Authors: Minjie Hong, Zirun Guo, Yan Xia, Zehan Wang, Ziang Zhang, Tao Jin, Zhou Zhao
Abstract: Multimodal Large Language Models (MLLMs) are powerful at integrating diverse data, but they often struggle with complex reasoning. While Reinforcement learning (RL) can boost reasoning in LLMs, applying it to MLLMs is tricky. Common issues include a drop in performance on general tasks and the generation of overly detailed or "overthinking" reasoning. Our work investigates how the KL penalty and overthinking affect RL training in MLLMs. We propose Asymmetric Policy Optimization (APO) to address these issues, which divides the sampled responses into positive and negative groups. For positive samples, Difficulty-Adaptive Divergence Shaping (DADS) is introduced to dynamically adjust the KL divergence weight based on their difficulty. This method prevents policy entropy from dropping sharply, improves training stability, utilizes samples better, and preserves the model's existing knowledge. For negative samples, Suboptimal Trajectory Complexity Regularization (STCR) is proposed to penalize overly long responses. This helps mitigate overthinking and encourages more concise reasoning while preserving the model's explorative capacity. We apply our method to Qwen2.5-VL-3B, creating View-R1-3B. View-R1-3B significantly enhances reasoning capabilities, showing an average 7\% gain over the base model and outperforming larger MLLMs (7-11B) on various reasoning benchmarks. Importantly, unlike other reasoning-tuned MLLMs that often degrade on general tasks, View-R1-3B maintains consistent improvement, demonstrating superior generalization. These results highlight the effectiveness and broad applicability of our DADS and STCR techniques for advancing complex multimodal reasoning in MLLMs. The code will be made available at https://github.com/Indolent-Kawhi/View-R1.
Authors: Xihong Su, Jia Lin Hau, Gersi Doko, Kishan Panaganti, Marek Petrik
Abstract: Risk-averse total-reward Markov Decision Processes (MDPs) offer a promising framework for modeling and solving undiscounted infinite-horizon objectives. Existing model-based algorithms for risk measures like the entropic risk measure (ERM) and entropic value-at-risk (EVaR) are effective in small problems, but require full access to transition probabilities. We propose a Q-learning algorithm to compute the optimal stationary policy for total-reward ERM and EVaR objectives with strong convergence and performance guarantees. The algorithm and its optimality are made possible by ERM's dynamic consistency and elicitability. Our numerical results on tabular domains demonstrate quick and reliable convergence of the proposed Q-learning algorithm to the optimal risk-averse value function.
Authors: Oron Nir, Jay Tenenbaum, Ariel Shamir
Abstract: Density-based clustering methods often surpass centroid-based counterparts, when addressing data with noise or arbitrary data distributions common in real-world problems. In this study, we reveal a key property intrinsic to density-based clustering methods regarding the relation between the number of clusters and the neighborhood radius of core points - we empirically show that it is nearly unimodal, and support this claim theoretically in a specific setting. We leverage this property to devise new strategies for finding appropriate values for the radius more efficiently based on the Ternary Search algorithm. This is especially important for large scale data that is high-dimensional, where parameter tuning is computationally intensive. We validate our methodology through extensive applications across a range of high-dimensional, large-scale NLP, Audio, and Computer Vision tasks, demonstrating its practical effectiveness and robustness. This work not only offers a significant advancement in parameter control for density-based clustering but also broadens the understanding regarding the relations between their guiding parameters. Our code is available at https://github.com/oronnir/UnimodalStrategies.
Authors: Denis Gudovskiy, Wenzhao Zheng, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer
Abstract: Recently, continuous normalizing flows (CNFs) and diffusion models (DMs) have been studied using the unified theoretical framework. Although such models can generate high-quality data points from a noise distribution, the sampling demands multiple iterations to solve an ordinary differential equation (ODE) with high computational complexity. Most existing methods focus on reducing the number of time steps during the sampling process to improve efficiency. In this work, we explore a complementary direction in which the quality-complexity tradeoff can be dynamically controlled in terms of time steps and in the length of the neural network. We achieve this by rewiring the blocks in the transformer-based architecture to solve an inner discretized ODE w.r.t. its length. Then, we employ time- and length-wise consistency terms during flow matching training, and as a result, the sampling can be performed with an arbitrary number of time steps and transformer blocks. Unlike others, our $\textrm{ODE}_t \left(\textrm{ODE}_l \right)$ approach is solver-agnostic in time dimension and decreases both latency and memory usage. Compared to the previous state of the art, image generation experiments on CelebA-HQ and ImageNet show a latency reduction of up to $3\times$ in the most efficient sampling mode, and a FID score improvement of up to $3.5$ points for high-quality sampling. We release our code and model weights with fully reproducible experiments.
Authors: Yash Akhauri, Bryan Lewandowski, Cheng-Hsi Lin, Adrian N. Reyes, Grant C. Forbes, Arissa Wongpanich, Bangding Yang, Mohamed S. Abdelfattah, Sagi Perel, Xingyou Song
Abstract: In many industries, predicting metric outcomes of large systems is a fundamental problem, driven largely by traditional tabular regression. However, such methods struggle on complex systems data in the wild such as configuration files or system logs, where feature engineering is often infeasible. We propose text-to-text regression as a general, scalable alternative. For predicting resource efficiency on Borg, Google's massive compute cluster scheduling system, a 60M parameter encoder-decoder, trained from random initialization, achieves up to a near perfect 0.99 (0.9 average) rank correlation across the entire fleet, and 100x lower MSE than tabular approaches. The model also easily adapts to new tasks in only 500 few-shot examples and captures the densities of complex outcome distributions. Ablation studies highlight the importance of using encoders, increasing sequence length, and the model's inherent uncertainty quantification. These findings pave the way for universal simulators of real-world outcomes.
Authors: Biying Zhou, Nanyu Luo, Feng Ji
Abstract: Item Response Theory (IRT) models have been widely used to estimate respondents' latent abilities and calibrate items' difficulty. Traditional IRT estimation requires all individual raw response data to be centralized in one place, thus potentially causing privacy issues. Federated learning is an emerging field in computer science and machine learning with added features of privacy protection and distributed computing. To integrate the advances from federated learning with modern psychometrics, we propose a novel framework, Federated Item Response Theory (IRT), to enable estimating traditional IRT models with additional privacy, allowing estimation in a distributed manner without losing estimation accuracy. Our numerical experiments confirm that FedIRT achieves statistical accuracy similar to standard IRT estimation using popular R packages, while offering critical advantages: privacy protection and reduced communication costs. We also validate FedIRT's utility through a real-world exam dataset, demonstrating its effectiveness in realistic educational contexts. This new framework extends IRT's applicability to distributed settings, such as multi-school assessments, without sacrificing accuracy or security. To support practical adoption, we provide an open-ource R package, FedIRT, implementing the framework for the two-parameter logistic (2PL) and partial credit models (PCM).
Authors: John Wesley Hostetter, Min Chi
Abstract: Neuro-fuzzy networks (NFNs) are transparent, symbolic, and universal function approximations that perform as well as conventional neural architectures, but their knowledge is expressed as linguistic IF-THEN rules. Despite these advantages, their systematic design process remains a challenge. Existing work will often sequentially build NFNs by inefficiently isolating parametric and structural identification, leading to a premature commitment to brittle and subpar architecture. We propose a novel application-independent approach called gradient-based neuroplastic adaptation for the concurrent optimization of NFNs' parameters and structure. By recognizing that NFNs' parameters and structure should be optimized simultaneously as they are deeply conjoined, settings previously unapproachable for NFNs are now accessible, such as the online reinforcement learning of NFNs for vision-based tasks. The effectiveness of concurrently optimizing NFNs is empirically shown as it is trained by online reinforcement learning to proficiently play challenging scenarios from a vision-based video game called DOOM.
Authors: Aditya Narendra, Dmitry Makarov, Aleksandr Panov
Abstract: We introduce Massively Multi-Task Model-Based Policy Optimization (M3PO), a scalable model-based reinforcement learning (MBRL) framework designed to address sample inefficiency in single-task settings and poor generalization in multi-task domains. Existing model-based approaches like DreamerV3 rely on pixel-level generative models that neglect control-centric representations, while model-free methods such as PPO suffer from high sample complexity and weak exploration. M3PO integrates an implicit world model, trained to predict task outcomes without observation reconstruction, with a hybrid exploration strategy that combines model-based planning and model-free uncertainty-driven bonuses. This eliminates the bias-variance trade-off in prior methods by using discrepancies between model-based and model-free value estimates to guide exploration, while maintaining stable policy updates through a trust-region optimizer. M3PO provides an efficient and robust alternative to existing model-based policy optimization approaches and achieves state-of-the-art performance across multiple benchmarks.
Authors: Massimiliano Lupo Pasini, Jong Youl Choi, Pei Zhang, Kshitij Mehta, Rylie Weaver, Ashwin M. Aji, Karl W. Schulz, Jorda Polo, Prasanna Balaprakash
Abstract: Graph foundation models using graph neural networks promise sustainable, efficient atomistic modeling. To tackle challenges of processing multi-source, multi-fidelity data during pre-training, recent studies employ multi-task learning, in which shared message passing layers initially process input atomistic structures regardless of source, then route them to multiple decoding heads that predict data-specific outputs. This approach stabilizes pre-training and enhances a model's transferability to unexplored chemical regions. Preliminary results on approximately four million structures are encouraging, yet questions remain about generalizability to larger, more diverse datasets and scalability on supercomputers. We propose a multi-task parallelism method that distributes each head across computing resources with GPU acceleration. Implemented in the open-source HydraGNN architecture, our method was trained on over 24 million structures from five datasets and tested on the Perlmutter, Aurora, and Frontier supercomputers, demonstrating efficient scaling on all three highly heterogeneous super-computing architectures.
Authors: Peihao Wang, Zhangyang Wang
Abstract: We develop a theoretical framework that explains how discrete symbolic structures can emerge naturally from continuous neural network training dynamics. By lifting neural parameters to a measure space and modeling training as Wasserstein gradient flow, we show that under geometric constraints, such as group invariance, the parameter measure $\mu_t$ undergoes two concurrent phenomena: (1) a decoupling of the gradient flow into independent optimization trajectories over some potential functions, and (2) a progressive contraction on the degree of freedom. These potentials encode algebraic constraints relevant to the task and act as ring homomorphisms under a commutative semi-ring structure on the measure space. As training progresses, the network transitions from a high-dimensional exploration to compositional representations that comply with algebraic operations and exhibit a lower degree of freedom. We further establish data scaling laws for realizing symbolic tasks, linking representational capacity to the group invariance that facilitates symbolic solutions. This framework charts a principled foundation for understanding and designing neurosymbolic systems that integrate continuous learning with discrete algebraic reasoning.
Authors: Kunjal Panchal, Sunav Choudhary, Yuriy Brun, Hui Guan
Abstract: Forward-mode automatic differentiation (FmAD) and zero-order (ZO) optimization have been proposed as memory-efficient alternatives to backpropagation (BP) for gradient computation, especially in low-resource settings. However, their practical benefits remain unclear due to two key gaps: a lack of comparison against memory-efficient BP variants, such as activation checkpointing, and a lack of a unified theoretical analysis. This work presents a comprehensive theoretical and empirical comparison of BP, FmAD, and ZO methods. Our theoretical analysis shows that while FmAD, and ZO can reduce memory usage, they incur significant costs in accuracy, convergence speed, and computation compared to BP with checkpointing. These drawbacks worsen with larger models or constrained perturbation budgets. Empirical experiments on large language and vision-language models show that BP with checkpointing outperforms FmAD and ZO variants, including those enhanced with variance reduction, achieving up to 31.1% higher accuracy, 34.8% faster convergence, and 3.8x fewer computations at comparable memory usage. Our results highlight fundamental limitations of FmAD and ZO, and reaffirm BP with checkpointing as the most effective strategy for model training under memory-constrained settings. Our code is available at https://github.com/Astuary/The_Cost_of_Avoiding_Backpropagation.
URLs: https://github.com/Astuary/The_Cost_of_Avoiding_Backpropagation.
Authors: Jun Ohkubo
Abstract: It is sometimes difficult to achieve a complete observation for a full set of observables, and partial observations are necessary. For deterministic systems, the Mori-Zwanzig formalism provides a theoretical framework for handling partial observations. Recently, data-driven algorithms based on the Koopman operator theory have made significant progress, and there is a discussion to connect the Mori-Zwanzig formalism with the Koopman operator theory. In this work, we discuss the effects of partial observation in stochastic systems using the Koopman operator theory. The discussion clarifies the importance of distinguishing the state space and the function space in stochastic systems. Even in stochastic systems, the delay embedding technique is beneficial for partial observation, and several numerical experiments showed a power-law behavior of the accuracy for the amplitude of the additive noise. We also discuss the relation between the exponent of the power-law behavior and the effects of partial observation.
Authors: Chaofan Pan, Xin Yang, Yanhua Li, Wei Wei, Tianrui Li, Bo An, Jiye Liang
Abstract: Reinforcement Learning (RL) is an important machine learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in this field due to the rapid development of deep neural networks. However, the success of RL currently relies on extensive training data and computational resources. In addition, RL's limited ability to generalize across tasks restricts its applicability in dynamic and real-world environments. With the arisen of Continual Learning (CL), Continual Reinforcement Learning (CRL) has emerged as a promising research direction to address these limitations by enabling agents to learn continuously, adapt to new tasks, and retain previously acquired knowledge. In this survey, we provide a comprehensive examination of CRL, focusing on its core concepts, challenges, and methodologies. Firstly, we conduct a detailed review of existing works, organizing and analyzing their metrics, tasks, benchmarks, and scenario settings. Secondly, we propose a new taxonomy of CRL methods, categorizing them into four types from the perspective of knowledge storage and/or transfer. Finally, our analysis highlights the unique challenges of CRL and provides practical insights into future directions.
Authors: Amara Zuffer, Michael Burke, Mehrtash Harandi
Abstract: The diversity of tasks and dynamic nature of reinforcement learning (RL) require RL agents to be able to learn sequentially and continuously, a learning paradigm known as continuous reinforcement learning. This survey reviews how continual learning transforms RL agents into dynamic continual learners. This enables RL agents to acquire and retain useful and reusable knowledge seamlessly. The paper delves into fundamental aspects of continual reinforcement learning, exploring key concepts, significant challenges, and novel methodologies. Special emphasis is placed on recent advancements in continual reinforcement learning within robotics, along with a succinct overview of evaluation environments utilized in prominent research, facilitating accessibility for newcomers to the field. The review concludes with a discussion on limitations and promising future directions, providing valuable insights for researchers and practitioners alike.
Authors: Sheng Yun, Jianhua Pei, Ping Wang
Abstract: The evolution toward 6G networks demands a fundamental shift from bit-centric transmission to semantic-aware communication that emphasizes task-relevant information. This work introduces TOAST (Task-Oriented Adaptive Semantic Transmission), a unified framework designed to address the core challenge of multi-task optimization in dynamic wireless environments through three complementary components. First, we formulate adaptive task balancing as a Markov decision process, employing deep reinforcement learning to dynamically adjust the trade-off between image reconstruction fidelity and semantic classification accuracy based on real-time channel conditions. Second, we integrate module-specific Low-Rank Adaptation (LoRA) mechanisms throughout our Swin Transformer-based joint source-channel coding architecture, enabling parameter-efficient fine-tuning that dramatically reduces adaptation overhead while maintaining full performance across diverse channel impairments including Additive White Gaussian Noise (AWGN), fading, phase noise, and impulse interference. Third, we incorporate an Elucidating diffusion model that operates in the latent space to restore features corrupted by channel noises, providing substantial quality improvements compared to baseline approaches. Extensive experiments across multiple datasets demonstrate that TOAST achieves superior performance compared to baseline approaches, with significant improvements in both classification accuracy and reconstruction quality at low Signal-to-Noise Ratio (SNR) conditions while maintaining robust performance across all tested scenarios.
Authors: Marwan Ait Haddou, Mohamed Bennai
Abstract: We propose HQCM-EBTC, a hybrid quantum-classical model for automated brain tumor classification using MRI images. Trained on a dataset of 7,576 scans covering normal, meningioma, glioma, and pituitary classes, HQCM-EBTC integrates a 5-qubit, depth-2 quantum layer with 5 parallel circuits, optimized via AdamW and a composite loss blending cross-entropy and attention consistency. HQCM-EBTC achieves 96.48% accuracy, substantially outperforming the classical baseline (86.72%). It delivers higher precision and F1-scores, especially for glioma detection. t-SNE projections reveal enhanced feature separability in quantum space, and confusion matrices show lower misclassification. Attention map analysis (Jaccard Index) confirms more accurate and focused tumor localization at high-confidence thresholds. These results highlight the promise of quantum-enhanced models in medical imaging, advancing both diagnostic accuracy and interpretability for clinical brain tumor assessment.
Authors: Marwan Ait Haddou, Mohamed Bennai
Abstract: Variational Quantum Algorithms (VQAs) offer potential for near-term quantum advantage but face challenges from barren plateaus, where gradients vanish, and poorly conditioned optimization landscapes. We introduce GuiderNet, a meta-learning framework that conditions Parameterized Quantum Circuits (PQCs) using data-dependent parameter shifts aimed at minimizing the log condition number of the Fubini-Study metric tensor. Implemented as a classical neural network, GuiderNet is meta-trained to guide PQC parameters into geometrically favorable regions and is embedded within hybrid quantum-classical pipelines to steer both initialization and adaptive modulation during training. Applied to the Kaggle Diabetes classification task, GuiderNet reduces cumulative training loss by over 5x, improves test accuracy from 75.3% to 98.6%, and increases the minority-class F1 score from 0.67 to 0.95. It also suppresses gradient explosion and stabilizes parameter updates, enabling smoother and more robust optimization. These results demonstrate that geometric meta-conditioning can mitigate barren plateaus and ill-conditioning, providing a scalable approach to enhance trainability and generalization in quantum machine learning.
Authors: Yangyang Wan, Haotian Wang, Xuhui Yu, Jiageng Chen, Xinyu Fan, Zuyuan He
Abstract: Distributed acoustic sensing (DAS) has attracted considerable attention across various fields and artificial intelligence (AI) technology plays an important role in DAS applications to realize event recognition and denoising. Existing AI models require real-world data (RWD), whether labeled or not, for training, which is contradictory to the fact of limited available event data in real-world scenarios. Here, a physics-informed DAS neural network paradigm is proposed, which does not need real-world events data for training. By physically modeling target events and the constraints of real world and DAS system, physical functions are derived to train a generative network for generation of DAS events data. DAS debackground net is trained by using the generated DAS events data to eliminate background noise in DAS data. The effectiveness of the proposed paradigm is verified in event identification application based on a public dataset of DAS spatiotemporal data and in belt conveyor fault monitoring application based on DAS time-frequency data, and achieved comparable or better performance than data-driven networks trained with RWD. Owing to the introduction of physical information and capability of background noise removal, the paradigm demonstrates generalization in same application on different sites. A fault diagnosis accuracy of 91.8% is achieved in belt conveyor field with networks which transferred from simulation test site without any fault events data of test site and field for training. The proposed paradigm is a prospective solution to address significant obstacles of data acquisition and intense noise in practical DAS applications and explore more potential fields for DAS.
Authors: Hao Jiang, Yongxiang Tang, Yanxiang Zeng, Pengjia Yuan, Yanhua Cheng, Teng Sha, Xialong Liu, Peng Jiang
Abstract: In the realm of online advertising, advertisers partake in ad auctions to obtain advertising slots, frequently taking advantage of auto-bidding tools provided by demand-side platforms. To improve the automation of these bidding systems, we adopt generative models, namely the Decision Transformer (DT), to tackle the difficulties inherent in automated bidding. Applying the Decision Transformer to the auto-bidding task enables a unified approach to sequential modeling, which efficiently overcomes short-sightedness by capturing long-term dependencies between past bidding actions and user behavior. Nevertheless, conventional DT has certain drawbacks: (1) DT necessitates a preset return-to-go (RTG) value before generating actions, which is not inherently produced; (2) The policy learned by DT is restricted by its training data, which is consists of mixed-quality trajectories. To address these challenges, we introduce the R* Decision Transformer (R* DT), developed in a three-step process: (1) R DT: Similar to traditional DT, R DT stores actions based on state and RTG value, as well as memorizing the RTG for a given state using the training set; (2) R^ DT: We forecast the highest value (within the training set) of RTG for a given state, deriving a suboptimal policy based on the current state and the forecasted supreme RTG value; (3) R* DT: Based on R^ DT, we generate trajectories and select those with high rewards (using a simulator) to augment our training dataset. This data enhancement has been shown to improve the RTG of trajectories in the training data and gradually leads the suboptimal policy towards optimality. Comprehensive tests on a publicly available bidding dataset validate the R* DT's efficacy and highlight its superiority when dealing with mixed-quality trajectories.
Authors: Shuhan Tan, John Lambert, Hong Jeon, Sakshum Kulshrestha, Yijing Bai, Jing Luo, Dragomir Anguelov, Mingxing Tan, Chiyu Max Jiang
Abstract: The goal of traffic simulation is to augment a potentially limited amount of manually-driven miles that is available for testing and validation, with a much larger amount of simulated synthetic miles. The culmination of this vision would be a generative simulated city, where given a map of the city and an autonomous vehicle (AV) software stack, the simulator can seamlessly simulate the trip from point A to point B by populating the city around the AV and controlling all aspects of the scene, from animating the dynamic agents (e.g., vehicles, pedestrians) to controlling the traffic light states. We refer to this vision as CitySim, which requires an agglomeration of simulation technologies: scene generation to populate the initial scene, agent behavior modeling to animate the scene, occlusion reasoning, dynamic scene generation to seamlessly spawn and remove agents, and environment simulation for factors such as traffic lights. While some key technologies have been separately studied in various works, others such as dynamic scene generation and environment simulation have received less attention in the research community. We propose SceneDiffuser++, the first end-to-end generative world model trained on a single loss function capable of point A-to-B simulation on a city scale integrating all the requirements above. We demonstrate the city-scale traffic simulation capability of SceneDiffuser++ and study its superior realism under long simulation conditions. We evaluate the simulation quality on an augmented version of the Waymo Open Motion Dataset (WOMD) with larger map regions to support trip-level simulation.
Authors: Rafael Sojo, Javier D\'iaz-Rozo, Concha Bielza, Pedro Larra\~naga
Abstract: This paper introduces a new type of probabilistic semiparametric model that takes advantage of data binning to reduce the computational cost of kernel density estimation in nonparametric distributions. Two new conditional probability distributions are developed for the new binned semiparametric Bayesian networks, the sparse binned kernel density estimation and the Fourier kernel density estimation. These two probability distributions address the curse of dimensionality, which typically impacts binned models, by using sparse tensors and restricting the number of parent nodes in conditional probability calculations. To evaluate the proposal, we perform a complexity analysis and conduct several comparative experiments using synthetic data and datasets from the UCI Machine Learning repository. The experiments include different binning rules, parent restrictions, grid sizes, and number of instances to get a holistic view of the model's behavior. As a result, our binned semiparametric Bayesian networks achieve structural learning and log-likelihood estimations with no statistically significant differences compared to the semiparametric Bayesian networks, but at a much higher speed. Thus, the new binned semiparametric Bayesian networks prove to be a reliable and more efficient alternative to their non-binned counterparts.
Authors: Mohammad Sabbaqi, Riccardo Taormina, Elvin Isufi
Abstract: Inference tasks with time series over graphs are of importance in applications such as urban water networks, economics, and networked neuroscience. Addressing these tasks typically relies on identifying a computationally affordable model that jointly captures the graph-temporal patterns of the data. In this work, we propose a graph-aware state space model for graph time series, where both the latent state and the observation equation are parametric graph-induced models with a limited number of parameters that need to be learned. More specifically, we consider the state equation to follow a stochastic partial differential equation driven by noise over the graphs edges accounting not only for potential edge uncertainties but also for increasing the degrees of freedom in the latter in a tractable manner. The graph structure conditioning of the noise dispersion allows the state variable to deviate from the stochastic process in certain neighborhoods. The observation model is a sampled and graph-filtered version of the state capturing multi-hop neighboring influence. The goal is to learn the parameters in both state and observation models from the partially observed data for downstream tasks such as prediction and imputation. The model is inferred first through a maximum likelihood approach that provides theoretical tractability but is limited in expressivity and scalability. To improve on the latter, we use the state-space formulation to build a principled deep learning architecture that jointly learns the parameters and tracks the state in an end-to-end manner in the spirit of Kalman neural networks.
Authors: Alessandro Sestini, Joakim Bergdahl, Konrad Tollmar, Andrew D. Bagdanov, Linus Gissl\'en
Abstract: In offline reinforcement learning, agents are trained using only a fixed set of stored transitions derived from a source policy. However, this requires that the dataset be labeled by a reward function. In applied settings such as video game development, the availability of the reward function is not always guaranteed. This paper proposes Trajectory-Ranked OFfline Inverse reinforcement learning (TROFI), a novel approach to effectively learn a policy offline without a pre-defined reward function. TROFI first learns a reward function from human preferences, which it then uses to label the original dataset making it usable for training the policy. In contrast to other approaches, our method does not require optimal trajectories. Through experiments on the D4RL benchmark we demonstrate that TROFI consistently outperforms baselines and performs comparably to using the ground truth reward to learn policies. Additionally, we validate the efficacy of our method in a 3D game environment. Our studies of the reward model highlight the importance of the reward function in this setting: we show that to ensure the alignment of a value function to the actual future discounted reward, it is fundamental to have a well-engineered and easy-to-learn reward function.
Authors: Ying Zhang, Yu Zhao, Xuhui Sui, Baohang Zhou, Xiangrui Cai, Li Shen, Xiaojie Yuan, Dacheng Tao
Abstract: With the increasing multimodal knowledge privatization requirements, multimodal knowledge graphs in different institutes are usually decentralized, lacking of effective collaboration system with both stronger reasoning ability and transmission safety guarantees. In this paper, we propose the Federated Multimodal Knowledge Graph Completion (FedMKGC) task, aiming at training over federated MKGs for better predicting the missing links in clients without sharing sensitive knowledge. We propose a framework named MMFeD3-HidE for addressing multimodal uncertain unavailability and multimodal client heterogeneity challenges of FedMKGC. (1) Inside the clients, our proposed Hyper-modal Imputation Diffusion Embedding model (HidE) recovers the complete multimodal distributions from incomplete entity embeddings constrained by available modalities. (2) Among clients, our proposed Multimodal FeDerated Dual Distillation (MMFeD3) transfers knowledge mutually between clients and the server with logit and feature distillation to improve both global convergence and semantic consistency. We propose a FedMKGC benchmark for a comprehensive evaluation, consisting of a general FedMKGC backbone named MMFedE, datasets with heterogeneous multimodal information, and three groups of constructed baselines. Experiments conducted on our benchmark validate the effectiveness, semantic consistency, and convergence robustness of MMFeD3-HidE.
Authors: Lu Han, Yu Liu, Qiwen Deng, Jian Jiang, Yinbo Sun, Zhe Yu, Binfeng Wang, Xingyu Lu, Lintao Ma, Han-Jia Ye, De-Chuan Zhan
Abstract: Time Series Foundation Models (TSFMs) have achieved remarkable success through large-scale pretraining. However, their design primarily targets real-valued series, limiting their ability to handle general forecasting tasks involving diverse and often heterogeneous covariates--such as categorical variables and multimodal data (e.g., images, text)--which are typically task-specific and difficult to leverage during pretraining. To address this gap, we propose Unified Covariate Adaptation (UniCA), a framework to bridge TSFMs with general covariate-aware forecasting. UniCA first performs covariate homogenization to transform heterogeneous covariates into high-level homogeneous series representations and then fuses them via a unified attention-based fusion mechanism. UniCA is compatible and universal for adaptation with both homogeneous and heterogeneous covariates, incorporating extra covariate information while preserving the generalization ability of TSFMs.Extensive experiments on multiple unimodal and multimodal covariate-aware forecasting benchmarks demonstrate the superiority of UniCA, highlighting the promise of covariate-aware TSFM adaptation in real-world forecasting scenarios. Codes are released on https://github.com/hanlu-nju/UniCA.
Authors: Tianhao Chen, Xin Xu, Zijing Liu, Pengxiang Li, Xinyuan Song, Ajay Kumar Jaiswal, Fan Zhang, Jishan Hu, Yang Wang, Hao Chen, Shizhe Diao, Shiwei Liu, Yu Li, Yin Lu, Can Yang
Abstract: Modern Large Language Models, such as the LLaMA, Qwen and DeepSeek series, predominantly adopt the Pre-LayerNorm (Pre-LN) Transformer architecture. While being stable during pretraining and scalable to large model sizes, Pre-LN suffers from an exponential growth in activation variance across layers, causing the residual path to dominate over sub-layer outputs and limiting the learning capacity of deeper layers. To mitigate this issue, we propose Gradient-Preserving Activation Scaling (GPAS), a simple technique that can be used in combination with existing approaches. GPAS works by scaling down the intermediate activations while keeping their gradients unchanged. This leaves information in the activations intact, and avoids the gradient vanishing problem associated with gradient downscaling. Extensive experiments across various model sizes from 71M to 1B show that GPAS achieves consistent performance gains. Beyond enhancing Pre-LN Transformers, GPAS also shows promise in improving alternative architectures such as Sandwich-LN and DeepNorm, demonstrating its versatility and potential for improving training dynamics in a wide range of settings.
Authors: Mehul Gautam
Abstract: The volatility and complex dynamics of cryptocurrency markets present unique challenges for accurate price forecasting. This research proposes a hybrid deep learning and machine learning model that integrates Long Short-Term Memory (LSTM) networks and Extreme Gradient Boosting (XGBoost) for cryptocurrency price prediction. The LSTM component captures temporal dependencies in historical price data, while XGBoost enhances prediction by modeling nonlinear relationships with auxiliary features such as sentiment scores and macroeconomic indicators. The model is evaluated on historical datasets of Bitcoin, Ethereum, Dogecoin, and Litecoin, incorporating both global and localized exchange data. Comparative analysis using Mean Absolute Percentage Error (MAPE) and Min-Max Normalized Root Mean Square Error (MinMax RMSE) demonstrates that the LSTM+XGBoost hybrid consistently outperforms standalone models and traditional forecasting methods. This study underscores the potential of hybrid architectures in financial forecasting and provides insights into model adaptability across different cryptocurrencies and market contexts.
Authors: Chaitanya K. Joshi
Abstract: We establish connections between the Transformer architecture, originally introduced for natural language processing, and Graph Neural Networks (GNNs) for representation learning on graphs. We show how Transformers can be viewed as message passing GNNs operating on fully connected graphs of tokens, where the self-attention mechanism capture the relative importance of all tokens w.r.t. each-other, and positional encodings provide hints about sequential ordering or structure. Thus, Transformers are expressive set processing networks that learn relationships among input elements without being constrained by apriori graphs. Despite this mathematical connection to GNNs, Transformers are implemented via dense matrix operations that are significantly more efficient on modern hardware than sparse message passing. This leads to the perspective that Transformers are GNNs currently winning the hardware lottery.
Authors: Filip Rydin, Attila Lischka, Jiaming Wu, Morteza Haghir Chehreghani, Bal\'azs Kulcs\'ar
Abstract: Learning-based methods for routing have gained significant attention in recent years, both in single-objective and multi-objective contexts. However, the multigraph setting, where multiple paths with distinct attributes can exist between destinations, has largely been overlooked, despite its high practical relevancy. In this paper, we introduce two neural approaches to address multi-objective routing on multigraphs. Our first approach works directly on the multigraph, by autoregressively selecting edges until a tour is completed. On the other hand, our second model first prunes the multigraph into a simple graph and then builds routes. We validate both models experimentally and find that they demonstrate strong performance across a variety of problems, including the Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP).
Authors: Tin Lai, Farnaz Farid, Yueyang Kuan, Xintian Zhang
Abstract: Detecting heavy metal pollution in soils and seaports is vital for regional environmental monitoring. The Pollution Load Index (PLI), an international standard, is commonly used to assess heavy metal containment. However, the conventional PLI assessment involves laborious procedures and data analysis of sediment samples. To address this challenge, we propose a deep-learning-based model that simplifies the heavy metal assessment process. Our model tackles the issue of data scarcity in the water-sediment domain, which is traditionally plagued by challenges in data collection and varying standards across nations. By leveraging transfer learning, we develop an accurate quantitative assessment method for predicting PLI. Our approach allows the transfer of learned features across domains with different sets of features. We evaluate our model using data from six major ports in New South Wales, Australia: Port Yamba, Port Newcastle, Port Jackson, Port Botany, Port Kembla, and Port Eden. The results demonstrate significantly lower Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) of approximately 0.5 and 0.03, respectively, compared to other models. Our model performance is up to 2 orders of magnitude than other baseline models. Our proposed model offers an innovative, accessible, and cost-effective approach to predicting water quality, benefiting marine life conservation, aquaculture, and industrial pollution monitoring.
Authors: Anurag Panda, Gaurav Kumar Yadav
Abstract: In the aftermath of major earthquakes, evaluating structural and infrastructural damage is vital for coordinating post-disaster response efforts. This includes assessing damage's extent and spatial distribution to prioritize rescue operations and resource allocation. Accurately estimating damage grades to buildings post-earthquake is paramount for effective response and recovery, given the significant impact on lives and properties, underscoring the urgency of streamlining relief fund allocation processes. Previous studies have shown the effectiveness of multi-class classification, especially XGBoost, along with other machine learning models and ensembling methods, incorporating regularization to address class imbalance. One consequence of class imbalance is that it may give rise to skewed models that undervalue minority classes and give preference to the majority class. This research deals with the problem of class imbalance with the help of the synthetic minority oversampling technique (SMOTE). We delve into multiple multi-class classification machine learning, deep learning models, and ensembling methods to forecast structural damage grades. The study elucidates performance determinants through comprehensive feature manipulation experiments and diverse training approaches. It identifies key factors contributing to seismic vulnerability while evaluating model performance using techniques like the confusion matrix further to enhance understanding of the effectiveness of earthquake damage prediction.
Authors: Kaikai Zheng, Dawei Shi, Yang Shi, Long Wang
Abstract: Thompson sampling (TS) is an effective method to explore parametric uncertainties and can therefore be used for active learning-based controller design. However, TS relies on finite parametric representations, which limits its applicability to more general spaces, which are more commonly encountered in control system design. To address this issue, this work pro poses a parameterization method for control law learning using reproducing kernel Hilbert spaces and designs a data-driven active learning control approach. Specifically, the proposed method treats the control law as an element in a function space, allowing the design of control laws without imposing restrictions on the system structure or the form of the controller. A TS framework is proposed in this work to explore potential optimal control laws, and the convergence guarantees are further provided for the learning process. Theoretical analysis shows that the proposed method learns the relationship between control laws and closed-loop performance metrics at an exponential rate, and the upper bound of control regret is also derived. Numerical experiments on controlling unknown nonlinear systems validate the effectiveness of the proposed method.
Authors: Laura van Weesep, Samuel Genheden, Ola Engkvist, Jens Sj\"olund
Abstract: Large-language models (LLMs) and agentic systems present exciting opportunities to accelerate drug discovery and design. In this study, we critically examine the modularity of LLM-based agentic systems for drug discovery, i.e., whether parts of the agentic system such as the LLM are interchangeable, a topic that has received limited attention in drug discovery applications. We compare the performance of different large language models (LLMs) and the effectiveness of tool-calling agents versus code-generating agents in this domain. Our case study, comparing performance in orchestrating tools for chemistry and drug discovery using an LLM-as-a-judge score, shows that Claude-3.5-Sonnet, Claude-3.7-Sonnet and GPT-4o outperform alternative language models such as Llama-3.1-8B, Llama-3.1-70B, GPT-3.5-Turbo, and Nova-Micro. Although we confirm that code-generating agents outperform the tool-calling ones on average, we show that this is highly question and model dependent. Furthermore, the impact of replacing system prompts is dependent on the specific question asked and the model used, underscoring that -- even in this particular domain -- one cannot just replace language models without considering prompt re-engineering. Our study highlights the necessity of further research into the modularity of agentic systems to enable the development of stable and scalable solutions for real-world problems.
Authors: Xiaobo Zhao, Aaron Hurst, Panagiotis Karras, Daniel E. Lucani
Abstract: Despite rapid advancements, machine learning, particularly deep learning, is hindered by the need for large amounts of labeled data to learn meaningful patterns without overfitting and immense demands for computation and storage, which motivate research into architectures that can achieve good performance with fewer resources. This paper introduces dreaMLearning, a novel framework that enables learning from compressed data without decompression, built upon Entropy-based Generalized Deduplication (EntroGeDe), an entropy-driven lossless compression method that consolidates information into a compact set of representative samples. DreaMLearning accommodates a wide range of data types, tasks, and model architectures. Extensive experiments on regression and classification tasks with tabular and image data demonstrate that dreaMLearning accelerates training by up to 8.8x, reduces memory usage by 10x, and cuts storage by 42%, with a minimal impact on model performance. These advancements enhance diverse ML applications, including distributed and federated learning, and tinyML on resource-constrained edge devices, unlocking new possibilities for efficient and scalable learning.
Authors: Jakub Pele\v{s}ka, Gustav \v{S}\'ir
Abstract: Relational databases (RDBs) are widely regarded as the gold standard for storing structured information. Consequently, predictive tasks leveraging this data format hold significant application promise. Recently, Relational Deep Learning (RDL) has emerged as a novel paradigm wherein RDBs are conceptualized as graph structures, enabling the application of various graph neural architectures to effectively address these tasks. However, given its novelty, there is a lack of analysis into the relationships between the performance of various RDL models and the characteristics of the underlying RDBs. In this study, we present REDELEX$-$a comprehensive exploration framework for evaluating RDL models of varying complexity on the most diverse collection of over 70 RDBs, which we make available to the community. Benchmarked alongside key representatives of classic methods, we confirm the generally superior performance of RDL while providing insights into the main factors shaping performance, including model complexity, database sizes and their structural properties.
Authors: Chen Wang, Lai Wei, Yanzhi Zhang, Chenyang Shao, Zedong Dan, Weiran Huang, Yue Wang, Yuzhi Zhang
Abstract: Recent advances in reinforcement learning (RL) have significantly enhanced the reasoning capabilities of large language models (LLMs). Group Relative Policy Optimization (GRPO), an efficient variant of PPO that lowers RL's computational cost, still faces limited exploration, low sample efficiency and instability, constraining its performance on complex reasoning tasks. To address these limitations, we introduce EFRame, an Exploration-Filtering-Replay framework that systematically augments GRPO along three critical dimensions. EFRame performs additional rollouts to explore high-quality trajectories, applies online filtering to eliminate low-quality samples that introduce noise and variance, and leverages experience replay to repeatedly exploit rare but informative samples. EFRame establishes a complete and stable learning cycle, guiding the model through a structured transition from exploration to convergence. Our experiments across a variety of reasoning benchmarks demonstrate that EFRame not only improves the robustness and efficiency of training, but also enables access to deeper reasoning capabilities that remain unattainable under vanilla GRPO. Furthermore, EFRame enables a more fine-grained categorization of training samples, allowing for a deeper analysis of how different types of samples contribute to the learning process in RL. Our code is available at https://github.com/597358816/EFRame.
Authors: Shunta Nonaga, Koji Tabata, Yuta Mizuno, Tamiki Komatsuzaki
Abstract: Decision making under uncertain environments in the maximization of expected reward while minimizing its risk is one of the ubiquitous problems in many subjects. Here, we introduce a novel problem setting in stochastic bandit optimization that jointly addresses two critical aspects of decision-making: maximizing expected reward and minimizing associated uncertainty, quantified via the mean-variance(MV) criterion. Unlike traditional bandit formulations that focus solely on expected returns, our objective is to efficiently and accurately identify the Pareto-optimal set of arms that strikes the best trade-off between expected performance and risk. We propose a unified meta-algorithmic framework capable of operating under both fixed-confidence and fixed-budget regimes, achieved through adaptive design of confidence intervals tailored to each scenario using the same sample exploration strategy. We provide theoretical guarantees on the correctness of the returned solutions in both settings. To complement this theoretical analysis, we conduct extensive empirical evaluations across synthetic benchmarks, demonstrating that our approach outperforms existing methods in terms of both accuracy and sample efficiency, highlighting its broad applicability to risk-aware decision-making tasks in uncertain environments.
Authors: Maciej Stefaniak, Micha{\l} Krutul, Jan Ma{\l}a\'snicki, Maciej Pi\'oro, Jakub Krajewski, Sebastian Jaszczur, Marek Cygan, Kamil Adamczewski, Jan Ludziejewski
Abstract: Large language models have steadily increased in size to achieve improved performance; however, this growth has also led to greater inference time and computational demands. Consequently, there is rising interest in model size reduction methods. To address this issue, we propose Projected Compression, a novel model compression technique, that reduces model weights by utilizing projection modules. Specifically, we first train additional trainable projections weights and preserve access to all the original model parameters. Subsequently, these projections are merged into a lower-dimensional product matrix, resulting in a reduced-size standard Transformer-based model. Unlike alternative approaches that require additional computational overhead, our method matches the base model's per-token computation step in FLOPs. Experimental results show that Projected Compression outperforms the comparable hard pruning and retraining approach on higher quality models. Moreover, the performance margin scales well with the number of tokens.
Authors: Zhengyun Cheng, Changhao Wang, Guanwen Zhang, Yi Xu, Wei Zhou, Xiangyang Ji
Abstract: Low-rank tensor decompositions (TDs) provide an effective framework for multiway data analysis. Traditional TD methods rely on predefined structural assumptions, such as CP or Tucker decompositions. From a probabilistic perspective, these can be viewed as using Dirac delta distributions to model the relationships between shared factors and the low-rank tensor. However, such prior knowledge is rarely available in practical scenarios, particularly regarding the optimal rank structure and contraction rules. The optimization procedures based on fixed contraction rules are complex, and approximations made during these processes often lead to accuracy loss. To address this issue, we propose a score-based model that eliminates the need for predefined structural or distributional assumptions, enabling the learning of compatibility between tensors and shared factors. Specifically, a neural network is designed to learn the energy function, which is optimized via score matching to capture the gradient of the joint log-probability of tensor entries and shared factors. Our method allows for modeling structures and distributions beyond the Dirac delta assumption. Moreover, integrating the block coordinate descent (BCD) algorithm with the proposed smooth regularization enables the model to perform both tensor completion and denoising. Experimental results demonstrate significant performance improvements across various tensor types, including sparse and continuous-time tensors, as well as visual data.
Authors: Tao Liu, Longlong Lin, Yunfeng Yu, Xi Ou, Youan Zhang, Zhiqiu Ye, Tao Jia
Abstract: Graph Neural Networks (GNNs) have garnered substantial attention due to their remarkable capability in learning graph representations. However, real-world graphs often exhibit substantial noise and incompleteness, which severely degrades the performance of GNNs. Existing methods typically address this issue through single-dimensional augmentation, focusing either on refining topology structures or perturbing node attributes, thereby overlooking the deeper interplays between the two. To bridge this gap, this paper presents CoATA, a dual-channel GNN framework specifically designed for the Co-Augmentation of Topology and Attribute. Specifically, CoATA first propagates structural signals to enrich and denoise node attributes. Then, it projects the enhanced attribute space into a node-attribute bipartite graph for further refinement or reconstruction of the underlying structure. Subsequently, CoATA introduces contrastive learning, leveraging prototype alignment and consistency constraints, to facilitate mutual corrections between the augmented and original graphs. Finally, extensive experiments on seven benchmark datasets demonstrate that the proposed CoATA outperforms eleven state-of-the-art baseline methods, showcasing its effectiveness in capturing the synergistic relationship between topology and attributes.
Authors: Takumi Okuo, Shinnosuke Matsuo, Shota Harada, Kiyohito Tanaka, Ryoma Bise
Abstract: Domain shift is a significant challenge in machine learning, particularly in medical applications where data distributions differ across institutions due to variations in data collection practices, equipment, and procedures. This can degrade performance when models trained on source domain data are applied to the target domain. Domain adaptation methods have been widely studied to address this issue, but most struggle when class proportions between the source and target domains differ. In this paper, we propose a weakly-supervised domain adaptation method that leverages class proportion information from the target domain, which is often accessible in medical datasets through prior knowledge or statistical reports. Our method assigns pseudo-labels to the unlabeled target data based on class proportion (called proportion-constrained pseudo-labeling), improving performance without the need for additional annotations. Experiments on two endoscopic datasets demonstrate that our method outperforms semi-supervised domain adaptation techniques, even when 5% of the target domain is labeled. Additionally, the experimental results with noisy proportion labels highlight the robustness of our method, further demonstrating its effectiveness in real-world application scenarios.
Authors: Erkan Turan, Aristotelis Siozopoulos, Maks Ovsjanikov
Abstract: Conditional Flow Matching (CFM) offers a simulation-free framework for training continuous-time generative models, bridging diffusion and flow-based approaches. However, sampling from CFM still relies on numerically solving non-linear ODEs which can be computationally expensive and difficult to interpret. Recent alternatives address sampling speed via trajectory straightening, mini-batch coupling or distillation. However, these methods typically do not shed light on the underlying \textit{structure} of the generative process. In this work, we propose to accelerate CFM and introduce an interpretable representation of its dynamics by integrating Koopman operator theory, which models non-linear flows as linear evolution in a learned space of observables. We introduce a decoder-free Koopman-CFM architecture that learns an embedding where the generative dynamics become linear, enabling closed-form, one-step sampling via matrix exponentiation. This results in significant speedups over traditional CFM as demonstrated on controlled 2D datasets and real-world benchmarks, MNIST, Fashion-MNIST (F-MNIST), and the Toronto Face Dataset (TFD). Unlike previous methods, our approach leads to a well-structured Koopman generator, whose spectral properties, eigenvalues, and eigenfunctions offer principled tools for analyzing generative behavior such as temporal scaling, mode stability, and decomposition in Koopman latent space. By combining sampling efficiency with analytical structure, Koopman-enhanced flow matching offers a potential step toward fast and interpretable generative modeling.
Authors: Adiba Ejaz, Elias Bareinboim
Abstract: Greedy Equivalence Search (GES) is a classic score-based algorithm for causal discovery from observational data. In the sample limit, it recovers the Markov equivalence class of graphs that describe the data. Still, it faces two challenges in practice: computational cost and finite-sample accuracy. In this paper, we develop Less Greedy Equivalence Search (LGES), a variant of GES that retains its theoretical guarantees while partially addressing these limitations. LGES modifies the greedy step: rather than always applying the highest-scoring insertion, it avoids edge insertions between variables for which the score implies some conditional independence. This more targeted search yields up to a \(10\)-fold speed-up and a substantial reduction in structural error relative to GES. Moreover, LGES can guide the search using prior assumptions, while correcting these assumptions when contradicted by the data. Finally, LGES can exploit interventional data to refine the learned observational equivalence class. We prove that LGES recovers the true equivalence class in the sample limit from observational and interventional data, even with misspecified prior assumptions. Experiments demonstrate that LGES outperforms GES and other baselines in speed, accuracy, and robustness to misspecified assumptions. Our code is available at https://github.com/CausalAILab/lges.
Authors: Zihan Guan, Zhiyuan Zhao, Fengwei Tian, Dung Nguyen, Payel Bhattacharjee, Ravi Tandon, B. Aditya Prakash, Anil Vullikanti
Abstract: It is now well understood that diverse datasets provide a lot of value in key epidemiology and public health analyses, such as forecasting and nowcasting, development of epidemic models, evaluation and design of interventions and resource allocation. Some of these datasets are often sensitive, and need adequate privacy protections. There are many models of privacy, but Differential Privacy (DP) has become a de facto standard because of its strong guarantees, without making models about adversaries. In this paper, we develop a framework the integrates deep learning and epidemic models to simultaneously perform epidemic forecasting and learning a mechanistic model of epidemic spread, while incorporating multiple datasets for these analyses, including some with DP guarantees. We demonstrate our framework using a realistic but synthetic financial dataset with DP; such a dataset has not been used in such epidemic analyses. We show that this dataset provides significant value in forecasting and learning an epidemic model, even when used with DP guarantees.
Authors: Tao Li, Haozhe Lei, Mingsheng Yin, Yaqi Hu
Abstract: When using reinforcement learning (RL) to tackle physical control tasks, inductive biases that encode physics priors can help improve sample efficiency during training and enhance generalization in testing. However, the current practice of incorporating these helpful physics-informed inductive biases inevitably runs into significant manual labor and domain expertise, making them prohibitive for general users. This work explores a symbolic approach to distill physics-informed inductive biases into RL agents, where the physics priors are expressed in a domain-specific language (DSL) that is human-readable and naturally explainable. Yet, the DSL priors do not translate directly into an implementable policy due to partial and noisy observations and additional physical constraints in navigation tasks. To address this gap, we develop a physics-informed program-guided RL (PiPRL) framework with applications to indoor navigation. PiPRL adopts a hierarchical and modularized neuro-symbolic integration, where a meta symbolic program receives semantically meaningful features from a neural perception module, which form the bases for symbolic programming that encodes physics priors and guides the RL process of a low-level neural controller. Extensive experiments demonstrate that PiPRL consistently outperforms purely symbolic or neural policies and reduces training time by over 26% with the help of the program-based inductive biases.
Authors: Abdulmomen Ghalkha, Zhuojun Tian, Chaouki Ben Issaid, Mehdi Bennis
Abstract: In large-scale communication systems, increasingly complex scenarios require more intelligent collaboration among edge devices collecting various multimodal sensory data to achieve a more comprehensive understanding of the environment and improve decision-making accuracy. However, conventional federated learning (FL) algorithms typically consider unimodal datasets, require identical model architectures, and fail to leverage the rich information embedded in multimodal data, limiting their applicability to real-world scenarios with diverse modalities and varying client capabilities. To address this issue, we propose Sheaf-DMFL, a novel decentralized multimodal learning framework leveraging sheaf theory to enhance collaboration among devices with diverse modalities. Specifically, each client has a set of local feature encoders for its different modalities, whose outputs are concatenated before passing through a task-specific layer. While encoders for the same modality are trained collaboratively across clients, we capture the intrinsic correlations among clients' task-specific layers using a sheaf-based structure. To further enhance learning capability, we propose an enhanced algorithm named Sheaf-DMFL-Att, which tailors the attention mechanism within each client to capture correlations among different modalities. A rigorous convergence analysis of Sheaf-DMFL-Att is provided, establishing its theoretical guarantees. Extensive simulations are conducted on real-world link blockage prediction and mmWave beamforming scenarios, demonstrate the superiority of the proposed algorithms in such heterogeneous wireless communication systems.
Authors: Youkang Wang, Jian Wang, Rubing Chen, Xiao-Yong Wei, Qing Li
Abstract: Inference-time scaling has emerged as a powerful technique for enhancing the reasoning performance of Large Language Models (LLMs). However, existing approaches often rely on heuristic strategies for parallel sampling, lacking a principled foundation. To address this gap, we propose a probabilistic framework that formalizes the optimality of inference-time scaling under the assumption that parallel samples are independently and identically distributed (i.i.d.), and where the Best-of-N selection strategy follows a probability distribution that can be estimated. Within this framework, we derive a theoretical lower bound on the required number of samples to achieve a target performance level, providing the first principled guidance for compute-efficient scaling. Leveraging this insight, we develop \textsc{OptScale}, a practical algorithm that dynamically determines the optimal number of sampled responses. \textsc{OptScale} employs a language model-based predictor to estimate probabilistic prior parameters, enabling the decision of the minimal number of samples needed that satisfy predefined performance thresholds and confidence levels. Extensive experiments on mathematical reasoning benchmarks (including MATH-500, GSM8K, AIME, and AMC) demonstrate that \textsc{OptScale} significantly reduces sampling overhead while remaining better or on par with state-of-the-art reasoning performance. Our work offers both a theoretical foundation and a practical solution for principled inference-time scaling, addressing a critical gap in the efficient deployment of LLMs for complex reasoning.
Authors: Aditya Cowsik, Tianyu He, Andrey Gromov
Abstract: We introduce and train distributed neural architectures (DNA) in vision and language domains. DNAs are initialized with a proto-architecture that consists of (transformer, MLP, attention, etc.) modules and routers. Any token (or patch) can traverse any series of modules in any order. DNAs are a natural generalization of the sparse methods such as Mixture-of-Experts, Mixture-of-Depths, parameter sharing, etc. Computation and communication patterns of DNA modules are learnt end-to-end during training and depend on the content and context of each token (or patch). These patterns can be shaped by further requirements added to the optimization objective such as compute/memory efficiency or load balancing. We empirically show that (i) trained DNAs are competitive with the dense baselines in both domains and (ii) compute efficiency/parameter sharing can be learnt from data. Next, we analyze the emergent connectivity and computation patterns in the trained DNAs. We find that the paths that tokens take through the models are themselves distributed according to a power-law. We show that some paths (or, equivalently, groups of modules) show emergent specialization. Finally, we demonstrate that models learn to allocate compute and active parameters in an interpretable way.
Authors: YongKyung Oh, Alex Bui
Abstract: Adapting machine learning models to medical time series across different domains remains a challenge due to complex temporal dependencies and dynamic distribution shifts. Current approaches often focus on isolated feature representations, limiting their ability to fully capture the intricate temporal dynamics necessary for robust domain adaptation. In this work, we propose a novel framework leveraging multi-view contrastive learning to integrate temporal patterns, derivative-based dynamics, and frequency-domain features. Our method employs independent encoders and a hierarchical fusion mechanism to learn feature-invariant representations that are transferable across domains while preserving temporal coherence. Extensive experiments on diverse medical datasets, including electroencephalogram (EEG), electrocardiogram (ECG), and electromyography (EMG) demonstrate that our approach significantly outperforms state-of-the-art methods in transfer learning tasks. By advancing the robustness and generalizability of machine learning models, our framework offers a practical pathway for deploying reliable AI systems in diverse healthcare settings.
Authors: Tong Yang, Bo Dai, Lin Xiao, Yuejie Chi
Abstract: Online reinforcement learning (RL) with complex function approximations such as transformers and deep neural networks plays a significant role in the modern practice of artificial intelligence. Despite its popularity and importance, balancing the fundamental trade-off between exploration and exploitation remains a long-standing challenge; in particular, we are still in lack of efficient and practical schemes that are backed by theoretical performance guarantees. Motivated by recent developments in exploration via optimistic regularization, this paper provides an interpretation of the principle of optimism through the lens of primal-dual optimization. From this fresh perspective, we set forth a new value-incentivized actor-critic (VAC) method, which optimizes a single easy-to-optimize objective integrating exploration and exploitation -- it promotes state-action and policy estimates that are both consistent with collected data transitions and result in higher value functions. Theoretically, the proposed VAC method has near-optimal regret guarantees under linear Markov decision processes (MDPs) in both finite-horizon and infinite-horizon settings, which can be extended to the general function approximation setting under appropriate assumptions.
Authors: Pritam Dash, Ethan Chan, Nathan P. Lawrence, Karthik Pattabiraman
Abstract: Unmanned Aerial Vehicles (UAVs) depend on onboard sensors for perception, navigation, and control. However, these sensors are susceptible to physical attacks, such as GPS spoofing, that can corrupt state estimates and lead to unsafe behavior. While reinforcement learning (RL) offers adaptive control capabilities, existing safe RL methods are ineffective against such attacks. We present ARMOR (Adaptive Robust Manipulation-Optimized State Representations), an attack-resilient, model-free RL controller that enables robust UAV operation under adversarial sensor manipulation. Instead of relying on raw sensor observations, ARMOR learns a robust latent representation of the UAV's physical state via a two-stage training framework. In the first stage, a teacher encoder, trained with privileged attack information, generates attack-aware latent states for RL policy training. In the second stage, a student encoder is trained via supervised learning to approximate the teacher's latent states using only historical sensor data, enabling real-world deployment without privileged information. Our experiments show that ARMOR outperforms conventional methods, ensuring UAV safety. Additionally, ARMOR improves generalization to unseen attacks and reduces training cost by eliminating the need for iterative adversarial training.
Authors: Randeep Bhatia, Nikos Papadis, Murali Kodialam, TV Lakshman, Sayak Chakrabarty
Abstract: We propose CLoVE (Clustering of Loss Vector Embeddings), a novel algorithm for Clustered Federated Learning (CFL). In CFL, clients are naturally grouped into clusters based on their data distribution. However, identifying these clusters is challenging, as client assignments are unknown. CLoVE utilizes client embeddings derived from model losses on client data, and leverages the insight that clients in the same cluster share similar loss values, while those in different clusters exhibit distinct loss patterns. Based on these embeddings, CLoVE is able to iteratively identify and separate clients from different clusters and optimize cluster-specific models through federated aggregation. Key advantages of CLoVE over existing CFL algorithms are (1) its simplicity, (2) its applicability to both supervised and unsupervised settings, and (3) the fact that it eliminates the need for near-optimal model initialization, which makes it more robust and better suited for real-world applications. We establish theoretical convergence bounds, showing that CLoVE can recover clusters accurately with high probability in a single round and converges exponentially fast to optimal models in a linear setting. Our comprehensive experiments comparing with a variety of both CFL and generic Personalized Federated Learning (PFL) algorithms on different types of datasets and an extensive array of non-IID settings demonstrate that CLoVE achieves highly accurate cluster recovery in just a few rounds of training, along with state-of-the-art model accuracy, across a variety of both supervised and unsupervised PFL tasks.
Authors: Yangyu Huang, Hao Yang, Chong Li, Jongyoo Kim, Fangyun Wei
Abstract: The recent progress of CNN has dramatically improved face alignment performance. However, few works have paid attention to the error-bias with respect to error distribution of facial landmarks. In this paper, we investigate the error-bias issue in face alignment, where the distributions of landmark errors tend to spread along the tangent line to landmark curves. This error-bias is not trivial since it is closely connected to the ambiguous landmark labeling task. Inspired by this observation, we seek a way to leverage the error-bias property for better convergence of CNN model. To this end, we propose anisotropic direction loss (ADL) and anisotropic attention module (AAM) for coordinate and heatmap regression, respectively. ADL imposes strong binding force in normal direction for each landmark point on facial boundaries. On the other hand, AAM is an attention module which can get anisotropic attention mask focusing on the region of point and its local edge connected by adjacent points, it has a stronger response in tangent than in normal, which means relaxed constraints in the tangent. These two methods work in a complementary manner to learn both facial structures and texture details. Finally, we integrate them into an optimized end-to-end training pipeline named ADNet. Our ADNet achieves state-of-the-art results on 300W, WFLW and COFW datasets, which demonstrates the effectiveness and robustness.
Authors: Yangyu Huang, Xi Chen, Jongyoo Kim, Hao Yang, Chong Li, Jiaolong Yang, Dong Chen
Abstract: Recent years have witnessed significant growth of face alignment. Though dense facial landmark is highly demanded in various scenarios, e.g., cosmetic medicine and facial beautification, most works only consider sparse face alignment. To address this problem, we present a framework that can enrich landmark density by existing sparse landmark datasets, e.g., 300W with 68 points and WFLW with 98 points. Firstly, we observe that the local patches along each semantic contour are highly similar in appearance. Then, we propose a weakly-supervised idea of learning the refinement ability on original sparse landmarks and adapting this ability to enriched dense landmarks. Meanwhile, several operators are devised and organized together to implement the idea. Finally, the trained model is applied as a plug-and-play module to the existing face alignment networks. To evaluate our method, we manually label the dense landmarks on 300W testset. Our method yields state-of-the-art accuracy not only in newly-constructed dense 300W testset but also in the original sparse 300W and WFLW testsets without additional cost.
Authors: Qihao Zhao, Yangyu Huang, Tengchao Lv, Lei Cui, Qinzheng Sun, Shaoguang Mao, Xin Zhang, Ying Xin, Qiufeng Yin, Scarlett Li, Furu Wei
Abstract: Multiple-choice question (MCQ) datasets like Massive Multitask Language Understanding (MMLU) are widely used to evaluate the commonsense, understanding, and problem-solving abilities of large language models (LLMs). However, the open-source nature of these benchmarks and the broad sources of training data for LLMs have inevitably led to benchmark contamination, resulting in unreliable evaluation results. To alleviate this issue, we propose a contamination-free and more challenging MCQ benchmark called MMLU-CF. This benchmark reassesses LLMs' understanding of world knowledge by averting both unintentional and malicious data leakage. To avoid unintentional data leakage, we source data from a broader domain and design three decontamination rules. To prevent malicious data leakage, we divide the benchmark into validation and test sets with similar difficulty and subject distributions. The test set remains closed-source to ensure reliable results, while the validation set is publicly available to promote transparency and facilitate independent verification. Our evaluation of mainstream LLMs reveals that the powerful GPT-4o achieves merely a 5-shot score of 73.4% and a 0-shot score of 71.9% on the test set, which indicates the effectiveness of our approach in creating a more rigorous and contamination-free evaluation standard. The GitHub repository is available at https://github.com/microsoft/MMLU-CF and the dataset refers to https://huggingface.co/datasets/microsoft/MMLU-CF.
URLs: https://github.com/microsoft/MMLU-CF, https://huggingface.co/datasets/microsoft/MMLU-CF.
Authors: Yalun Dai, Yangyu Huang, Xin Zhang, Wenshan Wu, Chong Li, Wenhui Lu, Shijie Cao, Li Dong, Scarlett Li
Abstract: Data is fundamental to the training of language models (LM). Recent research has been dedicated to data efficiency, which aims to maximize performance by selecting a minimal or optimal subset of training data. Techniques such as data filtering, sampling, and selection play a crucial role in this area. To complement it, we define Data Efficacy, which focuses on maximizing performance by optimizing the organization of training data and remains relatively underexplored. This work introduces a general paradigm, DELT, for considering data efficacy in LM training, which highlights the significance of training data organization. DELT comprises three components: Data Scoring, Data Selection, and Data Ordering. Among these components, we design Learnability-Quality Scoring (LQS), as a new instance of Data Scoring, which considers both the learnability and quality of each data sample from the gradient consistency perspective. We also devise Folding Ordering (FO), as a novel instance of Data Ordering, which addresses issues such as model forgetting and data distribution bias. Comprehensive experiments validate the data efficacy in LM training, which demonstrates the following: Firstly, various instances of the proposed DELT enhance LM performance to varying degrees without increasing the data scale and model size. Secondly, among these instances, the combination of our proposed LQS for data scoring and Folding for data ordering achieves the most significant improvement. Lastly, data efficacy can be achieved together with data efficiency by applying data selection. Therefore, we believe that data efficacy is a promising foundational area in LM training.
Authors: FutureSearch, :, Jack Wildman, Nikos I. Bosse, Daniel Hnyk, Peter M\"uhlbacher, Finn Hambly, Jon Evans, Dan Schwarz, Lawrence Phillips
Abstract: Forecasting is a challenging task that offers a clearly measurable way to study AI systems. Forecasting requires a large amount of research on the internet, and evaluations require time for events to happen, making the development of forecasting benchmarks challenging. To date, no forecasting benchmark provides a realistic, hermetic, and repeatable environment for LLM forecasters. We introduce Bench To the Future (BTF), a "pastcasting" benchmark with hundreds of high-quality questions for which the resolution is already known. Each question is accompanied by a large offline corpus of tens of thousands of relevant web pages, enabling a way to elicit realistic "forecasts" on past events from LLMs. Results suggest that our pastcasting environment can produce results comparable to those based on forecasts using the internet on at-the-time unresolved questions. We show results benchmarking agent and chain-of-thought forecasting approaches using several LLMs, including the recently-released Claude 4 models, and demonstrate BTF's ability to track steady forecasting capability progress over time. We intend this to be a living benchmark, with new questions added continually to account for increasing training data cutoff dates. We invite researchers to contact us at hello@futuresearch.ai to utilize our benchmark or tooling for their own research.
Authors: Takato Ueno, Keito Inoshita
Abstract: Japan's kairanban culture and idobata conversations have long functioned as traditional communication practices that foster nuanced dialogue among community members and contribute to the formation of social balance. Inspired by these information exchange processes, this study proposes a multi-agent inference framework (KCS+IBC) that integrates multiple large language models (LLMs) to achieve bias mitigation, improved explainability, and probabilistic prediction in sentiment analysis. In addition to sequentially sharing prediction results, the proposed method incorporates a mid-phase casual dialogue session to blend formal inference with individual perspectives and introduces probabilistic sentiment prediction. Experimental results show that KCS achieves accuracy comparable to that of a single LLM across datasets, while KCS+IBC exhibits a consistent decrease in entropy and a gradual increase in variance during the latter stages of inference, suggesting the framework's ability to balance aggregation and diversity of predictions. Future work will quantitatively assess the impact of these characteristics on bias correction and aim to develop more advanced sentiment analysis systems.
Authors: Arwa Arif
Abstract: Backtranslation BT is widely used in low resource machine translation MT to generate additional synthetic training data using monolingual corpora. While this approach has shown strong improvements for many language pairs, its effectiveness in high quality, low resource settings remains unclear. In this work, we explore the effectiveness of backtranslation for English Gujarati translation using the multilingual pretrained MBART50 model. Our baseline system, trained on a high quality parallel corpus of approximately 50,000 sentence pairs, achieves a BLEU score of 43.8 on a validation set. We augment this data with carefully filtered backtranslated examples generated from monolingual Gujarati text. Surprisingly, adding this synthetic data does not improve translation performance and, in some cases, slightly reduces it. We evaluate our models using multiple metrics like BLEU, ChrF++, TER, BLEURT and analyze possible reasons for this saturation. Our findings suggest that backtranslation may reach a point of diminishing returns in certain low-resource settings and we discuss implications for future research.
Authors: Baqer M. Merzah, Tania Taami, Salman Asoudeh, Amir reza Hossein pour, Saeed Mirzaee, Amir Ali Bengari
Abstract: Large Language Models (LLMs) have recently gained attention in the life sciences due to their capacity to model, extract, and apply complex biological information. Beyond their classical use as chatbots, these systems are increasingly used for complex analysis and problem-solving in specialized fields, including bioinformatics. First, we introduce BIOPARS-BENCH, a dataset from over 10,000 scientific articles, textbooks, and medical websites. BioParsQA was also introduced to evaluate the proposed model, which consists of 5,231 Persian medical questions and answers. This study then introduces BioPars, a simple but accurate measure designed to assess LLMs for three main abilities: acquiring subject-specific knowledge, interpreting and synthesizing such knowledge, and demonstrating proper evidence. Comparing ChatGPT, Llama, and Galactica, our study highlights their ability to remember and retrieve learned knowledge but also reveals shortcomings in addressing higher-level, real-world questions and fine-grained inferences. These findings indicate the need for further fine-tuning to address the capabilities of LLM in bioinformatics tasks. To our knowledge, BioPars is the first application of LLM in Persian medical QA, especially for generating long answers. Evaluation of four selected medical QA datasets shows that BioPars has achieved remarkable results compared to comparative approaches. The model on BioParsQA achieved a ROUGE-L score of 29.99, which is an improvement over GPT-4 1.0. The model achieved a BERTScore of 90.87 with the MMR method. The MoverScore and BLEURT values were also higher in this model than the other three models. In addition, the reported scores for the model are MoverScore=60.43 and BLEURT=50.78. BioPars is an ongoing project and all resources related to its development will be made available via the following GitHub repository: https://github.com/amirap80/BioPars.
Authors: Roland Riachi, Kashif Rasul, Arjun Ashok, Prateek Humane, Alexis Roger, Andrew R. Williams, Yuriy Nevmyvaka, Irina Rish
Abstract: Recent works have demonstrated the effectiveness of adapting pre-trained language models (LMs) for forecasting time series in the low-data regime. We build upon these findings by analyzing the effective transfer from language models to time series forecasting under various design choices including upstream post-training, time series tokenizer and language backbone size. In the low-data regime, these design choices have a significant impact on the validation loss, with clear-cut choices that outperform others. Contrary to Hernandez et al. (2021), we observe that the validation loss of the LMs continues to smoothly decrease long after the validation loss of the randomly initialized models has converged, leading to a non-vanishing transfer gap that holds across design choices. These findings not only help shed light on the effective use of compute-efficient training for time series, but also open the way for the study of modality-agnostic properties of data distributions leveraged by these models.
Authors: Yanwei Ren, Liu Liu, Baosheng Yu, Jiayan Qiu, Quan Chen
Abstract: Optimizing instructions for large language models (LLMs) is critical for harnessing their full potential in complex and diverse tasks. However, relying solely on white-box approaches demands extensive computational resources and offers limited representational capacity, while black-box models can incur prohibitive financial costs. To address these challenges, we introduce a novel framework that seamlessly merges the strengths of both paradigms. Black-box models provide high-quality, diverse instruction initializations, and white-box models supply fine-grained interpretability through hidden states and output features. By enforcing a semantic similarity constraint, these components fuse into a unified high-dimensional representation that captures deep semantic and structural nuances, enabling an iterative optimization process to refine instruction quality and adaptability. Extensive evaluations across a broad spectrum of tasks-ranging from complex reasoning to cross-lingual generalization-demonstrate that our approach consistently outperforms state-of-the-art baselines. This fusion of black-box initialization with advanced semantic refinement yields a scalable and efficient solution, paving the way for next-generation LLM-driven applications in diverse real-world scenarios. The source code will be released soon.
Authors: Sarthak Chaturvedi, Anurag Acharya, Rounak Meyur, Koby Hayashi, Sai Munikoti, Sameera Horawalavithana
Abstract: Evaluation benchmark characteristics may distort the true benefits of domain adaptation in retrieval models. This creates misleading assessments that influence deployment decisions in specialized domains. We show that two benchmarks with drastically different features such as topic diversity, boundary overlap, and semantic complexity can influence the perceived benefits of fine-tuning. Using environmental regulatory document retrieval as a case study, we fine-tune ColBERTv2 model on Environmental Impact Statements (EIS) from federal agencies. We evaluate these models across two benchmarks with different semantic structures. Our findings reveal that identical domain adaptation approaches show very different perceived benefits depending on evaluation methodology. On one benchmark, with clearly separated topic boundaries, domain adaptation shows small improvements (maximum 0.61% NDCG gain). However, on the other benchmark with overlapping semantic structures, the same models demonstrate large improvements (up to 2.22% NDCG gain), a 3.6-fold difference in the performance benefit. We compare these benchmarks through topic diversity metrics, finding that the higher-performing benchmark shows 11% higher average cosine distances between contexts and 23% lower silhouette scores, directly contributing to the observed performance difference. These results demonstrate that benchmark selection strongly determines assessments of retrieval system effectiveness in specialized domains. Evaluation frameworks with well-separated topics regularly underestimate domain adaptation benefits, while those with overlapping semantic boundaries reveal improvements that better reflect real-world regulatory document complexity. Our findings have important implications for developing and deploying AI systems for interdisciplinary domains that integrate multiple topics.
Authors: Christoph Brosch, Sian Brumm, Rolf Krieger, Jonas Scheffler
Abstract: Generative AI and large language models (LLMs) offer significant potential for automating the extraction of structured information from web pages. In this work, we focus on food product pages from online retailers and explore schema-constrained extraction approaches to retrieve key product attributes, such as ingredient lists and nutrition tables. We compare two LLM-based approaches, direct extraction and indirect extraction via generated functions, evaluating them in terms of accuracy, efficiency, and cost on a curated dataset of 3,000 food product pages from three different online shops. Our results show that although the indirect approach achieves slightly lower accuracy (96.48\%, $-1.61\%$ compared to direct extraction), it reduces the number of required LLM calls by 95.82\%, leading to substantial efficiency gains and lower operational costs. These findings suggest that indirect extraction approaches can provide scalable and cost-effective solutions for large-scale information extraction tasks from template-based web pages using LLMs.
Authors: Junqi Jiang, Tom Bewley, Salim I. Amoukou, Francesco Leofante, Antonio Rago, Saumitra Mishra, Francesca Toni
Abstract: Test-time scaling improves large language models' (LLMs) performance by allocating more compute budget during inference. To achieve this, existing methods often require intricate modifications to prompting and sampling strategies. In this work, we introduce representation consistency (RC), a test-time scaling method for aggregating answers drawn from multiple candidate responses of an LLM regardless of how they were generated, including variations in prompt phrasing and sampling strategy. RC enhances answer aggregation by not only considering the number of occurrences of each answer in the candidate response set, but also the consistency of the model's internal activations while generating the set of responses leading to each answer. These activations can be either dense (raw model activations) or sparse (encoded via pretrained sparse autoencoders). Our rationale is that if the model's representations of multiple responses converging on the same answer are highly variable, this answer is more likely to be the result of incoherent reasoning and should be down-weighted during aggregation. Importantly, our method only uses cached activations and lightweight similarity computations and requires no additional model queries. Through experiments with four open-source LLMs and four reasoning datasets, we validate the effectiveness of RC for improving task performance during inference, with consistent accuracy improvements (up to 4%) over strong test-time scaling baselines. We also show that consistency in the sparse activation signals aligns well with the common notion of coherent reasoning.
Authors: Peibo Li, Shuang Ao, Hao Xue, Yang Song, Maarten de Rijke, Johan Barth\'elemy, Tomasz Bednarz, Flora D. Salim
Abstract: Large language models (LLMs) have been adopted for next point-of-interest (POI) recommendation tasks. Typical LLM-based recommenders fall into two categories: prompt-based and supervised fine-tuning (SFT)-based models. Prompt-based models generally offer greater output flexibility but deliver lower accuracy, whereas SFT-based models achieve higher performance yet face a fundamental mismatch: next POI recommendation data does not naturally suit supervised fine-tuning. In SFT, the model is trained to reproduce the exact ground truth, but each training example provides only a single target POI, so there is no ground truth for producing a top-k list. To address this, we propose Refine-POI, a reinforcement fine-tuning framework for next POI recommendation. We introduce recommendation-driven rewards that enable LLMs to learn to generate top-k recommendation lists using only one ground-truth POI per example. Experiments on real-world datasets demonstrate that Refine-POI achieves state-of-the-art top-k recommendation performance.
Authors: Yenisel Plasencia-Cala\~na
Abstract: This paper explores the human-centric operationalization of Automated Essay Scoring (AES) systems, addressing aspects beyond accuracy. We compare various machine learning-based approaches with Large Language Models (LLMs) approaches, identifying their strengths, similarities and differences. The study investigates key dimensions such as bias, robustness, and explainability, considered important for human-aware operationalization of AES systems. Our study shows that ML-based AES models outperform LLMs in accuracy but struggle with explainability, whereas LLMs provide richer explanations. We also found that both approaches struggle with bias and robustness to edge scores. By analyzing these dimensions, the paper aims to identify challenges and trade-offs between different methods, contributing to more reliable and trustworthy AES methods.
Authors: Varun Mannam, Fang Wang, Xin Chen
Abstract: Current evaluation frameworks for multimodal generative AI struggle to establish trustworthiness, hindering enterprise adoption where reliability is paramount. We introduce a systematic, quantitative benchmarking framework to measure the trustworthiness of progressively integrating cross-modal inputs such as text, images, captions, and OCR within VisualRAG systems for enterprise document intelligence. Our approach establishes quantitative relationships between technical metrics and user-centric trust measures. Evaluation reveals that optimal modality weighting with weights of 30% text, 15% image, 25% caption, and 30% OCR improves performance by 57.3% over text-only baselines while maintaining computational efficiency. We provide comparative assessments of foundation models, demonstrating their differential impact on trustworthiness in caption generation and OCR extraction-a vital consideration for reliable enterprise AI. This work advances responsible AI deployment by providing a rigorous framework for quantifying and enhancing trustworthiness in multimodal RAG for critical enterprise applications.
Authors: Dipak Meher, Carlotta Domeniconi, Guadalupe Correa-Cabrera
Abstract: Human smuggling networks are increasingly adaptive and difficult to analyze. Legal case documents offer valuable insights but are unstructured, lexically dense, and filled with ambiguous or shifting references-posing challenges for automated knowledge graph (KG) construction. Existing KG methods often rely on static templates and lack coreference resolution, while recent LLM-based approaches frequently produce noisy, fragmented graphs due to hallucinations, and duplicate nodes caused by a lack of guided extraction. We propose CORE-KG, a modular framework for building interpretable KGs from legal texts. It uses a two-step pipeline: (1) type-aware coreference resolution via sequential, structured LLM prompts, and (2) entity and relationship extraction using domain-guided instructions, built on an adapted GraphRAG framework. CORE-KG reduces node duplication by 33.28%, and legal noise by 38.37% compared to a GraphRAG-based baseline-resulting in cleaner and more coherent graph structures. These improvements make CORE-KG a strong foundation for analyzing complex criminal networks.
Authors: Xiyuan Zhang, Boran Han, Haoyang Fang, Abdul Fatir Ansari, Shuai Zhang, Danielle C. Maddix, Cuixiong Hu, Andrew Gordon Wilson, Michael W. Mahoney, Hao Wang, Yan Liu, Huzefa Rangwala, George Karypis, Bernie Wang
Abstract: Recently, there has been growing interest in incorporating textual information into foundation models for time series forecasting. However, it remains unclear whether and under what conditions such multimodal integration consistently yields gains. We systematically investigate these questions across a diverse benchmark of 14 forecasting tasks spanning 7 domains, including health, environment, and economics. We evaluate two popular multimodal forecasting paradigms: aligning-based methods, which align time series and text representations; and prompting-based methods, which directly prompt large language models for forecasting. Although prior works report gains from multimodal input, we find these effects are not universal across datasets and models, and multimodal methods sometimes do not outperform the strongest unimodal baselines. To understand when textual information helps, we disentangle the effects of model architectural properties and data characteristics. Our findings highlight that on the modeling side, incorporating text information is most helpful given (1) high-capacity text models, (2) comparatively weaker time series models, and (3) appropriate aligning strategies. On the data side, performance gains are more likely when (4) sufficient training data is available and (5) the text offers complementary predictive signal beyond what is already captured from the time series alone. Our empirical findings offer practical guidelines for when multimodality can be expected to aid forecasting tasks, and when it does not.
Authors: Peiheng Gao, Chen Yang, Ning Sun, Ri\v{c}ardas Zitikis
Abstract: Machine learning (ML) has significantly advanced text classification by enabling automated understanding and categorization of complex, unstructured textual data. However, accurately capturing nuanced linguistic patterns and contextual variations inherent in natural language, particularly within consumer complaints, remains a challenge. This study addresses these issues by incorporating human-experience-trained algorithms that effectively recognize subtle semantic differences crucial for assessing consumer relief eligibility. Furthermore, we propose integrating synthetic data generation methods that utilize expert evaluations of generative adversarial networks and are refined through expert annotations. By combining expert-trained classifiers with high-quality synthetic data, our research seeks to significantly enhance machine learning classifier performance, reduce dataset acquisition costs, and improve overall evaluation metrics and robustness in text classification tasks.
Authors: Bla\v{z} \v{S}krlj, Yonatan Karni, Grega Ga\v{s}per\v{s}i\v{c}, Bla\v{z} Mramor, Yulia Stolin, Martin Jakomin, Jasna Urban\v{c}i\v{c}, Yuval Dishi, Natalia Silberstein, Ophir Friedler, Assaf Klein
Abstract: The Deep and Cross architecture (DCNv2) is a robust production baseline and is integral to numerous real-life recommender systems. Its inherent efficiency and ability to model interactions often result in models that are both simpler and highly competitive compared to more computationally demanding alternatives, such as Deep FFMs. In this work, we introduce three significant algorithmic improvements to the DCNv2 architecture, detailing their formulation and behavior at scale. The enhanced architecture we refer to as DCN^2 is actively used in a live recommender system, processing over 0.5 billion predictions per second across diverse use cases where it out-performed DCNv2, both offline and online (ab tests). These improvements effectively address key limitations observed in the DCNv2, including information loss in Cross layers, implicit management of collisions through learnable lookup-level weights, and explicit modeling of pairwise similarities with a custom layer that emulates FFMs' behavior. The superior performance of DCN^2 is also demonstrated on four publicly available benchmark data sets.
Authors: Magnus Dierking, Christopher E. Mower, Sarthak Das, Huang Helong, Jiacheng Qiu, Cody Reading, Wei Chen, Huidong Liang, Huang Guowei, Jan Peters, Quan Xingyue, Jun Wang, Haitham Bou-Ammar
Abstract: Robotics has made remarkable hardware strides-from DARPA's Urban and Robotics Challenges to the first humanoid-robot kickboxing tournament-yet commercial autonomy still lags behind progress in machine learning. A major bottleneck is software: current robot stacks demand steep learning curves, low-level C/C++ expertise, fragmented tooling, and intricate hardware integration, in stark contrast to the Python-centric, well-documented ecosystems that propelled modern AI. We introduce ARK, an open-source, Python-first robotics framework designed to close that gap. ARK presents a Gym-style environment interface that allows users to collect data, preprocess it, and train policies using state-of-the-art imitation-learning algorithms (e.g., ACT, Diffusion Policy) while seamlessly toggling between high-fidelity simulation and physical robots. A lightweight client-server architecture provides networked publisher-subscriber communication, and optional C/C++ bindings ensure real-time performance when needed. ARK ships with reusable modules for control, SLAM, motion planning, system identification, and visualization, along with native ROS interoperability. Comprehensive documentation and case studies-from manipulation to mobile navigation-demonstrate rapid prototyping, effortless hardware swapping, and end-to-end pipelines that rival the convenience of mainstream machine-learning workflows. By unifying robotics and AI practices under a common Python umbrella, ARK lowers entry barriers and accelerates research and commercial deployment of autonomous robots.
Authors: Yixin Sun, Li Li, Wenke E, Amir Atapour-Abarghouei, Toby P. Breckon
Abstract: Detecting traversable pathways in unstructured outdoor environments remains a significant challenge for autonomous robots, especially in critical applications such as wide-area search and rescue, as well as incident management scenarios like forest fires. Existing datasets and models primarily target urban settings or wide, vehicle-traversable off-road tracks, leaving a substantial gap in addressing the complexity of narrow, trail-like off-road scenarios. To address this, we introduce the Trail-based Off-road Multimodal Dataset (TOMD), a comprehensive dataset specifically designed for such environments. TOMD features high-fidelity multimodal sensor data -- including 128-channel LiDAR, stereo imagery, GNSS, IMU, and illumination measurements -- collected through repeated traversals under diverse conditions. We also propose a dynamic multiscale data fusion model for accurate traversable pathway prediction. The study analyzes the performance of early, cross, and mixed fusion strategies under varying illumination levels. Results demonstrate the effectiveness of our approach and the relevance of illumination in segmentation performance. We publicly release TOMD at https://github.com/yyyxs1125/TMOD to support future research in trail-based off-road navigation.
Authors: Tao Feng, Zhigang Hua, Zijie Lei, Yan Xie, Shuang Yang, Bo Long, Jiaxuan You
Abstract: Ranking tasks are ubiquitous, encompassing applications such as recommendation systems, LLM routing, and item re-ranking. We propose to unify these tasks using a single ranking foundation model (FM), as it eliminates the need for designing different models for each specific ranking task. However, unlike general supervision tasks in LLMs, ranking tasks do not have clear labels for supervision, posing great challenges to developing a ranking FM. To overcome these challenges, we propose IRanker, a ranking FM framework with reinforcement learning (RL) and iterative decoding. Our insight is to decompose the complex ranking task into an iterative decoding process that eliminates the worst candidate from the candidate pool step by step, which significantly reduces the output combinatorial space and better utilizes the limited context length during RL training. We meticulously train and comprehensively evaluate an IRanker-3B model on nine datasets across three scenarios: recommendation, routing, and passage ranking. The results show that a single IRanker-3B achieves state-of-the-art results on several datasets compared to models of similar size, and even surpasses the performance of larger models on certain datasets. We further demonstrate the effectiveness of our RL design and the robustness of the iterative mechanism across different LLM sizes. Moreover, we conducted both in-domain and out-of-domain zero-shot generalization experiments, which showed that IRanker-3B achieved good generalization on in-domain ranking tasks compared to the base LLM by at least 5% improvement. Surprisingly, on out-of-domain generic LLM tasks, IRanker-3B outperformed the base model by at least 9% on GSM8K, IFEval, and MathQA. In addition, the thoughts generated by IRanker-3B during training could further enhance zero-shot LLM performance.
Authors: Hakan \c{C}apuk, Andrew Bond, Muhammed Burak K{\i}z{\i}l, Emir G\"o\c{c}en, Erkut Erdem, Aykut Erdem
Abstract: Recent advances in image generation have led to remarkable improvements in synthesizing perspective images. However, these models still struggle with panoramic image generation due to unique challenges, including varying levels of geometric distortion and the requirement for seamless loop-consistency. To address these issues while leveraging the strengths of the existing models, we introduce TanDiT, a method that synthesizes panoramic scenes by generating grids of tangent-plane images covering the entire 360$^\circ$ view. Unlike previous methods relying on multiple diffusion branches, TanDiT utilizes a unified diffusion model trained to produce these tangent-plane images simultaneously within a single denoising iteration. Furthermore, we propose a model-agnostic post-processing step specifically designed to enhance global coherence across the generated panoramas. To accurately assess panoramic image quality, we also present two specialized metrics, TangentIS and TangentFID, and provide a comprehensive benchmark comprising captioned panoramic datasets and standardized evaluation scripts. Extensive experiments demonstrate that our method generalizes effectively beyond its training data, robustly interprets detailed and complex text prompts, and seamlessly integrates with various generative models to yield high-quality, diverse panoramic images.
Authors: Swastika Kundu, Autoshi Ibrahim, Mithila Rahman, Tanvir Ahmed
Abstract: Sentiment analysis for regional dialects of Bangla remains an underexplored area due to linguistic diversity and limited annotated data. This paper introduces ANUBHUTI, a comprehensive dataset consisting of 2000 sentences manually translated from standard Bangla into four major regional dialects Mymensingh, Noakhali, Sylhet, and Chittagong. The dataset predominantly features political and religious content, reflecting the contemporary socio political landscape of Bangladesh, alongside neutral texts to maintain balance. Each sentence is annotated using a dual annotation scheme: multiclass thematic labeling categorizes sentences as Political, Religious, or Neutral, and multilabel emotion annotation assigns one or more emotions from Anger, Contempt, Disgust, Enjoyment, Fear, Sadness, and Surprise. Expert native translators conducted the translation and annotation, with quality assurance performed via Cohens Kappa inter annotator agreement, achieving strong consistency across dialects. The dataset was further refined through systematic checks for missing data, anomalies, and inconsistencies. ANUBHUTI fills a critical gap in resources for sentiment analysis in low resource Bangla dialects, enabling more accurate and context aware natural language processing.
Authors: Thorsten Buss, Frank Gaede, Gregor Kasieczka, Anatolii Korol, Katja Kr\"uger, Peter McKeown, Martina Mozzanica
Abstract: Simulating showers of particles in highly-granular calorimeters is a key frontier in the application of machine learning to particle physics. Achieving high accuracy and speed with generative machine learning models can enable them to augment traditional simulations and alleviate a major computing constraint. Recent developments have shown how diffusion based generative shower simulation approaches that do not rely on a fixed structure, but instead generate geometry-independent point clouds, are very efficient. We present a transformer-based extension to previous architectures which were developed for simulating electromagnetic showers in the highly granular electromagnetic calorimeter of the International Large Detector, ILD. The attention mechanism now allows us to generate complex hadronic showers with more pronounced substructure across both the electromagnetic and hadronic calorimeters. This is the first time that machine learning methods are used to holistically generate showers across the electromagnetic and hadronic calorimeter in highly granular imaging calorimeter systems.
Authors: Ameya Salvi, Venkat Krovi
Abstract: Vision-based lane keeping is a topic of significant interest in the robotics and autonomous ground vehicles communities in various on-road and off-road applications. The skid-steered vehicle architecture has served as a useful vehicle platform for human controlled operations. However, systematic modeling, especially of the skid-slip wheel terrain interactions (primarily in off-road settings) has created bottlenecks for automation deployment. End-to-end learning based methods such as imitation learning and deep reinforcement learning, have gained prominence as a viable deployment option to counter the lack of accurate analytical models. However, the systematic formulation and subsequent verification/validation in dynamic operation regimes (particularly for skid-steered vehicles) remains a work in progress. To this end, a novel approach for structured formulation for learning visual navigation is proposed and investigated in this work. Extensive software simulations, hardware evaluations and ablation studies now highlight the significantly improved performance of the proposed approach against contemporary literature.
Authors: Guan Wang, Jin Li, Yuhao Sun, Xing Chen, Changling Liu, Yue Wu, Meng Lu, Sen Song, Yasin Abbasi Yadkori
Abstract: Reasoning, the process of devising and executing complex goal-oriented action sequences, remains a critical challenge in AI. Current large language models (LLMs) primarily employ Chain-of-Thought (CoT) techniques, which suffer from brittle task decomposition, extensive data requirements, and high latency. Inspired by the hierarchical and multi-timescale processing in the human brain, we propose the Hierarchical Reasoning Model (HRM), a novel recurrent architecture that attains significant computational depth while maintaining both training stability and efficiency. HRM executes sequential reasoning tasks in a single forward pass without explicit supervision of the intermediate process, through two interdependent recurrent modules: a high-level module responsible for slow, abstract planning, and a low-level module handling rapid, detailed computations. With only 27 million parameters, HRM achieves exceptional performance on complex reasoning tasks using only 1000 training samples. The model operates without pre-training or CoT data, yet achieves nearly perfect performance on challenging tasks including complex Sudoku puzzles and optimal path finding in large mazes. Furthermore, HRM outperforms much larger models with significantly longer context windows on the Abstraction and Reasoning Corpus (ARC), a key benchmark for measuring artificial general intelligence capabilities. These results underscore HRM's potential as a transformative advancement toward universal computation and general-purpose reasoning systems.
Authors: Felipe Rog\'erio Pimentel, Rafael Gustavo Alves
Abstract: Authors Yi-Cheng Chen, Ping-En Lu, Cheng-Shang Chang, and Tzu-Hsuan Liu use the Finite Impulse Response (FIR) linear system filtering method to track and predict the number of people infected and recovered from COVID-19, in a pandemic context in which there was still no vaccine and the only way to avoid contagion was isolation. To estimate the coefficients of these FIR filters, Chen et al. used machine learning methods through a classical optimization problem with regularization (ridge regression). These estimated coefficients are called ridge coefficients. The epidemic mathematical model adopted by these researchers to formulate the FIR filters is the time-dependent discrete SIR. In this paper, we propose a small modification to the algorithm of Chen et al. to obtain the ridge coefficients. We then used this modified algorithm to track and predict the number of people infected and recovered from COVID-19 in the state of Minas Gerais/Brazil, within a prediction window, during the initial period of the pandemic. We also compare the predicted data with the respective real data to check how good the approximation is. In the modified algorithm, we set values for the FIR filter orders and for the regularization parameters, both different from the respective values defined by Chen et al. in their algorithm. In this context, the numerical results obtained by the modified algorithm in some simulations present better approximation errors compared to the respective approximation errors presented by the algorithm of Chen et al.
Authors: Benjamin Sterling, Chad Gueli, M\'onica F. Bugallo
Abstract: Denoising Diffusion Probabilistic Models represent an entirely new class of generative AI methods that have yet to be fully explored. Critical damping has been successfully introduced in Critically-Damped Langevin Dynamics (CLD) and Critically-Damped Third-Order Langevin Dynamics (TOLD++), but has not yet been applied to dynamics of arbitrary order. The proposed line of work generalizes Higher-Order Langevin Dynamics (HOLD), a recent state-of-the-art diffusion method, by introducing the concept of critical damping from systems analysis.
Authors: Jinpai Zhao, Albert Cerrone, Eirik Valseth, Leendert Westerink, Clint Dawson
Abstract: Storm surge forecasting plays a crucial role in coastal disaster preparedness, yet existing machine learning approaches often suffer from limited spatial resolution, reliance on coastal station data, and poor generalization. Moreover, many prior models operate directly on unstructured spatial data, making them incompatible with modern deep learning architectures. In this work, we introduce a novel approach that projects unstructured water elevation fields onto structured Red Green Blue (RGB)-encoded image representations, enabling the application of Convolutional Long Short Term Memory (ConvLSTM) networks for end-to-end spatiotemporal surge forecasting. Our model further integrates ground-truth wind fields as dynamic conditioning signals and topo-bathymetry as a static input, capturing physically meaningful drivers of surge evolution. Evaluated on a large-scale dataset of synthetic storms in the Gulf of Mexico, our method demonstrates robust 48-hour forecasting performance across multiple regions along the Texas coast and exhibits strong spatial extensibility to other coastal areas. By combining structured representation, physically grounded forcings, and scalable deep learning, this study advances the frontier of storm surge forecasting in usability, adaptability, and interpretability.
Authors: Liav Hen, Erez Yosef, Dan Raviv, Raja Giryes, Jacob Scheuer
Abstract: Metasurfaces are ultra-thin optical elements composed of engineered sub-wavelength structures that enable precise control of light. Their inverse design - determining a geometry that yields a desired optical response - is challenging due to the complex, nonlinear relationship between structure and optical properties. This often requires expert tuning, is prone to local minima, and involves significant computational overhead. In this work, we address these challenges by integrating the generative capabilities of diffusion models into computational design workflows. Using an RCWA simulator, we generate training data consisting of metasurface geometries and their corresponding far-field scattering patterns. We then train a conditional diffusion model to predict meta-atom geometry and height from a target spatial power distribution at a specified wavelength, sampled from a continuous supported band. Once trained, the model can generate metasurfaces with low error, either directly using RCWA-guided posterior sampling or by serving as an initializer for traditional optimization methods. We demonstrate our approach on the design of a spatially uniform intensity splitter and a polarization beam splitter, both produced with low error in under 30 minutes. To support further research in data-driven metasurface design, we publicly release our code and datasets.
Authors: Tianrong Chen, Huangjie Zheng, David Berthelot, Jiatao Gu, Josh Susskind, Shuangfei Zhai
Abstract: Diffusion models have demonstrated exceptional capabilities in generating high-fidelity images but typically suffer from inefficient sampling. Many solver designs and noise scheduling strategies have been proposed to dramatically improve sampling speeds. In this paper, we introduce a new sampling method that is up to $186\%$ faster than the current state of the art solver for comparative FID on ImageNet512. This new sampling method is training-free and uses an ordinary differential equation (ODE) solver. The key to our method resides in using higher-dimensional initial noise, allowing to produce more detailed samples with less function evaluations from existing pretrained diffusion models. In addition, by design our solver allows to control the level of detail through a simple hyper-parameter at no extra computational cost. We present how our approach leverages momentum dynamics by establishing a fundamental equivalence between momentum diffusion models and conventional diffusion models with respect to their training paradigms. Moreover, we observe the use of higher-dimensional noise naturally exhibits characteristics similar to stochastic differential equations (SDEs). Finally, we demonstrate strong performances on a set of representative pretrained diffusion models, including EDM, EDM2, and Stable-Diffusion 3, which cover models in both pixel and latent spaces, as well as class and text conditional settings. The code is available at https://github.com/apple/ml-tada.
Authors: Rishiraj Paul Chowdhury, Nirmit Shekar Karkera
Abstract: Glaucoma is a leading cause of irreversible blindness, but early detection can significantly improve treatment outcomes. Traditional diagnostic methods are often invasive and require specialized equipment. In this work, we present a deep learning pipeline using the EfficientNet-B0 architecture for glaucoma detection from retinal fundus images. Unlike prior studies that rely on single datasets, we sequentially train and fine-tune our model across ACRIMA, ORIGA, and RIM-ONE datasets to enhance generalization. Our experiments show that minimal preprocessing yields higher AUC-ROC compared to more complex enhancements, and our model demonstrates strong discriminative performance on unseen datasets. The proposed pipeline offers a reproducible and scalable approach to early glaucoma detection, supporting its potential clinical utility.
Authors: No\'e Lallouet, Tristan Cazenave, Cyrille Enderli, St\'ephanie Gourdin
Abstract: Recent research works establish deep neural networks as high performing tools for radar target detection, especially on challenging environments (presence of clutter or interferences, multi-target scenarii...). However, the usually large computational complexity of these networks is one of the factors preventing them from being widely implemented in embedded radar systems. We propose to investigate novel neural architecture search (NAS) methods, based on Monte-Carlo Tree Search (MCTS), for finding neural networks achieving the required detection performance and striving towards a lower computational complexity. We evaluate the searched architectures on endoclutter radar signals, in order to compare their respective performance metrics and generalization properties. A novel network satisfying the required detection probability while being significantly lighter than the expert-designed baseline is proposed.
Authors: Reem Alothman, Hafida Benhidour, Said Kerrache
Abstract: The widespread use of text-based communication on social media-through chats, comments, and microblogs-has improved user interaction but has also led to an increase in offensive content, including hate speech, racism, and other forms of abuse. Due to the enormous volume of user-generated content, manual moderation is impractical, which creates a need for automated systems that can detect offensive language. Deep learning models, particularly those using transfer learning, have demonstrated significant success in understanding natural language through large-scale pretraining. In this study, we propose an automatic offensive language detection model based on XLNet, a generalized autoregressive pretraining method, and compare its performance with BERT (Bidirectional Encoder Representations from Transformers), which is a widely used baseline in natural language processing (NLP). Both models are evaluated using the Offensive Language Identification Dataset (OLID), a benchmark Twitter dataset that includes hierarchical annotations. Our experimental results show that XLNet outperforms BERT in detecting offensive content and in categorizing the types of offenses, while BERT performs slightly better in identifying the targets of the offenses. Additionally, we find that oversampling and undersampling strategies are effective in addressing class imbalance and improving classification performance. These findings highlight the potential of transfer learning and XLNet-based architectures to create robust systems for detecting offensive language on social media platforms.
Authors: Johan Hallberg Szabadv\'ary, Tuwe L\"ofstr\"om, Ulf Johansson, Cecilia S\"onstr\"od, Ernst Ahlberg, Lars Carlsson
Abstract: Machine learning (ML) models always make a prediction, even when they are likely to be wrong. This causes problems in practical applications, as we do not know if we should trust a prediction. ML with reject option addresses this issue by abstaining from making a prediction if it is likely to be incorrect. In this work, we formalise the approach to ML with reject option in binary classification, deriving theoretical guarantees on the resulting error rate. This is achieved through conformal prediction (CP), which produce prediction sets with distribution-free validity guarantees. In binary classification, CP can output prediction sets containing exactly one, two or no labels. By accepting only the singleton predictions, we turn CP into a binary classifier with reject option. Here, CP is formally put in the framework of predicting with reject option. We state and prove the resulting error rate, and give finite sample estimates. Numerical examples provide illustrations of derived error rate through several different conformal prediction settings, ranging from full conformal prediction to offline batch inductive conformal prediction. The former has a direct link to sharp validity guarantees, whereas the latter is more fuzzy in terms of validity guarantees but can be used in practice. Error-reject curves illustrate the trade-off between error rate and reject rate, and can serve to aid a user to set an acceptable error rate or reject rate in practice.
Authors: Fuying Wang, Jiacheng Xu, Lequan Yu
Abstract: Electrocardiograms (ECGs) play a vital role in monitoring cardiac health and diagnosing heart diseases. However, traditional deep learning approaches for ECG analysis rely heavily on large-scale manual annotations, which are both time-consuming and resource-intensive to obtain. To overcome this limitation, self-supervised learning (SSL) has emerged as a promising alternative, enabling the extraction of robust ECG representations that can be efficiently transferred to various downstream tasks. While previous studies have explored SSL for ECG pretraining and multi-modal ECG-language alignment, they often fail to capture the multi-scale nature of ECG signals. As a result, these methods struggle to learn generalized representations due to their inability to model the hierarchical structure of ECG data. To address this gap, we introduce MELP, a novel Multi-scale ECG-Language Pretraining (MELP) model that fully leverages hierarchical supervision from ECG-text pairs. MELP first pretrains a cardiology-specific language model to enhance its understanding of clinical text. It then applies three levels of cross-modal supervision-at the token, beat, and rhythm levels-to align ECG signals with textual reports, capturing structured information across different time scales. We evaluate MELP on three public ECG datasets across multiple tasks, including zero-shot ECG classification, linear probing, and transfer learning. Experimental results demonstrate that MELP outperforms existing SSL methods, underscoring its effectiveness and adaptability across diverse clinical applications. Our code is available at https://github.com/HKU-MedAI/MELP.
Authors: Felix Holm, G\"ozde \"Unver, Ghazal Ghazaei, Nassir Navab
Abstract: Understanding the intricate workflows of cataract surgery requires modeling complex interactions between surgical tools, anatomical structures, and procedural techniques. Existing datasets primarily address isolated aspects of surgical analysis, such as tool detection or phase segmentation, but lack comprehensive representations that capture the semantic relationships between entities over time. This paper introduces the Cataract Surgery Scene Graph (CAT-SG) dataset, the first to provide structured annotations of tool-tissue interactions, procedural variations, and temporal dependencies. By incorporating detailed semantic relations, CAT-SG offers a holistic view of surgical workflows, enabling more accurate recognition of surgical phases and techniques. Additionally, we present a novel scene graph generation model, CatSGG, which outperforms current methods in generating structured surgical representations. The CAT-SG dataset is designed to enhance AI-driven surgical training, real-time decision support, and workflow analysis, paving the way for more intelligent, context-aware systems in clinical practice.
Authors: Augustine Twumasi, Prokash Chandra Roy, Zixun Li, Soumya Shouvik Bhattacharjee, Zhengtao Gan
Abstract: Laser powder bed fusion (L-PBF) is a widely recognized additive manufacturing technology for producing intricate metal components with exceptional accuracy. A key challenge in L-PBF is the formation of complex microstructures affecting product quality. We propose a physics-guided, machine-learning approach to optimize scan paths for desired microstructure outcomes, such as equiaxed grains. We utilized a phase-field method (PFM) to model crystalline grain structure evolution. To reduce computational costs, we trained a surrogate machine learning model, a 3D U-Net convolutional neural network, using single-track phase-field simulations with various laser powers to predict crystalline grain orientations based on initial microstructure and thermal history. We investigated three scanning strategies across various hatch spacings within a square domain, achieving a two-orders-of-magnitude speedup using the surrogate model. To reduce trial and error in designing laser scan toolpaths, we used deep reinforcement learning (DRL) to generate optimized scan paths for target microstructure. Results from three cases demonstrate the DRL approach's effectiveness. We integrated the surrogate 3D U-Net model into our DRL environment to accelerate the reinforcement learning training process. The reward function minimizes both aspect ratio and grain volume of the predicted microstructure from the agent's scan path. The reinforcement learning algorithm was benchmarked against conventional zigzag approach for smaller and larger domains, showing machine learning methods' potential to enhance microstructure control and computational efficiency in L-PBF optimization.
Authors: Rafael Sterzinger, Marco Peer, Robert Sablatnig
Abstract: As rich sources of history, maps provide crucial insights into historical changes, yet their diverse visual representations and limited annotated data pose significant challenges for automated processing. We propose a simple yet effective approach for few-shot segmentation of historical maps, leveraging the rich semantic embeddings of large vision foundation models combined with parameter-efficient fine-tuning. Our method outperforms the state-of-the-art on the Siegfried benchmark dataset in vineyard and railway segmentation, achieving +5% and +13% relative improvements in mIoU in 10-shot scenarios and around +20% in the more challenging 5-shot setting. Additionally, it demonstrates strong performance on the ICDAR 2021 competition dataset, attaining a mean PQ of 67.3% for building block segmentation, despite not being optimized for this shape-sensitive metric, underscoring its generalizability. Notably, our approach maintains high performance even in extremely low-data regimes (10- & 5-shot), while requiring only 689k trainable parameters - just 0.21% of the total model size. Our approach enables precise segmentation of diverse historical maps while drastically reducing the need for manual annotations, advancing automated processing and analysis in the field. Our implementation is publicly available at: https://github.com/RafaelSterzinger/few-shot-map-segmentation.
URLs: https://github.com/RafaelSterzinger/few-shot-map-segmentation.
Authors: Weitao Tang, Johann Vargas-Calixto, Nasim Katebi, Robert Galinsky, Gari D. Clifford, Faezeh Marzbanrad
Abstract: Fetal sleep is a relatively underexplored yet vital aspect of prenatal neurodevelopment. Understanding fetal sleep patterns could provide insights into early brain maturation and help clinicians detect signs of neurological compromise that arise due to fetal hypoxia or fetal growth restriction. This review synthesizes over eight decades of research on the physiological characteristics, ontogeny, and regulation of fetal sleep. We compare sleep-state patterns in humans and large animal models, highlighting species-specific differences and the presence of sleep-state analogs. We review both invasive techniques in animals and non-invasive modalities in humans. Computational methods for sleep-state classification are also examined, including rule-based approaches (with and without clustering-based preprocessing) and state-of-the-art deep learning techniques. Finally, we discuss how intrauterine conditions such as hypoxia and fetal growth restriction can disrupt fetal sleep. This review provides a comprehensive foundation for the development of objective, multimodal, and non-invasive fetal sleep monitoring technologies to support early diagnosis and intervention in prenatal care.
Authors: Archisman Ghosh, Satwik Kundu, Swaroop Ghosh
Abstract: Quantum Machine Learning (QML) integrates quantum computing with classical machine learning, primarily to solve classification, regression and generative tasks. However, its rapid development raises critical security challenges in the Noisy Intermediate-Scale Quantum (NISQ) era. This chapter examines adversarial threats unique to QML systems, focusing on vulnerabilities in cloud-based deployments, hybrid architectures, and quantum generative models. Key attack vectors include model stealing via transpilation or output extraction, data poisoning through quantum-specific perturbations, reverse engineering of proprietary variational quantum circuits, and backdoor attacks. Adversaries exploit noise-prone quantum hardware and insufficiently secured QML-as-a-Service (QMLaaS) workflows to compromise model integrity, ownership, and functionality. Defense mechanisms leverage quantum properties to counter these threats. Noise signatures from training hardware act as non-invasive watermarks, while hardware-aware obfuscation techniques and ensemble strategies disrupt cloning attempts. Emerging solutions also adapt classical adversarial training and differential privacy to quantum settings, addressing vulnerabilities in quantum neural networks and generative architectures. However, securing QML requires addressing open challenges such as balancing noise levels for reliability and security, mitigating cross-platform attacks, and developing quantum-classical trust frameworks. This chapter summarizes recent advances in attacks and defenses, offering a roadmap for researchers and practitioners to build robust, trustworthy QML systems resilient to evolving adversarial landscapes.
Authors: Quan Xiao, Debarun Bhattacharjya, Balaji Ganesan, Radu Marinescu, Katsiaryna Mirylenka, Nhan H Pham, Michael Glass, Junkyu Lee
Abstract: Estimating the confidence of large language model (LLM) outputs is essential for real-world applications requiring high user trust. Black-box uncertainty quantification (UQ) methods, relying solely on model API access, have gained popularity due to their practical benefits. In this paper, we examine the implicit assumption behind several UQ methods, which use generation consistency as a proxy for confidence, an idea we formalize as the consistency hypothesis. We introduce three mathematical statements with corresponding statistical tests to capture variations of this hypothesis and metrics to evaluate LLM output conformity across tasks. Our empirical investigation, spanning 8 benchmark datasets and 3 tasks (question answering, text summarization, and text-to-SQL), highlights the prevalence of the hypothesis under different settings. Among the statements, we highlight the `Sim-Any' hypothesis as the most actionable, and demonstrate how it can be leveraged by proposing data-free black-box UQ methods that aggregate similarities between generations for confidence estimation. These approaches can outperform the closest baselines, showcasing the practical value of the empirically observed consistency hypothesis.
Authors: Ekaterina Redekop, Mara Pleasure, Zichen Wang, Kimberly Flores, Anthony Sisk, William Speier, Corey W. Arnold
Abstract: The rapid growth of digital pathology and advances in self-supervised deep learning have enabled the development of foundational models for various pathology tasks across diverse diseases. While multimodal approaches integrating diverse data sources have emerged, a critical gap remains in the comprehensive integration of whole-slide images (WSIs) with spatial transcriptomics (ST), which is crucial for capturing critical molecular heterogeneity beyond standard hematoxylin & eosin (H&E) staining. We introduce SPADE, a foundation model that integrates histopathology with ST data to guide image representation learning within a unified framework, in effect creating an ST-informed latent space. SPADE leverages a mixture-of-data experts technique, where experts, created via two-stage feature-space clustering, use contrastive learning to learn representations of co-registered WSI patches and gene expression profiles. Pre-trained on the comprehensive HEST-1k dataset, SPADE is evaluated on 14 downstream tasks, demonstrating significantly superior few-shot performance compared to baseline models, highlighting the benefits of integrating morphological and molecular information into one latent space.
Authors: Fabian Perez, Sara Rojas, Carlos Hinojosa, Hoover Rueda-Chac\'on, Bernard Ghanem
Abstract: Neural Radiance Field (NeRF)-based segmentation methods focus on object semantics and rely solely on RGB data, lacking intrinsic material properties. This limitation restricts accurate material perception, which is crucial for robotics, augmented reality, simulation, and other applications. We introduce UnMix-NeRF, a framework that integrates spectral unmixing into NeRF, enabling joint hyperspectral novel view synthesis and unsupervised material segmentation. Our method models spectral reflectance via diffuse and specular components, where a learned dictionary of global endmembers represents pure material signatures, and per-point abundances capture their distribution. For material segmentation, we use spectral signature predictions along learned endmembers, allowing unsupervised material clustering. Additionally, UnMix-NeRF enables scene editing by modifying learned endmember dictionaries for flexible material-based appearance manipulation. Extensive experiments validate our approach, demonstrating superior spectral reconstruction and material segmentation to existing methods. Project page: https://www.factral.co/UnMix-NeRF.
Authors: Edward Chen, Sang T. Truong, Natalie Dullerud, Sanmi Koyejo, Carlos Guestrin
Abstract: High-stakes decision-making involves navigating multiple competing objectives with expensive evaluations. For instance, in brachytherapy, clinicians must balance maximizing tumor coverage (e.g., an aspirational target or soft bound of >95% coverage) against strict organ dose limits (e.g., a non-negotiable hard bound of <601 cGy to the bladder), with each plan evaluation being resource-intensive. Selecting Pareto-optimal solutions that match implicit preferences is challenging, as exhaustive Pareto frontier exploration is computationally and cognitively prohibitive, necessitating interactive frameworks to guide users. While decision-makers (DMs) often possess domain knowledge to narrow the search via such soft-hard bounds, current methods often lack systematic approaches to iteratively refine these multi-faceted preference structures. Critically, DMs must trust their final decision, confident they haven't missed superior alternatives; this trust is paramount in high-consequence scenarios. We present Active-MoSH, an interactive local-global framework designed for this process. Its local component integrates soft-hard bounds with probabilistic preference learning, maintaining distributions over DM preferences and bounds for adaptive Pareto subset refinement. This is guided by an active sampling strategy optimizing exploration-exploitation while minimizing cognitive burden. To build DM trust, Active-MoSH's global component, T-MoSH, leverages multi-objective sensitivity analysis to identify potentially overlooked, high-value points beyond immediate feedback. We demonstrate Active-MoSH's performance benefits through diverse synthetic and real-world applications. A user study on AI-generated image selection further validates our hypotheses regarding the framework's ability to improve convergence, enhance DM trust, and provide expressive preference articulation, enabling more effective DMs.
Authors: Rafael Oliveira, Xuesong Wang, Kian Ming A. Chai, Edwin V. Bonilla
Abstract: We propose an extension of Thompson sampling to optimization problems over function spaces where the objective is a known functional of an unknown operator's output. We assume that functional evaluations are inexpensive, while queries to the operator (such as running a high-fidelity simulator) are costly. Our algorithm employs a sample-then-optimize approach using neural operator surrogates. This strategy avoids explicit uncertainty quantification by treating trained neural operators as approximate samples from a Gaussian process. We provide novel theoretical convergence guarantees, based on Gaussian processes in the infinite-dimensional setting, under minimal assumptions. We benchmark our method against existing baselines on functional optimization tasks involving partial differential equations and other nonlinear operator-driven phenomena, demonstrating improved sample efficiency and competitive performance.
Authors: Yifan Xue, Ruihuai Liang, Bo Yang, Xuelin Cao, Zhiwen Yu, M\'erouane Debbah, Chau Yuen
Abstract: With the rapid development of the low-altitude economy, air-ground integrated multi-access edge computing (MEC) systems are facing increasing demands for real-time and intelligent task scheduling. In such systems, task offloading and resource allocation encounter multiple challenges, including node heterogeneity, unstable communication links, and dynamic task variations. To address these issues, this paper constructs a three-layer heterogeneous MEC system architecture for low-altitude economic networks, encompassing aerial and ground users as well as edge servers. The system is systematically modeled from the perspectives of communication channels, computational costs, and constraint conditions, and the joint optimization problem of offloading decisions and resource allocation is uniformly abstracted into a graph-structured modeling task. On this basis, we propose a graph attention diffusion-based solution generator (GADSG). This method integrates the contextual awareness of graph attention networks with the solution distribution learning capability of diffusion models, enabling joint modeling and optimization of discrete offloading variables and continuous resource allocation variables within a high-dimensional latent space. We construct multiple simulation datasets with varying scales and topologies. Extensive experiments demonstrate that the proposed GADSG model significantly outperforms existing baseline methods in terms of optimization performance, robustness, and generalization across task structures, showing strong potential for efficient task scheduling in dynamic and complex low-altitude economic network environments.
Authors: Till Wenke
Abstract: Hitchhiking, a spontaneous and decentralized mode of travel, has long eluded systematic study due to its informal nature. This paper presents and analyzes the largest known structured dataset of hitchhiking rides, comprising over 63,000 entries collected over nearly two decades through platforms associated with hitchwiki.org and lately on hitchmap.com. By leveraging crowd-sourced contributions, the dataset captures key spatiotemporal and strategic aspects of hitchhiking. This work documents the dataset's origins, evolution, and community-driven maintenance, highlighting its Europe-centric distribution, seasonal patterns, and reliance on a small number of highly active contributors. Through exploratory analyses, I examine waiting times, user behavior, and comment metadata, shedding light on the lived realities of hitchhikers. While the dataset has inherent biases and limitations - such as demographic skew and unverifiable entries it offers a rare and valuable window into an alternative form of mobility. I conclude by outlining future directions for enriching the dataset and advancing research on hitchhiking as both a transportation practice and cultural phenomenon.
Authors: Weimin Xiong, Ke Wang, Yifan Song, Hanchao Liu, Sai Zhou, Wei Peng, Sujian Li
Abstract: Current evaluations of tool-integrated LLM agents typically focus on end-to-end tool-usage evaluation while neglecting their stability. This limits their real-world applicability, as various internal or external factors can cause agents to crash or behave abnormally. Our research addresses this by investigating whether agents are vulnerable to errors throughout the entire tool invocation process, including reading tool documentation, selecting tools and generating parameters, and processing the tool's response. Through extensive experiments, we observe that agents are highly susceptible to errors at each stage and agents based on open-source models are more vulnerable than those based on proprietary models. We also find that increasing the model size does not significantly improve tool invocation reasoning and may make agents more vulnerable to attacks resembling normal user instructions. This highlights the importance of evaluating agent stability and offers valuable insights for future LLM development and evaluation.
Authors: Mohamed Ahmed, Mohamed Abdelmouty, Mingyu Kim, Gunvanth Kandula, Alex Park, James C. Davis
Abstract: The advancement of Pre-Trained Language Models (PTLMs) and Large Language Models (LLMs) has led to their widespread adoption across diverse applications. Despite their success, these models remain vulnerable to attacks that exploit their inherent weaknesses to bypass safety measures. Two primary inference-phase threats are token-level and prompt-level jailbreaks. Token-level attacks embed adversarial sequences that transfer well to black-box models like GPT but leave detectable patterns and rely on gradient-based token optimization, whereas prompt-level attacks use semantically structured inputs to elicit harmful responses yet depend on iterative feedback that can be unreliable. To address the complementary limitations of these methods, we propose two hybrid approaches that integrate token- and prompt-level techniques to enhance jailbreak effectiveness across diverse PTLMs. GCG + PAIR and the newly explored GCG + WordGame hybrids were evaluated across multiple Vicuna and Llama models. GCG + PAIR consistently raised attack-success rates over its constituent techniques on undefended models; for instance, on Llama-3, its Attack Success Rate (ASR) reached 91.6%, a substantial increase from PAIR's 58.4% baseline. Meanwhile, GCG + WordGame matched the raw performance of WordGame maintaining a high ASR of over 80% even under stricter evaluators like Mistral-Sorry-Bench. Crucially, both hybrids retained transferability and reliably pierced advanced defenses such as Gradient Cuff and JBShield, which fully blocked single-mode attacks. These findings expose previously unreported vulnerabilities in current safety stacks, highlight trade-offs between raw success and defensive robustness, and underscore the need for holistic safeguards against adaptive adversaries.
Authors: Kartheek Kumar Reddy Nareddy, Sarah Ternus, Julia Niebling
Abstract: The developments in transformer encoder-decoder architectures have led to significant breakthroughs in machine translation, Automatic Speech Recognition (ASR), and instruction-based chat machines, among other applications. The pre-trained models were trained on vast amounts of generic data over a few epochs (fewer than five in most cases), resulting in their strong generalization capabilities. Nevertheless, the performance of these models does suffer when applied to niche domains like transcribing pilot speech in the cockpit, which involves a lot of specific vocabulary and multilingual conversations. This paper investigates and improves the transcription accuracy of cockpit conversations with Whisper models. We have collected around 85 minutes of cockpit simulator recordings and 130 minutes of interview recordings with pilots and manually labeled them. The speakers are middle aged men speaking both German and English. To improve the accuracy of transcriptions, we propose multiple normalization schemes to refine the transcripts and improve Word Error Rate (WER). We then employ fine-tuning to enhance ASR performance, utilizing performance-efficient fine-tuning with Low-Rank Adaptation (LoRA). Hereby, WER decreased from 68.49 \% (pretrained whisper Large model without normalization baseline) to 26.26\% (finetuned whisper Large model with the proposed normalization scheme).
Authors: Hyeongji Kim, Stine Hansen, Michael Kampffmeyer
Abstract: Common prototype-based medical image few-shot segmentation (FSS) methods model foreground and background classes using class-specific prototypes. However, given the high variability of the background, a more promising direction is to focus solely on foreground modeling, treating the background as an anomaly -- an approach introduced by ADNet. Yet, ADNet faces three key limitations: dependence on a single prototype per class, a focus on binary classification, and fixed thresholds that fail to adapt to patient and organ variability. To address these shortcomings, we propose the Tied Prototype Model (TPM), a principled reformulation of ADNet with tied prototype locations for foreground and background distributions. Building on its probabilistic foundation, TPM naturally extends to multiple prototypes and multi-class segmentation while effectively separating non-typical background features. Notably, both extensions lead to improved segmentation accuracy. Finally, we leverage naturally occurring class priors to define an ideal target for adaptive thresholds, boosting segmentation performance. Taken together, TPM provides a fresh perspective on prototype-based FSS for medical image segmentation. The code can be found at https://github.com/hjk92g/TPM-FSS.
Authors: David Demitri Africa
Abstract: I implement a procedure to isolate and interpret the sub-network (or "circuit") responsible for subject-verb agreement in GPT-2 Small. In this study, the model is given prompts where the subject is either singular (e.g. "Alice") or plural (e.g. "Alice and Bob"), and the task is to correctly predict the appropriate verb form ("walks" for singular subjects, "walk" for plural subjects). Using a series of techniques-including performance verification automatic circuit discovery via direct path patching, and direct logit attribution- I isolate a candidate circuit that contributes significantly to the model's correct verb conjugation. The results suggest that only a small fraction of the network's component-token pairs is needed to achieve near-model performance on the base task but substantially more for more complex settings.
Authors: Amirmohammad Izadi, Mohammad Ali Banayeeanzade, Fatemeh Askari, Ali Rahimiakbar, Mohammad Mahdi Vahedi, Hosein Hasani, Mahdieh Soleymani Baghshah
Abstract: Despite progress in Vision-Language Models (VLMs), their capacity for visual reasoning is often limited by the \textit{binding problem}: the failure to reliably associate perceptual features with their correct visual referents. This limitation underlies persistent errors in tasks such as counting, visual search, scene description, and spatial relationship understanding. A key factor is that current VLMs process visual features largely in parallel, lacking mechanisms for spatially grounded, serial attention. This paper introduces a simple yet effective intervention: augmenting visual inputs with low-level spatial structures (e.g., horizontal lines) and pairing this with a textual prompt that encourages sequential, spatially-aware parsing. We empirically demonstrate substantial performance improvements across core visual reasoning tasks. Specifically, our method improves GPT-4o visual search accuracy by 25.00%, increases counting accuracy by 26.83%, reduces edit distance error in scene description by 0.32, and enhances performance on spatial relationship tasks by 9.50% on a a 2D synthetic dataset. Furthermore, we find that the visual modification is essential for these gains; purely textual strategies, including Chain-of-Thought prompting, are insufficient and can even degrade performance. Our method enhances binding only with a single-query inference, underscoring the importance of visual input design over purely linguistically-based approaches. These findings suggest that low-level visual structuring is a powerful and underexplored direction for improving compositional visual reasoning and could serve as a general strategy for enhancing VLM performance on spatially grounded tasks.
Authors: Bavo Lesy, Siemen Herremans, Robin Kerstens, Jan Steckel, Walter Daems, Siegfried Mercelis, Ali Anwar
Abstract: The transport industry has recently shown significant interest in unmanned surface vehicles (USVs), specifically for port and inland waterway transport. These systems can improve operational efficiency and safety, which is especially relevant in the European Union, where initiatives such as the Green Deal are driving a shift towards increased use of inland waterways. At the same time, a shortage of qualified personnel is accelerating the adoption of autonomous solutions. However, there is a notable lack of open-source, high-fidelity simulation frameworks and datasets for developing and evaluating such solutions. To address these challenges, we introduce AirSim For Surface Vehicles (ASVSim), an open-source simulation framework specifically designed for autonomous shipping research in inland and port environments. The framework combines simulated vessel dynamics with marine sensor simulation capabilities, including radar and camera systems and supports the generation of synthetic datasets for training computer vision models and reinforcement learning agents. Built upon Cosys-AirSim, ASVSim provides a comprehensive platform for developing autonomous navigation algorithms and generating synthetic datasets. The simulator supports research of both traditional control methods and deep learning-based approaches. Through limited experiments, we demonstrate the potential of the simulator in these research areas. ASVSim is provided as an open-source project under the MIT license, making autonomous navigation research accessible to a larger part of the ocean engineering community.
Authors: Gurjeet Sangra Singh, Maciej Falkiewicz, Alexandros Kalousis
Abstract: Physics phenomena are often described by ordinary and/or partial differential equations (ODEs/PDEs), and solved analytically or numerically. Unfortunately, many real-world systems are described only approximately with missing or unknown terms in the equations. This makes the distribution of the physics model differ from the true data-generating process (DGP). Using limited and unpaired data between DGP observations and the imperfect model simulations, we investigate this particular setting by completing the known-physics model, combining theory-driven models and data-driven to describe the shifted distribution involved in the DGP. We present a novel hybrid generative model approach combining deep grey-box modelling with Optimal Transport (OT) methods to enhance incomplete physics models. Our method implements OT maps in data space while maintaining minimal source distribution distortion, demonstrating superior performance in resolving the unpaired problem and ensuring correct usage of physics parameters. Unlike black-box alternatives, our approach leverages physics-based inductive biases to accurately learn system dynamics while preserving interpretability through its domain knowledge foundation. Experimental results validate our method's effectiveness in both generation tasks and model transparency, offering detailed insights into learned physics dynamics.
Authors: Rong Ma, Xi Li, Jingyuan Hu, Bin Yu
Abstract: Single-cell sequencing is revolutionizing biology by enabling detailed investigations of cell-state transitions. Many biological processes unfold along continuous trajectories, yet it remains challenging to extract smooth, low-dimensional representations from inherently noisy, high-dimensional single-cell data. Neighbor embedding (NE) algorithms, such as t-SNE and UMAP, are widely used to embed high-dimensional single-cell data into low dimensions. But they often introduce undesirable distortions, resulting in misleading interpretations. Existing evaluation methods for NE algorithms primarily focus on separating discrete cell types rather than capturing continuous cell-state transitions, while dynamic modeling approaches rely on strong assumptions about cellular processes and specialized data. To address these challenges, we build on the Predictability-Computability-Stability (PCS) framework for reliable and reproducible data-driven discoveries. First, we systematically evaluate popular NE algorithms through empirical analysis, simulation, and theory, and reveal their key shortcomings, such as artifacts and instability. We then introduce NESS, a principled and interpretable machine learning approach to improve NE representations by leveraging algorithmic stability and to enable robust inference of smooth biological structures. NESS offers useful concepts, quantitative stability metrics, and efficient computational workflows to uncover developmental trajectories and cell-state transitions in single-cell data. Finally, we apply NESS to six single-cell datasets, spanning pluripotent stem cell differentiation, organoid development, and multiple tissue-specific lineage trajectories. Across these diverse contexts, NESS consistently yields useful biological insights, such as identification of transitional and stable cell states and quantification of transcriptional dynamics during development.
Authors: Hanti Lin
Abstract: The integration of the history and philosophy of statistics was initiated at least by Hacking (1965) and advanced by Mayo (1996), but it has not received sustained follow-up. Yet such integration is more urgent than ever, as the recent success of artificial intelligence has been driven largely by machine learning -- a field historically developed alongside statistics. Today, the boundary between statistics and machine learning is increasingly blurred. What we now need is integration, twice over: of history and philosophy, and of the field they engage -- statistics and machine learning. I present a case study of a philosophical idea in machine learning (and in formal epistemology) whose root can be traced back to an often under-appreciated insight in Neyman and Pearson's 1936 work (a follow-up to their 1933 classic). This leads to the articulation of a foundational assumption -- largely implicit in, but shared by, the practices of frequentist statistics and machine learning -- which I call achievabilism. Another integration also emerges at the level of methodology, combining two ends of the philosophy of science spectrum: history and philosophy of science on the one hand, and formal epistemology on the other hand.
Authors: Matthias Tsch\"ope, Vitor Fortes Rey, Sogo Pierre Sanon, Paul Lukowicz, Nikolaos Palaiodimopoulos, Maximilian Kiefer-Emmanouilidis
Abstract: Understanding the impact of small quantum gate perturbations, which are common in quantum digital devices but absent in classical computers, is crucial for identifying potential advantages in quantum machine learning. While these perturbations are typically seen as detrimental to quantum computation, they can actually enhance performance by serving as a natural source of data augmentation. Additionally, they can often be efficiently simulated on classical hardware, enabling quantum-inspired approaches to improve classical machine learning methods. In this paper, we investigate random Bloch sphere rotations, which are fundamental SU(2) transformations, as a simple yet effective quantum-inspired data augmentation technique. Unlike conventional augmentations such as flipping, rotating, or cropping, quantum transformations lack intuitive spatial interpretations, making their application to tasks like image classification less straightforward. While common quantum augmentation methods rely on applying quantum models or trainable quanvolutional layers to classical datasets, we focus on the direct application of small-angle Bloch rotations and their effect on classical data. Using the large-scale ImageNet dataset, we demonstrate that our quantum-inspired augmentation method improves image classification performance, increasing Top-1 accuracy by 3%, Top-5 accuracy by 2.5%, and the F$_1$ score from 8% to 12% compared to standard classical augmentation methods. Finally, we examine the use of stronger unitary augmentations. Although these transformations preserve information in principle, they result in visually unrecognizable images with potential applications for privacy computations. However, we show that our augmentation approach and simple SU(2) transformations do not enhance differential privacy and discuss the implications of this limitation.
Authors: Samy Badreddine, Emile van Krieken, Luciano Serafini
Abstract: Many Knowledge Graph Completion (KGC) models, despite using powerful encoders, rely on a simple vector-matrix multiplication to score queries against candidate object entities. When the number of entities is larger than the model's embedding dimension, which in practical scenarios is often by several orders of magnitude, we have a linear output layer with a rank bottleneck. Such bottlenecked layers limit model expressivity. We investigate both theoretically and empirically how rank bottlenecks affect KGC models. We find that, by limiting the set of feasible predictions, rank bottlenecks hurt ranking accuracy and the distribution fidelity of scores. Inspired by the language modelling literature, we propose KGE-MoS, a mixture-based output layer to break rank bottlenecks in many KGC models. Our experiments on four datasets show that KGE-MoS improves performance and probabilistic fit of KGC models for a low parameter cost.
Authors: Klara M. Gutekunst, Dominik D\"urrschnabel, Johannes Hirth, Gerd Stumme
Abstract: The vast growth of data has rendered traditional manual inspection infeasible, necessitating the adoption of computational methods for efficient data exploration. Topic modeling has emerged as a powerful tool for analyzing large-scale textual datasets, enabling the extraction of latent semantic structures. However, existing methods for topic modeling often struggle to provide interpretable representations that facilitate deeper insights into data structure and content. In this paper, we propose FAT-CAT, an approach based on Formal Concept Analysis (FCA) to enhance meaningful topic aggregation and visualization of discovered topics. Our approach can handle diverse topics and file types -- grouped by directories -- to construct a concept lattice that offers a structured, hierarchical representation of their topic distribution. In a case study on the ETYNTKE dataset, we evaluate the effectiveness of our approach against other representation methods to demonstrate that FCA-based aggregation provides more meaningful and interpretable insights into dataset composition than existing topic modeling techniques.
Authors: Osama Ahmed, Felix Tennie, Luca Magri
Abstract: We show that recurrent quantum reservoir computers (QRCs) and their recurrence-free architectures (RF-QRCs) are robust tools for learning and forecasting chaotic dynamics from time-series data. First, we formulate and interpret quantum reservoir computers as coupled dynamical systems, where the reservoir acts as a response system driven by training data; in other words, quantum reservoir computers are generalized-synchronization (GS) systems. Second, we show that quantum reservoir computers can learn chaotic dynamics and their invariant properties, such as Lyapunov spectra, attractor dimensions, and geometric properties such as the covariant Lyapunov vectors. This analysis is enabled by deriving the Jacobian of the quantum reservoir update. Third, by leveraging tools from generalized synchronization, we provide a method for designing robust quantum reservoir computers. We propose the criterion $GS=ESP$: GS implies the echo state property (ESP), and vice versa. We analytically show that RF-QRCs, by design, fulfill $GS=ESP$. Finally, we analyze the effect of simulated noise. We find that dissipation from noise enhances the robustness of quantum reservoir computers. Numerical verifications on systems of different dimensions support our conclusions. This work opens opportunities for designing robust quantum machines for chaotic time series forecasting on near-term quantum hardware.
Authors: Yannick Werner, Akash Malemath, Mengxi Liu, Vitor Fortes Rey, Nikolaos Palaiodimopoulos, Paul Lukowicz, Maximilian Kiefer-Emmanouilidis
Abstract: Kolmogorov Arnold Networks (KANs), built upon the Kolmogorov Arnold representation theorem (KAR), have demonstrated promising capabilities in expressing complex functions with fewer neurons. This is achieved by implementing learnable parameters on the edges instead of on the nodes, unlike traditional networks such as Multi-Layer Perceptrons (MLPs). However, KANs potential in quantum machine learning has not yet been well explored. In this work, we present an implementation of these KAN architectures in both hybrid and fully quantum forms using a Quantum Circuit Born Machine (QCBM). We adapt the KAN transfer using pre-trained residual functions, thereby exploiting the representational power of parametrized quantum circuits. In the hybrid model we combine classical KAN components with quantum subroutines, while the fully quantum version the entire architecture of the residual function is translated to a quantum model. We demonstrate the feasibility, interpretability and performance of the proposed Quantum KAN (QuKAN) architecture.
Authors: Xiang Li, Garrett Wen, Weiqing He, Jiayuan Wu, Qi Long, Weijie J. Su
Abstract: Text watermarks in large language models (LLMs) are an increasingly important tool for detecting synthetic text and distinguishing human-written content from LLM-generated text. While most existing studies focus on determining whether entire texts are watermarked, many real-world scenarios involve mixed-source texts, which blend human-written and watermarked content. In this paper, we address the problem of optimally estimating the watermark proportion in mixed-source texts. We cast this problem as estimating the proportion parameter in a mixture model based on \emph{pivotal statistics}. First, we show that this parameter is not even identifiable in certain watermarking schemes, let alone consistently estimable. In stark contrast, for watermarking methods that employ continuous pivotal statistics for detection, we demonstrate that the proportion parameter is identifiable under mild conditions. We propose efficient estimators for this class of methods, which include several popular unbiased watermarks as examples, and derive minimax lower bounds for any measurable estimator based on pivotal statistics, showing that our estimators achieve these lower bounds. Through evaluations on both synthetic data and mixed-source text generated by open-source models, we demonstrate that our proposed estimators consistently achieve high estimation accuracy.
Authors: Nouf Almesafri, Hector Figueiredo, Miguel Arana-Catania
Abstract: This study investigates the performance of the two most relevant computer vision deep learning architectures, Convolutional Neural Network and Vision Transformer, for event-based cameras. These cameras capture scene changes, unlike traditional frame-based cameras with capture static images, and are particularly suited for dynamic environments such as UAVs and autonomous vehicles. The deep learning models studied in this work are ResNet34 and ViT B16, fine-tuned on the GEN1 event-based dataset. The research evaluates and compares these models under both standard conditions and in the presence of simulated noise. Initial evaluations on the clean GEN1 dataset reveal that ResNet34 and ViT B16 achieve accuracies of 88% and 86%, respectively, with ResNet34 showing a slight advantage in classification accuracy. However, the ViT B16 model demonstrates notable robustness, particularly given its pre-training on a smaller dataset. Although this study focuses on ground-based vehicle classification, the methodologies and findings hold significant promise for adaptation to UAV contexts, including aerial object classification and event-based vision systems for aviation-related tasks.
Authors: Yang Yang, Yunpeng Li, George Sung, Shao-Fu Shih, Craig Dooley, Alessio Centazzo, Ramanan Rajeswaran
Abstract: Token-based language modeling is a prominent approach for speech generation, where tokens are obtained by quantizing features from self-supervised learning (SSL) models and extracting codes from neural speech codecs, generally referred to as semantic tokens and acoustic tokens. These tokens are often modeled autoregressively, with the inference speed being constrained by the token rate. In this work, we propose DiffSoundStream, a solution that improves the efficiency of speech tokenization in non-streaming scenarios through two techniques: (1) conditioning the neural codec on semantic tokens to minimize redundancy between semantic and acoustic tokens, and (2) leveraging latent diffusion models to synthesize high-quality waveforms from semantic and coarse-level acoustic tokens. Experiments show that at 50 tokens per second, DiffSoundStream achieves speech quality on par with a standard SoundStream model operating at twice the token rate. Additionally, we achieve step-size distillation using just four diffusion sampling steps with only a minor quality loss.
Authors: Bingchen Zhao, Despoina Magka, Minqi Jiang, Xian Li, Roberta Raileanu, Tatiana Shavrina, Jean-Christophe Gagnon-Audet, Kelvin Niu, Shagun Sodhani, Michael Shvartsman, Andrei Lupu, Alisia Lupidi, Edan Toledo, Karen Hambardzumyan, Martin Josifoski, Thomas Foster, Lucia Cipolina-Kun, Abhishek Charnalia, Derek Dunfield, Alexander H. Miller, Oisin Mac Aodha, Jakob Foerster, Yoram Bachrach
Abstract: Rapid advancements in large language models (LLMs) have the potential to assist in scientific progress. A critical capability toward this endeavor is the ability to reproduce existing work. To evaluate the ability of AI agents to reproduce results in an active research area, we introduce the Automated LLM Speedrunning Benchmark, leveraging the research community contributions on the NanoGPT speedrun, a competition to train a GPT-2 model in the shortest time. Each of the 19 speedrun tasks provides the agent with the previous records training script, optionally paired with one of three hint formats, ranging from pseudocode to paper-like descriptions of the new records improvements. Records execute quickly by design and speedrun improvements encompass diverse code-level changes, ranging from high-level algorithmic advancements to hardware-aware optimizations. These features make the benchmark both accessible and realistic for the frontier problem of improving LLM training. We find that recent reasoning LLMs combined with SoTA scaffolds struggle to reimplement already-known innovations in our benchmark, even when given detailed hints. Our benchmark thus provides a simple, non-saturated measure of an LLMs ability to automate scientific reproduction, a necessary (but not sufficient) skill for an autonomous research agent.
Authors: David Holzm\"uller, Max Sch\"olpple
Abstract: While the theory of deep learning has made some progress in recent years, much of it is limited to the ReLU activation function. In particular, while the neural tangent kernel (NTK) and neural network Gaussian process kernel (NNGP) have given theoreticians tractable limiting cases of fully connected neural networks, their properties for most activation functions except for powers of the ReLU function are poorly understood. Our main contribution is to provide a more general characterization of the RKHS of these kernels for typical activation functions whose only non-smoothness is at zero, such as SELU, ELU, or LeakyReLU. Our analysis also covers a broad set of special cases such as missing biases, two-layer networks, or polynomial activations. Our results show that a broad class of not infinitely smooth activations generate equivalent RKHSs at different network depths, while polynomial activations generate non-equivalent RKHSs. Finally, we derive results for the smoothness of NNGP sample paths, characterizing the smoothness of infinitely wide neural networks at initialization.
Authors: {\L}ukasz Struski, Tomasz Danel, Marek \'Smieja, Jacek Tabor, Bartosz Zieli\'nski
Abstract: Recent years have seen a surge in research on deep interpretable neural networks with decision trees as one of the most commonly incorporated tools. There are at least three advantages of using decision trees over logistic regression classification models: they are easy to interpret since they are based on binary decisions, they can make decisions faster, and they provide a hierarchy of classes. However, one of the well-known drawbacks of decision trees, as compared to decision graphs, is that decision trees cannot reuse the decision nodes. Nevertheless, decision graphs were not commonly used in deep learning due to the lack of efficient gradient-based training techniques. In this paper, we fill this gap and provide a general paradigm based on Markov processes, which allows for efficient training of the special type of decision graphs, which we call Self-Organizing Neural Graphs (SONG). We provide an extensive theoretical study of SONG, complemented by experiments conducted on Letter, Connect4, MNIST, CIFAR, and TinyImageNet datasets, showing that our method performs on par or better than existing decision models.
Authors: Zhilin Zhao, Longbing Cao, Yixuan Zhang, Kun-Yu Lin, Wei-Shi Zheng
Abstract: Out-of-distribution (OOD) detection is critical for identifying test samples that deviate from in-distribution (ID) data, ensuring network robustness and reliability. This paper presents a flexible framework for OOD knowledge distillation that extracts OOD-sensitive information from a network to develop a binary classifier capable of distinguishing between ID and OOD samples in both scenarios, with and without access to training ID data. To accomplish this, we introduce Confidence Amendment (CA), an innovative methodology that transforms an OOD sample into an ID one while progressively amending prediction confidence derived from the network to enhance OOD sensitivity. This approach enables the simultaneous synthesis of both ID and OOD samples, each accompanied by an adjusted prediction confidence, thereby facilitating the training of a binary classifier sensitive to OOD. Theoretical analysis provides bounds on the generalization error of the binary classifier, demonstrating the pivotal role of confidence amendment in enhancing OOD sensitivity. Extensive experiments spanning various datasets and network architectures confirm the efficacy of the proposed method in detecting OOD samples.
Authors: Riccardo Zaccone, Sai Praneeth Karimireddy, Carlo Masone, Marco Ciccone
Abstract: Federated Learning (FL) has emerged as the state-of-the-art approach for learning from decentralized data in privacy-constrained scenarios.However, system and statistical challenges hinder its real-world applicability, requiring efficient learning from edge devices and robustness to data heterogeneity. Despite significant research efforts, existing approaches often degrade severely due to the joint effect of heterogeneity and partial client participation. In particular, while momentum appears as a promising approach for overcoming statistical heterogeneity, in current approaches its update is biased towards the most recently sampled clients. As we show in this work, this is the reason why it fails to outperform FedAvg, preventing its effective use in real-world large-scale scenarios. In this work, we propose a novel Generalized Heavy-Ball Momentum (GHBM) and theoretically prove it enables convergence under unbounded data heterogeneity in cyclic partial participation, thereby advancing the understanding of momentum's effectiveness in FL. We then introduce adaptive and communication-efficient variants of GHBM that match the communication complexity of FedAvg in settings where clients can be stateful. Extensive experiments on vision and language tasks confirm our theoretical findings, demonstrating that GHBM substantially improves state-of-the-art performance under random uniform client sampling, particularly in large-scale settings with high data heterogeneity and low client participation. Code is available at https://rickzack.github.io/GHBM.
Authors: Anna M\'esz\'aros, Julian F. Schumann, Javier Alonso-Mora, Arkady Zgonnikov, Jens Kober
Abstract: The estimation of probability density functions is a fundamental problem in science and engineering. However, common methods such as kernel density estimation (KDE) have been demonstrated to lack robustness, while more complex methods have not been evaluated in multi-modal estimation problems. In this paper, we present ROME (RObust Multi-modal Estimator), a non-parametric approach for density estimation which addresses the challenge of estimating multi-modal, non-normal, and highly correlated distributions. ROME utilizes clustering to segment a multi-modal set of samples into multiple uni-modal ones and then combines simple KDE estimates obtained for individual clusters in a single multi-modal estimate. We compared our approach to state-of-the-art methods for density estimation as well as ablations of ROME, showing that it not only outperforms established methods but is also more robust to a variety of distributions. Our results demonstrate that ROME can overcome the issues of over-fitting and over-smoothing exhibited by other estimators.
Authors: Hugues Van Assel, C\'edric Vincent-Cuaz, Nicolas Courty, R\'emi Flamary, Pascal Frossard, Titouan Vayer
Abstract: Unsupervised learning aims to capture the underlying structure of potentially large and high-dimensional datasets. Traditionally, this involves using dimensionality reduction (DR) methods to project data onto lower-dimensional spaces or organizing points into meaningful clusters (clustering). In this work, we revisit these approaches under the lens of optimal transport and exhibit relationships with the Gromov-Wasserstein problem. This unveils a new general framework, called distributional reduction, that recovers DR and clustering as special cases and allows addressing them jointly within a single optimization problem. We empirically demonstrate its relevance to the identification of low-dimensional prototypes representing data at different scales, across multiple image and genomic datasets.
Authors: Andrea Giuseppe Di Francesco, Francesco Caso, Maria Sofia Bucarelli, Fabrizio Silvestri
Abstract: The message-passing mechanism underlying Graph Neural Networks (GNNs) is not naturally suited for heterophilic datasets, where adjacent nodes often have different labels. Most solutions to this problem remain confined to the task of node classification. In this article, we focus on the valuable task of link prediction under heterophily, an interesting problem for recommendation systems, social network analysis, and other applications. GNNs like GRAFF have improved node classification under heterophily by incorporating physics biases in the architecture. Similarly, we propose GRAFF-LP, an extension of GRAFF for link prediction. We show that GRAFF-LP effectively discriminates existing from non-existing edges by learning implicitly to separate the edge gradients. Based on this information, we propose a new readout function inspired by physics. Remarkably, this new function not only enhances the performance of GRAFF-LP but also improves that of other baseline models, leading us to reconsider how every link prediction experiment has been conducted so far. Finally, we provide evidence that even simple GNNs did not experience greater difficulty in predicting heterophilic links compared to homophilic ones. This leads us to believe in the necessity for heterophily measures specifically tailored for link prediction, distinct from those used in node classification. The code and appendix are available at https://github.com/difra100/Link_Prediction_with_PIGNN_IJCNN.
URLs: https://github.com/difra100/Link_Prediction_with_PIGNN_IJCNN.
Authors: Duke Nguyen, Du Yin, Aditya Joshi, Flora Salim
Abstract: Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods used a subset of combinations of component functions and weight matrices within the random feature paradigm. We identify the need for a systematic comparison of different combinations of weight matrices and component functions for attention learning in Transformer. Hence, we introduce Spectraformer, a unified framework for approximating and learning the kernel function in the attention mechanism of the Transformer. Our empirical results demonstrate, for the first time, that a random feature-based approach can achieve performance comparable to top-performing sparse and low-rank methods on the challenging Long Range Arena benchmark. Thus, we establish a new state-of-the-art for random feature-based efficient Transformers. The framework also produces many variants that offer different advantages in accuracy, training time, and memory consumption. Our code is available at: https://github.com/cruiseresearchgroup/spectraformer .
Authors: Mirza Farhan Bin Tarek, Raphael Poulain, Rahmatollah Beheshti
Abstract: Among various aspects of ensuring the responsible design of AI tools for healthcare applications, addressing fairness concerns has been a key focus area. Specifically, given the wide spread of electronic health record (EHR) data and their huge potential to inform a wide range of clinical decision support tasks, improving fairness in this category of health AI tools is of key importance. While such a broad problem (mitigating fairness in EHR-based AI models) has been tackled using various methods, task- and model-agnostic methods are noticeably rare. In this study, we aimed to target this gap by presenting a new pipeline that generates synthetic EHR data, which is not only consistent with (faithful to) the real EHR data but also can reduce the fairness concerns (defined by the end-user) in the downstream tasks, when combined with the real data. We demonstrate the effectiveness of our proposed pipeline across various downstream tasks and two different EHR datasets. Our proposed pipeline can add a widely applicable and complementary tool to the existing toolbox of methods to address fairness in health AI applications, such as those modifying the design of a downstream model. The codebase for our project is available at https://github.com/healthylaife/FairSynth
Authors: Bryan Wilder, Pim Welle
Abstract: Many social programs attempt to allocate scarce resources to people with the greatest need. Indeed, public services increasingly use algorithmic risk assessments motivated by this goal. However, targeting the highest-need recipients often conflicts with attempting to evaluate the causal effect of the program as a whole, as the best evaluations would be obtained by randomizing the allocation. We propose a framework to design randomized allocation rules which optimally balance targeting high-need individuals with learning treatment effects, presenting policymakers with a Pareto frontier between the two goals. We give sample complexity guarantees for the policy learning problem and provide a computationally efficient strategy to implement it. We then collaborate with the human services department of Allegheny County, Pennsylvania to evaluate our methods on data from real service delivery settings. Optimized policies can substantially mitigate the tradeoff between learning and targeting. For example, it is often possible to obtain 90% of the optimal utility in targeting high-need individuals while ensuring that the average treatment effect can be estimated with less than 2 times the samples that a randomized controlled trial would require. Mechanisms for targeting public services often focus on measuring need as accurately as possible. However, our results suggest that algorithmic systems in public services can be most impactful if they incorporate program evaluation as an explicit goal alongside targeting.
Authors: Chen Peng, Di Zhang, Urbashi Mitra
Abstract: In this paper, the causal bandit problem is investigated, with the objective of maximizing the long-term reward by selecting an optimal sequence of interventions on nodes in an unknown causal graph. It is assumed that both the causal topology and the distribution of interventions are unknown. First, based on the difference between the two types of graph identification errors (false positives and negatives), a causal graph learning method is proposed. Numerical results suggest that this method has a much lower sample complexity relative to the prior art by learning sub-graphs. However, we note that a sample complexity analysis for the new algorithm has not been undertaken, as of yet. Under the assumption of minimum-mean squared error weight estimation, a new uncertainty bound tailored to the causal bandit problem is derived. This uncertainty bound drives an upper confidence bound-based intervention selection to optimize the reward. Further, we consider a particular instance of non-stationary bandits wherein both the causal topology and interventional distributions can change. Our solution is the design of a sub-graph change detection mechanism that requires a modest number of samples. Numerical results compare the new methodology to existing schemes and show a substantial performance improvement in stationary and non-stationary settings. Averaged over 100 randomly generated causal bandits, the proposed scheme takes significantly fewer samples to learn the causal structure and achieves a reward gain of 85% compared to existing approaches.
Authors: Junxiong Wang, Daniele Paliotta, Avner May, Alexander M. Rush, Tri Dao
Abstract: Linear RNN architectures, like Mamba, can be competitive with Transformer models in language modeling while having advantageous deployment characteristics. Given the focus on training large-scale Transformer models, we consider the challenge of converting these pretrained models for deployment. We demonstrate that it is feasible to distill large Transformers into linear RNNs by reusing the linear projection weights from attention layers with academic GPU resources. The resulting hybrid model, which incorporates a quarter of the attention layers, achieves performance comparable to the original Transformer in chat benchmarks and outperforms open-source hybrid Mamba models trained from scratch with trillions of tokens in both chat benchmarks and general benchmarks. Moreover, we introduce a hardware-aware speculative decoding algorithm that accelerates the inference speed of Mamba and hybrid models. Overall we show how, with limited computation resources, we can remove many of the original attention layers and generate from the resulting model more efficiently. Our top-performing model, distilled from Llama3-8B-Instruct, achieves a 29.61 length-controlled win rate on AlpacaEval 2 against GPT-4 and 7.35 on MT-Bench, surpassing the best 8B scale instruction-tuned linear RNN model. We also find that the distilled model has natural length extrapolation, showing almost perfect accuracy in the needle-in-a-haystack test at 20x the distillation length. Code and pre-trained checkpoints are open-sourced at https://github.com/jxiw/MambaInLlama and https://github.com/itsdaniele/speculative_mamba.
URLs: https://github.com/jxiw/MambaInLlama, https://github.com/itsdaniele/speculative_mamba.
Authors: Mouhamadou Mansour Lo, Gildas Morvan, Mathieu Rossi, Fabrice Morganti, David Mercier
Abstract: This article presents a new approach based on MiniRocket, called SelF-Rocket, for fast time series classification (TSC). Unlike existing approaches based on random convolution kernels, it dynamically selects the best couple of input representations and pooling operator during the training process. SelF-Rocket achieves state-of-the-art accuracy on the University of California Riverside (UCR) TSC benchmark datasets.
Authors: Hyunchai Jeong, Adiba Ejaz, Jin Tian, Elias Bareinboim
Abstract: Testing a hypothesized causal model against observational data is a key prerequisite for many causal inference tasks. A natural approach is to test whether the conditional independence relations (CIs) assumed in the model hold in the data. While a model can assume exponentially many CIs (with respect to the number of variables), testing all of them is both impractical and unnecessary. Causal graphs, which encode these CIs in polynomial space, give rise to local Markov properties that enable model testing with a significantly smaller subset of CIs. Model testing based on local properties requires an algorithm to list the relevant CIs. However, existing algorithms for realistic settings with hidden variables and non-parametric distributions can take exponential time to produce even a single CI constraint. In this paper, we introduce the c-component local Markov property (C-LMP) for causal graphs with hidden variables. Since C-LMP can still invoke an exponential number of CIs, we develop a polynomial delay algorithm to list these CIs in poly-time intervals. To our knowledge, this is the first algorithm that enables poly-delay testing of CIs in causal graphs with hidden variables against arbitrary data distributions. Experiments on real-world and synthetic data demonstrate the practicality of our algorithm.
Authors: Louis Serrano, Armand Kassa\"i Koupa\"i, Thomas X Wang, Pierre Erbacher, Patrick Gallinari
Abstract: Solving time-dependent parametric partial differential equations (PDEs) is challenging for data-driven methods, as these models must adapt to variations in parameters such as coefficients, forcing terms, and initial conditions. State-of-the-art neural surrogates perform adaptation through gradient-based optimization and meta-learning to implicitly encode the variety of dynamics from observations. This often comes with increased inference complexity. Inspired by the in-context learning capabilities of large language models (LLMs), we introduce Zebra, a novel generative auto-regressive transformer designed to solve parametric PDEs without requiring gradient adaptation at inference. By leveraging in-context information during both pre-training and inference, Zebra dynamically adapts to new tasks by conditioning on input sequences that incorporate context example trajectories. As a generative model, Zebra can be used to generate new trajectories and allows quantifying the uncertainty of the predictions. We evaluate Zebra across a variety of challenging PDE scenarios, demonstrating its adaptability, robustness, and superior performance compared to existing approaches.
Authors: Saqib Javed, Hieu Le, Mathieu Salzmann
Abstract: A key challenge in Domain Generalization (DG) is preventing overfitting to source domains, which can be mitigated by finding flatter minima in the loss landscape. In this work, we propose Quantization-aware Training for Domain Generalization (QT-DoG) and demonstrate that weight quantization effectively leads to flatter minima in the loss landscape, thereby enhancing domain generalization. Unlike traditional quantization methods focused on model compression, QT-DoG exploits quantization as an implicit regularizer by inducing noise in model weights, guiding the optimization process toward flatter minima that are less sensitive to perturbations and overfitting. We provide both an analytical perspective and empirical evidence demonstrating that quantization inherently encourages flatter minima, leading to better generalization across domains. Moreover, with the benefit of reducing the model size through quantization, we demonstrate that an ensemble of multiple quantized models further yields superior accuracy than the state-of-the-art DG approaches with no computational or memory overheads. Code is released at: https://saqibjaved1.github.io/QT_DoG/.
Authors: Zhen Qin, Zhaomin Wu, Bingsheng He, Shuiguang Deng
Abstract: Instruction tuning is a crucial step in improving the responsiveness of pretrained large language models (LLMs) to human instructions. Federated learning (FL) helps to exploit the use of vast private instruction data from clients, becoming popular for LLM tuning by improving data diversity. Existing federated tuning simply consumes all local data, causing excessive computational overhead and overfitting to local data, while centralized data-efficient solutions are not suitable for FL due to privacy concerns. This work presents FedHDS, a federated data-efficient instruction tuning approach, which tunes LLMs with a representative subset of edge-side data. It reduces the data redundancy at both intra- and inter-client levels without sharing raw data. Experiments with various LLMs, datasets and partitions show that FedHDS improves Rouge-L on unseen tasks by an average of 10.72% over the SOTA full-data federated instruction tuning methods, while using less than 1.5% of the data samples, improving training efficiency by up to tens of times.
Authors: Karthik Mohan, Pengyu Chen
Abstract: In this paper, we describe our systems in which the objective is to determine whether a given news article could be considered as hyperpartisan. Hyperpartisan news is news that takes an extremely polarized political standpoint with an intention of creating political divide among the public. We attempted several approaches, including n-grams, sentiment analysis, as well as sentence and document representation using pre-tained ELMo. Our best system using pre-trained ELMo with Bidirectional LSTM achieved an accuracy of 83% through 10-fold cross-validation without much hyperparameter tuning.
Authors: Zhi Sheng, Daisy Yuan, Jingtao Ding, Yong Li
Abstract: Accurate prediction of mobile traffic, i.e., network traffic from cellular base stations, is crucial for optimizing network performance and supporting urban development. However, the non-stationary nature of mobile traffic, driven by human activity and environmental changes, leads to both regular patterns and abrupt variations. Diffusion models excel in capturing such complex temporal dynamics due to their ability to capture the inherent uncertainties. Most existing approaches prioritize designing novel denoising networks but often neglect the critical role of noise itself, potentially leading to sub-optimal performance. In this paper, we introduce a novel perspective by emphasizing the role of noise in the denoising process. Our analysis reveals that noise fundamentally shapes mobile traffic predictions, exhibiting distinct and consistent patterns. We propose NPDiff, a framework that decomposes noise into prior and residual components, with the prior} derived from data dynamics, enhancing the model's ability to capture both regular and abrupt variations. NPDiff can seamlessly integrate with various diffusion-based prediction models, delivering predictions that are effective, efficient, and robust. Extensive experiments demonstrate that it achieves superior performance with an improvement over 30\%, offering a new perspective on leveraging diffusion models in this domain. We provide code and data at https://github.com/tsinghua-fib-lab/NPDiff.
Authors: Feng Zhou, Quyu Kong, Jie Qiao, Cheng Wan, Yixuan Zhang, Ruichu Cai
Abstract: Temporal point processes (TPPs) are stochastic process models used to characterize event sequences occurring in continuous time. Traditional statistical TPPs have a long-standing history, with numerous models proposed and successfully applied across diverse domains. In recent years, advances in deep learning have spurred the development of neural TPPs, enabling greater flexibility and expressiveness in capturing complex temporal dynamics. The emergence of large language models (LLMs) has further sparked excitement, offering new possibilities for modeling and analyzing event sequences by leveraging their rich contextual understanding. This survey presents a comprehensive review of recent research on TPPs from three perspectives: Bayesian, deep learning, and LLM approaches. We begin with a review of the fundamental concepts of TPPs, followed by an in-depth discussion of model design and parameter estimation techniques in these three frameworks. We also revisit classic application areas of TPPs to highlight their practical relevance. Finally, we outline challenges and promising directions for future research.
Authors: Ali Zindari, Parham Yazdkhasti, Anton Rodomanov, Tatjana Chavdarova, Sebastian U. Stich
Abstract: We focus on reducing communication overhead in multiplayer games, where frequently exchanging strategies between players is not feasible and players have noisy or outdated strategies of the other players. We introduce Decoupled SGDA, a novel adaptation of Stochastic Gradient Descent Ascent (SGDA). In this approach, players independently update their strategies based on outdated opponent strategies, with periodic synchronization to align strategies. For Strongly-Convex-Strongly-Concave (SCSC) games, we demonstrate that Decoupled SGDA achieves near-optimal communication complexity comparable to the best-known GDA rates. For weakly coupled games where the interaction between players is lower relative to the non-interactive part of the game, Decoupled SGDA significantly reduces communication costs compared to standard SGDA. Our findings extend to multi-player games. To provide insights into the effect of communication frequency and convergence, we extensively study the convergence of Decoupled SGDA for quadratic minimax problems. Lastly, in settings where the noise over the players is imbalanced, Decoupled SGDA significantly outperforms federated minimax methods.
Authors: Pui Ieng Lei, Ximing Chen, Yijun Sheng, Yanyan Liu, Jingzhi Guo, Zhiguo Gong
Abstract: Existing literature lacks a graph domain adaptation technique for handling large distribution shifts, primarily due to the difficulty in simulating an evolving path from source to target graph. To make a breakthrough, we present a graph gradual domain adaptation (GGDA) framework with the construction of a compact domain sequence that minimizes information loss in adaptations. Our approach starts with an efficient generation of knowledge-preserving intermediate graphs over the Fused Gromov-Wasserstein (FGW) metric. With the bridging data pool, GGDA domains are then constructed via a novel vertex-based domain progression, which comprises "close" vertex selections and adaptive domain advancement to enhance inter-domain information transferability. Theoretically, our framework concretizes the intractable inter-domain distance $W_p(\mu_t,\mu_{t+1})$ via implementable upper and lower bounds, enabling flexible adjustments of this metric for optimizing domain formation. Extensive experiments under various transfer scenarios validate the superior performance of our GGDA framework.
Authors: Daniel T. Speckhard, Tim Bechtel, Sebastian Kehl, Jonathan Godwin, Claudia Draxl
Abstract: Graph neural networks (GNN) have shown promising results for several domains such as materials science, chemistry, and the social sciences. GNN models often contain millions of parameters, and like other neural network (NN) models, are often fed only a fraction of the graphs that make up the training dataset in batches to update model parameters. The effect of batching algorithms on training time and model performance has been thoroughly explored for NNs but not yet for GNNs. We analyze two different batching algorithms for graph based models, namely static and dynamic batching for two datasets, the QM9 dataset of small molecules and the AFLOW materials database. Our experiments show that changing the batching algorithm can provide up to a 2.7x speedup, but the fastest algorithm depends on the data, model, batch size, hardware, and number of training steps run. Experiments show that for a select number of combinations of batch size, dataset, and model, significant differences in model learning metrics are observed between static and dynamic batching algorithms.
Authors: David S. Hayden, Mao Ye, Timur Garipov, Gregory P. Meyer, Carl Vondrick, Zhao Chen, Yuning Chai, Eric Wolff, Siddhartha S. Srinivasa
Abstract: It is difficult to anticipate the myriad challenges that a predictive model will encounter once deployed. Common practice entails a reactive, cyclical approach: model deployment, data mining, and retraining. We instead develop a proactive longtail discovery process by imagining additional data during training. In particular, we develop general model-based longtail signals, including a differentiable, single forward pass formulation of epistemic uncertainty that does not impact model parameters or predictive performance but can flag rare or hard inputs. We leverage these signals as guidance to generate additional training data from a latent diffusion model in a process we call Longtail Guidance (LTG). Crucially, we can perform LTG without retraining the diffusion model or the predictive model, and we do not need to expose the predictive model to intermediate diffusion states. Data generated by LTG exhibit semantically meaningful variation, yield significant generalization improvements on numerous image classification benchmarks, and can be analyzed by a VLM to proactively discover, textually explain, and address conceptual gaps in a deployed predictive model.
Authors: Frederik Lizak Johansen, Ulrik Friis-Jensen, Erik Bj{\o}rnager Dam, Kirsten Marie {\O}rnsbjerg Jensen, Roc\'io Mercado, Raghavendra Selvan
Abstract: Novel materials drive progress across applications from energy storage to electronics. Automated characterization of material structures with machine learning methods offers a promising strategy for accelerating this key step in material design. In this work, we introduce an autoregressive language model that performs crystal structure prediction (CSP) from powder diffraction data. The presented model, deCIFer, generates crystal structures in the widely used Crystallographic Information File (CIF) format and can be conditioned on powder X-ray diffraction (PXRD) data. Unlike earlier works that primarily rely on high-level descriptors like composition, deCIFer is also able to use diffraction data to perform CSP. We train deCIFer on nearly 2.3M crystal structures and validate on diverse sets of PXRD patterns for characterizing challenging inorganic crystal systems. Qualitative checks and quantitative assessments using the residual weighted profile show that deCIFer produces structures that more accurately match the target diffraction data. Notably, deCIFer can achieve a 94% match rate on test data. deCIFer bridges experimental diffraction data with computational CSP, lending itself as a powerful tool for crystal structure characterization.
Authors: Corinna Coupette, Jeremy Wayland, Emily Simons, Bastian Rieck
Abstract: Benchmark datasets have proved pivotal to the success of graph learning, and good benchmark datasets are crucial to guide the development of the field. Recent research has highlighted problems with graph-learning datasets and benchmarking practices -- revealing, for example, that methods which ignore the graph structure can outperform graph-based approaches. Such findings raise two questions: (1) What makes a good graph-learning dataset, and (2) how can we evaluate dataset quality in graph learning? Our work addresses these questions. As the classic evaluation setup uses datasets to evaluate models, it does not apply to dataset evaluation. Hence, we start from first principles. Observing that graph-learning datasets uniquely combine two modes -- graph structure and node features --, we introduce Rings, a flexible and extensible mode-perturbation framework to assess the quality of graph-learning datasets based on dataset ablations -- i.e., quantifying differences between the original dataset and its perturbed representations. Within this framework, we propose two measures -- performance separability and mode complementarity -- as evaluation tools, each assessing the capacity of a graph dataset to benchmark the power and efficacy of graph-learning methods from a distinct angle. We demonstrate the utility of our framework for dataset evaluation via extensive experiments on graph-level tasks and derive actionable recommendations for improving the evaluation of graph-learning methods. Our work opens new research directions in data-centric graph learning, and it constitutes a step toward the systematic evaluation of evaluations.
Authors: Thomas Zeng, Shuibai Zhang, Shutong Wu, Christian Classen, Daewon Chae, Ethan Ewer, Minjae Lee, Heeju Kim, Wonjun Kang, Jackson Kunde, Ying Fan, Jungtaek Kim, Hyung Il Koo, Kannan Ramchandran, Dimitris Papailiopoulos, Kangwook Lee
Abstract: Process Reward Models (PRMs) have proven effective at enhancing mathematical reasoning for Large Language Models (LLMs) by leveraging increased inference-time computation. However, they are predominantly trained on mathematical data and their generalizability to non-mathematical domains has not been rigorously studied. In response, this work first shows that current PRMs have poor performance in other domains. To address this limitation, we introduce VersaPRM, a multi-domain PRM trained on synthetic reasoning data generated using our novel data generation and annotation method. VersaPRM achieves consistent performance gains across diverse domains. For instance, in the MMLU-Pro category of Law, VersaPRM via weighted majority voting, achieves a 7.9% performance gain over the majority voting baseline -- surpassing Qwen2.5-Math-PRM's gain of 1.3%. We further contribute to the community by open-sourcing all data, code and models for VersaPRM.
Authors: Benedikt Alkin, Maurits Bleeker, Richard Kurle, Tobias Kronlachner, Reinhard Sonnleitner, Matthias Dorfer, Johannes Brandstetter
Abstract: Recent advances in neural surrogate modeling offer the potential for transformative innovations in applications such as automotive aerodynamics. Yet, industrial-scale problems often involve volumetric meshes with cell counts reaching 100 million, presenting major scalability challenges. Complex geometries further complicate modeling through intricate surface-volume interactions, while quantities such as vorticity are highly nonlinear and must satisfy strict divergence-free constraints. To address these requirements, we introduce Anchored-Branched Universal Physics Transformers (AB-UPT) as a novel modeling scheme for building neural surrogates for computational fluid dynamics (CFD) simulations. AB-UPT is designed to: (i) decouple geometry encoding and prediction tasks via multi-branch operators; (ii) enable scalability to high-resolution outputs via neural simulation in a low-dimensional latent space, coupled with anchored neural field decoders to predict high-fidelity outputs; (iii) enforce physics consistency by a novel divergence-free formulation. We show that AB-UPT yields state-of-the-art predictive accuracy of surface and volume fields on automotive CFD simulations ranging from 33 thousand up to 150 million mesh cells. Furthermore, our anchored neural field architecture enables the enforcement of hard physical constraints on the physics predictions without degradation in performance, exemplified by modeling divergence-free vorticity fields. Notably, the proposed models can be trained on a single GPU in less than a day and predict industry-standard surface and volume fields within seconds. Additionally, we show that the flexible design of our method enables neural simulation from a computer-aided design geometry alone, omitting the need for costly CFD meshing procedures.
Authors: Arnav Kumar Jain, Gonzalo Gonzalez-Pumariega, Wayne Chen, Alexander M Rush, Wenting Zhao, Sanjiban Choudhury
Abstract: We address the problem of code generation from multi-turn execution feedback. Existing methods either generate code without feedback or use complex, hierarchical reinforcement learning to optimize multi-turn rewards. We propose a simple yet scalable approach, $\mu$Code, that solves multi-turn code generation using only single-step rewards. Our key insight is that code generation is a one-step recoverable MDP, where the correct code can be recovered from any intermediate code state in a single turn. $\mu$Code iteratively trains both a generator to provide code solutions conditioned on multi-turn execution feedback and a verifier to score the newly generated code. Experimental evaluations show that our approach achieves significant improvements over the state-of-the-art baselines. We provide analysis of the design choices of the reward models and policy, and show the efficacy of $\mu$Code at utilizing the execution feedback. Our code is available at https://github.com/portal-cornell/muCode.
Authors: Xi Zhu, Haochen Xue, Ziwei Zhao, Wujiang Xu, Jingyuan Huang, Minghao Guo, Qifan Wang, Kaixiong Zhou, Yongfeng Zhang
Abstract: Text-Attributed Graphs (TAGs), where each node is associated with text descriptions, are ubiquitous in real-world scenarios. They typically exhibit distinctive structure and domain-specific knowledge, motivating the development of a Graph Foundation Model (GFM) that generalizes across diverse graphs and tasks. Despite large efforts to integrate Large Language Models (LLMs) and Graph Neural Networks (GNNs) for TAGs, existing approaches suffer from decoupled architectures with two-stage alignment, limiting their synergistic potential. Even worse, existing methods assign out-of-vocabulary (OOV) tokens to graph nodes, leading to graph-specific semantics, token explosion, and incompatibility with task-oriented prompt templates, which hinders cross-graph and cross-task transferability. To address these challenges, we propose PromptGFM, a versatile GFM for TAGs grounded in graph vocabulary learning. PromptGFM comprises two key components: (1) Graph Understanding Module, which explicitly prompts LLMs to replicate the finest GNN workflow within the text space, facilitating seamless GNN-LLM integration and elegant graph-text alignment; (2) Graph Inference Module, which establishes a language-based graph vocabulary ensuring expressiveness, transferability, and scalability, enabling readable instructions for LLM fine-tuning. Extensive experiments demonstrate our superiority and transferability across diverse graphs and tasks. The code is available at this: https://github.com/agiresearch/PromptGFM.
Authors: Xuanke Jiang, Sherief Hashima, Kohei Hatano, Eiji Takimoto
Abstract: We consider a good arm identification problem in a stochastic bandit setting with multi-objectives, where each arm $i \in [K]$ is associated with a distribution $D_i$ defined over $R^M$. For each round $t$, the player pulls an arm $i_t$ and receives an $M$-dimensional reward vector sampled according to $D_{i_t}$. The goal is to find, with high probability, an $\epsilon$-good arm whose expected reward vector is larger than $\bm{\xi} - \epsilon \mathbf{1}$, where $\bm{\xi}$ is a predefined threshold vector, and the vector comparison is component-wise. We propose the Multi-Thresholding UCB~(MultiTUCB) algorithm with a sample complexity bound. Our bound matches the existing one in the special case where $M=1$ and $\epsilon=0$. The proposed algorithm demonstrates superior performance compared to baseline approaches across synthetic and real datasets.
Authors: Can Zheng, Jiguang He, Guofa Cai, Zitong Yu, Chung G. Kang
Abstract: In this paper, we propose BeamLLM, a vision-aided millimeter-wave (mmWave) beam prediction framework leveraging large language models (LLMs) to address the challenges of high training overhead and latency in mmWave communication systems. By combining computer vision (CV) with LLMs' cross-modal reasoning capabilities, the framework extracts user equipment (UE) positional features from RGB images and aligns visual-temporal features with LLMs' semantic space through reprogramming techniques. Evaluated on a realistic vehicle-to-infrastructure (V2I) scenario, the proposed method achieves 61.01% top-1 accuracy and 97.39% top-3 accuracy in standard prediction tasks, significantly outperforming traditional deep learning models. In few-shot prediction scenarios, the performance degradation is limited to 12.56% (top-1) and 5.55% (top-3) from time sample 1 to 10, demonstrating superior prediction capability.
Authors: Yebo Wu, Chunlin Tian, Jingguang Li, He Sun, Kahou Tam, Zhanting Zhou, Haicheng Liao, Zhijiang Guo, Li Li, Chengzhong Xu
Abstract: Large Language Models (LLMs) have demonstrated impressive success across various tasks. Integrating LLMs with Federated Learning (FL), a paradigm known as FedLLM, offers a promising avenue for collaborative model adaptation while preserving data privacy. This survey provides a systematic and comprehensive review of FedLLM. We begin by tracing the historical development of both LLMs and FL, summarizing relevant prior research to set the context. Subsequently, we delve into an in-depth analysis of the fundamental challenges inherent in deploying FedLLM. Addressing these challenges often requires efficient adaptation strategies; therefore, we conduct an extensive examination of existing Parameter-Efficient Fine-tuning (PEFT) methods and explore their applicability within the FL framework. To rigorously evaluate the performance of FedLLM, we undertake a thorough review of existing fine-tuning datasets and evaluation benchmarks. Furthermore, we discuss FedLLM's diverse real-world applications across multiple domains. Finally, we identify critical open challenges and outline promising research directions to foster future advancements in FedLLM. This survey aims to serve as a foundational resource for researchers and practitioners, offering valuable insights into the rapidly evolving landscape of federated fine-tuning for LLMs. It also establishes a roadmap for future innovations in privacy-preserving AI. We actively maintain a GitHub repo \href{https://github.com/Clin0212/Awesome-Federated-LLM-Learning}{https://github.com/Clin0212/Awesome-Federated-LLM-Learning} to track cutting-edge advancements in this field.
URLs: https://github.com/Clin0212/Awesome-Federated-LLM-Learning, https://github.com/Clin0212/Awesome-Federated-LLM-Learning
Authors: Zewen Liu, Xiaoda Wang, Bohan Wang, Zijie Huang, Carl Yang, Wei Jin
Abstract: Graph Neural Networks (GNNs) and differential equations (DEs) are two rapidly advancing areas of research that have shown remarkable synergy in recent years. GNNs have emerged as powerful tools for learning on graph-structured data, while differential equations provide a principled framework for modeling continuous dynamics across time and space. The intersection of these fields has led to innovative approaches that leverage the strengths of both, enabling applications in physics-informed learning, spatiotemporal modeling, and scientific computing. This survey aims to provide a comprehensive overview of the burgeoning research at the intersection of GNNs and DEs. We will categorize existing methods, discuss their underlying principles, and highlight their applications across domains such as molecular modeling, traffic prediction, and epidemic spreading. Furthermore, we identify open challenges and outline future research directions to advance this interdisciplinary field. A comprehensive paper list is provided at https://github.com/Emory-Melody/Awesome-Graph-NDEs. This survey serves as a resource for researchers and practitioners seeking to understand and contribute to the fusion of GNNs and DEs
Authors: Benjamin T. Brown, Haoxiang Zhang, Daniel L. Lau, Gonzalo R. Arce
Abstract: In graph signal processing, learning the weighted connections between nodes from a set of sample signals is a fundamental task when the underlying relationships are not known a priori. This task is typically addressed by finding a graph Laplacian on which the observed signals are smooth. With the extension of graphs to hypergraphs - where edges can connect more than two nodes - graph learning methods have similarly been generalized to hypergraphs. However, the absence of a unified framework for calculating total variation has led to divergent definitions of smoothness and, consequently, differing approaches to hyperedge recovery. We confront this challenge through generalization of several previously proposed hypergraph total variations, subsequently allowing ease of substitution into a vector based optimization. To this end, we propose a novel hypergraph learning method that recovers a hypergraph topology from time-series signals based on a smoothness prior. Our approach, designated as Hypergraph Structure Learning with Smoothness (HSLS), addresses key limitations in prior works, such as hyperedge selection and convergence issues, by formulating the problem as a convex optimization solved via a forward-backward-forward algorithm, ensuring guaranteed convergence. Additionally, we introduce a process that simultaneously limits the span of the hyperedge search and maintains a valid hyperedge selection set. In doing so, our method becomes scalable in increasingly complex network structures. The experimental results demonstrate improved performance, in terms of accuracy, over other state-of-the-art hypergraph inference methods; furthermore, we empirically show our method to be robust to total variation terms, biased towards global smoothness, and scalable to larger hypergraphs.
Authors: Carlos Fern\'andez-Lor\'ia
Abstract: Causal inference is often portrayed as fundamentally distinct from predictive modeling, with its own terminology, goals, and intellectual challenges. But at its core, causal inference is simply a structured instance of prediction under distribution shift. In both cases, we begin with labeled data from a source domain and seek to generalize to a target domain where outcomes are not observed. The key difference is that in causal inference, the labels -- potential outcomes -- are selectively observed based on treatment assignment, introducing bias that must be addressed through assumptions. This perspective reframes causal estimation as a familiar generalization problem and highlights how techniques from predictive modeling, such as reweighting and domain adaptation, apply directly to causal tasks. It also clarifies that causal assumptions are not uniquely strong -- they are simply more explicit. By viewing causal inference through the lens of prediction, we demystify its logic, connect it to familiar tools, and make it more accessible to practitioners and educators alike.
Authors: Patr\'icia Mu\~noz Ewald
Abstract: We fully characterize a large class of feedforward neural networks in terms of truncation maps. As an application, we show how a ReLU neural network can implement a feature map which separates concentric data.
Authors: Han Weng, Puzhen Wu, Cui Longjie, Yi Zhan, Boyi Liu, Yuanfeng Song, Dun Zeng, Yingxiang Yang, Qianru Zhang, Dong Huang, Xiaoming Yin, Yang Sun, Xing Chen
Abstract: Reinforcement learning (RL) has been widely adopted to enhance the performance of large language models (LLMs) on Text-to-SQL tasks. However, existing methods often rely on execution-based or LLM-based Bradley-Terry reward models. The former suffers from high execution latency caused by repeated database calls, whereas the latter imposes substantial GPU memory overhead, both of which significantly hinder the efficiency and scalability of RL pipelines. To this end, we propose a novel Text-to-SQL RL fine-tuning framework named Graph-Reward-SQL, which employs the GMNScore outcome reward model. We leverage SQL graph representations to provide accurate reward signals while significantly reducing inference time and GPU memory usage. Building on this foundation, we further introduce StepRTM, a stepwise reward model that provides intermediate supervision over Common Table Expression (CTE) subqueries. This encourages both functional correctness and structural clarity of SQL. Extensive comparative and ablation experiments on standard benchmarks, including Spider and BIRD, demonstrate that our method consistently outperforms existing reward models.
Authors: Dhanesh Ramachandram, Ananya Raval
Abstract: Competing risks are crucial considerations in survival modelling, particularly in healthcare domains where patients may experience multiple distinct event types. We propose CRISP-NAM (Competing Risks Interpretable Survival Prediction with Neural Additive Models), an interpretable neural additive model for competing risks survival analysis which extends the neural additive architecture to model cause-specific hazards while preserving feature-level interpretability. Each feature contributes independently to risk estimation through dedicated neural networks, allowing for visualization of complex non-linear relationships between covariates and each competing risk. We demonstrate competitive performance on multiple datasets compared to existing approaches.
Authors: Mihir Prabhudesai, Lili Chen, Alex Ippoliti, Katerina Fragkiadaki, Hao Liu, Deepak Pathak
Abstract: Reinforcement learning (RL) has enabled machine learning models to achieve significant advances in many fields. Most recently, RL has empowered frontier language models to solve challenging math, science, and coding problems. However, central to any RL algorithm is the reward function, and reward engineering is a notoriously difficult problem in any domain. In this paper, we propose RENT: Reinforcement Learning via Entropy Minimization -- a fully unsupervised RL method that requires no external reward or ground-truth answers, and instead uses the model's entropy of its underlying distribution as an intrinsic reward. We find that by reinforcing the chains of thought that yield high model confidence on its generated answers, the model improves its reasoning ability. In our experiments, we showcase these improvements on an extensive suite of commonly-used reasoning benchmarks, including GSM8K, MATH500, AMC, AIME, and GPQA, and models of varying sizes from the Qwen, Mistral, and Llama families. The generality of our unsupervised learning method lends itself to applicability in a wide range of domains where external supervision is unavailable.
Authors: Giannis Nikolentzos, Konstantinos Skianis
Abstract: The Lipschitz constant of a neural network is connected to several important properties of the network such as its robustness and generalization. It is thus useful in many settings to estimate the Lipschitz constant of a model. Prior work has focused mainly on estimating the Lipschitz constant of multi-layer perceptrons and convolutional neural networks. Here we focus on data modeled as sets or multisets of vectors and on neural networks that can handle such data. These models typically apply some permutation invariant aggregation function, such as the sum, mean or max operator, to the input multisets to produce a single vector for each input sample. In this paper, we investigate whether these aggregation functions are Lipschitz continuous with respect to three distance functions for unordered multisets, and we compute their Lipschitz constants. In the general case, we find that each aggregation function is Lipschitz continuous with respect to only one of the three distance functions. Then, we build on these results to derive upper bounds on the Lipschitz constant of neural networks that can process multisets of vectors, while we also study their stability to perturbations and generalization under distribution shifts. To empirically verify our theoretical analysis, we conduct a series of experiments on datasets from different domains.
Authors: Luca Beurer-Kellner, Beat Buesser, Ana-Maria Cre\c{t}u, Edoardo Debenedetti, Daniel Dobos, Daniel Fabian, Marc Fischer, David Froelicher, Kathrin Grosse, Daniel Naeff, Ezinwanne Ozoani, Andrew Paverd, Florian Tram\`er, V\'aclav Volhejn
Abstract: As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt injection attacks, which exploit the agent's resilience on natural language inputs -- an especially dangerous threat when agents are granted tool access or handle sensitive information. In this work, we propose a set of principled design patterns for building AI agents with provable resistance to prompt injection. We systematically analyze these patterns, discuss their trade-offs in terms of utility and security, and illustrate their real-world applicability through a series of case studies.
Authors: Samin Yeasar Arnob, Scott Fujimoto, Doina Precup
Abstract: In this paper, we investigate the use of small datasets in the context of offline reinforcement learning (RL). While many common offline RL benchmarks employ datasets with over a million data points, many offline RL applications rely on considerably smaller datasets. We show that offline RL algorithms can overfit on small datasets, resulting in poor performance. To address this challenge, we introduce "Sparse-Reg": a regularization technique based on sparsity to mitigate overfitting in offline reinforcement learning, enabling effective learning in limited data settings and outperforming state-of-the-art baselines in continuous control.
Authors: C. Shi, S. Zhang, W. Lu, R. Song
Abstract: Reinforcement learning is a general technique that allows an agent to learn an optimal policy and interact with an environment in sequential decision making problems. The goodness of a policy is measured by its value function starting from some initial state. The focus of this paper is to construct confidence intervals (CIs) for a policy's value in infinite horizon settings where the number of decision points diverges to infinity. We propose to model the action-value state function (Q-function) associated with a policy based on series/sieve method to derive its confidence interval. When the target policy depends on the observed data as well, we propose a SequentiAl Value Evaluation (SAVE) method to recursively update the estimated policy and its value estimator. As long as either the number of trajectories or the number of decision points diverges to infinity, we show that the proposed CI achieves nominal coverage even in cases where the optimal policy is not unique. Simulation studies are conducted to back up our theoretical findings. We apply the proposed method to a dataset from mobile health studies and find that reinforcement learning algorithms could help improve patient's health status. A Python implementation of the proposed procedure is available at https://github.com/shengzhang37/SAVE.
Authors: Salar Nouri, Mojdeh Karbalaee Motalleb, Vahid Shah-Mansouri, Seyed Pooya Shariatpanahi
Abstract: This paper introduces a novel generative AI (GAI)-driven, unified semi-supervised learning architecture for optimizing resource allocation and network slicing in O-RAN. Termed Generative Semi-Supervised VAE-Contrastive Learning, our approach maximizes the weighted user equipment (UE) throughput and allocates physical resource blocks (PRBs) to enhance the quality of service for eMBB and URLLC services. The GAI framework utilizes a dedicated xApp for intelligent power control and PRB allocation. This integrated GAI model synergistically combines the generative power of a VAE with contrastive learning to achieve robustness in an end-to-end trainable system. It is a semi-supervised training approach that concurrently optimizes supervised regression of resource allocation decisions (i.e., power, UE association, PRB) and unsupervised contrastive objectives. This intrinsic fusion improves the precision of resource management and model generalization in dynamic mobile networks. We evaluated our GAI methodology against exhaustive search and deep Q-Network algorithms using key performance metrics. Results show our integrated GAI approach offers superior efficiency and effectiveness in various scenarios, presenting a compelling GAI-based solution for critical network slicing and resource management challenges in next-generation O-RAN systems.
Authors: Tiffany Tianhui Cai, Yuri Fonseca, Kaiwen Hou, Hongseok Namkoong
Abstract: Popular debiased estimation methods for causal inference -- such as augmented inverse propensity weighting and targeted maximum likelihood estimation -- enjoy desirable asymptotic properties like statistical efficiency and double robustness but they can produce unstable estimates when there is limited overlap between treatment and control, requiring additional assumptions or ad hoc adjustments in practice (e.g., truncating propensity scores). In contrast, simple plug-in estimators are stable but lack desirable asymptotic properties. We propose a novel debiasing approach that achieves the best of both worlds, producing stable plug-in estimates with desirable asymptotic properties. Our constrained learning framework solves for the best plug-in estimator under the constraint that the first-order error with respect to the plugged-in quantity is zero, and can leverage flexible model classes including neural networks and tree ensembles. In several experimental settings, including ones in which we handle text-based covariates by fine-tuning language models, our constrained learning-based estimator outperforms basic versions of one-step estimation and targeting in challenging settings with limited overlap between treatment and control, and performs similarly otherwise.
Authors: Piyush Jha, Prithwish Jana, Pranavkrishna Suresh, Arnav Arora, Vijay Ganesh
Abstract: Large Language Models (LLMs) have transformed AI but often struggle with tasks that require domain-specific reasoning and logical alignment. Traditional fine-tuning methods do not leverage the vast amount of symbolic domain-knowledge available to us via symbolic reasoning tools (e.g., provers), and are further limited by sparse rewards and unreliable reward models. We introduce Reinforcement Learning via Symbolic Feedback (RLSF), a novel fine-tuning paradigm where symbolic reasoning tools (e.g., solvers, provers, and algebra systems) provide fine-grained feedback to LLMs. RLSF uses poly-sized certificates (e.g., proofs) generated by symbolic tools to identify and correct errors in model outputs, offering token-level guidance without requiring differentiable reasoning systems. This paradigm bridges the gap between symbolic reasoning and LLM fine-tuning, enabling precise alignment with domain-specific constraints while addressing key limitations of traditional reward signals. Via extensive evaluations, we show that our RLSF-based fine-tuning of LLMs outperforms traditional approaches on five different applications (that have some associated logical or domain constraints), namely, program synthesis from natural language pseudo-code to programming language, three chemistry tasks, and solving the Game of 24. A key takeaway is that fine-tuning via RLSF enables relatively smaller LLMs to significantly outperform closed-source models that are orders of magnitude larger.
Authors: Jia-Hau Bai, Chi-Ting Liu, Yu Wang, Fu-Chieh Chang, Pei-Yuan Wu
Abstract: This study uses CAPM (Convex Adversarial Polytope for Maxpool-based CNN) to improve the verified bound for general purpose maxpool-based convolutional neural networks (CNNs) under bounded norm adversarial perturbations. The maxpool function is decomposed as a series of ReLU functions to extend the convex relaxation technique to maxpool functions, by which the verified bound can be efficiently computed through a dual network. The experimental results demonstrate that this technique allows the state-of-the-art verification precision for maxpool-based CNNs and involves a much lower computational cost than current verification methods, such as DeepZ, DeepPoly and PRIMA. This method is also applicable to large-scale CNNs, which previous studies show to be often computationally prohibitively expensive. Under certain circumstances, CAPM is 40-times, 20-times or twice as fast and give a significantly higher verification bound (CAPM 98% vs. PRIMA 76%/DeepPoly 73%/DeepZ 8%) as compared to PRIMA/DeepPoly/DeepZ. Furthermore, we additionally present the time complexity of our algorithm as $O(W^2NK)$, where $W$ is the maximum width of the neural network, $N$ is the number of neurons, and $K$ is the size of the maxpool layer's kernel.
Authors: Cheng Shi, Liming Pan, Ivan Dokmani\'c
Abstract: Feature-learning deep nets progressively collapse data to a regular low-dimensional geometry. How this emerges from the collective action of nonlinearity, noise, learning rate, and other factors, has eluded first-principles theories built from microscopic neuronal dynamics. We exhibit a noise-nonlinearity phase diagram that identifies regimes where shallow or deep layers learn more effectively and propose a macroscopic mechanical theory that reproduces the diagram and links feature learning across layers to generalization.
Authors: Vindula Jayawardana, Baptiste Freydt, Ao Qu, Cameron Hickert, Edgar Sanchez, Catherine Tang, Mark Taylor, Blaine Leonard, Cathy Wu
Abstract: The sheer scale and diversity of transportation make it a formidable sector to decarbonize. Here, we consider an emerging opportunity to reduce carbon emissions: the growing adoption of semi-autonomous vehicles, which can be programmed to mitigate stop-and-go traffic through intelligent speed commands and, thus, reduce emissions. But would such dynamic eco-driving move the needle on climate change? A comprehensive impact analysis has been out of reach due to the vast array of traffic scenarios and the complexity of vehicle emissions. We address this challenge with large-scale scenario modeling efforts and by using multi-task deep reinforcement learning with a carefully designed network decomposition strategy. We perform an in-depth prospective impact assessment of dynamic eco-driving at 6,011 signalized intersections across three major US metropolitan cities, simulating a million traffic scenarios. Overall, we find that vehicle trajectories optimized for emissions can cut city-wide intersection carbon emissions by 11-22%, without harming throughput or safety, and with reasonable assumptions, equivalent to the national emissions of Israel and Nigeria, respectively. We find that 10% eco-driving adoption yields 25%-50% of the total reduction, and nearly 70% of the benefits come from 20% of intersections, suggesting near-term implementation pathways. However, the composition of this high-impact subset of intersections varies considerably across different adoption levels, with minimal overlap, calling for careful strategic planning for eco-driving deployments. Moreover, the impact of eco-driving, when considered jointly with projections of vehicle electrification and hybrid vehicle adoption remains significant. More broadly, this work paves the way for large-scale analysis of traffic externalities, such as time, safety, and air quality, and the potential impact of solution strategies.
Authors: Ibrahim K. Ozaslan, Panagiotis Patrinos, Mihailo R. Jovanovi\'c
Abstract: We examine stability properties of primal-dual gradient flow dynamics for composite convex optimization problems with multiple, possibly nonsmooth, terms in the objective function under the generalized consensus constraint. The proposed dynamics are based on the proximal augmented Lagrangian and they provide a viable alternative to ADMM which faces significant challenges from both analysis and implementation viewpoints in large-scale multi-block scenarios. In contrast to customized algorithms with individualized convergence guarantees, we develop a systematic approach for solving a broad class of challenging composite optimization problems. We leverage various structural properties to establish global (exponential) convergence guarantees for the proposed dynamics. Our assumptions are much weaker than those required to prove (exponential) stability of primal-dual dynamics as well as (linear) convergence of discrete-time methods such as standard two-block and multi-block ADMM and EXTRA algorithms. Finally, we show necessity of some of our structural assumptions for exponential stability and provide computational experiments to demonstrate the convenience of the proposed approach for parallel and distributed computing applications.
Authors: Johan Hallberg Szabadv\'ary, Tuwe L\"ofstr\"om
Abstract: Adaptive Conformal Inference (ACI) provides finite-sample coverage guarantees, enhancing the prediction reliability under non-exchangeability. This study demonstrates that these desirable properties of ACI do not require the use of Conformal Predictors (CP). We show that the guarantees hold for the broader class of confidence predictors, defined by the requirement of producing nested prediction sets, a property we argue is essential for meaningful confidence statements. We empirically investigate the performance of Non-Conformal Confidence Predictors (NCCP) against CP when used with ACI on non-exchangeable data. In online settings, the NCCP offers significant computational advantages while maintaining a comparable predictive efficiency. In batch settings, inductive NCCP (INCCP) can outperform inductive CP (ICP) by utilising the full training dataset without requiring a separate calibration set, leading to improved efficiency, particularly when the data are limited. Although these initial results highlight NCCP as a theoretically sound and practically effective alternative to CP for uncertainty quantification with ACI in non-exchangeable scenarios, further empirical studies are warranted across diverse datasets and predictors.
Authors: Tianyu Gao, Alexander Wettig, Howard Yen, Danqi Chen
Abstract: We study continued training and supervised fine-tuning (SFT) of a language model (LM) to make effective use of long-context information. We first establish a reliable evaluation protocol to guide model development -- instead of perplexity or simple needle-in-a-haystack (NIAH) tests, we use a broad set of long-context downstream tasks, and we evaluate models after SFT as this better reveals long-context abilities. Supported by our robust evaluations, we run thorough experiments to decide the data mix for continued pre-training, the instruction tuning dataset, and many other design choices such as position extrapolation. We find that (1) code repositories and books are excellent sources of long data, but it is crucial to combine them with high-quality short-context data; (2) training with a sequence length beyond the evaluation length boosts long-context performance; (3) for SFT, using only short instruction datasets yields strong performance on long-context tasks. Our final model, ProLong-8B, which is initialized from Llama-3 and trained on 40B tokens, demonstrates state-of-the-art long-context performance among similarly sized models at a length of 128K. ProLong outperforms Llama-3.1-8B-Instruct on the majority of long-context tasks despite using only 5% as many tokens during long-context training. Additionally, ProLong can effectively process up to 512K tokens, one of the longest context windows of publicly available LMs.
Authors: Marc Lanctot, Kate Larson, Michael Kaisers, Quentin Berthet, Ian Gemp, Manfred Diaz, Roberto-Rafael Maura-Rivero, Yoram Bachrach, Anna Koop, Doina Precup
Abstract: Driving progress of AI models and agents requires comparing their performance on standardized benchmarks; for general agents, individual performances must be aggregated across a potentially wide variety of different tasks. In this paper, we describe a novel ranking scheme inspired by social choice frameworks, called Soft Condorcet Optimization (SCO), to compute the optimal ranking of agents: the one that makes the fewest mistakes in predicting the agent comparisons in the evaluation data. This optimal ranking is the maximum likelihood estimate when evaluation data (which we view as votes) are interpreted as noisy samples from a ground truth ranking, a solution to Condorcet's original voting system criteria. SCO ratings are maximal for Condorcet winners when they exist, which we show is not necessarily true for the classical rating system Elo. We propose three optimization algorithms to compute SCO ratings and evaluate their empirical performance. When serving as an approximation to the Kemeny-Young voting method, SCO rankings are on average 0 to 0.043 away from the optimal ranking in normalized Kendall-tau distance across 865 preference profiles from the PrefLib open ranking archive. In a simulated noisy tournament setting, SCO achieves accurate approximations to the ground truth ranking and the best among several baselines when 59\% or more of the preference data is missing. Finally, SCO ranking provides the best approximation to the optimal ranking, measured on held-out test sets, in a problem containing 52,958 human players across 31,049 games of the classic seven-player game of Diplomacy.
Authors: Xiang Li, Feng Ruan, Huiyuan Wang, Qi Long, Weijie J. Su
Abstract: Watermarking has offered an effective approach to distinguishing text generated by large language models (LLMs) from human-written text. However, the pervasive presence of human edits on LLM-generated text dilutes watermark signals, thereby significantly degrading detection performance of existing methods. In this paper, by modeling human edits through mixture model detection, we introduce a new method in the form of a truncated goodness-of-fit test for detecting watermarked text under human edits, which we refer to as Tr-GoF. We prove that the Tr-GoF test achieves optimality in robust detection of the Gumbel-max watermark in a certain asymptotic regime of substantial text modifications and vanishing watermark signals. Importantly, Tr-GoF achieves this optimality \textit{adaptively} as it does not require precise knowledge of human edit levels or probabilistic specifications of the LLMs, in contrast to the optimal but impractical (Neyman--Pearson) likelihood ratio test. Moreover, we establish that the Tr-GoF test attains the highest detection efficiency rate in a certain regime of moderate text modifications. In stark contrast, we show that sum-based detection rules, as employed by existing methods, fail to achieve optimal robustness in both regimes because the additive nature of their statistics is less resilient to edit-induced noise. Finally, we demonstrate the competitive and sometimes superior empirical performance of the Tr-GoF test on both synthetic data and open-source LLMs in the OPT and LLaMA families.
Authors: Anirudh Rayas, Jiajun Cheng, Rajasekhar Anguluri, Deepjyoti Deka, Gautam Dasarathy
Abstract: Complex networked systems driven by latent inputs are common in fields like neuroscience, finance, and engineering. A key inference problem here is to learn edge connectivity from node outputs (potentials). We focus on systems governed by steady-state linear conservation laws: $X_t = {L^{\ast}}Y_{t}$, where $X_t, Y_t \in \mathbb{R}^p$ denote inputs and potentials, respectively, and the sparsity pattern of the $p \times p$ Laplacian $L^{\ast}$ encodes the edge structure. Assuming $X_t$ to be a wide-sense stationary stochastic process with a known spectral density matrix, we learn the support of $L^{\ast}$ from temporally correlated samples of $Y_t$ via an $\ell_1$-regularized Whittle's maximum likelihood estimator (MLE). The regularization is particularly useful for learning large-scale networks in the high-dimensional setting where the network size $p$ significantly exceeds the number of samples $n$. We show that the MLE problem is strictly convex, admitting a unique solution. Under a novel mutual incoherence condition and certain sufficient conditions on $(n, p, d)$, we show that the ML estimate recovers the sparsity pattern of $L^\ast$ with high probability, where $d$ is the maximum degree of the graph underlying $L^{\ast}$. We provide recovery guarantees for $L^\ast$ in element-wise maximum, Frobenius, and operator norms. Finally, we complement our theoretical results with several simulation studies on synthetic and benchmark datasets, including engineered systems (power and water networks), and real-world datasets from neural systems (such as the human brain).
Authors: Young Seok Jeon, Hongfei Yang, Huazhu Fu, Mengling Feng
Abstract: 3D models surpass 2D models in CT/MRI segmentation by effectively capturing inter-slice relationships. However, the added depth dimension substantially increases memory consumption. While patch-based training alleviates memory constraints, it significantly slows down the inference speed due to the sliding window (SW) approach. We propose No-More-Sliding-Window (NMSW), a novel end-to-end trainable framework that enhances the efficiency of generic 3D segmentation backbone during an inference step by eliminating the need for SW. NMSW employs a differentiable Top-k module to selectively sample only the most relevant patches, thereby minimizing redundant computations. When patch-level predictions are insufficient, the framework intelligently leverages coarse global predictions to refine results. Evaluated across 3 tasks using 3 segmentation backbones, NMSW achieves competitive accuracy compared to SW inference while significantly reducing computational complexity by 91% (88.0 to 8.00 TMACs). Moreover, it delivers a 9.1x faster inference on the H100 GPU (99.0 to 8.3 sec) and a 11.1x faster inference on the Xeon Gold CPU (2110 to 189 sec). NMSW is model-agnostic, further boosting efficiency when integrated with any existing efficient segmentation backbones. The code is avaialble: https://github.com/Youngseok0001/open_nmsw.
Authors: Sadegh Mahdavi, Muchen Li, Kaiwen Liu, Christos Thrampoulidis, Leonid Sigal, Renjie Liao
Abstract: Advances in Large Language Models (LLMs) have sparked interest in their ability to solve Olympiad-level math problems. However, the training and evaluation of these models are constrained by the limited size and quality of available datasets, as creating large-scale data for such advanced problems requires extensive effort from human experts. In addition, current benchmarks are prone to contamination, leading to unreliable evaluations. In this paper, we present an automated pipeline that leverages the rich resources of the Art of Problem Solving (AoPS) forum, which predominantly features Olympiad-level problems and community-driven solutions. Using open-source LLMs, we develop a method to extract question-answer pairs from the forum, resulting in AoPS-Instruct, a dataset of more than 600,000 high-quality QA pairs. Our experiments demonstrate that fine-tuning LLMs on AoPS-Instruct improves their reasoning abilities across various benchmarks. Moreover, we build an automatic pipeline that introduces LiveAoPSBench, an evolving evaluation set with timestamps, derived from the latest forum data, providing a contamination-resistant benchmark for assessing LLM performance. Notably, we observe a significant decline in LLM performance over time, suggesting their success on older examples may stem from pre-training exposure rather than true reasoning ability. Our work presents a scalable approach to creating and maintaining large-scale, high-quality datasets for advanced math reasoning, offering valuable insights into the capabilities and limitations of LLMs in this domain. Our benchmark and code is available at https://github.com/DSL-Lab/aops
Authors: Paul Fuchs, Micha{\l} Sanocki, Julija Zavadlav
Abstract: Graph Neural Network (GNN) potentials relying on chemical locality offer near-quantum mechanical accuracy at significantly reduced computational costs. Message-passing GNNs model interactions beyond their immediate neighborhood by propagating local information between neighboring particles while remaining effectively local. However, locality precludes modeling long-range effects critical to many real-world systems, such as charge transfer, electrostatic interactions, and dispersion effects. In this work, we propose the Charge Equilibration Layer for Long-range Interactions (CELLI) to address the challenge of efficiently modeling non-local interactions. This novel architecture generalizes the classical charge equilibration (Qeq) method to a model-agnostic building block for modern equivariant GNN potentials. Therefore, CELLI extends the capability of GNNs to model long-range interactions while providing high interpretability through explicitly modeled charges. On benchmark systems, CELLI achieves state-of-the-art results for strictly local models. CELLI generalizes to diverse datasets and large structures while providing high computational efficiency and robust predictions.
Authors: Koen W. van Arem, Floris Goes-Smit, Jakob S\"ohl
Abstract: Transfers in professional football (soccer) are risky investments because of the large transfer fees and high risks involved. Although data-driven models can be used to improve transfer decisions, existing models focus on describing players' historical progress, leaving their future performance unknown. Moreover, recent developments have called for the use of explainable models combined with uncertainty quantification of predictions. This paper assesses explainable machine learning models based on predictive accuracy and uncertainty quantification methods for the prediction of the future development in quality and transfer value of professional football players. The predictive accuracy is studied by training the models to predict the quality and value of players one year ahead. This is carried out by training them on two data sets containing data-driven indicators describing the player quality and player value in historical settings. In general, the random forest model is found to be the most suitable model because it provides accurate predictions as well as an uncertainty quantification method that naturally arises from the bagging procedure of the random forest model. Additionally, this research shows that the development of player performance contains nonlinear patterns and interactions between variables, and that time series information can provide useful information for the modeling of player performance metrics. The resulting models can help football clubs make more informed, data-driven transfer decisions by forecasting player quality and transfer value.
Authors: Alexandra Stadler, Werner G. M\"uller, Radoslav Harman
Abstract: In artificial intelligence (AI), the complexity of many models and processes surpasses human understanding, making it challenging to determine why a specific prediction is made. This lack of transparency is particularly problematic in critical fields like healthcare, where trust in a model's predictions is paramount. As a result, the explainability of machine learning (ML) and other complex models has become a key area of focus. Efforts to improve model explainability often involve experimenting with AI systems and approximating their behavior through interpretable surrogate mechanisms. However, these procedures can be resource-intensive. Optimal design of experiments, which seeks to maximize the information obtained from a limited number of observations, offers promising methods for improving the efficiency of these explainability techniques. To demonstrate this potential, we explore Local Interpretable Model-agnostic Explanations (LIME), a widely used method introduced by Ribeiro et al. (2016). LIME provides explanations by generating new data points near the instance of interest and passing them through the model. While effective, this process can be computationally expensive, especially when predictions are costly or require many samples. LIME is highly versatile and can be applied to a wide range of models and datasets. In this work, we focus on models involving tabular data, regression tasks, and linear models as interpretable local approximations. By utilizing optimal design of experiments' techniques, we reduce the number of function evaluations of the complex model, thereby reducing the computational effort of LIME by a significant amount. We consider this modified version of LIME to be energy-efficient or "green".
Authors: Ahmed Heakl, Abdullah Sohail, Mukul Ranjan, Rania Hossam, Ghazi Shazan Ahmad, Mohamed El-Geish, Omar Maher, Zhiqiang Shen, Fahad Khan, Salman Khan
Abstract: With the growing adoption of Retrieval-Augmented Generation (RAG) in document processing, robust text recognition has become increasingly critical for knowledge extraction. While OCR (Optical Character Recognition) for English and other languages benefits from large datasets and well-established benchmarks, Arabic OCR faces unique challenges due to its cursive script, right-to-left text flow, and complex typographic and calligraphic features. We present KITAB-Bench, a comprehensive Arabic OCR benchmark that fills the gaps in current evaluation systems. Our benchmark comprises 8,809 samples across 9 major domains and 36 sub-domains, encompassing diverse document types including handwritten text, structured tables, and specialized coverage of 21 chart types for business intelligence. Our findings show that modern vision-language models (such as GPT-4o, Gemini, and Qwen) outperform traditional OCR approaches (like EasyOCR, PaddleOCR, and Surya) by an average of 60% in Character Error Rate (CER). Furthermore, we highlight significant limitations of current Arabic OCR models, particularly in PDF-to-Markdown conversion, where the best model Gemini-2.0-Flash achieves only 65% accuracy. This underscores the challenges in accurately recognizing Arabic text, including issues with complex fonts, numeral recognition errors, word elongation, and table structure detection. This work establishes a rigorous evaluation framework that can drive improvements in Arabic document analysis methods and bridge the performance gap with English OCR technologies.
Authors: Jose L. Bonilla, Krzysztof M. Graczyk, Artur M. Ankowski, Rwik Dharmapal Banerjee, Beata E. Kowal, Hemant Prasad, Jan T. Sobczyk
Abstract: We propose a new approach to simulate neutrino scattering events as an alternative to the standard Monte Carlo generator approach. Generative adversarial neural network (GAN) models are developed to simulate charged current neutrino-carbon collisions in the few-GeV energy range. We consider a simplified framework to generate muon kinematic variables, specifically its energy and scattering angle. GAN models are trained on simulation data from \nuwro{} Monte Carlo event generator. Two GAN models have been obtained: one simulating quasielastic neutrino-nucleus scatterings and another simulating all interactions at given neutrino energy. The models work for neutrino energy ranging from 300 MeV to 10 GeV. The performance of both models has been assessed using two statistical metrics. It is shown that both GAN models successfully reproduce the distribution of muon kinematics.
Authors: Akylas Stratigakos, Panagiotis Andrianesis
Abstract: Short-term forecasting models typically assume the availability of input data (features) when they are deployed and in use. However, equipment failures, disruptions, cyberattacks, may lead to missing features when such models are used operationally, which could negatively affect forecast accuracy, and result in suboptimal operational decisions. In this paper, we use adaptive robust optimization and adversarial machine learning to develop forecasting models that seamlessly handle missing data operationally. We propose linear- and neural network-based forecasting models with parameters that adapt to available features, combining linear adaptation with a novel algorithm for learning data-driven uncertainty set partitions. The proposed adaptive models do not rely on identifying historical missing data patterns and are suitable for real-time operations under stringent time constraints. Extensive numerical experiments on short-term wind power forecasting considering horizons from 15 minutes to 4 hours ahead illustrate that our proposed adaptive models are on par with imputation when data are missing for very short periods (e.g., when only the latest measurement is missing) whereas they significantly outperform imputation when data are missing for longer periods. We further provide insights by showcasing how linear adaptation and data-driven partitions (even with a few subsets) approach the performance of the optimal, yet impractical, method of retraining for every possible realization of missing data.
Authors: Yufeng Yang, Yi Zhou, Zhaosong Lu
Abstract: Distributionally robust optimization (DRO) is a powerful technique to train robust models against data distribution shift. This paper aims to solve regularized nonconvex DRO problems, where the uncertainty set is modeled by a so-called generalized Sinkhorn distance and the loss function is nonconvex and possibly unbounded. Such a distance allows to model uncertainty of distributions with different probability supports and divergence functions. For this class of regularized DRO problems, we derive a novel dual formulation taking the form of nested stochastic optimization, where the dual variable depends on the data sample. To solve the dual problem, we provide theoretical evidence to design a nested stochastic gradient descent (SGD) algorithm, which leverages stochastic approximation to estimate the nested stochastic gradients. We study the convergence rate of nested SGD and establish polynomial iteration and sample complexities that are independent of the data size and parameter dimension, indicating its potential for solving large-scale DRO problems. We conduct numerical experiments to demonstrate the efficiency and robustness of the proposed algorithm.
Authors: Arad Gast, Luc Le Magoarou, Nir Shlezinger
Abstract: The increasing demands for high-throughput and energy-efficient wireless communications are driving the adoption of extremely large antennas operating at high-frequency bands. In these regimes, multiple users will reside in the radiative near-field, and accurate localization becomes essential. Unlike conventional far-field systems that rely solely on DOA estimation, near-field localization exploits spherical wavefront propagation to recover both DOA and range information. While subspace-based methods, such as MUSIC and its extensions, offer high resolution and interpretability for near-field localization, their performance is significantly impacted by model assumptions, including non-coherent sources, well-calibrated arrays, and a sufficient number of snapshots. To address these limitations, this work proposes AI-aided subspace methods for near-field localization that enhance robustness to real-world challenges. Specifically, we introduce NF-SubspaceNet, a deep learning-augmented 2D MUSIC algorithm that learns a surrogate covariance matrix to improve localization under challenging conditions, and DCD-MUSIC, a cascaded AI-aided approach that decouples angle and range estimation to reduce computational complexity. We further develop a novel model-order-aware training method to accurately estimate the number of sources, that is combined with casting of near field subspace methods as AI models for learning. Extensive simulations demonstrate that the proposed methods outperform classical and existing deep-learning-based localization techniques, providing robust near-field localization even under coherent sources, miscalibrations, and few snapshots.
Authors: Yuanhong A, Guoyu Zhang, Yongcheng Zeng, Bo Zhang
Abstract: While the matrix completion problem has attracted considerable attention over the decades, few works address the nonignorable missing issue and all have their limitations. In this article, we propose a nuclear norm regularized row- and column-wise matrix U-statistic loss function for the generalized nonignorable missing mechanism, a flexible and generally applicable missing mechanism which contains both ignorable and nonignorable missing mechanism assumptions. The proposed method achieves computational efficiency comparable to the existing missing-at-random approaches, while providing the near minimax optimal statistical convergence rate guarantees for the more general nonignorable missing case. We propose an accelerated proximal gradient algorithm to solve the associated optimization problem, and characterize the interaction between algorithmic and statistical convergence. Simulations and real data analyzes further support the practical utility of the proposed method.
Authors: Hugo Lebeau
Abstract: We are interested in the estimation of a rank-one tensor signal when only a portion $\varepsilon$ of its noisy observation is available. We show that the study of this problem can be reduced to that of a random matrix model whose spectral analysis gives access to the reconstruction performance. These results shed light on and specify the loss of performance induced by an artificial reduction of the memory cost of a tensor via the deletion of a random part of its entries.
Authors: Zakaria Lamine, Abdelatif Hafid, Mohamed Rahouti
Abstract: This study presents a novel mathematical model derived from cohomology, leveraging the KEEL-proven theorem that establishes cohomology as tautological, generated by boundary classes of curves with fixed dual graphs. Simplicial complexes are constructed using skew-commutative graded algebra, and the structure theorem is applied to connect distinct homologies, enabling precise interpretations of the resulting geometric forms. The proposed model is utilized for protein structure analysis and prediction, with a specific application to the Flagellar Motor structure. This approach offers new insights into the geometric and algebraic foundations of biological macromolecular modeling, highlighting its potential for advancement in structural biology.
Authors: Anna Katariina Wisakanto, Joe Rogero, Avyay M. Casheekar, Richard Mallah
Abstract: Modern general-purpose artificial intelligence (AI) systems present an urgent risk management challenge, as their rapidly evolving capabilities and potential for catastrophic harm outpace our ability to reliably assess their risks. Current methods often rely on selective testing and undocumented assumptions about risk priorities, frequently failing to make a serious attempt at assessing the set of pathways through which AI systems pose direct or indirect risks to society and the biosphere. This paper introduces the probabilistic risk assessment (PRA) for AI framework, adapting established PRA techniques from high-reliability industries (e.g., nuclear power, aerospace) for the new challenges of advanced AI. The framework guides assessors in identifying potential risks, estimating likelihood and severity bands, and explicitly documenting evidence, underlying assumptions, and analyses at appropriate granularities. The framework's implementation tool synthesizes the results into a risk report card with aggregated risk estimates from all assessed risks. It introduces three methodological advances: (1) Aspect-oriented hazard analysis provides systematic hazard coverage guided by a first-principles taxonomy of AI system aspects (e.g. capabilities, domain knowledge, affordances); (2) Risk pathway modeling analyzes causal chains from system aspects to societal impacts using bidirectional analysis and incorporating prospective techniques; and (3) Uncertainty management employs scenario decomposition, reference scales, and explicit tracing protocols to structure credible projections with novelty or limited data. Additionally, the framework harmonizes diverse assessment methods by integrating evidence into comparable, quantified absolute risk estimates for lifecycle decisions. We have implemented this as a workbook tool for AI developers, evaluators, and regulators.
Authors: Sabbir M. Saleh, Nazim Madhavji, John Steinbacher
Abstract: Protecting cloud applications is critical in an era where security threats are increasingly sophisticated and persistent. Continuous Integration and Continuous Deployment (CI/CD) pipelines are particularly vulnerable, making innovative security approaches essential. This research explores the application of Natural Language Processing (NLP) techniques, specifically Topic Modelling, to analyse security-related text data and anticipate potential threats. We focus on Latent Dirichlet Allocation (LDA) and Probabilistic Latent Semantic Analysis (PLSA) to extract meaningful patterns from data sources, including logs, reports, and deployment traces. Using the Gensim framework in Python, these methods categorise log entries into security-relevant topics (e.g., phishing, encryption failures). The identified topics are leveraged to highlight patterns indicative of security issues across CI/CD's continuous stages (build, test, deploy). This approach introduces a semantic layer that supports early vulnerability recognition and contextual understanding of runtime behaviours.
Authors: Utkarsh Pratiush, Austin Houston, Kamyar Barakati, Aditya Raghavan, Dasol Yoon, Harikrishnan KP, Zhaslan Baraissov, Desheng Ma, Samuel S. Welborn, Mikolaj Jakowski, Shawn-Patrick Barhorst, Alexander J. Pattison, Panayotis Manganaris, Sita Sirisha Madugula, Sai Venkata Gayathri Ayyagari, Vishal Kennedy, Ralph Bulanadi, Michelle Wang, Kieran J. Pang, Ian Addison-Smith, Willy Menacho, Horacio V. Guzman, Alexander Kiefer, Nicholas Furth, Nikola L. Kolev, Mikhail Petrov, Viktoriia Liu, Sergey Ilyev, Srikar Rairao, Tommaso Rodani, Ivan Pinto-Huguet, Xuli Chen, Josep Crua\~nes, Marta Torrens, Jovan Pomar, Fanzhi Su, Pawan Vedanti, Zhiheng Lyu, Xingzhi Wang, Lehan Yao, Amir Taqieddin, Forrest Laskowski, Xiangyu Yin, Yu-Tsun Shao, Benjamin Fein-Ashley, Yi Jiang, Vineet Kumar, Himanshu Mishra, Yogesh Paul, Adib Bazgir, Rama chandra Praneeth Madugula, Yuwen Zhang, Pravan Omprakash, Jian Huang, Eric Montufar-Morales, Vivek Chawla, Harshit Sethi, Jie Huang, Lauri Kurki, Grace Guinan, Addison Salvador, Arman Ter-Petrosyan, Madeline Van Winkle, Steven R. Spurgeon, Ganesh Narasimha, Zijie Wu, Richard Liu, Yongtao Liu, Boris Slautin, Andrew R Lupini, Rama Vasudevan, Gerd Duscher, Sergei V. Kalinin
Abstract: Microscopy is a primary source of information on materials structure and functionality at nanometer and atomic scales. The data generated is often well-structured, enriched with metadata and sample histories, though not always consistent in detail or format. The adoption of Data Management Plans (DMPs) by major funding agencies promotes preservation and access. However, deriving insights remains difficult due to the lack of standardized code ecosystems, benchmarks, and integration strategies. As a result, data usage is inefficient and analysis time is extensive. In addition to post-acquisition analysis, new APIs from major microscope manufacturers enable real-time, ML-based analytics for automated decision-making and ML-agent-controlled microscope operation. Yet, a gap remains between the ML and microscopy communities, limiting the impact of these methods on physics, materials discovery, and optimization. Hackathons help bridge this divide by fostering collaboration between ML researchers and microscopy experts. They encourage the development of novel solutions that apply ML to microscopy, while preparing a future workforce for instrumentation, materials science, and applied ML. This hackathon produced benchmark datasets and digital twins of microscopes to support community growth and standardized workflows. All related code is available at GitHub: https://github.com/KalininGroup/Mic-hackathon-2024-codes-publication/tree/1.0.0.1
URLs: https://github.com/KalininGroup/Mic-hackathon-2024-codes-publication/tree/1.0.0.1
Authors: Michela Lapenna, Caterina De Bacco
Abstract: Graphs are a powerful data structure for representing relational data and are widely used to describe complex real-world systems. Probabilistic Graphical Models (PGMs) and Graph Neural Networks (GNNs) can both leverage graph-structured data, but their inherent functioning is different. The question is how do they compare in capturing the information contained in networked datasets? We address this objective by solving a link prediction task and we conduct three main experiments, on both synthetic and real networks: one focuses on how PGMs and GNNs handle input features, while the other two investigate their robustness to noisy features and increasing heterophily of the graph. PGMs do not necessarily require features on nodes, while GNNs cannot exploit the network edges alone, and the choice of input features matters. We find that GNNs are outperformed by PGMs when input features are low-dimensional or noisy, mimicking many real scenarios where node attributes might be scalar or noisy. Then, we find that PGMs are more robust than GNNs when the heterophily of the graph is increased. Finally, to assess performance beyond prediction tasks, we also compare the two frameworks in terms of their computational complexity and interpretability.
Authors: Zhijing Wan, Zhixiang Wang, Zheng Wang, Xin Xu, Shin'ichi Satoh
Abstract: One-shot subset selection serves as an effective tool to reduce deep learning training costs by identifying an informative data subset based on the information extracted by an information extractor (IE). Traditional IEs, typically pre-trained on the target dataset, are inherently dataset-dependent. Foundation models (FMs) offer a promising alternative, potentially mitigating this limitation. This work investigates two key questions: (1) Can FM-based subset selection outperform traditional IE-based methods across diverse datasets? (2) Do all FMs perform equally well as IEs for subset selection? Extensive experiments uncovered surprising insights: FMs consistently outperform traditional IEs on fine-grained datasets, whereas their advantage diminishes on coarse-grained datasets with noisy labels. Motivated by these finding, we propose RAM-APL (RAnking Mean-Accuracy of Pseudo-class Labels), a method tailored for fine-grained image datasets. RAM-APL leverages multiple FMs to enhance subset selection by exploiting their complementary strengths. Our approach achieves state-of-the-art performance on fine-grained datasets, including Oxford-IIIT Pet, Food-101, and Caltech-UCSD Birds-200-2011.
Authors: Akio Hayakawa, Masato Ishii, Takashi Shibuya, Yuki Mitsufuji
Abstract: We propose a novel step-by-step video-to-audio generation method that sequentially produces individual audio tracks, each corresponding to a specific sound event in the video. Our approach mirrors traditional Foley workflows, aiming to capture all sound events induced by a given video comprehensively. Each generation step is formulated as a guided video-to-audio synthesis task, conditioned on a target text prompt and previously generated audio tracks. This design is inspired by the idea of concept negation from prior compositional generation frameworks. To enable this guided generation, we introduce a training framework that leverages pre-trained video-to-audio models and eliminates the need for specialized paired datasets, allowing training on more accessible data. Experimental results demonstrate that our method generates multiple semantically distinct audio tracks for a single input video, leading to higher-quality composite audio synthesis than existing baselines.