, this scheme successfully achieves a recognition accuracy of 95%. Meanwhile, this study deeply optimizes the frequency domain feature extraction process, which effectively reduces the running time by 55.55% and the storage overhead by about 34.6%. The algorithm performance will be further optimized in future research work. Considering that the elimination of voltage transformer design can significantly reduce the cost, the subsequent research will focus on this direction, and is committed to providing more cost-effective solutions for the practical application of NILM, and providing a solid theoretical foundation and feasible technical paths for the design of efficient NILM systems in edge computing environments.
Authors: Gideon Vos, Maryam Ebrahimpour, Liza van Eijk, Zoltan Sarnyai, Mostafa Rahimi Azghadi
Abstract: Electroencephalogram (EEG) data is crucial for diagnosing mental health conditions but is costly and time-consuming to collect at scale. Synthetic data generation offers a promising solution to augment datasets for machine learning applications. However, generating high-quality synthetic EEG that preserves emotional and mental health signals remains challenging. This study proposes a method combining correlation analysis and random sampling to generate realistic synthetic EEG data. We first analyze interdependencies between EEG frequency bands using correlation analysis. Guided by this structure, we generate synthetic samples via random sampling. Samples with high correlation to real data are retained and evaluated through distribution analysis and classification tasks. A Random Forest model trained to distinguish synthetic from real EEG performs at chance level, indicating high fidelity. The generated synthetic data closely match the statistical and structural properties of the original EEG, with similar correlation coefficients and no significant differences in PERMANOVA tests. This method provides a scalable, privacy-preserving approach for augmenting EEG datasets, enabling more efficient model training in mental health research.
Authors: Mohammad Molaee, Nasrollah Moghadam Charkari
Abstract: Drug discovery requires a tremendous amount of time and cost. Computational drug-target interaction prediction, a significant part of this process, can reduce these requirements by narrowing the search space for wet lab experiments. In this survey, we provide comprehensive details of graph machine learning-based methods in predicting drug-target interaction, as they have shown promising results in this field. These details include the overall framework, main contribution, datasets, and their source codes. The selected papers were mainly published from 2020 to 2024. Prior to discussing papers, we briefly introduce the datasets commonly used with these methods and measurements to assess their performance. Finally, future challenges and some crucial areas that need to be explored are discussed.
Authors: Zexi Fan, Yan Sun, Shihao Yang, Yiping Lu
Abstract: High-dimensional partial differential equations (PDEs) pose significant computational challenges across fields ranging from quantum chemistry to economics and finance. Although scientific machine learning (SciML) techniques offer approximate solutions, they often suffer from bias and neglect crucial physical insights. Inspired by inference-time scaling strategies in language models, we propose Simulation-Calibrated Scientific Machine Learning (SCaSML), a physics-informed framework that dynamically refines and debiases the SCiML predictions during inference by enforcing the physical laws. SCaSML leverages derived new physical laws that quantifies systematic errors and employs Monte Carlo solvers based on the Feynman-Kac and Elworthy-Bismut-Li formulas to dynamically correct the prediction. Both numerical and theoretical analysis confirms enhanced convergence rates via compute-optimal inference methods. Our numerical experiments demonstrate that SCaSML reduces errors by 20-50% compared to the base surrogate model, establishing it as the first algorithm to refine approximated solutions to high-dimensional PDE during inference. Code of SCaSML is available at https://github.com/Francis-Fan-create/SCaSML.
Authors: Emily Minus, R. Yates Coley, Susan M. Shortreed, Brian D. Williamson
Abstract: Area under the receiving operator characteristic curve (AUC) is commonly reported alongside binary prediction models. However, there are concerns that AUC might be a misleading measure of prediction performance in the rare event setting. This setting is common since many events of clinical importance are rare events. We conducted a simulation study to determine when or whether AUC is unstable in the rare event setting. Specifically, we aimed to determine whether the bias and variance of AUC are driven by the number of events or the event rate. We also investigated the behavior of other commonly used measures of prediction performance, including positive predictive value, accuracy, sensitivity, and specificity. Our results indicate that poor AUC behavior -- as measured by empirical bias, variability of cross-validated AUC estimates, and empirical coverage of confidence intervals -- is driven by the minimum class size, not event rate. Performance of sensitivity is driven by the number of events, while that of specificity is driven by the number of non-events. Other measures, including positive predictive value and accuracy, depend on the event rate even in large samples. AUC is reliable in the rare event setting provided that the total number of events is moderately large.
Authors: Jabez Magomere, Elena Kochkina, Samuel Mensah, Simerjot Kaur, Charese H. Smiley
Abstract: We introduce FinNLI, a benchmark dataset for Financial Natural Language Inference (FinNLI) across diverse financial texts like SEC Filings, Annual Reports, and Earnings Call transcripts. Our dataset framework ensures diverse premise-hypothesis pairs while minimizing spurious correlations. FinNLI comprises 21,304 pairs, including a high-quality test set of 3,304 instances annotated by finance experts. Evaluations show that domain shift significantly degrades general-domain NLI performance. The highest Macro F1 scores for pre-trained (PLMs) and large language models (LLMs) baselines are 74.57% and 78.62%, respectively, highlighting the dataset's difficulty. Surprisingly, instruction-tuned financial LLMs perform poorly, suggesting limited generalizability. FinNLI exposes weaknesses in current LLMs for financial reasoning, indicating room for improvement.
Authors: Lucas Howard, Aneesh C. Subramanian, Gregory Thompson, Benjamin Johnson, Thomas Auligne
Abstract: The continuous improvement in weather forecast skill over the past several decades is largely due to the increasing quantity of available satellite observations and their assimilation into operational forecast systems. Assimilating these observations requires observation operators in the form of radiative transfer models. Significant efforts have been dedicated to enhancing the computational efficiency of these models. Computational cost remains a bottleneck, and a large fraction of available data goes unused for assimilation. To address this, we used machine learning to build an efficient neural network based probabilistic emulator of the Community Radiative Transfer Model (CRTM), applied to the GOES Advanced Baseline Imager. The trained NN emulator predicts brightness temperatures output by CRTM and the corresponding error with respect to CRTM. RMSE of the predicted brightness temperature is 0.3 K averaged across all channels. For clear sky conditions, the RMSE is less than 0.1 K for 9 out of 10 infrared channels. The error predictions are generally reliable across a wide range of conditions. Explainable AI methods demonstrate that the trained emulator reproduces the relevant physics, increasing confidence that the model will perform well when presented with new data.
Authors: Yazan Otoum, Arghavan Asad, Amiya Nayak
Abstract: Edge computing-based Next-Generation Wireless Networks (NGWN)-IoT offer enhanced bandwidth capacity for large-scale service provisioning but remain vulnerable to evolving cyber threats. Existing intrusion detection and prevention methods provide limited security as adversaries continually adapt their attack strategies. We propose a dynamic attack detection and prevention approach to address this challenge. First, blockchain-based authentication uses the Deoxys Authentication Algorithm (DAA) to verify IoT device legitimacy before data transmission. Next, a bi-stage intrusion detection system is introduced: the first stage uses signature-based detection via an Improved Random Forest (IRF) algorithm. In contrast, the second stage applies feature-based anomaly detection using a Diffusion Convolution Recurrent Neural Network (DCRNN). To ensure Quality of Service (QoS) and maintain Service Level Agreements (SLA), trust-aware service migration is performed using Heap-Based Optimization (HBO). Additionally, on-demand virtual High-Interaction honeypots deceive attackers and extract attack patterns, which are securely stored using the Bimodal Lattice Signature Scheme (BLISS) to enhance signature-based Intrusion Detection Systems (IDS). The proposed framework is implemented in the NS3 simulation environment and evaluated against existing methods across multiple performance metrics, including accuracy, attack detection rate, false negative rate, precision, recall, ROC curve, memory usage, CPU usage, and execution time. Experimental results demonstrate that the framework significantly outperforms existing approaches, reinforcing the security of NGWN-enabled IoT ecosystems
Authors: Amir Ali-Pour, Sadra Bekrani, Laya Samizadeh, Julien Gascon-Samson
Abstract: Federated learning has become a promising distributed learning concept with extra insurance on data privacy. Extensive studies on various models of Federated learning have been done since the coinage of its term. One of the important derivatives of federated learning is hierarchical semi-decentralized federated learning, which distributes the load of the aggregation task over multiple nodes and parallelizes the aggregation workload at the breadth of each level of the hierarchy. Various methods have also been proposed to perform inter-cluster and intra-cluster aggregation optimally. Most of the solutions, nonetheless, require monitoring the nodes' performance and resource consumption at each round, which necessitates frequently exchanging systematic data. To optimally perform distributed aggregation in SDFL with minimal reliance on systematic data, we propose Flag-Swap, a Particle Swarm Optimization (PSO) method that optimizes the aggregation placement according only to the processing delay. Our simulation results show that PSO-based placement can find the optimal placement relatively fast, even in scenarios with many clients as candidates for aggregation. Our real-world docker-based implementation of Flag-Swap over the recently emerged FL framework shows superior performance compared to black-box-based deterministic placement strategies, with about 43% minutes faster than random placement, and 32% minutes faster than uniform placement, in terms of total processing time.
Authors: Obed Korshie Dzikunu, Amirhossein Toosi, Shadab Ahamed, Sara Harsini, Francois Benard, Xiaoxiao Li, Arman Rahmim
Abstract: This study performs a comprehensive evaluation of quantitative measurements as extracted from automated deep-learning-based segmentation methods, beyond traditional Dice Similarity Coefficient assessments, focusing on six quantitative metrics, namely SUVmax, SUVmean, total lesion activity (TLA), tumor volume (TMTV), lesion count, and lesion spread. We analyzed 380 prostate-specific membrane antigen (PSMA) targeted [18F]DCFPyL PET/CT scans of patients with biochemical recurrence of prostate cancer, training deep neural networks, U-Net, Attention U-Net and SegResNet with four loss functions: Dice Loss, Dice Cross Entropy, Dice Focal Loss, and our proposed L1 weighted Dice Focal Loss (L1DFL). Evaluations indicated that Attention U-Net paired with L1DFL achieved the strongest correlation with the ground truth (concordance correlation = 0.90-0.99 for SUVmax and TLA), whereas models employing the Dice Loss and the other two compound losses, particularly with SegResNet, underperformed. Equivalence testing (TOST, alpha = 0.05, Delta = 20%) confirmed high performance for SUV metrics, lesion count and TLA, with L1DFL yielding the best performance. By contrast, tumor volume and lesion spread exhibited greater variability. Bland-Altman, Coverage Probability, and Total Deviation Index analyses further highlighted that our proposed L1DFL minimizes variability in quantification of the ground truth clinical measures. The code is publicly available at: https://github.com/ObedDzik/pca\_segment.git.
Authors: Ye Qiao, Zhiheng Cheng, Yifan Zhang, Yian Wang, Sitao Huang
Abstract: Deploying large language models (LLMs) on edge platforms is challenged by their high computational and memory demands. Although recent low-bit quantization methods (e.g., BitNet, DeepSeek) compress weights to as little as 1.58 bits with minimal accuracy loss, edge deployment is still constrained by limited on-chip resources, power budgets, and the often-neglected latency of the prefill phase. We present TeLLMe, the first ternary LLM accelerator for low-power FPGAs (e.g., AMD KV260) that fully supports both prefill and autoregressive decoding using 1.58-bit weights and 8-bit activations. Our contributions include: (1) a table-lookup matrix engine for ternary matmul that merges grouped activations with online precomputation to minimize resource use; (2) a fused, bandwidth-efficient attention module featuring a reversed reordering scheme to accelerate prefill; and (3) a tightly integrated normalization and quantization--dequantization unit optimized for ultra-low-bit inference. Under a 7W power budget, TeLLMe delivers up to 9 tokens/s throughput over 1,024-token contexts and prefill latencies of 0.55--1.15 s for 64--128 token prompts, marking a significant energy-efficiency advance and establishing a new edge FPGA benchmark for generative AI.
Authors: Ye Qiao, Zhiheng Cheng, Yian Wang, Yifan Zhang, Yunzhe Deng, Sitao Huang
Abstract: Transformer-based models have demonstrated superior performance in various fields, including natural language processing and computer vision. However, their enormous model size and high demands in computation, memory, and communication limit their deployment to edge platforms for local, secure inference. Binary transformers offer a compact, low-complexity solution for edge deployment with reduced bandwidth needs and acceptable accuracy. However, existing binary transformers perform inefficiently on current hardware due to the lack of binary specific optimizations. To address this, we introduce COBRA, an algorithm-architecture co-optimized binary Transformer accelerator for edge computing. COBRA features a real 1-bit binary multiplication unit, enabling matrix operations with -1, 0, and +1 values, surpassing ternary methods. With further hardware-friendly optimizations in the attention block, COBRA achieves up to 3,894.7 GOPS throughput and 448.7 GOPS/Watt energy efficiency on edge FPGAs, delivering a 311x energy efficiency improvement over GPUs and a 3.5x throughput improvement over the state-of-the-art binary accelerator, with only negligible inference accuracy degradation.
Authors: Naren Sarayu Manoj
Abstract: We give new results for problems in computational and statistical machine learning using tools from high-dimensional geometry and probability. We break up our treatment into two parts. In Part I, we focus on computational considerations in optimization. Specifically, we give new algorithms for approximating convex polytopes in a stream, sparsification and robust least squares regression, and dueling optimization. In Part II, we give new statistical guarantees for data science problems. In particular, we formulate a new model in which we analyze statistical properties of backdoor data poisoning attacks, and we study the robustness of graph clustering algorithms to ``helpful'' misspecification.
Authors: Andr\'e Longon
Abstract: An important capacity in visual object recognition is invariance to image-altering variables which leave the identity of objects unchanged, such as lighting, rotation, and scale. How do neural networks achieve this? Prior mechanistic interpretability research has illuminated some invariance-building circuitry in InceptionV1, but the results are limited and networks with different architectures have remained largely unexplored. This work investigates ResNet18 with a particular focus on its residual stream, an architectural component which InceptionV1 lacks. We observe that many convolutional channels in intermediate blocks exhibit scale invariant properties, computed by the element-wise residual summation of scale equivariant representations: the block input's smaller-scale copy with the block pre-sum output's larger-scale copy. Through subsequent ablation experiments, we attempt to causally link these neural properties with scale-robust object recognition behavior. Our tentative findings suggest how the residual stream computes scale invariance and its possible role in behavior. Code is available at: https://github.com/cest-andre/residual-stream-interp
Authors: Hossein Shokouhinejad, Griffin Higgins, Roozbeh Razavi-Far, Hesamodin Mohammadian, Ali A. Ghorbani
Abstract: Control Flow Graphs (CFGs) are critical for analyzing program execution and characterizing malware behavior. With the growing adoption of Graph Neural Networks (GNNs), CFG-based representations have proven highly effective for malware detection. This study proposes a novel framework that dynamically constructs CFGs and embeds node features using a hybrid approach combining rule-based encoding and autoencoder-based embedding. A GNN-based classifier is then constructed to detect malicious behavior from the resulting graph representations. To improve model interpretability, we apply state-of-the-art explainability techniques, including GNNExplainer, PGExplainer, and CaptumExplainer, the latter is utilized three attribution methods: Integrated Gradients, Guided Backpropagation, and Saliency. In addition, we introduce a novel aggregation method, called RankFusion, that integrates the outputs of the top-performing explainers to enhance the explanation quality. We also evaluate explanations using two subgraph extraction strategies, including the proposed Greedy Edge-wise Composition (GEC) method for improved structural coherence. A comprehensive evaluation using accuracy, fidelity, and consistency metrics demonstrates the effectiveness of the proposed framework in terms of accurate identification of malware samples and generating reliable and interpretable explanations.
Authors: Yaofeng Cheng, Fusheng Zha, Wei Guo, Pengfei Wang, Chao Zeng, Lining Sun, Chenguang Yang
Abstract: The 6-Degree of Freedom (DoF) grasp method based on point clouds has shown significant potential in enabling robots to grasp target objects. However, most existing methods are based on the point clouds (2.5D points) generated from single-view depth images. These point clouds only have one surface side of the object providing incomplete geometry information, which mislead the grasping algorithm to judge the shape of the target object, resulting in low grasping accuracy. Humans can accurately grasp objects from a single view by leveraging their geometry experience to estimate object shapes. Inspired by humans, we propose a novel 6-DoF grasping framework that converts the point completion results as object shape features to train the 6-DoF grasp network. Here, point completion can generate approximate complete points from the 2.5D points similar to the human geometry experience, and converting it as shape features is the way to utilize it to improve grasp efficiency. Furthermore, due to the gap between the network generation and actual execution, we integrate a score filter into our framework to select more executable grasp proposals for the real robot. This enables our method to maintain a high grasp quality in any camera viewpoint. Extensive experiments demonstrate that utilizing complete point features enables the generation of significantly more accurate grasp proposals and the inclusion of a score filter greatly enhances the credibility of real-world robot grasping. Our method achieves a 17.8\% success rate higher than the state-of-the-art method in real-world experiments.
Authors: Jie JW Wu, Manav Chaudhary, Davit Abrahamyan, Arhaan Khaku, Anjiang Wei, Fatemeh H. Fard
Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, a significant gap remains between their current performance and that of expert software engineers. A key differentiator is that human engineers actively seek clarification when faced with ambiguous requirements, while LLMs typically generate code regardless of uncertainties in the problem description. We present ClarifyCoder, a novel framework with synthetic data generation and instruction-tuning that enables LLMs to identify ambiguities and request clarification before proceeding with code generation. While recent work has focused on LLM-based agents for iterative code generation, we argue that the fundamental ability to recognize and query ambiguous requirements should be intrinsic to the models themselves. Our approach consists of two main components: (1) a data synthesis technique that augments existing programming datasets with scenarios requiring clarification to generate clarification-aware training data, and (2) a fine-tuning strategy that teaches models to prioritize seeking clarification over immediate code generation when faced with incomplete or ambiguous requirements. We further provide an empirical analysis of integrating ClarifyCoder with standard fine-tuning for a joint optimization of both clarify-awareness and coding ability. Experimental results demonstrate that ClarifyCoder significantly improves the communication capabilities of Code LLMs through meaningful clarification dialogues while maintaining code generation capabilities.
Authors: Kamran Majid
Abstract: The emergence of classical behavior from quantum mechanics as Planck's constant $\hbar$ approaches zero remains a fundamental challenge in physics [1-3]. This paper introduces a novel approach employing deep neural networks to directly learn the dynamical mapping from initial quantum state parameters (for Gaussian wave packets of the one-dimensional harmonic oscillator) and $\hbar$ to the parameters of the time-evolved Wigner function in phase space [4-6]. A comprehensive dataset of analytically derived time-evolved Wigner functions was generated, and a deep feedforward neural network with an enhanced architecture was successfully trained for this prediction task, achieving a final training loss of ~ 0.0390. The network demonstrates a significant and previously unrealized ability to accurately capture the underlying mapping of the Wigner function dynamics. This allows for a direct emulation of the quantum-classical transition by predicting the evolution of phase-space distributions as $\hbar$ is systematically varied. The implications of these findings for providing a new computational lens on the emergence of classicality are discussed, highlighting the potential of this direct phase-space learning approach for studying fundamental aspects of quantum mechanics. This work presents a significant advancement beyond previous efforts that focused on learning observable mappings [7], offering a direct route via the phase-space representation.
Authors: Hassan Asghar, Chenhan Zhang, Dali Kaafar
Abstract: Perceptual hashing is used to detect whether an input image is similar to a reference image with a variety of security applications. Recently, they have been shown to succumb to adversarial input attacks which make small imperceptible changes to the input image yet the hashing algorithm does not detect its similarity to the original image. Property-preserving hashing (PPH) is a recent construct in cryptography, which preserves some property (predicate) of its inputs in the hash domain. Researchers have so far shown constructions of PPH for Hamming distance predicates, which, for instance, outputs 1 if two inputs are within Hamming distance $t$. A key feature of PPH is its strong correctness guarantee, i.e., the probability that the predicate will not be correctly evaluated in the hash domain is negligible. Motivated by the use case of detecting similar images under adversarial setting, we propose the first PPH construction for an $\ell_1$-distance predicate. Roughly, this predicate checks if the two one-sided $\ell_1$-distances between two images are within a threshold $t$. Since many adversarial attacks use $\ell_2$-distance (related to $\ell_1$-distance) as the objective function to perturb the input image, by appropriately choosing the threshold $t$, we can force the attacker to add considerable noise to evade detection, and hence significantly deteriorate the image quality. Our proposed scheme is highly efficient, and runs in time $O(t^2)$. For grayscale images of size $28 \times 28$, we can evaluate the predicate in $0.0784$ seconds when pixel values are perturbed by up to $1 \%$. For larger RGB images of size $224 \times 224$, by dividing the image into 1,000 blocks, we achieve times of $0.0128$ seconds per block for $1 \%$ change, and up to $0.2641$ seconds per block for $14\%$ change.
Authors: Jiahe Lin, Yikai Zhang, George Michailidis
Abstract: Graphical models are widely used in diverse application domains to model the conditional dependencies amongst a collection of random variables. In this paper, we consider settings where the graph structure is covariate-dependent, and investigate a deep neural network-based approach to estimate it. The method allows for flexible functional dependency on the covariate, and fits the data reasonably well in the absence of a Gaussianity assumption. Theoretical results with PAC guarantees are established for the method, under assumptions commonly used in an Empirical Risk Minimization framework. The performance of the proposed method is evaluated on several synthetic data settings and benchmarked against existing approaches. The method is further illustrated on real datasets involving data from neuroscience and finance, respectively, and produces interpretable results.
Authors: Ying Chang, Xiaohu Shi, Xiaohui Zhao, Zhaohuang Chen, Deyin Ma
Abstract: Personalized federated learning (PFL) has garnered significant attention for its ability to address heterogeneous client data distributions while preserving data privacy. However, when local client data is limited, deep learning models often suffer from insufficient training, leading to suboptimal performance. Foundation models, such as CLIP (Contrastive Language-Image Pretraining), exhibit strong feature extraction capabilities and can alleviate this issue by fine-tuning on limited local data. Despite their potential, foundation models are rarely utilized in federated learning scenarios, and challenges related to integrating new clients remain largely unresolved. To address these challenges, we propose the Dual Prompt Personalized Federated Learning (DP2FL) framework, which introduces dual prompts and an adaptive aggregation strategy. DP2FL combines global task awareness with local data-driven insights, enabling local models to achieve effective generalization while remaining adaptable to specific data distributions. Moreover, DP2FL introduces a global model that enables prediction on new data sources and seamlessly integrates newly added clients without requiring retraining. Experimental results in highly heterogeneous environments validate the effectiveness of DP2FL's prompt design and aggregation strategy, underscoring the advantages of prediction on novel data sources and demonstrating the seamless integration of new clients into the federated learning framework.
Authors: Arghavan Zibaie, Spencer Hutchinson, Ramtin Pedarsani, Mahnoosh Alizadeh
Abstract: We consider a collection of linear stochastic bandit problems, each modeling the random response of different agents to proposed interventions, coupled together by a global safety constraint. We assume a central coordinator must choose actions to play on each bandit with the objective of regret minimization, while also ensuring that the expected response of all agents satisfies the global safety constraints at each round, in spite of uncertainty about the bandits' parameters. The agents consider their observed responses to be private and in order to protect their sensitive information, the data sharing with the central coordinator is performed under local differential privacy (LDP). However, providing higher level of privacy to different agents would have consequences in terms of safety and regret. We formalize these tradeoffs by building on the notion of the sharpness of the safety set - a measure of how the geometric properties of the safe set affects the growth of regret - and propose a unilaterally unimprovable vector of privacy levels for different agents given a maximum regret budget.
Authors: Banruo Liu, Wei-Yu Lin, Minghao Fang, Yihan Jiang, Fan Lai
Abstract: The rise of compound AI serving -- integrating multiple operators in a pipeline that may span edge and cloud tiers -- enables end-user applications such as autonomous driving, generative AI-powered meeting companions, and immersive gaming. Achieving high service goodput -- i.e., meeting service level objectives (SLOs) for pipeline latency, accuracy, and costs -- requires effective planning of operator placement, configuration, and resource allocation across infrastructure tiers. However, the diverse SLO requirements, varying edge capabilities, and high query volumes create an enormous planning search space, rendering current solutions fundamentally limited for real-time serving and cost-efficient deployments. This paper presents Circinus, an SLO-aware query planner for large-scale compound AI workloads. Circinus novelly decomposes multi-query planning and multi-dimensional SLO objectives while preserving global decision quality. By exploiting plan similarities within and across queries, it significantly reduces search steps. It further improves per-step efficiency with a precision-aware plan profiler that incrementally profiles and strategically applies early stopping based on imprecise estimates of plan performance. At scale, Circinus selects query-plan combinations to maximize global SLO goodput. Evaluations in real-world settings show that Circinus improves service goodput by 3.2-5.0$\times$, accelerates query planning by 4.2-5.8$\times$, achieving query response in seconds, while reducing deployment costs by 3.2-4.0$\times$ over state of the arts even in their intended single-tier deployments.
Authors: Md Fahimuzzman Sohan
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: Ye Tian, Yanqiu Yu, Jianguo Sun, Yanbin Wang
Abstract: Malicious URLs persistently threaten the cybersecurity ecosystem, by either deceiving users into divulging private data or distributing harmful payloads to infiltrate host systems. Gaining timely insights into the current state of this ongoing battle holds significant importance. However, existing reviews exhibit 4 critical gaps: 1) Their reliance on algorithm-centric taxonomies obscures understanding of how detection approaches exploit specific modal information channels; 2) They fail to incorporate pivotal LLM/Transformer-based defenses; 3) No open-source implementations are collected to facilitate benchmarking; 4) Insufficient dataset coverage.This paper presents a comprehensive review of malicious URL detection technologies, systematically analyzing methods from traditional blacklisting to advanced deep learning approaches (e.g. Transformer, GNNs, and LLMs). Unlike prior surveys, we propose a novel modality-based taxonomy that categorizes existing works according to their primary data modalities (URL, HTML, Visual, etc.). This hierarchical classification enables both rigorous technical analysis and clear understanding of multimodal information utilization. Furthermore, to establish a profile of accessible datasets and address the lack of standardized benchmarking (where current studies often lack proper baseline comparisons), we curate and analyze: 1) publicly available datasets (2016-2024), and 2) open-source implementations from published works(2013-2025). Then, we outline essential design principles and architectural frameworks for product-level implementations. The review concludes by examining emerging challenges and proposing actionable directions for future research. We maintain a GitHub repository for ongoing curating datasets and open-source implementations: https://github.com/sevenolu7/Malicious-URL-Detection-Open-Source/tree/master.
URLs: https://github.com/sevenolu7/Malicious-URL-Detection-Open-Source/tree/master.
Authors: Meixi Zheng, Kehan Wu, Yanbo Fan, Rui Huang, Baoyuan Wu
Abstract: The transfer-based black-box adversarial attack setting poses the challenge of crafting an adversarial example (AE) on known surrogate models that remain effective against unseen target models. Due to the practical importance of this task, numerous methods have been proposed to address this challenge. However, most previous methods are heuristically designed and intuitively justified, lacking a theoretical foundation. To bridge this gap, we derive a novel transferability bound that offers provable guarantees for adversarial transferability. Our theoretical analysis has the advantages of \textit{(i)} deepening our understanding of previous methods by building a general attack framework and \textit{(ii)} providing guidance for designing an effective attack algorithm. Our theoretical results demonstrate that optimizing AEs toward flat minima over the surrogate model set, while controlling the surrogate-target model shift measured by the adversarial model discrepancy, yields a comprehensive guarantee for AE transferability. The results further lead to a general transfer-based attack framework, within which we observe that previous methods consider only partial factors contributing to the transferability. Algorithmically, inspired by our theoretical results, we first elaborately construct the surrogate model set in which models exhibit diverse adversarial vulnerabilities with respect to AEs to narrow an instantiated adversarial model discrepancy. Then, a \textit{model-Diversity-compatible Reverse Adversarial Perturbation} (DRAP) is generated to effectively promote the flatness of AEs over diverse surrogate models to improve transferability. Extensive experiments on NIPS2017 and CIFAR-10 datasets against various target models demonstrate the effectiveness of our proposed attack.
Authors: Luuk H. E. Kempen, Marius Juul Nielsen, Mie Andersen
Abstract: The conversion of $\mathrm{CO_2}$ into useful products such as methanol is a key strategy for abating climate change and our dependence on fossil fuels. Developing new catalysts for this process is costly and time-consuming and can thus benefit from computational exploration of possible active sites. However, this is complicated by the complexity of the materials and reaction networks. Here, we present a workflow for exploring transition states of elementary reaction steps at inverse catalysts, which is based on the training of a neural network-based machine learning interatomic potential. We focus on the crucial formate intermediate and its formation over nanoclusters of indium oxide supported on Cu(111). The speedup compared to an approach purely based on density functional theory allows us to probe a wide variety of active sites found at nanoclusters of different sizes and stoichiometries. Analysis of the obtained set of transition state geometries reveals different structure--activity trends at the edge or interior of the nanoclusters. Furthermore, the identified geometries allow for the breaking of linear scaling relations, which could be a key underlying reason for the excellent catalytic performance of inverse catalysts observed in experiments.
Authors: Ji\v{r}\'i Kubal\'ik, Robert Babu\v{s}ka
Abstract: Symbolic regression is a technique that can automatically derive analytic models from data. Traditionally, symbolic regression has been implemented primarily through genetic programming that evolves populations of candidate solutions sampled by genetic operators, crossover and mutation. More recently, neural networks have been employed to learn the entire analytical model, i.e., its structure and coefficients, using regularized gradient-based optimization. Although this approach tunes the model's coefficients better, it is prone to premature convergence to suboptimal model structures. Here, we propose a neuro-evolutionary symbolic regression method that combines the strengths of evolutionary-based search for optimal neural network (NN) topologies with gradient-based tuning of the network's parameters. Due to the inherent high computational demand of evolutionary algorithms, it is not feasible to learn the parameters of every candidate NN topology to full convergence. Thus, our method employs a memory-based strategy and population perturbations to enhance exploitation and reduce the risk of being trapped in suboptimal NNs. In this way, each NN topology can be trained using only a short sequence of backpropagation iterations. The proposed method was experimentally evaluated on three real-world test problems and has been shown to outperform other NN-based approaches regarding the quality of the models obtained.
Authors: Joan Perez (Urban Geo Analytics, France), Giovanni Fusco (Universite Cote-Azur-CNRS-AMU-Avignon Universite, ESPACE, France)
Abstract: Streetscapes are an essential component of urban space. Their assessment is presently either limited to morphometric properties of their mass skeleton or requires labor-intensive qualitative evaluations of visually perceived qualities. This paper introduces SAGAI: Streetscape Analysis with Generative Artificial Intelligence, a modular workflow for scoring street-level urban scenes using open-access data and vision-language models. SAGAI integrates OpenStreetMap geometries, Google Street View imagery, and a lightweight version of the LLaVA model to generate structured spatial indicators from images via customizable natural language prompts. The pipeline includes an automated mapping module that aggregates visual scores at both the point and street levels, enabling direct cartographic interpretation. It operates without task-specific training or proprietary software dependencies, supporting scalable and interpretable analysis of urban environments. Two exploratory case studies in Nice and Vienna illustrate SAGAI's capacity to produce geospatial outputs from vision-language inference. The initial results show strong performance for binary urban-rural scene classification, moderate precision in commercial feature detection, and lower estimates, but still informative, of sidewalk width. Fully deployable by any user, SAGAI can be easily adapted to a wide range of urban research themes, such as walkability, safety, or urban design, through prompt modification alone.
Authors: Eugenio Clerico, Hamish Flynn, Wojciech Kot{\l}owski, Gergely Neu
Abstract: We develop a methodology for constructing confidence sets for parameters of statistical models via a reduction to sequential prediction. Our key observation is that for any generalized linear model (GLM), one can construct an associated game of sequential probability assignment such that achieving low regret in the game implies a high-probability upper bound on the excess likelihood of the true parameter of the GLM. This allows us to develop a scheme that we call online-to-confidence-set conversions, which effectively reduces the problem of proving the desired statistical claim to an algorithmic question. We study two varieties of this conversion scheme: 1) analytical conversions that only require proving the existence of algorithms with low regret and provide confidence sets centered at the maximum-likelihood estimator 2) algorithmic conversions that actively leverage the output of the online algorithm to construct confidence sets (and may be centered at other, adaptively constructed point estimators). The resulting methodology recovers all state-of-the-art confidence set constructions within a single framework, and also provides several new types of confidence sets that were previously unknown in the literature.
Authors: Defne E. Ozan, Andrea N\'ovoa, Luca Magri
Abstract: The goal of many applications in energy and transport sectors is to control turbulent flows. However, because of chaotic dynamics and high dimensionality, the control of turbulent flows is exceedingly difficult. Model-free reinforcement learning (RL) methods can discover optimal control policies by interacting with the environment, but they require full state information, which is often unavailable in experimental settings. We propose a data-assimilated model-based RL (DA-MBRL) framework for systems with partial observability and noisy measurements. Our framework employs a control-aware Echo State Network for data-driven prediction of the dynamics, and integrates data assimilation with an Ensemble Kalman Filter for real-time state estimation. An off-policy actor-critic algorithm is employed to learn optimal control strategies from state estimates. The framework is tested on the Kuramoto-Sivashinsky equation, demonstrating its effectiveness in stabilizing a spatiotemporally chaotic flow from noisy and partial measurements.
Authors: Gojko Perovic, Nuno Ferreira Duarte, Atabak Dehban, Gon\c{c}alo Teixeira, Egidio Falotico, Jos\'e Santos-Victor
Abstract: Packing objects efficiently is a fundamental problem in logistics, warehouse automation, and robotics. While traditional packing solutions focus on geometric optimization, packing irregular, 3D objects presents significant challenges due to variations in shape and stability. Reinforcement Learning~(RL) has gained popularity in robotic packing tasks, but training purely from simulation can be inefficient and computationally expensive. In this work, we propose HERB, a human-augmented RL framework for packing irregular objects. We first leverage human demonstrations to learn the best sequence of objects to pack, incorporating latent factors such as space optimization, stability, and object relationships that are difficult to model explicitly. Next, we train a placement algorithm that uses visual information to determine the optimal object positioning inside a packing container. Our approach is validated through extensive performance evaluations, analyzing both packing efficiency and latency. Finally, we demonstrate the real-world feasibility of our method on a robotic system. Experimental results show that our method outperforms geometric and purely RL-based approaches by leveraging human intuition, improving both packing robustness and adaptability. This work highlights the potential of combining human expertise-driven RL to tackle complex real-world packing challenges in robotic systems.
Authors: Max Kirchner, Alexander C. Jenke, Sebastian Bodenstedt, Fiona R. Kolbinger, Oliver Saldanha, Jakob N. Kather, Martin Wagner, Stefanie Speidel
Abstract: Purpose: In this study, we investigate the training of foundation models using federated learning to address data-sharing limitations and enable collaborative model training without data transfer for minimally invasive surgery. Methods: Inspired by the EndoViT study, we adapt the Masked Autoencoder for federated learning, enhancing it with adaptive Sharpness-Aware Minimization (FedSAM) and Stochastic Weight Averaging (SWA). Our model is pretrained on the Endo700k dataset collection and later fine-tuned and evaluated for tasks such as Semantic Segmentation, Action Triplet Recognition, and Surgical Phase Recognition. Results: Our findings demonstrate that integrating adaptive FedSAM into the federated MAE approach improves pretraining, leading to a reduction in reconstruction loss per patch. The application of FL-EndoViT in surgical downstream tasks results in performance comparable to CEN-EndoViT. Furthermore, FL-EndoViT exhibits advantages over CEN-EndoViT in surgical scene segmentation when data is limited and in action triplet recognition when large datasets are used. Conclusion: These findings highlight the potential of federated learning for privacy-preserving training of surgical foundation models, offering a robust and generalizable solution for surgical data science. Effective collaboration requires adapting federated learning methods, such as the integration of FedSAM, which can accommodate the inherent data heterogeneity across institutions. In future, exploring FL in video-based models may enhance these capabilities by incorporating spatiotemporal dynamics crucial for real-world surgical environments.
Authors: William Corrias, Fabio De Gaspari, Dorjan Hitaj, Luigi V. Mancini
Abstract: The rapid evolution of generative models has led to their integration across various fields, including password guessing, aiming to generate passwords that resemble human-created ones in complexity, structure, and patterns. Despite generative model's promise, inconsistencies in prior research and a lack of rigorous evaluation have hindered a comprehensive understanding of their true potential. In this paper, we introduce MAYA, a unified, customizable, plug-and-play password benchmarking framework. MAYA provides a standardized approach for evaluating generative password-guessing models through a rigorous set of advanced testing scenarios and a collection of eight real-life password datasets. Using MAYA, we comprehensively evaluate six state-of-the-art approaches, which have been re-implemented and adapted to ensure standardization, for a total of over 15,000 hours of computation. Our findings indicate that these models effectively capture different aspects of human password distribution and exhibit strong generalization capabilities. However, their effectiveness varies significantly with long and complex passwords. Through our evaluation, sequential models consistently outperform other generative architectures and traditional password-guessing tools, demonstrating unique capabilities in generating accurate and complex guesses. Moreover, models learn and generate different password distributions, enabling a multi-model attack that outperforms the best individual model. By releasing MAYA, we aim to foster further research, providing the community with a new tool to consistently and reliably benchmark password-generation techniques. Our framework is publicly available at https://github.com/williamcorrias/MAYA-Password-Benchmarking
URLs: https://github.com/williamcorrias/MAYA-Password-Benchmarking
Authors: Chenhao Li, Andreas Krause, Marco Hutter
Abstract: Reinforcement Learning (RL) has demonstrated impressive capabilities in robotic control but remains challenging due to high sample complexity, safety concerns, and the sim-to-real gap. While offline RL eliminates the need for risky real-world exploration by learning from pre-collected data, it suffers from distributional shift, limiting policy generalization. Model-Based RL (MBRL) addresses this by leveraging predictive models for synthetic rollouts, yet existing approaches often lack robust uncertainty estimation, leading to compounding errors in offline settings. We introduce Offline Robotic World Model (RWM-O), a model-based approach that explicitly estimates epistemic uncertainty to improve policy learning without reliance on a physics simulator. By integrating these uncertainty estimates into policy optimization, our approach penalizes unreliable transitions, reducing overfitting to model errors and enhancing stability. Experimental results show that RWM-O improves generalization and safety, enabling policy learning purely from real-world data and advancing scalable, data-efficient RL for robotics.
Authors: Gerardus Croonen, Andreas Trondl, Julia Simon, Daniel Steininger
Abstract: While sugar beets are stored prior to processing, they lose sugar due to factors such as microorganisms present in adherent soil and excess vegetation. Their automated visual inspection promises to aide in quality assurance and thereby increase efficiency throughout the processing chain of sugar production. In this work, we present a novel high-quality annotated dataset and two-stage method for the detection, semantic segmentation and mass estimation of post-harvest and post-storage sugar beets in monocular RGB images. We conduct extensive ablation experiments for the detection of sugar beets and their fine-grained semantic segmentation regarding damages, rot, soil adhesion and excess vegetation. For these tasks, we evaluate multiple image sizes, model architectures and encoders, as well as the influence of environmental conditions. Our experiments show an mAP50-95 of 98.8 for sugar-beet detection and an mIoU of 64.0 for the best-performing segmentation model.
Authors: Nahshon Mokua, Obiri, Kristof, Van Laerhoven
Abstract: Modeling path loss in indoor LoRaWAN technology deployments is inherently challenging due to structural obstructions, occupant density and activities, and fluctuating environmental conditions. This study proposes a two-stage approach to capture and analyze these complexities using an extensive dataset of 1,328,334 field measurements collected over six months in a single-floor office at the University of Siegen's Hoelderlinstrasse Campus, Germany. First, we implement a multiple linear regression model that includes traditional propagation metrics (distance, structural walls) and an extension with proposed environmental variables (relative humidity, temperature, carbon dioxide, particulate matter, and barometric pressure). Using analysis of variance, we demonstrate that adding these environmental factors can reduce unexplained variance by 42.32 percent. Secondly, we examine residual distributions by fitting five candidate probability distributions: Normal, Skew-Normal, Cauchy, Student's t, and Gaussian Mixture Models with one to five components. Our results show that a four-component Gaussian Mixture Model captures the residual heterogeneity of indoor signal propagation most accurately, significantly outperforming single-distribution approaches. Given the push toward ultra-reliable, context-aware communications in 6G networks, our analysis shows that environment-aware modeling can substantially improve LoRaWAN network design in dynamic indoor IoT deployments.
Authors: Yanjie Wu, Yuhao Ji, Saiho Lee, Juniad Akram, Ali Braytee, Ali Anaissi
Abstract: The complexities of healthcare data, including privacy concerns, imbalanced datasets, and interoperability issues, necessitate innovative machine learning solutions. Swarm Learning (SL), a decentralized alternative to Federated Learning, offers privacy-preserving distributed training, but its reliance on blockchain technology hinders accessibility and scalability. This paper introduces a \textit{Simplified Peer-to-Peer Swarm Learning (P2P-SL) Framework} tailored for resource-constrained environments. By eliminating blockchain dependencies and adopting lightweight peer-to-peer communication, the proposed framework ensures robust model synchronization while maintaining data privacy. Applied to cancer histopathology, the framework integrates optimized pre-trained models, such as TorchXRayVision, enhanced with DenseNet decoders, to improve diagnostic accuracy. Extensive experiments demonstrate the framework's efficacy in handling imbalanced and biased datasets, achieving comparable performance to centralized models while preserving privacy. This study paves the way for democratizing advanced machine learning in healthcare, offering a scalable, accessible, and efficient solution for privacy-sensitive diagnostic applications.
Authors: Fengwei Zhou, Jiafei Song, Wenjin Jason Li, Gengjian Xue, Zhikang Zhao, Yichao Lu, Bailin Na
Abstract: Recent advances in large language models have significantly improved their ability to process long-context input, but practical applications are challenged by increased inference time and resource consumption, particularly in resource-constrained environments. To address these challenges, we propose MOOSComp, a token-classification-based long-context compression method that enhances the performance of a BERT-based compressor by mitigating the over-smoothing problem and incorporating outlier scores. In the training phase, we add an inter-class cosine similarity loss term to penalize excessively similar token representations, thereby improving the token classification accuracy. During the compression phase, we introduce outlier scores to preserve rare but critical tokens that are prone to be discarded in task-agnostic compression. These scores are integrated with the classifier's output, making the compressor more generalizable to various tasks. Superior performance is achieved at various compression ratios on long-context understanding and reasoning benchmarks. Moreover, our method obtains a speedup of 3.3x at a 4x compression ratio on a resource-constrained mobile device.
Authors: Yuxiang Wei, Yanteng Zhang, Xi Xiao, Tianyang Wang, Xiao Wang, Vince D. Calhoun
Abstract: Multimodal neuroimaging provides complementary structural and functional insights into both human brain organization and disease-related dynamics. Recent studies demonstrate enhanced diagnostic sensitivity for Alzheimer's disease (AD) through synergistic integration of neuroimaging data (e.g., sMRI, fMRI) with behavioral cognitive scores tabular data biomarkers. However, the intrinsic heterogeneity across modalities (e.g., 4D spatiotemporal fMRI dynamics vs. 3D anatomical sMRI structure) presents critical challenges for discriminative feature fusion. To bridge this gap, we propose M2M-AlignNet: a geometry-aware multimodal co-attention network with latent alignment for early AD diagnosis using sMRI and fMRI. At the core of our approach is a multi-patch-to-multi-patch (M2M) contrastive loss function that quantifies and reduces representational discrepancies via geometry-weighted patch correspondence, explicitly aligning fMRI components across brain regions with their sMRI structural substrates without one-to-one constraints. Additionally, we propose a latent-as-query co-attention module to autonomously discover fusion patterns, circumventing modality prioritization biases while minimizing feature redundancy. We conduct extensive experiments to confirm the effectiveness of our method and highlight the correspondance between fMRI and sMRI as AD biomarkers.
Authors: Manuel Quintero, William T. Stephenson, Advik Shreekumar, Tamara Broderick
Abstract: In science and social science, we often wish to explain why an outcome is different in two populations. For instance, if a jobs program benefits members of one city more than another, is that due to differences in program participants (particular covariates) or the local labor markets (outcomes given covariates)? The Kitagawa-Oaxaca-Blinder (KOB) decomposition is a standard tool in econometrics that explains the difference in the mean outcome across two populations. However, the KOB decomposition assumes a linear relationship between covariates and outcomes, while the true relationship may be meaningfully nonlinear. Modern machine learning boasts a variety of nonlinear functional decompositions for the relationship between outcomes and covariates in one population. It seems natural to extend the KOB decomposition using these functional decompositions. We observe that a successful extension should not attribute the differences to covariates -- or, respectively, to outcomes given covariates -- if those are the same in the two populations. Unfortunately, we demonstrate that, even in simple examples, two common decompositions -- functional ANOVA and Accumulated Local Effects -- can attribute differences to outcomes given covariates, even when they are identical in two populations. We provide a characterization of when functional ANOVA misattributes, as well as a general property that any discrete decomposition must satisfy to avoid misattribution. We show that if the decomposition is independent of its input distribution, it does not misattribute. We further conjecture that misattribution arises in any reasonable additive decomposition that depends on the distribution of the covariates.
Authors: Puja Chaudhury, Alexander Estornell, Michael Everett
Abstract: To provide safety guarantees for learning-based control systems, recent work has developed formal verification methods to apply after training ends. However, if the trained policy does not meet the specifications, or there is conservatism in the verification algorithm, establishing these guarantees may not be possible. Instead, this work proposes to perform verification throughout training to ultimately aim for policies whose properties can be evaluated throughout runtime with lightweight, relaxed verification algorithms. The approach is to use differentiable reachability analysis and incorporate new components into the loss function. Numerical experiments on a quadrotor model and unicycle model highlight the ability of this approach to lead to learned control policies that satisfy desired reach-avoid and invariance specifications.
Authors: Arnav Sharma, Anthony Gitter
Abstract: The ability to make zero-shot predictions about the fitness consequences of protein sequence changes with pre-trained machine learning models enables many practical applications. Such models can be applied for downstream tasks like genetic variant interpretation and protein engineering without additional labeled data. The advent of capable protein structure prediction tools has led to the availability of orders of magnitude more precomputed predicted structures, giving rise to powerful structure-based fitness prediction models. Through our experiments, we assess several modeling choices for structure-based models and their effects on downstream fitness prediction. Zero-shot fitness prediction models can struggle to assess the fitness landscape within disordered regions of proteins, those that lack a fixed 3D structure. We confirm the importance of matching protein structures to fitness assays and find that predicted structures for disordered regions can be misleading and affect predictive performance. Lastly, we evaluate an additional structure-based model on the ProteinGym substitution benchmark and show that simple multi-modal ensembles are strong baselines.
Authors: Ivan Moshkov, Darragh Hanley, Ivan Sorokin, Shubham Toshniwal, Christof Henkel, Benedikt Schifferer, Wei Du, Igor Gitman
Abstract: This paper presents our winning submission to the AI Mathematical Olympiad - Progress Prize 2 (AIMO-2) competition. Our recipe for building state-of-the-art mathematical reasoning models relies on three key pillars. First, we create a large-scale dataset comprising 540K unique high-quality math problems, including olympiad-level problems, and their 3.2M long-reasoning solutions. Second, we develop a novel method to integrate code execution with long reasoning models through iterative training, generation, and quality filtering, resulting in 1.7M high-quality Tool-Integrated Reasoning solutions. Third, we create a pipeline to train models to select the most promising solution from many candidates. We show that such generative solution selection (GenSelect) can significantly improve upon majority voting baseline. Combining these ideas, we train a series of models that achieve state-of-the-art results on mathematical reasoning benchmarks. To facilitate further research, we release our code, models, and the complete OpenMathReasoning dataset under a commercially permissive license.
Authors: Ghazal Mirzaee, Jonathan Chang, Shahrzad Latifi
Abstract: Decoding behavior, such as movement, from multiscale brain networks remains a central objective in neuroscience. Over the past decades, artificial intelligence and machine learning have played an increasingly significant role in elucidating the neural mechanisms underlying motor function. The advancement of brain-monitoring technologies, capable of capturing complex neuronal signals with high spatial and temporal resolution, necessitates the development and application of more sophisticated machine learning models for behavioral decoding. In this study, we employ a hybrid deep learning framework, an attention-based CNN-BiLSTM model, to decode skilled and complex forelimb movements using signals obtained from in vivo two-photon calcium imaging. Our findings demonstrate that the intricate movements of both ipsilateral and contralateral forelimbs can be accurately decoded from unilateral M1 neuronal ensembles. These results highlight the efficacy of advanced hybrid deep learning models in capturing the spatiotemporal dependencies of neuronal networks activity linked to complex movement execution.
Authors: Ali Hassani, Fengzhe Zhou, Aditya Kane, Jiannan Huang, Chieh-Yun Chen, Min Shi, Steven Walton, Markus Hoehnerbach, Vijay Thakkar, Michael Isaev, Qinsheng Zhang, Bing Xu, Haicheng Wu, Wen-mei Hwu, Ming-Yu Liu, Humphrey Shi
Abstract: Many sparse attention mechanisms such as Neighborhood Attention have typically failed to consistently deliver speedup over the self attention baseline. This is largely due to the level of complexity in attention infrastructure, and the rapid evolution of AI hardware architecture. At the same time, many state-of-the-art foundational models, particularly in computer vision, are heavily bound by attention, and need reliable sparsity to escape the O(n^2) complexity. In this paper, we study a class of promising sparse attention mechanisms that focus on locality, and aim to develop a better analytical model of their performance improvements. We first introduce Generalized Neighborhood Attention (GNA), which can describe sliding window, strided sliding window, and blocked attention. We then consider possible design choices in implementing these approaches, and create a simulator that can provide much more realistic speedup upper bounds for any given setting. Finally, we implement GNA on top of a state-of-the-art fused multi-headed attention (FMHA) kernel designed for the NVIDIA Blackwell architecture in CUTLASS. Our implementation can fully realize the maximum speedup theoretically possible in many perfectly block-sparse cases, and achieves an effective utilization of 1.3 petaFLOPs/second in FP16. In addition, we plug various GNA configurations into off-the-shelf generative models, such as Cosmos-7B, HunyuanVideo, and FLUX, and show that it can deliver 28% to 46% end-to-end speedup on B200 without any fine-tuning. We will open source our simulator and Blackwell kernels directly through the NATTEN project.
Authors: Jacob Levy, Jason Gibson, Bogdan Vlahov, Erica Tevere, Evangelos Theodorou, David Fridovich-Keil, Patrick Spieler
Abstract: High-speed off-road autonomous driving presents unique challenges due to complex, evolving terrain characteristics and the difficulty of accurately modeling terrain-vehicle interactions. While dynamics models used in model-based control can be learned from real-world data, they often struggle to generalize to unseen terrain, making real-time adaptation essential. We propose a novel framework that combines a Kalman filter-based online adaptation scheme with meta-learned parameters to address these challenges. Offline meta-learning optimizes the basis functions along which adaptation occurs, as well as the adaptation parameters, while online adaptation dynamically adjusts the onboard dynamics model in real time for model-based control. We validate our approach through extensive experiments, including real-world testing on a full-scale autonomous off-road vehicle, demonstrating that our method outperforms baseline approaches in prediction accuracy, performance, and safety metrics, particularly in safety-critical scenarios. Our results underscore the effectiveness of meta-learned dynamics model adaptation, advancing the development of reliable autonomous systems capable of navigating diverse and unseen environments. Video is available at: https://youtu.be/cCKHHrDRQEA
Authors: Burcu Sayin, Jie Yang, Xinyue Chen, Andrea Passerini, Fabio Casati
Abstract: In this paper, we argue that the prevailing approach to training and evaluating machine learning models often fails to consider their real-world application within organizational or societal contexts, where they are intended to create beneficial value for people. We propose a shift in perspective, redefining model assessment and selection to emphasize integration into workflows that combine machine predictions with human expertise, particularly in scenarios requiring human intervention for low-confidence predictions. Traditional metrics like accuracy and f-score fail to capture the beneficial value of models in such hybrid settings. To address this, we introduce a simple yet theoretically sound "value" metric that incorporates task-specific costs for correct predictions, errors, and rejections, offering a practical framework for real-world evaluation. Through extensive experiments, we show that existing metrics fail to capture real-world needs, often leading to suboptimal choices in terms of value when used to rank classifiers. Furthermore, we emphasize the critical role of calibration in determining model value, showing that simple, well-calibrated models can often outperform more complex models that are challenging to calibrate.
Authors: Dai Hai Nguyen, Tetsuya Sakurai, Hiroshi Mamitsuka
Abstract: Variational inference (VI) can be cast as an optimization problem in which the variational parameters are tuned to closely align a variational distribution with the true posterior. The optimization task can be approached through vanilla gradient descent in black-box VI or natural-gradient descent in natural-gradient VI. In this work, we reframe VI as the optimization of an objective that concerns probability distributions defined over a \textit{variational parameter space}. Subsequently, we propose Wasserstein gradient descent for tackling this optimization problem. Notably, the optimization techniques, namely black-box VI and natural-gradient VI, can be reinterpreted as specific instances of the proposed Wasserstein gradient descent. To enhance the efficiency of optimization, we develop practical methods for numerically solving the discrete gradient flows. We validate the effectiveness of the proposed methods through empirical experiments on a synthetic dataset, supplemented by theoretical analyses.
Authors: Zhongdong Liu, Keyuan Zhang, Bin Li, Yin Sun, Y. Thomas Hou, Bo Ji
Abstract: We consider a discrete-time system where a resource-constrained source (e.g., a small sensor) transmits its time-sensitive data to a destination over a time-varying wireless channel. Each transmission incurs a fixed transmission cost (e.g., energy cost), and no transmission results in a staleness cost represented by the Age-of-Information. The source must balance the tradeoff between transmission and staleness costs. To address this challenge, we develop a robust online algorithm to minimize the sum of transmission and staleness costs, ensuring a worst-case performance guarantee. While online algorithms are robust, they are usually overly conservative and may have a poor average performance in typical scenarios. In contrast, by leveraging historical data and prediction models, machine learning (ML) algorithms perform well in average cases. However, they typically lack worst-case performance guarantees. To achieve the best of both worlds, we design a learning-augmented online algorithm that exhibits two desired properties: (i) consistency: closely approximating the optimal offline algorithm when the ML prediction is accurate and trusted; (ii) robustness: ensuring worst-case performance guarantee even ML predictions are inaccurate. Finally, we perform extensive simulations to show that our online algorithm performs well empirically and that our learning-augmented algorithm achieves both consistency and robustness.
Authors: Yipeng Li, Xinchen Lyu
Abstract: There are two paradigms in Federated Learning (FL): parallel FL (PFL), where models are trained in a parallel manner across clients, and sequential FL (SFL), where models are trained in a sequential manner across clients. Specifically, in PFL, clients perform local updates independently and send the updated model parameters to a global server for aggregation; in SFL, one client starts its local updates only after receiving the model parameters from the previous client in the sequence. In contrast to that of PFL, the convergence theory of SFL on heterogeneous data is still lacking. To resolve the theoretical dilemma of SFL, we establish sharp convergence guarantees for SFL on heterogeneous data with both upper and lower bounds. Specifically, we derive the upper bounds for the strongly convex, general convex and non-convex objective functions, and construct the matching lower bounds for the strongly convex and general convex objective functions. Then, we compare the upper bounds of SFL with those of PFL, showing that SFL outperforms PFL on heterogeneous data (at least, when the level of heterogeneity is relatively high). Experimental results validate the counterintuitive theoretical finding.
Authors: Or Raveh, Junya Honda, Masashi Sugiyama
Abstract: Various approaches have emerged for multi-armed bandits in distributed systems. The multiplayer dueling bandit problem, common in scenarios with only preference-based information like human feedback, introduces challenges related to controlling collaborative exploration of non-informative arm pairs, but has received little attention. To fill this gap, we demonstrate that the direct use of a Follow Your Leader black-box approach matches the lower bound for this setting when utilizing known dueling bandit algorithms as a foundation. Additionally, we analyze a message-passing fully distributed approach with a novel Condorcet-winner recommendation protocol, resulting in expedited exploration in many cases. Our experimental comparisons reveal that our multiplayer algorithms surpass single-player benchmark algorithms, underscoring their efficacy in addressing the nuanced challenges of the multiplayer dueling bandit setting.
Authors: Xutong Liu, Siwei Wang, Jinhang Zuo, Han Zhong, Xuchuang Wang, Zhiyong Wang, Shuai Li, Mohammad Hajiesmaili, John C. S. Lui, Wei Chen
Abstract: We introduce a novel framework of combinatorial multi-armed bandits (CMAB) with multivariant and probabilistically triggering arms (CMAB-MT), where the outcome of each arm is a $d$-dimensional multivariant random variable and the feedback follows a general arm triggering process. Compared with existing CMAB works, CMAB-MT not only enhances the modeling power but also allows improved results by leveraging distinct statistical properties for multivariant random variables. For CMAB-MT, we propose a general 1-norm multivariant and triggering probability-modulated smoothness condition, and an optimistic CUCB-MT algorithm built upon this condition. Our framework can include many important problems as applications, such as episodic reinforcement learning (RL) and probabilistic maximum coverage for goods distribution, all of which meet the above smoothness condition and achieve matching or improved regret bounds compared to existing works. Through our new framework, we build the first connection between the episodic RL and CMAB literature, by offering a new angle to solve the episodic RL through the lens of CMAB, which may encourage more interactions between these two important directions.
Authors: Axel Levy, Eric R. Chan, Sara Fridovich-Keil, Fr\'ed\'eric Poitevin, Ellen D. Zhong, Gordon Wetzstein
Abstract: The interaction of a protein with its environment can be understood and controlled via its 3D structure. Experimental methods for protein structure determination, such as X-ray crystallography or cryogenic electron microscopy, shed light on biological processes but introduce challenging inverse problems. Learning-based approaches have emerged as accurate and efficient methods to solve these inverse problems for 3D structure determination, but are specialized for a predefined type of measurement. Here, we introduce a versatile framework to turn biophysical measurements, such as cryo-EM density maps, into 3D atomic models. Our method combines a physics-based forward model of the measurement process with a pretrained generative model providing a task-agnostic, data-driven prior. Our method outperforms posterior sampling baselines on linear and non-linear inverse problems. In particular, it is the first diffusion-based method for refining atomic models from cryo-EM maps and building atomic models from sparse distance matrices.
Authors: Jingyao Wang, Siyu Zhao, Wenwen Qiang, Jiangmeng Li, Fuchun Sun, Hui Xiong
Abstract: Multi-Modal Learning (MML) aims to learn effective representations across modalities for accurate predictions. Existing methods typically focus on modality consistency and specificity to learn effective representations. However, from a causal perspective, they may lead to representations that contain insufficient and unnecessary information. To address this, we propose that effective MML representations should be causally sufficient and necessary. Considering practical issues like spurious correlations and modality conflicts, we relax the exogeneity and monotonicity assumptions prevalent in prior works and explore the concepts specific to MML, i.e., Causal Complete Cause (\(C^3\)). We begin by defining \(C^3\), which quantifies the probability of representations being causally sufficient and necessary. We then discuss the identifiability of \(C^3\) and introduce an instrumental variable to support identifying \(C^3\) with non-exogeneity and non-monotonicity. Building on this, we conduct the $C^3$ measurement, i.e., \(C^3\) risk. We propose a twin network to estimate it through (i) the real-world branch: utilizing the instrumental variable for sufficiency, and (ii) the hypothetical-world branch: applying gradient-based counterfactual modeling for necessity. Theoretical analyses confirm its reliability. Based on these results, we propose $C^3$ Regularization, a plug-and-play method that enforces the causal completeness of the learned representations by minimizing \(C^3\) risk. Extensive experiments demonstrate its effectiveness.
Authors: Joshua Shay Kricheli, Khoa Vo, Aniruddha Datta, Spencer Ozgur, Paulo Shakarian
Abstract: Recent advances in Hierarchical Multi-label Classification (HMC), particularly neurosymbolic-based approaches, have demonstrated improved consistency and accuracy by enforcing constraints on a neural model during training. However, such work assumes the existence of such constraints a-priori. In this paper, we relax this strong assumption and present an approach based on Error Detection Rules (EDR) that allow for learning explainable rules about the failure modes of machine learning models. We show that these rules are not only effective in detecting when a machine learning classifier has made an error but also can be leveraged as constraints for HMC, thereby allowing the recovery of explainable constraints even if they are not provided. We show that our approach is effective in detecting machine learning errors and recovering constraints, is noise tolerant, and can function as a source of knowledge for neurosymbolic models on multiple datasets, including a newly introduced military vehicle recognition dataset.
Authors: Georgios Is. Detorakis
Abstract: Deep learning has become a popular tool across many scientific fields, including the study of differential equations, particularly partial differential equations. This work introduces the basic principles of deep learning and the Deep Galerkin method, which uses deep neural networks to solve differential equations. This primer aims to provide technical and practical insights into the Deep Galerkin method and its implementation. We demonstrate how to solve the one-dimensional heat equation step-by-step. We also show how to apply the Deep Galerkin method to solve systems of ordinary differential equations and integral equations, such as the Fredholm of the second kind. Additionally, we provide code snippets within the text and the complete source code on Github. The examples are designed so that one can run them on a simple computer without needing a GPU.
Authors: Xin Jin, Hongyu Zhu, Siyuan Li, Zedong Wang, Zicheng Liu, Juanxi Tian, Chang Yu, Huafeng Qin, Stan Z. Li
Abstract: As Deep Neural Networks have achieved thrilling breakthroughs in the past decade, data augmentations have garnered increasing attention as regularization techniques when massive labeled data are unavailable. Among existing augmentations, Mixup and relevant data-mixing methods that convexly combine selected samples and the corresponding labels are widely adopted because they yield high performances by generating data-dependent virtual data while easily migrating to various domains. This survey presents a comprehensive review of foundational mixup methods and their applications. We first elaborate on the training pipeline with mixup augmentations as a unified framework containing modules. A reformulated framework could contain various mixup methods and give intuitive operational procedures. Then, we systematically investigate the applications of mixup augmentations on vision downstream tasks, various data modalities, and some analysis \& theorems of mixup. Meanwhile, we conclude the current status and limitations of mixup research and point out further work for effective and efficient mixup augmentations. This survey can provide researchers with the current state of the art in mixup methods and provide some insights and guidance roles in the mixup arena. An online project with this survey is available at https://github.com/Westlake-AI/Awesome-Mixup.
Authors: Wenxian Shi, Menghua Wu, Regina Barzilay
Abstract: Forecasting the change in the distribution of viral variants is crucial for therapeutic design and disease surveillance. This task poses significant modeling challenges due to the sharp differences in virus distributions across sub-populations (e.g., countries) and their dynamic interactions. Existing machine learning approaches that model the variant distribution as a whole are incapable of making location-specific predictions and ignore transmissions that shape the viral landscape. In this paper, we propose a sub-population specific protein evolution model, which predicts the time-resolved distributions of viral proteins in different locations. The algorithm explicitly models the transmission rates between sub-populations and learns their interdependence from data. The change in protein distributions across all sub-populations is defined through a linear ordinary differential equation (ODE) parametrized by transmission rates. Solving this ODE yields the likelihood of a given protein occurring in particular sub-populations. Multi-year evaluation on both SARS-CoV-2 and influenza A/H3N2 demonstrates that our model outperforms baselines in accurately predicting distributions of viral proteins across continents and countries. We also find that the transmission rates learned from data are consistent with the transmission pathways discovered by retrospective phylogenetic analysis.
Authors: Jung Yeon Park, Sujay Bhatt, Sihan Zeng, Lawson L. S. Wong, Alec Koppel, Sumitra Ganesh, Robin Walters
Abstract: Equivariant neural networks have shown great success in reinforcement learning, improving sample efficiency and generalization when there is symmetry in the task. However, in many problems, only approximate symmetry is present, which makes imposing exact symmetry inappropriate. Recently, approximately equivariant networks have been proposed for supervised classification and modeling physical systems. In this work, we develop approximately equivariant algorithms in reinforcement learning (RL). We define approximately equivariant MDPs and theoretically characterize the effect of approximate equivariance on the optimal $Q$ function. We propose novel RL architectures using relaxed group and steerable convolutions and experiment on several continuous control domains and stock trading with real financial data. Our results demonstrate that the approximately equivariant network performs on par with exactly equivariant networks when exact symmetries are present, and outperforms them when the domains exhibit approximate symmetry. As an added byproduct of these techniques, we observe increased robustness to noise at test time. Our code is available at https://github.com/jypark0/approx_equiv_rl.
Authors: Fanjin Wang, Maryam Parhizkar, Anthony Harker, Mohan Edirisinghe
Abstract: Polymeric nano- and micro-scale particles have critical roles in tackling critical healthcare and energy challenges with their miniature characteristics. However, tailoring their synthesis process to meet specific design targets has traditionally depended on domain expertise and costly trial-and-errors. Recently, modeling strategies, particularly Bayesian optimization (BO), have been proposed to aid materials discovery for maximized/minimized properties. Coming from practical demands, this study for the first time integrates constrained and composite Bayesian optimization (CCBO) to perform efficient target value optimization under black-box feasibility constraints and limited data for laboratory experimentation. Using a synthetic problem that simulates electrospraying, a model nanomanufacturing process, CCBO strategically avoided infeasible conditions and efficiently optimized particle production towards predefined size targets, surpassing standard BO pipelines and providing decisions comparable to human experts. Further laboratory experiments validated CCBO capability to guide the rational synthesis of poly(lactic-co-glycolic acid) (PLGA) particles with diameters of 300 nm and 3.0 $\mu$m via electrospraying. With minimal initial data and unknown experiment constraints, CCBO reached the design targets within 4 iterations. Overall, the CCBO approach presents a versatile and holistic optimization paradigm for next-generation target-driven particle synthesis empowered by artificial intelligence (AI).
Authors: Hemal Mahmud, Hasan Mahmud, Mohammad Rifat Ahmmad Rashid
Abstract: Sentiment analysis (SA) is a process of identifying the emotional tone or polarity within a given text and aims to uncover the user's complex emotions and inner feelings. While sentiment analysis has been extensively studied for languages like English, research in Bengali, remains limited, particularly for fine-grained sentiment categorization. This work aims to connect this gap by developing a novel approach that integrates rule-based algorithms with pre-trained language models. We developed a dataset from scratch, comprising over 15,000 manually labeled reviews. Next, we constructed a Lexicon Data Dictionary, assigning polarity scores to the reviews. We developed a novel rule based algorithm Bangla Sentiment Polarity Score (BSPS), an approach capable of generating sentiment scores and classifying reviews into nine distinct sentiment categories. To assess the performance of this method, we evaluated the classified sentiments using BanglaBERT, a pre-trained transformer-based language model. We also performed sentiment classification directly with BanglaBERT on the original data and evaluated this model's results. Our analysis revealed that the BSPS + BanglaBERT hybrid approach outperformed the standalone BanglaBERT model, achieving higher accuracy, precision, and nuanced classification across the nine sentiment categories. The results of our study emphasize the value and effectiveness of combining rule-based and pre-trained language model approaches for enhanced sentiment analysis in Bengali and suggest pathways for future research and application in languages with similar linguistic complexities.
Authors: Yuyang Tao, Shufei Ge
Abstract: The Mapper algorithm is an essential tool for visualizing complex, high dimensional data in topology data analysis (TDA) and has been widely used in biomedical research. It outputs a combinatorial graph whose structure implies the shape of the data. However,the need for manual parameter tuning and fixed intervals, along with fixed overlapping ratios may impede the performance of the standard Mapper algorithm. Variants of the standard Mapper algorithms have been developed to address these limitations, yet most of them still require manual tuning of parameters. Additionally, many of these variants, including the standard version found in the literature, were built within a deterministic framework and overlooked the uncertainty inherent in the data. To relax these limitations, in this work, we introduce a novel framework that implicitly represents intervals through a hidden assignment matrix, enabling automatic parameter optimization via stochastic gradient descent. In this work, we develop a soft Mapper framework based on a Gaussian mixture model(GMM) for flexible and implicit interval construction. We further illustrate the robustness of the soft Mapper algorithm by introducing the Mapper graph mode as a point estimation for the output graph. Moreover, a stochastic gradient descent algorithm with a specific topological loss function is proposed for optimizing parameters in the model. Both simulation and application studies demonstrate its effectiveness in capturing the underlying topological structures. In addition, the application to an RNA expression dataset obtained from the Mount Sinai/JJ Peters VA Medical Center Brain Bank (MSBB) successfully identifies a distinct subgroup of Alzheimer's Disease.
Authors: Bao-Bing Li, Yi Gu, Shao-Feng Wu
Abstract: Machine learning can uncover physical concepts or physical equations when prior knowledge from the other is available. However, these two aspects are often intertwined and cannot be discovered independently. We extend SciNet, which is a neural network architecture that simulates the human physical reasoning process for physics discovery, by proposing a model that combines Variational Autoencoders (VAE) with Neural Ordinary Differential Equations (Neural ODEs). This allows us to simultaneously discover physical concepts and governing equations from simulated experimental data across various physical systems. We apply the model to several examples inspired by the history of physics, including Copernicus' heliocentrism, Newton's law of gravity, Schr\"odinger's wave mechanics, and Pauli's spin-magnetic formulation. The results demonstrate that the correct physical theories can emerge in the neural network.
Authors: Yoontae Hwang, Yongjae Lee
Abstract: Tabular data poses unique challenges due to its heterogeneous nature, combining both continuous and categorical variables. Existing approaches often struggle to effectively capture the underlying structure and relationships within such data. We propose GFTab (Geodesic Flow Kernels for Semi- Supervised Learning on Mixed-Variable Tabular Dataset), a semi-supervised framework specifically designed for tabular datasets. GFTab incorporates three key innovations: 1) Variable-specific corruption methods tailored to the distinct properties of continuous and categorical variables, 2) A Geodesic flow kernel based similarity measure to capture geometric changes between corrupted inputs, and 3) Tree-based embedding to leverage hierarchical relationships from available labeled data. To rigorously evaluate GFTab, we curate a comprehensive set of 21 tabular datasets spanning various domains, sizes, and variable compositions. Our experimental results show that GFTab outperforms existing ML/DL models across many of these datasets, particularly in settings with limited labeled data.
Authors: Yiting Hu, Lingjie Duan
Abstract: The contextual bandit problem, where agents arrive sequentially with personal contexts and the system adapts its arm allocation decisions accordingly, has recently garnered increasing attention for enabling more personalized outcomes. However, in many healthcare and recommendation applications, agents have private profiles and may misreport their contexts to gain from the system. For example, in adaptive clinical trials, where hospitals sequentially recruit volunteers to test multiple new treatments and adjust plans based on volunteers' reported profiles such as symptoms and interim data, participants may misreport severe side effects like allergy and nausea to avoid perceived suboptimal treatments. We are the first to study this issue of private context misreporting in a stochastic contextual bandit game between the system and non-repeated agents. We show that traditional low-regret algorithms, such as UCB family algorithms and Thompson sampling, fail to ensure truthful reporting and can result in linear regret in the worst case, while traditional truthful algorithms like explore-then-commit (ETC) and $\epsilon$-greedy algorithm incur sublinear but high regret. We propose a mechanism that uses a linear program to ensure truthfulness while minimizing deviation from Thompson sampling, yielding an $O(\ln T)$ frequentist regret. Our numerical experiments further demonstrate strong performance in multiple contexts and across other distribution families.
Authors: Arun Sharma, Majid Farhadloo, Mingzhou Yang, Ruolei Zeng, Subhankar Ghosh, Shashi Shekhar
Abstract: Given inputs of diverse soil characteristics and climate data gathered from various regions, we aimed to build a model to predict accurate land emissions. The problem is important since accurate quantification of the carbon cycle in agroecosystems is crucial for mitigating climate change and ensuring sustainable food production. Predicting accurate land emissions is challenging since calibrating the heterogeneous nature of soil properties, moisture, and environmental conditions is hard at decision-relevant scales. Traditional approaches do not adequately estimate land emissions due to location-independent parameters failing to leverage the spatial heterogeneity and also require large datasets. To overcome these limitations, we proposed Spatial Distribution-Shift Aware Knowledge-Guided Machine Learning (SDSA-KGML), which leverages location-dependent parameters that account for significant spatial heterogeneity in soil moisture from multiple sites within the same region. Experimental results demonstrate that SDSA-KGML models achieve higher local accuracy for the specified states in the Midwest Region.
Authors: Majid Farhadloo, Arun Sharma, Mingzhou Yang, Bharat Jayaprakash, William Northrop, Shashi Shekhar
Abstract: Traditional foundation models are pre-trained on broad datasets to reduce the training resources (e.g., time, energy, labeled samples) needed for fine-tuning a wide range of downstream tasks. However, traditional foundation models struggle with out-of-distribution prediction and can produce outputs that are unrealistic and physically infeasible. We propose the notation of physics-guided foundation models (PGFM), that is, foundation models integrated with broad or general domain (e.g., scientific) physical knowledge applicable to a wide range of downstream tasks.
Authors: Ichiro Ohta, Shota Koyanagi, Kayo Kinjo, Jun Ohkubo
Abstract: In recent years, there has been a growing interest in data-driven approaches in physics, such as extended dynamic mode decomposition (EDMD). The EDMD algorithm focuses on nonlinear time-evolution systems, and the constructed Koopman matrix yields the next-time prediction with only linear matrix-product operations. Note that data-driven approaches generally require a large dataset. However, assume that one has some prior knowledge, even if it may be ambiguous. Then, one could achieve sufficient learning from only a small dataset by taking advantage of the prior knowledge. This paper yields methods for incorporating ambiguous prior knowledge into the EDMD algorithm. The ambiguous prior knowledge in this paper corresponds to the underlying time-evolution equations with unknown parameters. First, we apply the proposed method to forward problems, i.e., prediction tasks. Second, we propose a scheme to apply the proposed method to inverse problems, i.e., parameter estimation tasks. We demonstrate the learning with only a small dataset using guiding examples, i.e., the Duffing and the van der Pol systems.
Authors: Hongjie He, Xu Pan, Yudong Yao
Abstract: As deep learning continues to advance, the transparency of neural network decision-making remains a critical challenge, limiting trust and applicability in high-stakes domains. Class Activation Mapping (CAM) techniques have emerged as a key approach toward visualizing model decisions, yet existing methods face inherent trade-offs. Gradient-based CAM variants suffer from sensitivity to gradient perturbations due to gradient noise, leading to unstable and unreliable explanations. Conversely, gradient-free approaches mitigate gradient instability but incur significant computational overhead and inference latency. To address these limitations, we propose a Cluster Filter Class Activation Map (CF-CAM) technique, a novel framework that reintroduces gradient-based weighting while enhancing robustness against gradient noise. CF-CAM utilizes hierarchical importance weighting strategy to balance discriminative feature preservation and noise elimination. A density-aware channel clustering method via Density-Based Spatial Clustering of Applications with Noise (DBSCAN) groups semantically relevant feature channels and discard noise-prone activations. Additionally, cluster-conditioned gradient filtering leverages Gaussian filters to refine gradient signals, preserving edge-aware localization while suppressing noise impact. Experiment results demonstrate that CF-CAM achieves superior interpretability performance while enhancing computational efficiency, outperforming state-of-the-art CAM methods in faithfulness and robustness. By effectively mitigating gradient instability without excessive computational cost, CF-CAM provides a competitive solution for enhancing the interpretability of deep neural networks in critical applications such as autonomous driving and medical diagnosis.
Authors: Qingyang Zhang, Haitao Wu, Changqing Zhang, Peilin Zhao, Yatao Bian
Abstract: While large language models (LLMs) have demonstrated exceptional capabilities in challenging tasks such as mathematical reasoning, existing methods to enhance reasoning ability predominantly rely on supervised fine-tuning (SFT) followed by reinforcement learning (RL) on reasoning-specific data after pre-training. However, these approaches critically depend on external supervision--such as human-labelled reasoning traces, verified golden answers, or pre-trained reward models--which limits scalability and practical applicability. In this work, we propose Entropy Minimized Policy Optimization (EMPO), which makes an early attempt at fully unsupervised LLM reasoning incentivization. EMPO does not require any supervised information for incentivizing reasoning capabilities (i.e., neither verifiable reasoning traces, problems with golden answers, nor additional pre-trained reward models). By continuously minimizing the predictive entropy of LLMs on unlabeled user queries in a latent semantic space, EMPO enables purely self-supervised evolution of reasoning capabilities with strong flexibility and practicality. Our experiments demonstrate competitive performance of EMPO on both mathematical reasoning and free-form natural reasoning tasks. Specifically, without any supervised signals, \ours boosts the accuracy of Qwen2.5-Math-7B Base from 30.7\% to 48.1\% on mathematical benchmarks and improves the accuracy of Qwen2.5-7B Base from 32.1\% to 50.1\% on MMLU-Pro.
Authors: Jos\'e I. Orlicki
Abstract: We present a design called Proof of Gradient Optimization (PoGO) for blockchain consensus, where miners produce verifiable evidence of training large-scale machine-learning models. Building on previous work, we incorporate quantized gradients (4-bit precision) to reduce storage and computation requirements, while still preserving the ability of verifiers to check that real progress has been made on lowering the model's loss. Additionally, we employ Merkle proofs over the full 32-bit model to handle large parameter sets and to enable random leaf checks with minimal on-chain data. We illustrate these ideas using GPT-3 (175B parameters) as a reference example and also refer to smaller but high-performance models (e.g., Gemma~3 with 27B parameters). We provide an empirical cost analysis showing that verification is significantly cheaper than training, thanks in part to quantization and sampling. We also discuss the necessity of longer block times (potentially hours) when incorporating meaningful training steps, the trade-offs when using specialized GPU hardware, and how binary diffs may incrementally optimize updates. Finally, we note that fine-tuning can be handled in a similar manner, merely changing the dataset and the manner of sampling but preserving the overall verification flow. Our protocol allows verifiers to issue either positive or negative attestations; these are aggregated at finalization to either confirm the update or slash the miner.
Authors: Jinfeng Zhuang, Yinrui Li, Runze Su, Ke Xu, Zhixuan Shao, Kungang Li, Ling Leng, Han Sun, Meng Qi, Yixiong Meng, Yang Tang, Zhifang Liu, Qifei Shen, Aayush Mudgal, Caleb Lu, Jie Liu, Hongda Shen
Abstract: The predictions of click through rate (CTR) and conversion rate (CVR) play a crucial role in the success of ad-recommendation systems. A Deep Hierarchical Ensemble Network (DHEN) has been proposed to integrate multiple feature crossing modules and has achieved great success in CTR prediction. However, its performance for CVR prediction is unclear in the conversion ads setting, where an ad bids for the probability of a user's off-site actions on a third party website or app, including purchase, add to cart, sign up, etc. A few challenges in DHEN: 1) What feature-crossing modules (MLP, DCN, Transformer, to name a few) should be included in DHEN? 2) How deep and wide should DHEN be to achieve the best trade-off between efficiency and efficacy? 3) What hyper-parameters to choose in each feature-crossing module? Orthogonal to the model architecture, the input personalization features also significantly impact model performance with a high degree of freedom. In this paper, we attack this problem and present our contributions biased to the applied data science side, including: First, we propose a multitask learning framework with DHEN as the single backbone model architecture to predict all CVR tasks, with a detailed study on how to make DHEN work effectively in practice; Second, we build both on-site real-time user behavior sequences and off-site conversion event sequences for CVR prediction purposes, and conduct ablation study on its importance; Last but not least, we propose a self-supervised auxiliary loss to predict future actions in the input sequence, to help resolve the label sparseness issue in CVR prediction. Our method achieves state-of-the-art performance compared to previous single feature crossing modules with pre-trained user personalization features.
Authors: Siow Meng Low, Akshat Kumar
Abstract: In safe reinforcement learning (RL), auxiliary safety costs are used to align the agent to safe decision making. In practice, safety constraints, including cost functions and budgets, are unknown or hard to specify, as it requires anticipation of all possible unsafe behaviors. We therefore address a general setting where the true safety definition is unknown, and has to be learned from sparsely labeled data. Our key contributions are: first, we design a safety model that performs credit assignment to estimate each decision step's impact on the overall safety using a dataset of diverse trajectories and their corresponding binary safety labels (i.e., whether the corresponding trajectory is safe/unsafe). Second, we illustrate the architecture of our safety model to demonstrate its ability to learn a separate safety score for each timestep. Third, we reformulate the safe RL problem using the proposed safety model and derive an effective algorithm to optimize a safe yet rewarding policy. Finally, our empirical results corroborate our findings and show that this approach is effective in satisfying unknown safety definition, and scalable to various continuous control tasks.
Authors: Anna C. M. Th\"oni, Yoram Bachrach, Tal Kachman
Abstract: Mean-field game theory relies on approximating games that would otherwise have been intractable to model. While the games can be solved analytically via the associated system of partial derivatives, this approach is not model-free, can lead to the loss of the existence or uniqueness of solutions and may suffer from modelling bias. To reduce the dependency between the model and the game, we combine mean-field game theory with deep learning in the form of neural ordinary differential equations. The resulting model is data-driven, lightweight and can learn extensive strategic interactions that are hard to capture using mean-field theory alone. In addition, the model is based on automatic differentiation, making it more robust and objective than approaches based on finite differences. We highlight the efficiency and flexibility of our approach by solving three mean-field games that vary in their complexity, observability and the presence of noise. Using these results, we show that the model is flexible, lightweight and requires few observations to learn the distribution underlying the data.
Authors: Zhanglin Wu, Tengfei Song, Ning Xie, Mengli Zhu, Weidong Zhang, Shuang Wu, Pengfei Li, Chong Li, Junhao Zhu, Hao Yang, Shiliang Sun
Abstract: The rapid advancement of large vision-language models (LVLMs) has significantly propelled applications in document understanding, particularly in optical character recognition (OCR) and multilingual translation. However, current evaluations of LVLMs, like the widely used OCRBench, mainly focus on verifying the correctness of their short-text responses and long-text responses with simple layout, while the evaluation of their ability to understand long texts with complex layout design is highly significant but largely overlooked. In this paper, we propose Menu OCR and Translation Benchmark (MOTBench), a specialized evaluation framework emphasizing the pivotal role of menu translation in cross-cultural communication. MOTBench requires LVLMs to accurately recognize and translate each dish, along with its price and unit items on a menu, providing a comprehensive assessment of their visual understanding and language processing capabilities. Our benchmark is comprised of a collection of Chinese and English menus, characterized by intricate layouts, a variety of fonts, and culturally specific elements across different languages, along with precise human annotations. Experiments show that our automatic evaluation results are highly consistent with professional human evaluation. We evaluate a range of publicly available state-of-the-art LVLMs, and through analyzing their output to identify the strengths and weaknesses in their performance, offering valuable insights to guide future advancements in LVLM development. MOTBench is available at https://github.com/gitwzl/MOTBench.
Authors: Raghavv Goel, Junyoung Park, Mukul Gagrani, Dalton Jones, Matthew Morse, Harper Langston, Mingu Lee, Chris Lott
Abstract: While long context support of large language models has extended their abilities, it also incurs challenges in memory and compute which becomes crucial bottlenecks in resource-restricted devices. Token eviction, a widely adopted post-training methodology designed to alleviate the bottlenecks by evicting less important tokens from the cache, typically uses attention scores as proxy metrics for token importance. However, one major limitation of attention score as a token-wise importance metrics is that it lacks the information about contribution of tokens to the attention output. In this paper, we propose a simple eviction criterion based on the contribution of cached tokens to attention outputs. Our method, CAOTE, optimizes for eviction error due to token eviction, by seamlessly integrating attention scores and value vectors. This is the first method which uses value vector information on top of attention-based eviction scores. Additionally, CAOTE can act as a meta-heuristic method with flexible usage with any token eviction method. We show that CAOTE, when combined with the state-of-the-art attention score-based methods, always improves accuracies on the downstream task, indicating the importance of leveraging information from values during token eviction process.
Authors: Dennis Liu, Zijie Yan, Xin Yao, Tong Liu, Vijay Korthikanti, Evan Wu, Shiqing Fan, Gao Deng, Hongxiao Bai, Jianbin Chang, Ashwath Aithal, Michael Andersch, Mohammad Shoeybi, Jiajie Yao, Chandler Zhou, David Wu, Xipeng Li, June Yang
Abstract: Mixture of Experts (MoE) models enhance neural network scalability by dynamically selecting relevant experts per input token, enabling larger model sizes while maintaining manageable computation costs. However, efficient training of large-scale MoE models across thousands of GPUs presents significant challenges due to limitations in existing parallelism strategies. We introduce an end-to-end training framework for large-scale MoE models that utilizes five-dimensional hybrid parallelism: Tensor Parallelism, Expert Parallelism, Context Parallelism, Data Parallelism, and Pipeline Parallelism. Central to our approach is MoE Parallel Folding, a novel strategy that decouples the parallelization of attention and MoE layers in Transformer models, allowing each layer type to adopt optimal parallel configurations. Additionally, we develop a flexible token-level dispatcher that supports both token-dropping and token-dropless MoE training across all five dimensions of parallelism. This dispatcher accommodates dynamic tensor shapes and coordinates different parallelism schemes for Attention and MoE layers, facilitating complex parallelism implementations. Our experiments demonstrate significant improvements in training efficiency and scalability. We achieve up to 49.3% Model Flops Utilization (MFU) for the Mixtral 8x22B model and 39.0% MFU for the Qwen2-57B-A14B model on H100 GPUs, outperforming existing methods. The framework scales efficiently up to 1,024 GPUs and maintains high performance with sequence lengths up to 128K tokens, validating its effectiveness for large-scale MoE model training. The code is available in Megatron-Core.
Authors: Kai Luo, Juan Tang, Mingchao Cai, Xiaoqing Zeng, Manqi Xie, Ming Yan
Abstract: Kolmogorov-Arnold Networks (KANs) have emerged as a promising alternative to Multi-layer Perceptrons (MLPs) due to their superior function-fitting abilities in data-driven modeling. In this paper, we propose a novel framework, DAE-KAN, for solving high-index differential-algebraic equations (DAEs) by integrating KANs with Physics-Informed Neural Networks (PINNs). This framework not only preserves the ability of traditional PINNs to model complex systems governed by physical laws but also enhances their performance by leveraging the function-fitting strengths of KANs. Numerical experiments demonstrate that for DAE systems ranging from index-1 to index-3, DAE-KAN reduces the absolute errors of both differential and algebraic variables by 1 to 2 orders of magnitude compared to traditional PINNs. To assess the effectiveness of this approach, we analyze the drift-off error and find that both PINNs and DAE-KAN outperform classical numerical methods in controlling this phenomenon. Our results highlight the potential of neural network methods, particularly DAE-KAN, in solving high-index DAEs with substantial computational accuracy and generalization, offering a promising solution for challenging partial differential-algebraic equations.
Authors: Soham Sane
Abstract: We introduce AlphaGrad, a memory-efficient, conditionally stateless optimizer addressing the memory overhead and hyperparameter complexity of adaptive methods like Adam. AlphaGrad enforces scale invariance via tensor-wise L2 gradient normalization followed by a smooth hyperbolic tangent transformation, $g' = \tanh(\alpha \cdot \tilde{g})$, controlled by a single steepness parameter $\alpha$. Our contributions include: (1) the AlphaGrad algorithm formulation; (2) a formal non-convex convergence analysis guaranteeing stationarity; (3) extensive empirical evaluation on diverse RL benchmarks (DQN, TD3, PPO). Compared to Adam, AlphaGrad demonstrates a highly context-dependent performance profile. While exhibiting instability in off-policy DQN, it provides enhanced training stability with competitive results in TD3 (requiring careful $\alpha$ tuning) and achieves substantially superior performance in on-policy PPO. These results underscore the critical importance of empirical $\alpha$ selection, revealing strong interactions between the optimizer's dynamics and the underlying RL algorithm. AlphaGrad presents a compelling alternative optimizer for memory-constrained scenarios and shows significant promise for on-policy learning regimes where its stability and efficiency advantages can be particularly impactful.
Authors: Ioannis Avramopoulos
Abstract: We show that, by using multiplicative weights in a game-theoretic thought experiment (and an important convexity result on the composition of multiplicative weights with the relative entropy function), a symmetric bimatrix game (that is, a bimatrix matrix wherein the payoff matrix of each player is the transpose of the payoff matrix of the other) either has an interior symmetric equilibrium or there is a pure strategy that is weakly dominated by some mixed strategy. Weakly dominated pure strategies can be detected and eliminated in polynomial time by solving a linear program. Furthermore, interior symmetric equilibria are a special case of a more general notion, namely, that of an "equalizer," which can also be computed efficiently in polynomial time by solving a linear program. An elegant "symmetrization method" of bimatrix games [Jurg et al., 1992] and the well-known PPAD-completeness results on equilibrium computation in bimatrix games [Daskalakis et al., 2009, Chen et al., 2009] imply then the compelling P = PPAD.
Authors: Andrew Kiruluta, Andreas Lemos, Eric Lundy
Abstract: We revisit the use of spectral techniques to replaces the attention mechanism in Transformers through Fourier Transform based token mixing, and present a comprehensive and novel reformulation of this technique in next generation transformer models. We provide expanded literature context, detailed mathematical formulations of Fourier mixing and causal masking, and introduce a novel MultiDomain Fourier Wavelet Attention(MDFWA) that integrates frequency and time localized transforms to capture both global and local dependencies efficiently. We derive the complexity bounds, gradient formulas, and show that MDFWA achieves sub quadratic time and memory cost while improving expressive power. We validate our design on an abstractive summarization task using PubMed dataset, by enhancing the proposed approach with learned frequency bases, adaptive scale selection, and multi-modal extensions.
Authors: Utkarsh Singhal, Yifei Xing, Stella X. Yu
Abstract: We study complex-valued scaling as a type of symmetry natural and unique to complex-valued measurements and representations. Deep Complex Networks (DCN) extends real-valued algebra to the complex domain without addressing complex-valued scaling. SurReal takes a restrictive manifold view of complex numbers, adopting a distance metric to achieve complex-scaling invariance while losing rich complex-valued information. We analyze complex-valued scaling as a co-domain transformation and design novel equivariant and invariant neural network layer functions for this special transformation. We also propose novel complex-valued representations of RGB images, where complex-valued scaling indicates hue shift or correlated changes across color channels. Benchmarked on MSTAR, CIFAR10, CIFAR100, and SVHN, our co-domain symmetric (CDS) classifiers deliver higher accuracy, better generalization, robustness to co-domain transformations, and lower model bias and variance than DCN and SurReal with far fewer parameters.
Authors: Francesco Santini, Jakob Wasserthal, Abramo Agosti, Xeni Deligianni, Kevin R. Keene, Hermien E. Kan, Stefan Sommer, Fengdan Wang, Claudia Weidensteiner, Giulia Manco, Matteo Paoletti, Valentina Mazzoli, Arjun Desai, Anna Pichiecchio
Abstract: Purpose: To present and evaluate Dafne (deep anatomical federated network), a freely available decentralized, collaborative deep learning system for the semantic segmentation of radiological images through federated incremental learning. Materials and Methods: Dafne is free software with a client-server architecture. The client side is an advanced user interface that applies the deep learning models stored on the server to the user's data and allows the user to check and refine the prediction. Incremental learning is then performed at the client's side and sent back to the server, where it is integrated into the root model. Dafne was evaluated locally, by assessing the performance gain across model generations on 38 MRI datasets of the lower legs, and through the analysis of real-world usage statistics (n = 639 use-cases). Results: Dafne demonstrated a statistically improvement in the accuracy of semantic segmentation over time (average increase of the Dice Similarity Coefficient by 0.007 points/generation on the local validation set, p < 0.001). Qualitatively, the models showed enhanced performance on various radiologic image types, including those not present in the initial training sets, indicating good model generalizability. Conclusion: Dafne showed improvement in segmentation quality over time, demonstrating potential for learning and generalization.
Authors: Gilchan Park, Byung-Jun Yoon, Xihaier Luo, Vanessa L\'opez-Marrero, Shinjae Yoo, Shantenu Jha
Abstract: Background: Identification of the interactions and regulatory relations between biomolecules play pivotal roles in understanding complex biological systems and the mechanisms underlying diverse biological functions. However, the collection of such molecular interactions has heavily relied on expert curation in the past, making it labor-intensive and time-consuming. To mitigate these challenges, we propose leveraging the capabilities of large language models (LLMs) to automate genome-scale extraction of this crucial knowledge. Results: In this study, we investigate the efficacy of various LLMs in addressing biological tasks, such as the recognition of protein interactions, identification of genes linked to pathways affected by low-dose radiation, and the delineation of gene regulatory relationships. Overall, the larger models exhibited superior performance, indicating their potential for specific tasks that involve the extraction of complex interactions among genes and proteins. Although these models possessed detailed information for distinct gene and protein groups, they faced challenges in identifying groups with diverse functions and in recognizing highly correlated gene regulatory relationships. Conclusions: By conducting a comprehensive assessment of the state-of-the-art models using well-established molecular interaction and pathway databases, our study reveals that LLMs can identify genes/proteins associated with pathways of interest and predict their interactions to a certain extent. Furthermore, these models can provide important insights, marking a noteworthy stride toward advancing our understanding of biological systems through AI-assisted knowledge discovery.
Authors: Fedor Noskov, Maxim Panov
Abstract: Community detection is one of the most critical problems in modern network science. Its applications can be found in various fields, from protein modeling to social network analysis. Recently, many papers appeared studying the problem of overlapping community detection, where each node of a network may belong to several communities. In this work, we consider Mixed-Membership Stochastic Block Model (MMSB) first proposed by Airoldi et al. MMSB provides quite a general setting for modeling overlapping community structure in graphs. The central question of this paper is to reconstruct relations between communities given an observed network. We compare different approaches and establish the minimax lower bound on the estimation error. Then, we propose a new estimator that matches this lower bound. Theoretical results are proved under fairly general conditions on the considered model. Finally, we illustrate the theory in a series of experiments.
Authors: Jian Cheng Wong, Chin Chun Ooi, Abhishek Gupta, Pao-Hsiung Chiu, Joshua Shao Zheng Low, My Ha Dao, Yew-Soon Ong
Abstract: Physics-informed neural networks (PINNs) are at the forefront of scientific machine learning, making possible the creation of machine intelligence that is cognizant of physical laws and able to accurately simulate them. However, today's PINNs are often trained for a single physics task and require computationally expensive re-training for each new task, even for tasks from similar physics domains. To address this limitation, this paper proposes a pioneering approach to advance the generalizability of PINNs through the framework of Baldwinian evolution. Drawing inspiration from the neurodevelopment of precocial species that have evolved to learn, predict and react quickly to their environment, we envision PINNs that are pre-wired with connection strengths inducing strong biases towards efficient learning of physics. A novel two-stage stochastic programming formulation coupling evolutionary selection pressure (based on proficiency over a distribution of physics tasks) with lifetime learning (to specialize on a sampled subset of those tasks) is proposed to instantiate the Baldwin effect. The evolved Baldwinian-PINNs demonstrate fast and physics-compliant prediction capabilities across a range of empirically challenging problem instances with more than an order of magnitude improvement in prediction accuracy at a fraction of the computation cost compared to state-of-the-art gradient-based meta-learning methods. For example, when solving the diffusion-reaction equation, a 70x improvement in accuracy was obtained while taking 700x less computational time. This paper thus marks a leap forward in the meta-learning of PINNs as generalizable physics solvers. Sample codes are available at https://github.com/chiuph/Baldwinian-PINN.
Authors: Taesik Gong, Si Young Jang, Utku G\"unay Acer, Fahim Kawsar, Chulhong Min
Abstract: The advent of tiny artificial intelligence (AI) accelerators enables AI to run at the extreme edge, offering reduced latency, lower power cost, and improved privacy. When integrated into wearable devices, these accelerators open exciting opportunities, allowing various AI apps to run directly on the body. We present Synergy that provides AI apps with best-effort performance via system-driven holistic collaboration over AI accelerator-equipped wearables. To achieve this, Synergy provides device-agnostic programming interfaces to AI apps, giving the system visibility and controllability over the app's resource use. Then, Synergy maximizes the inference throughput of concurrent AI models by creating various execution plans for each app considering AI accelerator availability and intelligently selecting the best set of execution plans. Synergy further improves throughput by leveraging parallelization opportunities over multiple computation units. Our evaluations with 7 baselines and 8 models demonstrate that, on average, Synergy achieves a 23.0 times improvement in throughput, while reducing latency by 73.9% and power consumption by 15.8%, compared to the baselines.
Authors: Asad Aali, Dave Van Veen, Yamin Ishraq Arefeen, Jason Hom, Christian Bluethgen, Eduardo Pontes Reis, Sergios Gatidis, Namuun Clifford, Joseph Daws, Arash S. Tehrani, Jangwon Kim, Akshay S. Chaudhari
Abstract: Brief hospital course (BHC) summaries are clinical documents that summarize a patient's hospital stay. While large language models (LLMs) depict remarkable capabilities in automating real-world tasks, their capabilities for healthcare applications such as synthesizing BHCs from clinical notes have not been shown. We introduce a novel pre-processed dataset, the MIMIC-IV-BHC, encapsulating clinical note and brief hospital course (BHC) pairs to adapt LLMs for BHC synthesis. Furthermore, we introduce a benchmark of the summarization performance of two general-purpose LLMs and three healthcare-adapted LLMs. Using clinical notes as input, we apply prompting-based (using in-context learning) and fine-tuning-based adaptation strategies to three open-source LLMs (Clinical-T5-Large, Llama2-13B, FLAN-UL2) and two proprietary LLMs (GPT-3.5, GPT-4). We evaluate these LLMs across multiple context-length inputs using natural language similarity metrics. We further conduct a clinical study with five clinicians, comparing clinician-written and LLM-generated BHCs across 30 samples, focusing on their potential to enhance clinical decision-making through improved summary quality. We observe that the Llama2-13B fine-tuned LLM outperforms other domain-adapted models given quantitative evaluation metrics of BLEU and BERT-Score. GPT-4 with in-context learning shows more robustness to increasing context lengths of clinical note inputs than fine-tuned Llama2-13B. Despite comparable quantitative metrics, the reader study depicts a significant preference for summaries generated by GPT-4 with in-context learning compared to both Llama2-13B fine-tuned summaries and the original summaries, highlighting the need for qualitative clinical evaluation.
Authors: Kyla H. Levin, Nicolas van Kempen, Emery D. Berger, Stephen N. Freund
Abstract: Debugging is a critical but challenging task for programmers. This paper proposes ChatDBG, an AI-powered debugging assistant. ChatDBG integrates large language models (LLMs) to significantly enhance the capabilities and user-friendliness of conventional debuggers. ChatDBG lets programmers engage in a collaborative dialogue with the debugger, allowing them to pose complex questions about program state, perform root cause analysis for crashes or assertion failures, and explore open-ended queries like "why is x null?". To handle these queries, ChatDBG grants the LLM autonomy to "take the wheel": it can act as an independent agent capable of querying and controlling the debugger to navigate through stacks and inspect program state. It then reports its findings and yields back control to the programmer. By leveraging the real-world knowledge embedded in LLMs, ChatDBG can diagnose issues identifiable only through the use of domain-specific reasoning. Our ChatDBG prototype integrates with standard debuggers including LLDB and GDB for native code and Pdb for Python. Our evaluation across a diverse set of code, including C/C++ code with known bugs and a suite of Python code including standalone scripts and Jupyter notebooks, demonstrates that ChatDBG can successfully analyze root causes, explain bugs, and generate accurate fixes for a wide range of real-world errors. For the Python programs, a single query led to an actionable bug fix 67% of the time; one additional follow-up query increased the success rate to 85%. ChatDBG has seen rapid uptake; it has already been downloaded more than 75,000 times.
Authors: Pranav Gokhale, Caitlin Carnahan, William Clark, Teague Tomesh, Frederic T. Chong
Abstract: Recent work has shown the promise of applying deep learning to enhance software processing of radio frequency (RF) signals. In parallel, hardware developments with quantum RF sensors based on Rydberg atoms are breaking longstanding barriers in frequency range, resolution, and sensitivity. In this paper, we describe our implementations of quantum-ready machine learning approaches for RF signal classification. Our primary objective is latency: while deep learning offers a more powerful computational paradigm, it also traditionally incurs latency overheads that hinder wider scale deployment. Our work spans three axes. (1) A novel continuous wavelet transform (CWT) based recurrent neural network (RNN) architecture that enables flexible online classification of RF signals on-the-fly with reduced sampling time. (2) Low-latency inference techniques for both GPU and CPU that span over 100x reductions in inference time, enabling real-time operation with sub-millisecond inference. (3) Quantum-readiness validated through application of our models to physics-based simulation of Rydberg atom QRF sensors. Altogether, our work bridges towards next-generation RF sensors that use quantum technology to surpass previous physical limits, paired with latency-optimized AI/ML software that is suitable for real-time deployment.
Authors: Jin Ma, Gaozhan Wang, Jianfeng Zhang
Abstract: In this paper we investigate the convergence of the Policy Iteration Algorithm (PIA) for a class of general continuous-time entropy-regularized stochastic control problems. In particular, instead of employing sophisticated PDE estimates for the iterative PDEs involved in the algorithm (see, e.g., Huang-Wang-Zhou(2025)), we shall provide a simple proof from scratch for the convergence of the PIA. Our approach builds on probabilistic representation formulae for solutions of PDEs and their derivatives. Moreover, in the finite horizon model and in the infinite horizon model with large discount factor, the similar arguments lead to a super-exponential rate of convergence without tear. Finally, with some extra efforts we show that our approach can be extended to the diffusion control case in the one dimensional setting, also with a super-exponential rate of convergence.
Authors: Yanis Labrak, Markus Frohmann, Gabriel Meseguer-Brocal, Elena V. Epure
Abstract: In recent years, the use of large language models (LLMs) to generate music content, particularly lyrics, has gained in popularity. These advances provide valuable tools for artists and enhance their creative processes, but they also raise concerns about copyright violations, consumer satisfaction, and content spamming. Previous research has explored content detection in various domains. However, no work has focused on the text modality, lyrics, in music. To address this gap, we curated a diverse dataset of real and synthetic lyrics from multiple languages, music genres, and artists. The generation pipeline was validated using both humans and automated methods. We performed a thorough evaluation of existing synthetic text detection approaches on lyrics, a previously unexplored data type. We also investigated methods to adapt the best-performing features to lyrics through unsupervised domain adaptation. Following both music and industrial constraints, we examined how well these approaches generalize across languages, scale with data availability, handle multilingual language content, and perform on novel genres in few-shot settings. Our findings show promising results that could inform policy decisions around AI-generated music and enhance transparency for users.
Authors: Ricardo Dominguez-Olmedo, Vedant Nanda, Rediet Abebe, Stefan Bechtold, Christoph Engel, Jens Frankenreiter, Krishna Gummadi, Moritz Hardt, Michael Livermore
Abstract: Annotation and classification of legal text are central components of empirical legal research. Traditionally, these tasks are often delegated to trained research assistants. Motivated by the advances in language modeling, empirical legal scholars are increasingly turning to prompting commercial models, hoping that it will alleviate the significant cost of human annotation. Despite growing use, our understanding of how to best utilize large language models for legal annotation remains limited. To bridge this gap, we introduce CaselawQA, a benchmark comprising 260 legal annotation tasks, nearly all new to the machine learning community. We demonstrate that commercial models, such as GPT-4.5 and Claude 3.7 Sonnet, achieve non-trivial yet highly variable accuracy, generally falling short of the performance required for legal work. We then demonstrate that small, lightly fine-tuned models outperform commercial models. A few hundred to a thousand labeled examples are usually enough to achieve higher accuracy. Our work points to a viable alternative to the predominant practice of prompting commercial models. For concrete legal annotation tasks with some available labeled data, researchers are likely better off using a fine-tuned open-source model.
Authors: Alex N. Wang, Christopher Hoang, Yuwen Xiong, Yann LeCun, Mengye Ren
Abstract: Self-supervised learning has driven significant progress in learning from single-subject, iconic images. However, there are still unanswered questions about the use of minimally-curated, naturalistic video data, which contain dense scenes with many independent objects, imbalanced class distributions, and varying object sizes. In this paper, we propose PooDLe, a self-supervised learning method that combines an invariance-based objective on pooled representations with a dense SSL objective that enforces equivariance to optical flow warping. Our results show that a unified objective applied at multiple feature scales is essential for learning effective image representations from naturalistic videos. We validate our method with experiments on the BDD100K driving video dataset and the Walking Tours first-person video dataset, demonstrating its ability to capture spatial understanding from a dense objective and semantic understanding via a pooled representation objective.
Authors: Niklas Risse, Jing Liu, Marcel B\"ohme
Abstract: According to our survey of machine learning for vulnerability detection (ML4VD), 9 in every 10 papers published in the past five years define ML4VD as a function-level binary classification problem: Given a function, does it contain a security flaw? From our experience as security researchers, faced with deciding whether a given function makes the program vulnerable to attacks, we would often first want to understand the context in which this function is called. In this paper, we study how often this decision can really be made without further context and study both vulnerable and non-vulnerable functions in the most popular ML4VD datasets. We call a function "vulnerable" if it was involved in a patch of an actual security flaw and confirmed to cause the program's vulnerability. It is "non-vulnerable" otherwise. We find that in almost all cases this decision cannot be made without further context. Vulnerable functions are often vulnerable only because a corresponding vulnerability-inducing calling context exists while non-vulnerable functions would often be vulnerable if a corresponding context existed. But why do ML4VD techniques achieve high scores even though there is demonstrably not enough information in these samples? Spurious correlations: We find that high scores can be achieved even when only word counts are available. This shows that these datasets can be exploited to achieve high scores without actually detecting any security vulnerabilities. We conclude that the prevailing problem statement of ML4VD is ill-defined and call into question the internal validity of this growing body of work. Constructively, we call for more effective benchmarking methodologies to evaluate the true capabilities of ML4VD, propose alternative problem statements, and examine broader implications for the evaluation of machine learning and programming analysis research.
Authors: Yetao Wu, Yihong Wang, Teng Chen, Ningyuan Xi, Qingqing Gu, Hongyang Lei, Luo Ji
Abstract: Hallucination is a major challenge for large language models (LLMs), prevent ing their further application in some fields. The skeptical thinking of humankind could be useful for LLMs to self-cognition, self-reflection and alleviate their hal lucinations. Inspired by this consideration, we propose a novel approach called LaMsS, which combines the semantic understanding capability of LLMs with self-skepticism. By introducing a series of skepticism tokens and augmenting them into the vocabulary, we conduct both pertaining and finetuning, which allow the LLM to decode each normal token followed by a skeptical token, represent ing different skepticism levels. By calculating the response skepticism given a query, one can define a new self-aware LLM which is only willing to answer with relative lower skepticism level than the threshold. By examining the accu racy, AUC and AP of willingly answering questions, we demonstrate that LaMsS achieves better performance than baselines on both multi-choice questions and open-domain question-answering benchmarks, and can generalize to multi-task and out-of-domain settings. Our study sheds some lights on the self-skepticism modeling on further artificial intelligence. Project code and model checkpoints can be found in https://anonymous.4open.science/r/SM-1E76.
Authors: Tongfe Guo, Taposh Banerjee, Rui Liu, Lili Su
Abstract: Accurate trajectory prediction is essential for the safe operation of autonomous vehicles in real-world environments. Even well-trained machine learning models may produce unreliable predictions due to discrepancies between training data and real-world conditions encountered during inference. In particular, the training dataset tends to overrepresent common scenes (e.g., straight lanes) while underrepresenting less frequent ones (e.g., traffic circles). In addition, it often overlooks unpredictable real-world events such as sudden braking or falling objects. To ensure safety, it is critical to detect in real-time when a model's predictions become unreliable. Leveraging the intuition that in-distribution (ID) scenes exhibit error patterns similar to training data, while out-of-distribution (OOD) scenes do not, we introduce a principled, real-time approach for OOD detection by framing it as a change-point detection problem. We address the challenging settings where the OOD scenes are deceptive, meaning that they are not easily detectable by human intuitions. Our lightweight solutions can handle the occurrence of OOD at any time during trajectory prediction inference. Experimental results on multiple real-world datasets using a benchmark trajectory prediction model demonstrate the effectiveness of our methods.
Authors: Kuo-Han Hung, Ching-Yun Ko, Ambrish Rawat, I-Hsin Chung, Winston H. Hsu, Pin-Yu Chen
Abstract: Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks, where malicious inputs manipulate the model into ignoring original instructions and executing designated action. In this paper, we investigate the underlying mechanisms of these attacks by analyzing the attention patterns within LLMs. We introduce the concept of the distraction effect, where specific attention heads, termed important heads, shift focus from the original instruction to the injected instruction. Building on this discovery, we propose Attention Tracker, a training-free detection method that tracks attention patterns on instruction to detect prompt injection attacks without the need for additional LLM inference. Our method generalizes effectively across diverse models, datasets, and attack types, showing an AUROC improvement of up to 10.0% over existing methods, and performs well even on small LLMs. We demonstrate the robustness of our approach through extensive evaluations and provide insights into safeguarding LLM-integrated systems from prompt injection vulnerabilities.
Authors: Leandro Von Krannichfeldt, Kristina Orehounig, Olga Fink
Abstract: Building energy modeling plays a vital role in optimizing the operation of building energy systems by providing accurate predictions of the building's real-world conditions. In this context, various techniques have been explored, ranging from traditional physics-based models to data-driven models. Recently, researchers are combining physics-based and data-driven models into hybrid approaches. This includes using the physics-based model output as additional data-driven input, learning the residual between physics-based model and real data, learning a surrogate of the physics-based model, or fine-tuning a surrogate model with real data. However, a comprehensive comparison of the inherent advantages of these hybrid approaches is still missing. The primary objective of this work is to evaluate four predominant hybrid approaches in building energy modeling through a real-world case study, with focus on indoor thermodynamics. To achieve this, we devise three scenarios reflecting common levels of building documentation and sensor availability, assess their performance, and analyze their explainability using hierarchical Shapley values. The real-world study reveals three notable findings. First, greater building documentation and sensor availability lead to higher prediction accuracy for hybrid approaches. Second, the performance of hybrid approaches depends on the type of building room, but the residual approach using a Feedforward Neural Network as data-driven sub-model performs best on average across all rooms. This hybrid approach also demonstrates a superior ability to leverage the simulation from the physics-based sub-model. Third, hierarchical Shapley values prove to be an effective tool for explaining and improving hybrid models while accounting for input correlations.
Authors: Laura Cabello, Carmen Martin-Turrero, Uchenna Akujuobi, Anders S{\o}gaard, Carlos Bobed
Abstract: Question answering is a natural language understanding task that involves reasoning over both explicit context, and unstated relevant domain knowledge. Despite the high cost of training, large language models (LLMs) -- the backbone of most modern question-answering systems -- still struggle to reliably capture the nuanced relationships between concepts that are crucial for reasoning in specialized fields like medicine. In this work, we present MEG, a parameter-efficient approach for medical knowledge-augmented LLMs. MEG uses a lightweight mapping network to incorporate knowledge graph embeddings into the LLM, enabling it to leverage external knowledge in a cost-effective way. We evaluate our method on four popular medical multiple-choice datasets and show that LLMs i) can effectively interpret knowledge graph embeddings and ii) gain significant advantages from the factual grounding these embeddings provide. MEG attains an average of +6.7% and +9.9% accuracy over specialized models like BioMistral-7B and MediTron-7B, respectively. Finally, we show that MEG's performance remains robust to the choice of graph encoder.
Authors: Santhosh Malarvannan, Pandiyaraju V, Shravan Venkatraman, Abeshek A, Priyadarshini B, Kannan A
Abstract: Diabetic retinopathy is a leading cause of blindness around the world and demands precise AI-based diagnostic tools. Traditional loss functions in multi-class classification, such as Categorical Cross-Entropy (CCE), are very common but break down with class imbalance, especially in cases with inherently challenging or overlapping classes, which leads to biased and less sensitive models. Since a heavy imbalance exists in the number of examples for higher severity stage 4 diabetic retinopathy, etc., classes compared to those very early stages like class 0, achieving class balance is key. For this purpose, we propose the Adaptive Hybrid Focal-Entropy Loss which combines the ideas of focal loss and entropy loss with adaptive weighting in order to focus on minority classes and highlight the challenging samples. The state-of-the art models applied for diabetic retinopathy detection with AHFE revealed good performance improvements, indicating the top performances of ResNet50 at 99.79%, DenseNet121 at 98.86%, Xception at 98.92%, MobileNetV2 at 97.84%, and InceptionV3 at 93.62% accuracy. This sheds light into how AHFE promotes enhancement in AI-driven diagnostics for complex and imbalanced medical datasets.
Authors: Ashesh Rambachan, Rahul Singh, Davide Viviano
Abstract: Economists often estimate treatment effects in experiments using remotely sensed variables (RSVs), e.g. satellite images or mobile phone activity, in place of directly measured economic outcomes. A common practice is to use an observational sample to train a predictor of the economic outcome from the RSV, and then to use its predictions as the outcomes in the experiment. We show that this method is biased whenever the RSV is post-outcome, i.e. if variation in the economic outcome causes variation in the RSV. In program evaluation, changes in poverty or environmental quality cause changes in satellite images, but not vice versa. As our main result, we nonparametrically identify the treatment effect by formalizing the intuition that underlies common practice: the conditional distribution of the RSV given the outcome and treatment is stable across the samples.Based on our identifying formula, we find that the efficient representation of RSVs for causal inference requires three predictions rather than one. Valid inference does not require any rate conditions on RSV predictions, justifying the use of complex deep learning algorithms with unknown statistical properties. We re-analyze the effect of an anti-poverty program in India using satellite images.
Authors: Christel Grimaud (IRIT-LILaC), Dominique Longin (IRIT-LILaC), Andreas Herzig (IRIT-LILaC)
Abstract: We present the architecture of a fully autonomous, bio-inspired cognitive agent built around a spiking neural network (SNN) implementing the agent's semantic memory. This agent explores its universe and learns concepts of objects/situations and of its own actions in a one-shot manner. While object/situation concepts are unary, action concepts are triples made up of an initial situation, a motor activity, and an outcome. They embody the agent's knowledge of its universe's action laws. Both kinds of concepts have different degrees of generality. To make decisions the agent queries its semantic memory for the expected outcomes of envisaged actions and chooses the action to take on the basis of these predictions. Our experiments show that the agent handles new situations by appealing to previously learned general concepts and rapidly modifies its concepts to adapt to environment changes.
Authors: Asad Aali, Marius Arvinte, Sidharth Kumar, Yamin I. Arefeen, Jonathan I. Tamir
Abstract: We study the effect of incorporating self-supervised denoising as a pre-processing step for training deep learning (DL) based reconstruction methods on data corrupted by Gaussian noise. K-space data employed for training are typically multi-coil and inherently noisy. Although DL-based reconstruction methods trained on fully sampled data can enable high reconstruction quality, obtaining large, noise-free datasets is impractical. We leverage Generalized Stein's Unbiased Risk Estimate (GSURE) for denoising. We evaluate two DL-based reconstruction methods: Diffusion Probabilistic Models (DPMs) and Model-Based Deep Learning (MoDL). We evaluate the impact of denoising on the performance of these DL-based methods in solving accelerated multi-coil magnetic resonance imaging (MRI) reconstruction. The experiments were carried out on T2-weighted brain and fat-suppressed proton-density knee scans. We observed that self-supervised denoising enhances the quality and efficiency of MRI reconstructions across various scenarios. Specifically, employing denoised images rather than noisy counterparts when training DL networks results in lower normalized root mean squared error (NRMSE), higher structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) across different SNR levels, including 32dB, 22dB, and 12dB for T2-weighted brain data, and 24dB, 14dB, and 4dB for fat-suppressed knee data. Overall, we showed that denoising is an essential pre-processing technique capable of improving the efficacy of DL-based MRI reconstruction methods under diverse conditions. By refining the quality of input data, denoising enables training more effective DL networks, potentially bypassing the need for noise-free reference MRI scans.
Authors: Pu Zhao, Xuan Shen, Zhenglun Kong, Yixin Shen, Sung-En Chang, Timothy Rupprecht, Lei Lu, Enfu Nan, Changdi Yang, Yumei He, Weiyan Shi, Xingchen Xu, Yu Huang, Wei Jiang, Wei Wang, Yue Chen, Yong He, Yanzhi Wang
Abstract: Recently, Large Language Models (LLMs) have undergone a significant transformation, marked by a rapid rise in both their popularity and capabilities. Leading this evolution are proprietary LLMs like GPT-4 and GPT-o1, which have captured widespread attention in the AI community due to their remarkable performance and versatility. Simultaneously, open-source LLMs, such as LLaMA, have made great contributions to the ever-increasing popularity of LLMs due to the ease to customize and deploy the models across diverse applications. Although open-source LLMs present unprecedented opportunities for innovation and research, the commercialization of LLMs has raised concerns about transparency, reproducibility, and safety. Many open-source LLMs fail to meet fundamental transparency requirements by withholding essential components like training code and data, which may hinder further innovations on LLMs. To mitigate this issue, we introduce Moxin 7B, a fully open-source LLM developed, adhering to principles of open science, open source, open data, and open access. We release the pre-training code and configurations, training and fine-tuning datasets, and intermediate and final checkpoints, aiming to make continuous commitments to fully open-source LLMs. After pre-training and obtaining the base model, we finetune the Moxin Base model with SOTA post-training framework and instruction data to obtain Moxin Instruct model. To improve the reasoning capability, we further finetune our Instruct model with chain-of-thought data distilled from DeepSeek R1, and then use Group Relative Policy Optimization (GRPO), an efficient and effective reinforcement learning algorithm following DeepSeek R1, to finetune our model, leading to the Moxin Reasoning model. Experiments show that our models achieve superior performance in various evaluations such as zero-shot evaluation, few-shot evaluation, and CoT evaluation.
Authors: Baocai Yin, Ji Zhao, Huajie Jiang, Ningning Hou, Yongli Hu, Amin Beheshti, Ming-Hsuan Yang, Yuankai Qi
Abstract: Continual learning (CL) enables models to adapt to evolving data streams. A major challenge of CL is catastrophic forgetting, where new knowledge will overwrite previously acquired knowledge. Traditional methods usually retain the past data for replay or add additional branches in the model to learn new knowledge, which has high memory requirements. In this paper, we propose a novel lightweight CL framework, Adapter-Enhanced Semantic Prompting (AESP), which integrates prompt tuning and adapter techniques. Specifically, we design semantic-guided prompts to enhance the generalization ability of visual features and utilize adapters to efficiently fuse the semantic information, aiming to learn more adaptive features for the continual learning task. Furthermore, to choose the right task prompt for feature adaptation, we have developed a novel matching mechanism for prompt selection. Extensive experiments on three CL datasets demonstrate that our approach achieves favorable performance across multiple metrics, showing its potential for advancing CL.
Authors: Tri Kurniawan Wijaya, Edoardo D'Amico, Xinyang Shao
Abstract: Recommender systems have become a cornerstone of personalized user experiences, yet their development typically involves significant manual intervention, including dataset-specific feature engineering, hyperparameter tuning, and configuration. To this end, we introduce a novel paradigm: Dataset-Agnostic Recommender Systems (DAReS) that aims to enable a single codebase to autonomously adapt to various datasets without the need for fine-tuning, for a given recommender system task. Central to this approach is the Dataset Description Language (DsDL), a structured format that provides metadata about the dataset's features and labels, and allow the system to understand dataset's characteristics, allowing it to autonomously manage processes like feature selection, missing values imputation, noise removal, and hyperparameter optimization. By reducing the need for domain-specific expertise and manual adjustments, DAReS offers a more efficient and scalable solution for building recommender systems across diverse application domains. It addresses critical challenges in the field, such as reusability, reproducibility, and accessibility for non-expert users or entry-level researchers.
Authors: Chenhao Li, Andreas Krause, Marco Hutter
Abstract: Learning robust and generalizable world models is crucial for enabling efficient and scalable robotic control in real-world environments. In this work, we introduce a novel framework for learning world models that accurately capture complex, partially observable, and stochastic dynamics. The proposed method employs a dual-autoregressive mechanism and self-supervised training to achieve reliable long-horizon predictions without relying on domain-specific inductive biases, ensuring adaptability across diverse robotic tasks. We further propose a policy optimization framework that leverages world models for efficient training in imagined environments and seamless deployment in real-world systems. This work advances model-based reinforcement learning by addressing the challenges of long-horizon prediction, error accumulation, and sim-to-real transfer. By providing a scalable and robust framework, the introduced methods pave the way for adaptive and efficient robotic systems in real-world applications.
Authors: Yun-Peng Li, Hans-Andrea Loeliger
Abstract: Normals with unknown parameters (NUP) can be used to convert nontrivial model-based estimation problems into iterations of linear least-squares or Gaussian estimation problems. In this paper, we extend this approach by augmenting factor graphs with convex-dual variables and pertinent NUP representations. In particular, in a state space setting, we propose a new iterative forward-backward algorithm that is dual to a recently proposed backward-forward algorithm.
Authors: Stephan Naunheim, Luis Lopes de Paiva, Vanessa Nadig, Yannick Kuhl, Stefan Gundacker, Florian Mueller, Volkmar Schulz
Abstract: PET is a functional imaging method that visualizes metabolic processes. TOF information can be derived from coincident detector signals and incorporated into image reconstruction to enhance the SNR. PET detectors are typically assessed by their CTR, but timing performance is degraded by various factors. Research on timing calibration seeks to mitigate these degradations and restore accurate timing information. While many calibration methods use analytical approaches, machine learning techniques have recently gained attention due to their flexibility. We developed a residual physics-based calibration approach that combines prior domain knowledge with the power of machine learning models. This approach begins with an initial analytical calibration addressing first-order skews. The remaining deviations, regarded as residual effects, are used to train machine learning models to eliminate higher-order skews. The key advantage is that the experimenter guides the learning process through the definition of timing residuals. In earlier studies, we developed models that directly predicted the expected time difference, which offered corrections only implicitly (implicit correction models). In this study, we introduce a new definition for timing residuals, enabling us to train models that directly predict correction values (explicit correction models). The explicit correction approach significantly simplifies data acquisition, improves linearity, and enhances timing performance from $371 \pm 6$ ps to $281 \pm 5$ ps for coincidences from 430 keV to 590 keV. Additionally, the new definition reduces model size, making it suitable for high-throughput applications like PET scanners. Experiments were conducted using two detector stacks composed of $4 \times 4$ LYSO:Ce,Ca crystals ($3.8\times 3.8\times 20$ mm$^{3}$) coupled to $4 \times 4$ Broadcom NUV-MT SiPMs and digitized with the TOFPET2 ASIC.
Authors: Nektarios A. Valous, Eckhard Hitzer, Drago\c{s} Du\c{s}e, Rodrigo Rojas Moraleda, Ferdinand Popp, Meggy Suarez-Carmona, Anna Berthel, Ismini Papageorgiou, Carlo Fremd, Alexander R\"olle, Christina C. Westhoff, B\'en\'edicte Lenoir, Niels Halama, Inka Z\"ornig, Dirk J\"ager
Abstract: Hypercomplex image processing extends conventional techniques in a unified paradigm encompassing algebraic and geometric principles. This work leverages quaternions and the two-dimensional orthogonal planes split framework (splitting of a quaternion - representing a pixel - into pairs of orthogonal 2D planes) for natural/biomedical image analysis through the following computational workflows and outcomes: natural/biomedical image re-colorization, natural image de-colorization, natural/biomedical image contrast enhancement, computational re-staining and stain separation in histological images, and performance gains in machine/deep learning pipelines for histological images. The workflows are analyzed separately for natural and biomedical images to showcase the effectiveness of the proposed approaches. The proposed workflows can regulate color appearance (e.g. with alternative renditions and grayscale conversion) and image contrast, be part of automated image processing pipelines (e.g. isolating stain components, boosting learning models), and assist in digital pathology applications (e.g. enhancing biomarker visibility, enabling colorblind-friendly renditions). Employing only basic arithmetic and matrix operations, this work offers a computationally accessible methodology - in the hypercomplex domain - that showcases versatility and consistency across image processing tasks and a range of computer vision and biomedical applications. The proposed non-data-driven methods achieve comparable or better results (particularly in cases involving well-known methods) to those reported in the literature, showcasing the potential of robust theoretical frameworks with practical effectiveness. Results, methods, and limitations are detailed alongside discussion of promising extensions, emphasizing the potential of feature-rich mathematical/computational frameworks for natural and biomedical images.
Authors: Xiang Fu, Brandon M. Wood, Luis Barroso-Luque, Daniel S. Levine, Meng Gao, Misko Dzamba, C. Lawrence Zitnick
Abstract: Machine learning interatomic potentials (MLIPs) have become increasingly effective at approximating quantum mechanical calculations at a fraction of the computational cost. However, lower errors on held out test sets do not always translate to improved results on downstream physical property prediction tasks. In this paper, we propose testing MLIPs on their practical ability to conserve energy during molecular dynamic simulations. If passed, improved correlations are found between test errors and their performance on physical property prediction tasks. We identify choices which may lead to models failing this test, and use these observations to improve upon highly-expressive models. The resulting model, eSEN, provides state-of-the-art results on a range of physical property prediction tasks, including materials stability prediction, thermal conductivity prediction, and phonon calculations.
Authors: Priyaranjan Pattnayak, Hitesh Laxmichand Patel, Amit Agarwal, Bhargava Kumar, Srikant Panda, Tejaswini Kumar
Abstract: Clinical Question Answering (CQA) plays a crucial role in medical decision-making, enabling physicians to extract relevant information from Electronic Medical Records (EMRs). While transformer-based models such as BERT, BioBERT, and ClinicalBERT have demonstrated state-of-the-art performance in CQA, existing models lack the ability to categorize extracted answers, which is critical for structured retrieval, content filtering, and medical decision support. To address this limitation, we introduce a Multi-Task Learning (MTL) framework that jointly trains CQA models for both answer extraction and medical categorization. In addition to predicting answer spans, our model classifies responses into five standardized medical categories: Diagnosis, Medication, Symptoms, Procedure, and Lab Reports. This categorization enables more structured and interpretable outputs, making clinical QA models more useful in real-world healthcare settings. We evaluate our approach on emrQA, a large-scale dataset for medical question answering. Results show that MTL improves F1-score by 2.2% compared to standard fine-tuning, while achieving 90.7% accuracy in answer categorization. These findings suggest that MTL not only enhances CQA performance but also introduces an effective mechanism for categorization and structured medical information retrieval.
Authors: Han Xue, Jieji Ren, Wendi Chen, Gu Zhang, Yuan Fang, Guoying Gu, Huazhe Xu, Cewu Lu
Abstract: Humans can accomplish complex contact-rich tasks using vision and touch, with highly reactive capabilities such as fast response to external changes and adaptive control of contact forces; however, this remains challenging for robots. Existing visual imitation learning (IL) approaches rely on action chunking to model complex behaviors, which lacks the ability to respond instantly to real-time tactile feedback during the chunk execution. Furthermore, most teleoperation systems struggle to provide fine-grained tactile / force feedback, which limits the range of tasks that can be performed. To address these challenges, we introduce TactAR, a low-cost teleoperation system that provides real-time tactile feedback through Augmented Reality (AR), along with Reactive Diffusion Policy (RDP), a novel slow-fast visual-tactile imitation learning algorithm for learning contact-rich manipulation skills. RDP employs a two-level hierarchy: (1) a slow latent diffusion policy for predicting high-level action chunks in latent space at low frequency, (2) a fast asymmetric tokenizer for closed-loop tactile feedback control at high frequency. This design enables both complex trajectory modeling and quick reactive behavior within a unified framework. Through extensive evaluation across three challenging contact-rich tasks, RDP significantly improves performance compared to state-of-the-art visual IL baselines. Furthermore, experiments show that RDP is applicable across different tactile / force sensors. Code and videos are available on https://reactive-diffusion-policy.github.io.
Authors: Zeyue Tian, Yizhu Jin, Zhaoyang Liu, Ruibin Yuan, Xu Tan, Qifeng Chen, Wei Xue, Yike Guo
Abstract: Audio and music generation have emerged as crucial tasks in many applications, yet existing approaches face significant limitations: they operate in isolation without unified capabilities across modalities, suffer from scarce high-quality, multi-modal training data, and struggle to effectively integrate diverse inputs. In this work, we propose AudioX, a unified Diffusion Transformer model for Anything-to-Audio and Music Generation. Unlike previous domain-specific models, AudioX can generate both general audio and music with high quality, while offering flexible natural language control and seamless processing of various modalities including text, video, image, music, and audio. Its key innovation is a multi-modal masked training strategy that masks inputs across modalities and forces the model to learn from masked inputs, yielding robust and unified cross-modal representations. To address data scarcity, we curate two comprehensive datasets: vggsound-caps with 190K audio captions based on the VGGSound dataset, and V2M-caps with 6 million music captions derived from the V2M dataset. Extensive experiments demonstrate that AudioX not only matches or outperforms state-of-the-art specialized models, but also offers remarkable versatility in handling diverse input modalities and generation tasks within a unified architecture. The code and datasets will be available at https://zeyuet.github.io/AudioX/
Authors: Runzhi Wang, Prianka Sengupta, Cristhian Roman-Vicharra, Yiran Chen, Jiang Hu
Abstract: In chip design planning, obtaining reliable performance and power forecasts for various design options is of critical importance. Traditionally, this involves using system-level models, which often lack accuracy, or trial synthesis, which is both labor-intensive and time-consuming. We introduce a new methodology, called Lorecast, which accepts English prompts as input to rapidly generate layout-aware performance and power estimates. This approach bypasses the need for HDL code development and synthesis, making it both fast and user-friendly. Experimental results demonstrate that Lorecast achieves accuracy within a few percent of error compared to post-layout analysis, while significantly reducing turnaround time.
Authors: Rory Clements, James Ellis, Geoff Hassall, Simon Horsley, Gavin Tabor
Abstract: In this paper, we introduce a formulation of Physics-Informed Neural Networks (PINNs), based on learning the form of the Fourier decomposition, and a training methodology based on a spread of randomly chosen boundary conditions. By training in this way we produce a PINN that generalises; after training it can be used to correctly predict the solution for an arbitrary set of boundary conditions and interpolate this solution between the samples that spanned the training domain. We demonstrate for a toy system of two coupled oscillators that this gives the PINN formulation genuine predictive capability owing to an effective reduction of the training to evaluation times ratio due to this decoupling of the solution from specific boundary conditions.
Authors: Yiling He, Hongyu She, Xingzhi Qian, Xinran Zheng, Zhuo Chen, Zhan Qin, Lorenzo Cavallaro
Abstract: Large Language Models (LLMs) have demonstrated strong capabilities in various code intelligence tasks. However, their effectiveness for Android malware analysis remains underexplored. Decompiled Android malware code presents unique challenges for analysis, due to the malicious logic being buried within a large number of functions and the frequent lack of meaningful function names. This paper presents CAMA, a benchmarking framework designed to systematically evaluate the effectiveness of Code LLMs in Android malware analysis. CAMA specifies structured model outputs to support key malware analysis tasks, including malicious function identification and malware purpose summarization. Built on these, it integrates three domain-specific evaluation metrics (consistency, fidelity, and semantic relevance), enabling rigorous stability and effectiveness assessment and cross-model comparison. We construct a benchmark dataset of 118 Android malware samples from 13 families collected in recent years, encompassing over 7.5 million distinct functions, and use CAMA to evaluate four popular open-source Code LLMs. Our experiments provide insights into how Code LLMs interpret decompiled code and quantify the sensitivity to function renaming, highlighting both their potential and current limitations in malware analysis.
Authors: Ruidong Zhu, Ziheng Jiang, Chao Jin, Peng Wu, Cesar A. Stuardo, Dongyang Wang, Xinlei Zhang, Huaping Zhou, Haoran Wei, Yang Cheng, Jianzhe Xiao, Xinyi Zhang, Lingjun Liu, Haibin Lin, Li-Wen Chang, Jianxi Ye, Xiao Yu, Xuanzhe Liu, Xin Jin, Xin Liu
Abstract: Mixture-of-Experts (MoE) showcases tremendous potential to scale large language models (LLMs) with enhanced performance and reduced computational complexity. However, its sparsely activated architecture shifts feed-forward networks (FFNs) from being compute-intensive to memory-intensive during inference, leading to substantially lower GPU utilization and increased operational costs. We present MegaScale-Infer, an efficient and cost-effective system for serving large-scale MoE models. MegaScale-Infer disaggregates attention and FFN modules within each model layer, enabling independent scaling, tailored parallelism strategies, and heterogeneous deployment for both modules. To fully exploit disaggregation in the presence of MoE's sparsity, MegaScale-Infer introduces ping-pong pipeline parallelism, which partitions a request batch into micro-batches and shuttles them between attention and FFNs for inference. Combined with distinct model parallelism for each module, MegaScale-Infer effectively hides communication overhead and maximizes GPU utilization. To adapt to disaggregated attention and FFN modules and minimize data transmission overhead (e.g., token dispatch), MegaScale-Infer provides a high-performance M2N communication library that eliminates unnecessary GPU-to-CPU data copies, group initialization overhead, and GPU synchronization. Experimental results indicate that MegaScale-Infer achieves up to 1.90x higher per-GPU throughput than state-of-the-art solutions.
Authors: Haoyu Ji, Yalan Song, Tadd Bindas, Chaopeng Shen, Yuan Yang, Ming Pan, Jiangtao Liu, Farshid Rahmani, Ather Abbas, Hylke Beck, Kathryn Lawson, Yoshihide Wada
Abstract: To track rapid changes within our water sector, Global Water Models (GWMs) need to realistically represent hydrologic systems' response patterns - such as baseflow fraction - but are hindered by their limited ability to learn from data. Here we introduce a high-resolution physics-embedded big-data-trained model as a breakthrough in reliably capturing characteristic hydrologic response patterns ('signatures') and their shifts. By realistically representing the long-term water balance, the model revealed widespread shifts - up to ~20% over 20 years - in fundamental green-blue-water partitioning and baseflow ratios worldwide. Shifts in these response patterns, previously considered static, contributed to increasing flood risks in northern mid-latitudes, heightening water supply stresses in southern subtropical regions, and declining freshwater inputs to many European estuaries, all with ecological implications. With more accurate simulations at monthly and daily scales than current operational systems, this next-generation model resolves large, nonlinear seasonal runoff responses to rainfall ('elasticity') and streamflow flashiness in semi-arid and arid regions. These metrics highlight regions with management challenges due to large water supply variability and high climate sensitivity, but also provide tools to forecast seasonal water availability. This capability newly enables global-scale models to deliver reliable and locally relevant insights for water management.
Authors: Sara Sippola, Siiri Rautio, Andreas Hauptmann, Takanori Ide, Samuli Siltanen
Abstract: Electrical impedance tomography (EIT) is a non-invasive imaging method with diverse applications, including medical imaging and non-destructive testing. The inverse problem of reconstructing internal electrical conductivity from boundary measurements is nonlinear and highly ill-posed, making it difficult to solve accurately. In recent years, there has been growing interest in combining analytical methods with machine learning to solve inverse problems. In this paper, we propose a method for estimating the convex hull of inclusions from boundary measurements by combining the enclosure method proposed by Ikehata with neural networks. We demonstrate its performance using experimental data. Compared to the classical enclosure method with least squares fitting, the learned convex hull achieves superior performance on both simulated and experimental data.
Authors: Suhas BN, Dominik Mattioli, Saeed Abdullah, Rosa I. Arriaga, Chris W. Wiese, Andrew M. Sherrill
Abstract: The advancement of AI systems for mental health support is hindered by limited access to therapeutic conversation data, particularly for trauma treatment. We present Thousand Voices of Trauma, a synthetic benchmark dataset of 3,000 therapy conversations based on Prolonged Exposure therapy protocols for Post-traumatic Stress Disorder (PTSD). The dataset comprises 500 unique cases, each explored through six conversational perspectives that mirror the progression of therapy from initial anxiety to peak distress to emotional processing. We incorporated diverse demographic profiles (ages 18-80, M=49.3, 49.4% male, 44.4% female, 6.2% non-binary), 20 trauma types, and 10 trauma-related behaviors using deterministic and probabilistic generation methods. Analysis reveals realistic distributions of trauma types (witnessing violence 10.6%, bullying 10.2%) and symptoms (nightmares 23.4%, substance abuse 20.8%). Clinical experts validated the dataset's therapeutic fidelity, highlighting its emotional depth while suggesting refinements for greater authenticity. We also developed an emotional trajectory benchmark with standardized metrics for evaluating model responses. This privacy-preserving dataset addresses critical gaps in trauma-focused mental health data, offering a valuable resource for advancing both patient-facing applications and clinician training tools.
Authors: Bert de Vries, Wouter Nuijten, Thijs van de Laar, Wouter Kouw, Sepideh Adamiat, Tim Nisslbeck, Mykola Lukashchuk, Hoang Minh Huu Nguyen, Marco Hidalgo Araya, Raphael Tresor, Thijs Jenneskens, Ivana Nikoloska, Raaja Ganapathy Subramanian, Bart van Erp, Dmitry Bagaev, Albert Podusenko
Abstract: We address the problem of planning under uncertainty, where an agent must choose actions that not only achieve desired outcomes but also reduce uncertainty. Traditional methods often treat exploration and exploitation as separate objectives, lacking a unified inferential foundation. Active inference, grounded in the Free Energy Principle, provides such a foundation by minimizing Expected Free Energy (EFE), a cost function that combines utility with epistemic drives, such as ambiguity resolution and novelty seeking. However, the computational burden of EFE minimization had remained a significant obstacle to its scalability. In this paper, we show that EFE-based planning arises naturally from minimizing a variational free energy functional on a generative model augmented with preference and epistemic priors. This result reinforces theoretical consistency with the Free Energy Principle by casting planning under uncertainty itself as a form of variational inference. Our formulation yields policies that jointly support goal achievement and information gain, while incorporating a complexity term that accounts for bounded computational resources. This unifying framework connects and extends existing methods, enabling scalable, resource-aware implementations of active inference agents.
Authors: Tianliang Yao, Bo Lu, Markus Kowarschik, Yixuan Yuan, Hubin Zhao, Sebastien Ourselin, Kaspar Althoefer, Junbo Ge, Peng Qi
Abstract: Endovascular procedures have revolutionized the treatment of vascular diseases thanks to minimally invasive solutions that significantly reduce patient recovery time and enhance clinical outcomes. However, the precision and dexterity required during these procedures poses considerable challenges for interventionists. Robotic systems have emerged offering transformative solutions, addressing issues such as operator fatigue, radiation exposure, and the inherent limitations of human precision. The integration of Embodied Intelligence (EI) into these systems signifies a paradigm shift, enabling robots to navigate complex vascular networks and adapt to dynamic physiological conditions. Data-driven approaches, advanced computer vision, medical image analysis, and machine learning techniques, are at the forefront of this evolution. These methods augment procedural intelligence by facilitating real-time vessel segmentation, device tracking, and anatomical landmark detection. Reinforcement learning and imitation learning further refine navigation strategies and replicate experts' techniques. This review systematically examines the integration of EI principles into robotic technologies, in relation to endovascular procedures. We discuss recent advancements in intelligent perception and data-driven control, and their practical applications in robot-assisted endovascular procedures. By critically evaluating current limitations and emerging opportunities, this review establishes a framework for future developments, emphasizing the potential for greater autonomy and improved clinical outcomes. Emerging trends and specific areas of research, such as federated learning for medical data sharing, explainable AI for clinical decision support, and advanced human-robot collaboration paradigms, are also explored, offering insights into the future direction of this rapidly evolving field.
Authors: Lotfi Abdelkrim Mecharbat, Ibrahim Almakky, Martin Takac, Mohammad Yaqub
Abstract: Deep learning (DL) has achieved remarkable progress in the field of medical imaging. However, adapting DL models to medical tasks remains a significant challenge, primarily due to two key factors: (1) architecture selection, as different tasks necessitate specialized model designs, and (2) weight initialization, which directly impacts the convergence speed and final performance of the models. Although transfer learning from ImageNet is a widely adopted strategy, its effectiveness is constrained by the substantial differences between natural and medical images. To address these challenges, we introduce Medical Neural Network Search (MedNNS), the first Neural Network Search framework for medical imaging applications. MedNNS jointly optimizes architecture selection and weight initialization by constructing a meta-space that encodes datasets and models based on how well they perform together. We build this space using a Supernetwork-based approach, expanding the model zoo size by 51x times over previous state-of-the-art (SOTA) methods. Moreover, we introduce rank loss and Fr\'echet Inception Distance (FID) loss into the construction of the space to capture inter-model and inter-dataset relationships, thereby achieving more accurate alignment in the meta-space. Experimental results across multiple datasets demonstrate that MedNNS significantly outperforms both ImageNet pre-trained DL models and SOTA Neural Architecture Search (NAS) methods, achieving an average accuracy improvement of 1.7% across datasets while converging substantially faster. The code and the processed meta-space is available at https://github.com/BioMedIA-MBZUAI/MedNNS.