Authors: Rylan Schaeffer, Joshua Kazdan, Yegor Denisov-Blanch, Brando Miranda, Matthias Gerstgrasser, Susan Zhang, Andreas Haupt, Isha Gupta, Elyas Obbad, Jesse Dodge, Jessica Zosa Forde, Koustuv Sinha, Francesco Orabona, Sanmi Koyejo, David Donoho
Abstract: Science progresses by iteratively advancing and correcting humanity's understanding of the world. In machine learning (ML) research, rapid advancements have led to an explosion of publications, but have also led to misleading, incorrect, flawed or perhaps even fraudulent studies being accepted and sometimes highlighted at ML conferences due to the fallibility of peer review. While such mistakes are understandable, ML conferences do not offer robust processes to help the field systematically correct when such errors are made.This position paper argues that ML conferences should establish a dedicated "Refutations and Critiques" (R & C) Track. This R & C Track would provide a high-profile, reputable platform to support vital research that critically challenges prior research, thereby fostering a dynamic self-correcting research ecosystem. We discuss key considerations including track design, review principles, potential pitfalls, and provide an illustrative example submission concerning a recent ICLR 2025 Oral. We conclude that ML conferences should create official, reputable mechanisms to help ML research self-correct.
Authors: Zhuqing Liu, Chaosheng Dong, Michinari Momma, Simone Shao, Shaoyuan Xu, Yan Gao, Haibo Yang, Jia Liu
Abstract: Recently, multi-objective optimization (MOO) has gained attention for its broad applications in ML, operations research, and engineering. However, MOO algorithm design remains in its infancy and many existing MOO methods suffer from unsatisfactory convergence rate and sample complexity performance. To address this challenge, in this paper, we propose an algorithm called STIMULUS( stochastic path-integrated multi-gradient recursive e\ulstimator), a new and robust approach for solving MOO problems. Different from the traditional methods, STIMULUS introduces a simple yet powerful recursive framework for updating stochastic gradient estimates to improve convergence performance with low sample complexity. In addition, we introduce an enhanced version of STIMULUS, termed STIMULUS-M, which incorporates a momentum term to further expedite convergence. We establish $O(1/T)$ convergence rates of the proposed methods for non-convex settings and $O (\exp{-\mu T})$ for strongly convex settings, where $T$ is the total number of iteration rounds. Additionally, we achieve the state-of-the-art $O \left(n+\sqrt{n}\epsilon^{-1}\right)$ sample complexities for non-convex settings and $O\left(n+ \sqrt{n} \ln ({\mu/\epsilon})\right)$ for strongly convex settings, where $\epsilon>0$ is a desired stationarity error. Moreover, to alleviate the periodic full gradient evaluation requirement in STIMULUS and STIMULUS-M, we further propose enhanced versions with adaptive batching called STIMULUS+/ STIMULUS-M+ and provide their theoretical analysis.
Authors: Jing Lu, Xuan Wu, Yizhun Tian, Songhan Fan, Yali Fang
Abstract: The Koopman theory is a powerful and effective modeling tool for converting nonlinear systems into linear representations, and flight trajectory prediction (FTP) is a complex nonlinear system. However, current models applying the Koopman theory to FTP tasks are not very effective, model interpretability is indeed an issue, and the Koopman operators are computationally intensive, resulting in long training times. To address this issue, this paper proposes a new modeling and control framework based on the HIPPO method, the Koopman theory, and state space equations from cybernetics: FlightKooba. Inspired by the idea of structural state space equations, FlightKooba directly constructs the Koopman operators from data. This makes the framework highly interpretable and significantly reduces the number of trainable parameters in the module, thereby greatly reducing training time. Experiments have demonstrated the superiority of the FlightKooba modeling method in terms of time and memory consumption (training time comparable to the Mamba module without using CUDA-level acceleration; memory reduced by more than 50% on most datasets, with a tenfold reduction in the number of parameters), essentially completing the FTP task. It provides a new method for the fast computation of the Koopman operators, opening up new possibilities for the combination of time series forecasting and control.
Authors: Ziru Zhang, Jiadong Yu, Danny H. K. Tsang
Abstract: The optimization of quality of experience (QoE) in multi-user virtual reality (VR) interactions demands a delicate balance between ultra-low latency, high-fidelity motion synchronization, and equitable resource allocation. While adaptive keyframe extraction mitigates transmission overhead, existing approaches often overlook the causal relationships among allocated bandwidth, CPU frequency, and user perception, limiting QoE gains. This paper proposes an intelligent framework to maximize QoE by integrating adaptive keyframe extraction with causal-aware reinforcement learning (RL). First, a novel QoE metric is formulated using the Weber-Fechner Law, combining perceptual sensitivity, attention-driven priorities, and motion reconstruction accuracy. The QoE optimization problem is then modeled as a mixed integer programming (MIP) task, jointly optimizing keyframe ratios, bandwidth, and computational resources under horizon-fairness constraints. We propose Partial State Causal Deep Deterministic Policy Gradient (PS-CDDPG), which integrates the Deep Deterministic Policy Gradient (DDPG) method with causal influence detection. By leveraging causal information regarding how QoE is influenced and determined by various actions, we explore actions guided by weights calculated from causal inference (CI), which in turn improves training efficiency. Experiments conducted with the CMU Motion Capture Database demonstrate that our framework significantly reduces interactive latency, enhances QoE, and maintains fairness, achieving superior performance compared to benchmark methods.
Authors: Qinghui Gong, Xue Yang, Xiaohu Tang
Abstract: Machine unlearning aims to selectively remove class-specific knowledge from pretrained neural networks to satisfy privacy regulations such as the GDPR. Existing methods typically face a trade-off between unlearning speed and preservation of predictive accuracy, often incurring either high computational overhead or significant performance degradation on retained classes. In this paper, we propose a novel class-aware soft pruning framework leveraging orthogonal convolutional kernel regularization to achieve rapid and precise forgetting with millisecond-level response times. By enforcing orthogonality constraints during training, our method decorrelates convolutional filters and disentangles feature representations, while efficiently identifying class-specific channels through activation difference analysis. Extensive evaluations across multiple architectures and datasets demonstrate stable pruning with near-instant execution, complete forgetting of targeted classes, and minimal accuracy loss on retained data. Experiments on CIFAR-10, CIFAR-100, and TinyImageNet confirm that our approach substantially reduces membership inference attack risks and accelerates unlearning by orders of magnitude compared to state-of-the-art baselines. This framework provides an efficient, practical solution for real-time machine unlearning in Machine Learning as a Service (MLaaS) scenarios.
Authors: Jingzhi Hu, Geoffrey Ye Li
Abstract: Due to the surging amount of AI-generated content (AIGC), its provisioning to edges and mobile users from the cloud incurs substantial traffic on networks. Generative semantic communication (GSC) offers a promising solution by transmitting highly compact information, i.e., prompt text and latent representations, instead of high-dimensional AIGC data. However, GSC relies on the alignment between the knowledge in the cloud generative AI (GAI) and that possessed by the edges and users, and between the knowledge for wireless transmission and that of actual channels, which remains challenging. In this paper, we propose DeKA-g, a distillation-enabled knowledge alignment algorithm for GSC systems. The core idea is to distill the generation knowledge from the cloud-GAI into low-rank matrices, which can be incorporated by the edge and used to adapt the transmission knowledge to diverse wireless channel conditions. DeKA-g comprises two novel methods: metaword-aided knowledge distillation (MAKD) and variable-rate grouped SNR adaptation (VGSA). For MAKD, an optimized metaword is employed to enhance the efficiency of knowledge distillation, while VGSA enables efficient adaptation to diverse compression rates and SNR ranges. From simulation results, DeKA-g improves the alignment between the edge-generated images and the cloud-generated ones by 44%. Moreover, it adapts to compression rates with 116% higher efficiency than the baseline and enhances the performance in low-SNR conditions by 28%.
Authors: Antoine Pesenti, Aidan OSullivan
Abstract: Electricity markets are highly complex, involving lots of interactions and complex dependencies that make it hard to understand the inner workings of the market and what is driving prices. Econometric methods have been developed for this, white-box models, however, they are not as powerful as deep neural network models (DNN). In this paper, we use a DNN to forecast the price and then use XAI methods to understand the factors driving the price dynamics in the market. The objective is to increase our understanding of how different electricity markets work. To do that, we apply explainable methods such as SHAP and Gradient, combined with visual techniques like heatmaps (saliency maps) to analyse the behaviour and contributions of various features across five electricity markets. We introduce the novel concepts of SSHAP values and SSHAP lines to enhance the complex representation of high-dimensional tabular models.
Authors: Miguel N. Font, Jos\'e L. Jorro-Aragoneses, Carlos M. Ala\'iz
Abstract: Neural Networks have high accuracy in solving problems where it is difficult to detect patterns or create a logical model. However, these algorithms sometimes return wrong solutions, which become problematic in high-risk domains like medical diagnosis or autonomous driving. One strategy to detect and mitigate these errors is the measurement of the uncertainty over neural network decisions. In this paper, we present a novel post-hoc framework for measuring the uncertainty of a decision based on retrieved training cases that have a similar activation vector to the query for each layer. Based on these retrieved cases, we propose two new metrics: Decision Change and Layer Uncertainty, which capture changes in nearest-neighbor class distributions across layers. We evaluated our approach in a classification model for two datasets: CIFAR-10 and MNIST. The results show that these metrics enhance uncertainty estimation, especially in challenging classification tasks, outperforming softmax-based confidence.
Authors: Efe \c{C}ak{\i}r, Patrick Dumond
Abstract: Bearing faults in rotating machinery can lead to significant operational disruptions and maintenance costs. Modern methods for bearing fault diagnosis rely heavily on vibration analysis and machine learning techniques, which often require extensive labeled data and may not adapt well to dynamic environments. This study explores the feasibility of reinforcement learning (RL), specifically Deep Q-Networks (DQNs), for bearing fault classification tasks in machine condition monitoring to enhance the accuracy and adaptability of bearing fault diagnosis. The results demonstrate that while RL models developed in this study can match the performance of traditional supervised learning models under controlled conditions, they excel in adaptability when equipped with optimized reward structures. However, their computational demands highlight areas for further improvement. These findings demonstrate RL's potential to complement traditional methods, paving the way for adaptive diagnostic frameworks.
Authors: Shuchen Xue, Tianyu Xie, Tianyang Hu, Zijin Feng, Jiacheng Sun, Kenji Kawaguchi, Zhenguo Li, Zhi-Ming Ma
Abstract: Large language models (LLMs) predominantly use autoregressive (AR) approaches, but masked diffusion models (MDMs) are emerging as viable alternatives. A key challenge in comparing AR and MDM paradigms is their typical architectural difference: AR models are often decoder-only, while MDMs have largely been encoder-only. This practice of changing both the modeling paradigm and architecture simultaneously makes direct comparisons unfair, as it's hard to distinguish whether observed differences stem from the paradigm itself or the architectural shift. This research evaluates MDMs within a decoder-only framework to: (1) equitably compare MDM (as Any-Order AR, or AO-AR) and standard AR paradigms. Our investigation suggests that the standard AO-AR objective, which averages over all token permutations, may benefit from refinement, as many permutations appear less informative compared to the language's inherent left-to-right structure. (2) Investigate architectural influences (decoder-only vs. encoder-only) within MDMs. We demonstrate that while encoder-only MDMs model a simpler conditional probability space, decoder-only MDMs can achieve dramatic generation speedups ($\sim25\times$) and comparable perplexity with temperature annealing despite modeling a vastly larger space, highlighting key trade-offs. This work thus decouples core paradigm differences from architectural influences, offering insights for future model design. Code is available at https://github.com/scxue/AO-GPT-MDM.
Authors: Tomas M. Bosschieter, Luis Franca, Jessica Wolk, Yiyuan Wu, Bella Mehta, Joseph Dehoney, Orsolya Kiss, Fiona C. Baker, Qingyu Zhao, Rich Caruana, Kilian M. Pohl
Abstract: While analyzing the importance of features has become ubiquitous in interpretable machine learning, the joint signal from a group of related features is sometimes overlooked or inadvertently excluded. Neglecting the joint signal could bypass a critical insight: in many instances, the most significant predictors are not isolated features, but rather the combined effect of groups of features. This can be especially problematic for datasets that contain natural groupings of features, including multimodal datasets. This paper introduces a novel approach to determine the importance of a group of features for Generalized Additive Models (GAMs) that is efficient, requires no model retraining, allows defining groups posthoc, permits overlapping groups, and remains meaningful in high-dimensional settings. Moreover, this definition offers a parallel with explained variation in statistics. We showcase properties of our method on three synthetic experiments that illustrate the behavior of group importance across various data regimes. We then demonstrate the importance of groups of features in identifying depressive symptoms from a multimodal neuroscience dataset, and study the importance of social determinants of health after total hip arthroplasty. These two case studies reveal that analyzing group importance offers a more accurate, holistic view of the medical issues compared to a single-feature analysis.
Authors: Gabor Petnehazi, Bernadett Aradi
Abstract: The explosive growth of complex datasets across various modalities necessitates advanced analytical tools that not only group data effectively but also provide human-understandable insights into the discovered structures. We introduce HERCULES (Hierarchical Embedding-based Recursive Clustering Using LLMs for Efficient Summarization), a novel algorithm and Python package designed for hierarchical k-means clustering of diverse data types, including text, images, and numeric data (processed one modality per run). HERCULES constructs a cluster hierarchy by recursively applying k-means clustering, starting from individual data points at level 0. A key innovation is its deep integration of Large Language Models (LLMs) to generate semantically rich titles and descriptions for clusters at each level of the hierarchy, significantly enhancing interpretability. The algorithm supports two main representation modes: `direct' mode, which clusters based on original data embeddings or scaled numeric features, and `description' mode, which clusters based on embeddings derived from LLM-generated summaries. Users can provide a `topic\_seed' to guide LLM-generated summaries towards specific themes. An interactive visualization tool facilitates thorough analysis and understanding of the clustering results. We demonstrate HERCULES's capabilities and discuss its potential for extracting meaningful, hierarchical knowledge from complex datasets.
Authors: Geonwoo Cho, Jaegyun Im, Jihwan Lee, Hojun Yi, Sejin Kim, Sundong Kim
Abstract: Generalizing deep reinforcement learning agents to unseen environments remains a significant challenge. One promising solution is Unsupervised Environment Design (UED), a co-evolutionary framework in which a teacher adaptively generates tasks with high learning potential, while a student learns a robust policy from this evolving curriculum. Existing UED methods typically measure learning potential via regret, the gap between optimal and current performance, approximated solely by value-function loss. Building on these approaches, we introduce the transition prediction error as an additional term in our regret approximation. To capture how training on one task affects performance on others, we further propose a lightweight metric called co-learnability. By combining these two measures, we present Transition-aware Regret Approximation with Co-learnability for Environment Design (TRACED). Empirical evaluations show that TRACED yields curricula that improve zero-shot generalization across multiple benchmarks while requiring up to 2x fewer environment interactions than strong baselines. Ablation studies confirm that the transition prediction error drives rapid complexity ramp-up and that co-learnability delivers additional gains when paired with the transition prediction error. These results demonstrate how refined regret approximation and explicit modeling of task relationships can be leveraged for sample-efficient curriculum design in UED.
Authors: Francesco Ignazio Re, Andreas Opedal, Glib Manaiev, Mario Giulianelli, Ryan Cotterell
Abstract: Reading is a process that unfolds across space and time, alternating between fixations where a reader focuses on a specific point in space, and saccades where a reader rapidly shifts their focus to a new point. An ansatz of psycholinguistics is that modeling a reader's fixations and saccades yields insight into their online sentence processing. However, standard approaches to such modeling rely on aggregated eye-tracking measurements and models that impose strong assumptions, ignoring much of the spatio-temporal dynamics that occur during reading. In this paper, we propose a more general probabilistic model of reading behavior, based on a marked spatio-temporal point process, that captures not only how long fixations last, but also where they land in space and when they take place in time. The saccades are modeled using a Hawkes process, which captures how each fixation excites the probability of a new fixation occurring near it in time and space. The duration time of fixation events is modeled as a function of fixation-specific predictors convolved across time, thus capturing spillover effects. Empirically, our Hawkes process model exhibits a better fit to human saccades than baselines. With respect to fixation durations, we observe that incorporating contextual surprisal as a predictor results in only a marginal improvement in the model's predictive accuracy. This finding suggests that surprisal theory struggles to explain fine-grained eye movements.
Authors: Dengyu Wu, Jiechen Chen, H. Vincent Poor, Bipin Rajendran, Osvaldo Simeone
Abstract: Neuromorphic computing offers an energy-efficient alternative to conventional deep learning accelerators for real-time time-series processing. However, many edge applications, such as wireless sensing and audio recognition, generate streaming signals with rich spectral features that are not effectively captured by conventional leaky integrate-and-fire (LIF) spiking neurons. This paper investigates a wireless split computing architecture that employs resonate-and-fire (RF) neurons with oscillatory dynamics to process time-domain signals directly, eliminating the need for costly spectral pre-processing. By resonating at tunable frequencies, RF neurons extract time-localized spectral features while maintaining low spiking activity. This temporal sparsity translates into significant savings in both computation and transmission energy. Assuming an OFDM-based analog wireless interface for spike transmission, we present a complete system design and evaluate its performance on audio classification and modulation classification tasks. Experimental results show that the proposed RF-SNN architecture achieves comparable accuracy to conventional LIF-SNNs and ANNs, while substantially reducing spike rates and total energy consumption during inference and communication.
Authors: Shanika Iroshi Nanayakkara, Shiva Raj Pokhrel
Abstract: Client heterogeneity poses significant challenges to the performance of Quantum Federated Learning (QFL). To overcome these limitations, we propose a new approach leveraging deep unfolding, which enables clients to autonomously optimize hyperparameters, such as learning rates and regularization factors, based on their specific training behavior. This dynamic adaptation mitigates overfitting and ensures robust optimization in highly heterogeneous environments where standard aggregation methods often fail. Our framework achieves approximately 90% accuracy, significantly outperforming traditional methods, which typically yield around 55% accuracy, as demonstrated through real-time training on IBM quantum hardware and Qiskit Aer simulators. By developing self adaptive fine tuning, the proposed method proves particularly effective in critical applications such as gene expression analysis and cancer detection, enhancing diagnostic precision and predictive modeling within quantum systems. Our results are attributed to convergence-aware, learnable optimization steps intrinsic to the deep unfolded framework, which maintains the generalization. Hence, this study addresses the core limitations of conventional QFL, streamlining its applicability to any complex challenges such as healthcare and genomic research.
Authors: Ryan Hildebrant, Rahul Bhope, Sharad Mehrotra, Christopher Tull, Nalini Venkatasubramanian
Abstract: Time series imputation models have traditionally been developed using complete datasets with artificial masking patterns to simulate missing values. However, in real-world infrastructure monitoring, practitioners often encounter datasets where large amounts of data are missing and follow complex, heterogeneous patterns. We introduce DIM-SUM, a preprocessing framework for training robust imputation models that bridges the gap between artificially masked training data and real missing patterns. DIM-SUM combines pattern clustering and adaptive masking strategies with theoretical learning guarantees to handle diverse missing patterns actually observed in the data. Through extensive experiments on over 2 billion readings from California water districts, electricity datasets, and benchmarks, we demonstrate that DIM-SUM outperforms traditional methods by reaching similar accuracy with lower processing time and significantly less training data. When compared against a large pre-trained model, DIM-SUM averages 2x higher accuracy with significantly less inference time.
Authors: Salva R\"uhling Cachay, Miika Aittala, Karsten Kreis, Noah Brenowitz, Arash Vahdat, Morteza Mardani, Rose Yu
Abstract: Diffusion models are a powerful tool for probabilistic forecasting, yet most applications in high-dimensional chaotic systems predict future snapshots one-by-one. This common approach struggles to model complex temporal dependencies and fails to explicitly account for the progressive growth of uncertainty inherent to such systems. While rolling diffusion frameworks, which apply increasing noise to forecasts at longer lead times, have been proposed to address this, their integration with state-of-the-art, high-fidelity diffusion techniques remains a significant challenge. We tackle this problem by introducing Elucidated Rolling Diffusion Models (ERDM), the first framework to successfully unify a rolling forecast structure with the principled, performant design of Elucidated Diffusion Models (EDM). To do this, we adapt the core EDM components-its noise schedule, network preconditioning, and Heun sampler-to the rolling forecast setting. The success of this integration is driven by three key contributions: (i) a novel loss weighting scheme that focuses model capacity on the mid-range forecast horizons where determinism gives way to stochasticity; (ii) an efficient initialization strategy using a pre-trained EDM for the initial window; and (iii) a bespoke hybrid sequence architecture for robust spatiotemporal feature extraction under progressive denoising. On 2D Navier-Stokes simulations and ERA5 global weather forecasting at 1.5^\circ resolution, ERDM consistently outperforms key diffusion-based baselines, including conditional autoregressive EDM. ERDM offers a flexible and powerful general framework for tackling diffusion-based sequence generation problems where modeling escalating uncertainty is paramount. Code is available at: https://github.com/salvaRC/erdm
Authors: Nathan Stromberg, Christos Thrampoulidis, Lalitha Sankar
Abstract: While machine learning models become more capable in discriminative tasks at scale, their ability to overcome biases introduced by training data has come under increasing scrutiny. Previous results suggest that there are two extremes of parameterization with very different behaviors: the population (underparameterized) setting where loss weighting is optimal and the separable overparameterized setting where loss weighting is ineffective at ensuring equal performance across classes. This work explores the regime of last layer retraining (LLR) in which the unseen limited (retraining) data is frequently inseparable and the model proportionately sized, falling between the two aforementioned extremes. We show, in theory and practice, that loss weighting is still effective in this regime, but that these weights \emph{must} take into account the relative overparameterization of the model.
Authors: Prithvi Poddar, Ehsan Tarkesh Esfahani, Karthik Dantu, Souma Chowdhury
Abstract: Operations in disaster response, search \& rescue, and military missions that involve multiple agents demand automated processes to support the planning of the courses of action (COA). Moreover, traverse-affecting changes in the environment (rain, snow, blockades, etc.) may impact the expected performance of a COA, making it desirable to have a pool of COAs that are diverse in task distributions across agents. Further, variations in agent capabilities, which could be human crews and/or autonomous systems, present practical opportunities and computational challenges to the planning process. This paper presents a new theoretical formulation and computational framework to generate such diverse pools of COAs for operations with soft variations in agent-task compatibility. Key to the problem formulation is a graph abstraction of the task space and the pool of COAs itself to quantify its diversity. Formulating the COAs as a centralized multi-robot task allocation problem, a genetic algorithm is used for (order-ignoring) allocations of tasks to each agent that jointly maximize diversity within the COA pool and overall compatibility of the agent-task mappings. A graph neural network is trained using a policy gradient approach to then perform single agent task sequencing in each COA, which maximizes completion rates adaptive to task features. Our tests of the COA generation process in a simulated environment demonstrate significant performance gain over a random walk baseline, small optimality gap in task sequencing, and execution time of about 50 minutes to plan up to 20 COAs for 5 agent/100 task operations.
Authors: Mohammad M Maheri, Alex Davidson, Hamed Haddadi
Abstract: Machine learning providers commonly distribute global models to edge devices, which subsequently personalize these models using local data. However, issues such as copyright infringements, biases, or regulatory requirements may require the verifiable removal of certain data samples across all edge devices. Ensuring that edge devices correctly execute such unlearning operations is critical to maintaining integrity. In this work, we introduce a verification framework leveraging zero-knowledge proofs, specifically zk-SNARKs, to confirm data unlearning on personalized edge-device models without compromising privacy. We have developed algorithms explicitly designed to facilitate unlearning operations that are compatible with efficient zk-SNARK proof generation, ensuring minimal computational and memory overhead suitable for constrained edge environments. Furthermore, our approach carefully preserves personalized enhancements on edge devices, maintaining model performance post-unlearning. Our results affirm the practicality and effectiveness of this verification framework, demonstrating verifiable unlearning with minimal degradation in personalization-induced performance improvements. Our methodology ensures verifiable, privacy-preserving, and effective machine unlearning across edge devices.
Authors: Ankur Garg, Xuemin Yu, Hassan Sajjad, Samira Ebrahimi Kahou
Abstract: Uncovering emergent concepts across transformer layers remains a significant challenge because the residual stream linearly mixes and duplicates information, obscuring how features evolve within large language models. Current research efforts primarily inspect neural representations at single layers, thereby overlooking this cross-layer superposition and the redundancy it introduces. These representations are typically either analyzed directly for activation patterns or passed to probing classifiers that map them to a limited set of predefined concepts. To address these limitations, we propose \gls{clvqvae}, a framework that uses vector quantization to map representations across layers and in the process collapse duplicated residual-stream features into compact, interpretable concept vectors. Our approach uniquely combines top-$k$ temperature-based sampling during quantization with EMA codebook updates, providing controlled exploration of the discrete latent space while maintaining code-book diversity. We further enhance the framework with scaled-spherical k-means++ for codebook initialization, which clusters by directional similarity rather than magnitude, better aligning with semantic structure in word embedding space.
Authors: Soheil Abadifard, Fazli Can
Abstract: The classification of imbalanced data streams, which have unequal class distributions, is a key difficulty in machine learning, especially when dealing with multiple classes. While binary imbalanced data stream classification tasks have received considerable attention, only a few studies have focused on multi-class imbalanced data streams. Effectively managing the dynamic imbalance ratio is a key challenge in this domain. This study introduces a novel, robust, and resilient approach to address these challenges by integrating Locality Sensitive Hashing with Random Hyperplane Projections (LSH-RHP) into the Dynamic Ensemble Diversification (DynED) framework. To the best of our knowledge, we present the first application of LSH-RHP for undersampling in the context of imbalanced non-stationary data streams. The proposed method undersamples the majority classes by utilizing LSH-RHP, provides a balanced training set, and improves the ensemble's prediction performance. We conduct comprehensive experiments on 23 real-world and ten semi-synthetic datasets and compare LSH-DynED with 15 state-of-the-art methods. The results reveal that LSH-DynED outperforms other approaches in terms of both Kappa and mG-Mean effectiveness measures, demonstrating its capability in dealing with multi-class imbalanced non-stationary data streams. Notably, LSH-DynED performs well in large-scale, high-dimensional datasets with considerable class imbalances and demonstrates adaptation and robustness in real-world circumstances. To motivate our design, we review existing methods for imbalanced data streams, outline key challenges, and offer guidance for future work. For the reproducibility of our results, we have made our implementation available on GitHub.
Authors: Hirad Daneshvar, Reza Samavi
Abstract: Graph Neural Networks (GNNs) have shown remarkable performance in the healthcare domain. However, what remained challenging is quantifying the predictive uncertainty of GNNs, which is an important aspect of trustworthiness in clinical settings. While Bayesian and ensemble methods can be used to quantify uncertainty, they are computationally expensive. Additionally, the disagreement metric used by ensemble methods to compute uncertainty cannot capture the diversity of models in an ensemble network. In this paper, we propose a novel method, based on knowledge distillation, to quantify GNNs' uncertainty more efficiently and with higher precision. We apply self-distillation, where the same network serves as both the teacher and student models, thereby avoiding the need to train several networks independently. To ensure the impact of self-distillation, we develop an uncertainty metric that captures the diverse nature of the network by assigning different weights to each GNN classifier. We experimentally evaluate the precision, performance, and ability of our approach in distinguishing out-of-distribution data on two graph datasets: MIMIC-IV and Enzymes. The evaluation results demonstrate that the proposed method can effectively capture the predictive uncertainty of the model while having performance similar to that of the MC Dropout and ensemble methods. The code is publicly available at https://github.com/tailabTMU/UQ_GNN.
Authors: Peter Bloem
Abstract: We investigate the use of randomly generated data for the sake of pre-training a model. We justify this approach theoretically from the perspective of algorithmic complexity, building on recent research that shows that sequence models can be trained to approximate Solomonoff induction. We derive similar, but complementary theoretical results. We show empirically that synthetically generated data can be used to pre-train a model before the data is seen. We replicate earlier results that models trained this way show zero-shot in-context learning across a variety of datasets, and that this performance improves with scale. We extend earlier results to real-world data, and show that finetuning a model after pre-training offers faster convergence and better generalization.
Authors: Zhicheng Zhang, Ziyan Wang, Yali Du, Fei Fang
Abstract: Developing effective instruction-following policies in reinforcement learning remains challenging due to the reliance on extensive human-labeled instruction datasets and the difficulty of learning from sparse rewards. In this paper, we propose a novel approach that leverages the capabilities of large language models (LLMs) to automatically generate open-ended instructions retrospectively from previously collected agent trajectories. Our core idea is to employ LLMs to relabel unsuccessful trajectories by identifying meaningful subtasks the agent has implicitly accomplished, thereby enriching the agent's training data and substantially alleviating reliance on human annotations. Through this open-ended instruction relabeling, we efficiently learn a unified instruction-following policy capable of handling diverse tasks within a single policy. We empirically evaluate our proposed method in the challenging Craftax environment, demonstrating clear improvements in sample efficiency, instruction coverage, and overall policy performance compared to state-of-the-art baselines. Our results highlight the effectiveness of utilizing LLM-guided open-ended instruction relabeling to enhance instruction-following reinforcement learning.
Authors: Cristian Minoccheri, Sophia Tesic, Kayvan Najarian, Ryan Stidham
Abstract: Phenotyping is the process of distinguishing groups of patients to identify different types of disease progression. A recent trend employs low-rank matrix and tensor factorization methods for their capability of dealing with multi-modal, heterogeneous, and missing data. Symptom quantification is crucial for understanding patient experiences in inflammatory bowel disease, especially in conditions such as ulcerative colitis (UC). However, patient-reported symptoms are typically noisy, subjective, and significantly more sparse than other data types. For this reason, they are usually not included in phenotyping and other machine learning methods. This paper explores the application of computational phenotyping to leverage Patient-Reported Outcomes (PROs) using a novel supervised coupled matrix-tensor factorization (SCMTF) method, which integrates temporal PROs and temporal labs with static features to predict medication persistence in ulcerative colitis. This is the first tensor-based method that is both supervised and coupled, it is the first application to the UC domain, and the first application to PROs. We use a deep learning framework that makes the model flexible and easy to train. The proposed method allows us to handle the large amount of missing data in the PROs. The best model predicts changes in medication 8 and 20 months in the future with AUCs of 0.853 and 0.803 on the test set respectively. We derive interpretable phenotypes consisting of static features and temporal features (including their temporal patterns). We show that low-rank matrix and tensor based phenotyping can be successfully applied to the UC domain and to highly missing PRO data. We identify phenotypes useful to predict medication persistence - these phenotypes include several symptom variables, showing that PROs contain relevant infromation that is usually discarded.
Authors: Ainaz Jamshidi, Dongchan Kim, Muhammad Arif
Abstract: Predictive maintenance (PdM) has become a crucial element of modern industrial practice. PdM plays a significant role in operational dependability and cost management by decreasing unforeseen downtime and optimizing asset life cycle management. Machine learning and deep learning have enabled more precise forecasts of equipment failure and remaining useful life (RUL). Although many studies have been conducted on PdM, there has not yet been a standalone comparative study between regression- and classification-based approaches. In this review, we look across a range of PdM methodologies, while focusing more strongly on the comparative use of classification and regression methods in prognostics. While regression-based methods typically provide estimates of RUL, classification-based methods present a forecast of the probability of failure across defined time intervals. Through a comprehensive analysis of recent literature, we highlight key advancements, challenges-such as data imbalance and high-dimensional feature spaces-and emerging trends, including hybrid approaches and AI-enabled prognostic systems. This review aims to provide researchers and practitioners with an awareness of the strengths and compromises of various PdM methods and to help identify future research and build more robust, directed adaptive maintenance systems. Future work may include a systematic review of practical aspects such as public datasets, benchmarking platforms, and open-source tools to support the advancement of PdM research.
Authors: Krishna Praneet Gudipaty, Walid A. Hanafy, Kaan Ozkara, Qianlin Liang, Jesse Milzman, Prashant Shenoy, Suhas Diggavi
Abstract: AI inference at the edge is becoming increasingly common for low-latency services. However, edge environments are power- and resource-constrained, and susceptible to failures. Conventional failure resilience approaches, such as cloud failover or compressed backups, often compromise latency or accuracy, limiting their effectiveness for critical edge inference services. In this paper, we propose Multi-Level Ensemble Learning (MEL), a new framework for resilient edge inference that simultaneously trains multiple lightweight backup models capable of operating collaboratively, refining each other when multiple servers are available, and independently under failures while maintaining good accuracy. Specifically, we formulate our approach as a multi-objective optimization problem with a loss formulation that inherently encourages diversity among individual models to promote mutually refining representations, while ensuring each model maintains good standalone performance. Empirical evaluations across vision, language, and audio datasets show that MEL provides performance comparable to original architectures while also providing fault tolerance and deployment flexibility across edge platforms. Our results show that our ensemble model, sized at 40\% of the original model, achieves similar performance, while preserving 95.6\% of ensemble accuracy in the case of failures when trained using MEL.
Authors: Patrick Alan Johnson, Gabriel Tseng, Yawen Zhang, Heather Heward, Virginia Sjahli, Favyen Bastani, Joseph Redmon, Patrick Beukema
Abstract: Wildfires are increasing in intensity and severity at an alarming rate. Recent advances in AI and publicly available satellite data enable monitoring critical wildfire risk factors globally, at high resolution and low latency. Live Fuel Moisture Content (LFMC) is a critical wildfire risk factor and is valuable for both wildfire research and operational response. However, ground-based LFMC samples are both labor intensive and costly to acquire, resulting in sparse and infrequent updates. In this work, we explore the use of a pretrained, highly-multimodal earth-observation model for generating large-scale spatially complete (wall-to-wall) LFMC maps. Our approach achieves significant improvements over previous methods using randomly initialized models (20 reduction in RMSE). We provide an automated pipeline that enables rapid generation of these LFMC maps across the United States, and demonstrate its effectiveness in two regions recently impacted by wildfire (Eaton and Palisades).
Authors: Bala Rajesh Konkathi, Arun K. Tangirala
Abstract: Discovering pure causes or driver variables in deterministic LTI systems is of vital importance in the data-driven reconstruction of causal networks. A recent work by Kathari and Tangirala, proposed in 2022, formulated the causal discovery method as a constraint identification problem. The constraints are identified using a dynamic iterative PCA (DIPCA)-based approach for dynamical systems corrupted with Gaussian measurement errors. The DIPCA-based method works efficiently for dynamical systems devoid of any algebraic relations. However, several dynamical systems operate under feedback control and/or are coupled with conservation laws, leading to differential-algebraic (DAE) or mixed causal systems. In this work, a method, namely the partition of variables (PoV), for causal discovery in LTI-DAE systems is proposed. This method is superior to the method that was presented by Kathari and Tangirala (2022), as PoV also works for pure dynamical systems, which are devoid of algebraic equations. The proposed method identifies the causal drivers up to a minimal subset. PoV deploys DIPCA to first determine the number of algebraic relations ($n_a$), the number of dynamical relations ($n_d$) and the constraint matrix. Subsequently, the subsets are identified through an admissible partitioning of the constraint matrix by finding the condition number of it. Case studies are presented to demonstrate the effectiveness of the proposed method.
Authors: Ronald Katende
Abstract: We develop a principled framework for discovering causal structure in partial differential equations (PDEs) using physics-informed neural networks and counterfactual perturbations. Unlike classical residual minimization or sparse regression methods, our approach quantifies operator-level necessity through functional interventions on the governing dynamics. We introduce causal sensitivity indices and structural deviation metrics to assess the influence of candidate differential operators within neural surrogates. Theoretically, we prove exact recovery of the causal operator support under restricted isometry or mutual coherence conditions, with residual bounds guaranteeing identifiability. Empirically, we validate the framework on both synthetic and real-world datasets across climate dynamics, tumor diffusion, and ocean flows. Our method consistently recovers governing operators even under noise, redundancy, and data scarcity, outperforming standard PINNs and DeepONets in structural fidelity. This work positions causal PDE discovery as a tractable and interpretable inference task grounded in structural causal models and variational residual analysis.
Authors: Ruokai Yin, Yuhang Li, Donghyun Lee, Priyadarshini Panda
Abstract: Large language models (LLMs) deliver strong performance but are difficult to deploy due to high memory and compute costs. While pruning reduces these demands, most methods ignore activation sparsity observed at runtime. We reinterpret activation sparsity as dynamic structured weight sparsity and propose DuoGPT, a unified framework that constructs dual-sparse (spMspV) workloads by combining unstructured weight pruning with activation sparsity. To preserve accuracy, we extend the Optimal Brain Compression (OBC) framework with activation-aware calibration and introduce output residuals from the dense model as correction terms. We further optimize the solution for efficient GPU execution, enabling scalability to billion-parameter LLMs. Evaluations on LLaMA-2 and LLaMA-3 show that DuoGPT outperforms state-of-the-art structured pruning methods by up to 9.17% accuracy at an iso-speedup of 1.39$\times$ compared to the baseline dense model.
Authors: Cl\'ement L. Canonne, Yash Pote, Uddalok Sarkar
Abstract: A growing fraction of all code is sampled from Large Language Models (LLMs). We investigate the problem of attributing code generated by language models using hypothesis testing to leverage established techniques and guarantees. Given a set of samples $S$ and a suspect model $\mathcal{L}^*$, our goal is to assess the likelihood of $S$ originating from $\mathcal{L}^*$. Due to the curse of dimensionality, this is intractable when only samples from the LLM are given: to circumvent this, we use both samples and density estimates from the LLM, a form of access commonly available. We introduce $\mathsf{Anubis}$, a zero-shot attribution tool that frames attribution as a distribution testing problem. Our experiments on a benchmark of code samples show that $\mathsf{Anubis}$ achieves high AUROC scores ( $\ge0.9$) when distinguishing between LLMs like DeepSeek-Coder, CodeGemma, and Stable-Code using only $\approx 2000$ samples.
Authors: Eduardo Gutierrez Maestro, Hadi Banaee, Amy Loutfi
Abstract: Affective priming exemplifies the challenge of ambiguity in affective computing. While the community has largely addressed this issue from a label-based perspective, identifying data points in the sequence affected by the priming effect, the impact of priming on data itself, particularly in physiological signals, remains underexplored. Data affected by priming can lead to misclassifications when used in learning models. This study proposes the Affective Priming Score (APS), a data-driven method to detect data points influenced by the priming effect. The APS assigns a score to each data point, quantifying the extent to which it is affected by priming. To validate this method, we apply it to the SEED and SEED-VII datasets, which contain sufficient transitions between emotional events to exhibit priming effects. We train models with the same configuration using both the original data and priming-free sequences. The misclassification rate is significantly reduced when using priming-free sequences compared to the original data. This work contributes to the broader challenge of ambiguity by identifying and mitigating priming effects at the data level, enhancing model robustness, and offering valuable insights for the design and collection of affective computing datasets.
Authors: Yuyang Zhang, Xu Shen, Yu Xie, Ka-Chun Wong, Weidun Xie, Chengbin Peng
Abstract: Link prediction is a classical problem in graph analysis with many practical applications. For directed graphs, recently developed deep learning approaches typically analyze node similarities through contrastive learning and aggregate neighborhood information through graph convolutions. In this work, we propose a novel graph neural network (GNN) framework to fuse feature embedding with community information. We theoretically demonstrate that such hybrid features can improve the performance of directed link prediction. To utilize such features efficiently, we also propose an approach to transform input graphs into directed line graphs so that nodes in the transformed graph can aggregate more information during graph convolutions. Experiments on benchmark datasets show that our approach outperforms the state-of-the-art in most cases when 30%, 40%, 50%, and 60% of the connected links are used as training data, respectively.
Authors: Yushan Zhao, Jinyuan He, Donglai Chen, Weijie Luo, Chong Xie, Ri Zhang, Yonghong Chen, Yan Xu
Abstract: Federated learning (FL) is a decentralized collaborative machine learning (ML) technique. It provides a solution to the issues of isolated data islands and data privacy leakage in industrial ML practices. One major challenge in FL is handling the non-identical and independent distributed (non-IID) data. Current solutions either focus on constructing an all-powerful global model, or customizing personalized local models. Few of them can provide both a well-generalized global model and well-performed local models at the same time. Additionally, many FL solutions to the non-IID problem are benefited from introducing public datasets. However, this will also increase the risk of data leakage. To tackle the problems, we propose a novel data-free distillation framework, Federated Bidirectional Knowledge Distillation (FedBKD). Specifically, we train Generative Adversarial Networks (GAN) for synthetic data. During the GAN training, local models serve as discriminators and their parameters are frozen. The synthetic data is then used for bidirectional distillation between global and local models to achieve knowledge interactions so that performances for both sides are improved. We conduct extensive experiments on 4 benchmarks under different non-IID settings. The results show that FedBKD achieves SOTA performances in every case.
Authors: Kejia Chen, Jiawen Zhang, Jiacong Hu, Yu Wang, Jian Lou, Zunlei Feng, Mingli Song
Abstract: Quantized large language models (LLMs) have gained increasing attention and significance for enabling deployment in resource-constrained environments. However, emerging studies on a few calibration dataset-free quantization methods suggest that quantization may compromise the safety capabilities of LLMs, underscoring the urgent need for systematic safety evaluations and effective mitigation strategies. In this paper, we present comprehensive safety evaluations across various mainstream quantization techniques and diverse calibration datasets, utilizing widely accepted safety benchmarks. To address the identified safety vulnerabilities, we propose a quantization-aware safety patching framework, Q-resafe, to efficiently restore the safety capabilities of quantized LLMs while minimizing any adverse impact on utility. Extensive experimental results demonstrate that Q-resafe successfully re-aligns the safety of quantized LLMs with their pre-quantization counterparts, even under challenging evaluation scenarios. Project page is available at: https://github.com/Thecommonirin/Qresafe.
Authors: Ben Gerhards, Nikita Popkov, Annekatrin K\"onig, Marcel Arpogaus, Bastian Sch\"afermeier, Leonie Riedl, Stephan Vogt, Philip Hehlert
Abstract: Forecasting attracts a lot of research attention in the electricity value chain. However, most studies concentrate on short-term forecasting of generation or consumption with a focus on systems and less on individual consumers. Even more neglected is the topic of long-term forecasting of individual power consumption. Here, we provide an in-depth comparative evaluation of data-driven methods for generating synthetic time series data tailored to energy consumption long-term forecasting. High-fidelity synthetic data is crucial for a wide range of applications, including state estimations in energy systems or power grid planning. In this study, we assess and compare the performance of multiple state-of-the-art but less common techniques: a hybrid Wasserstein Generative Adversarial Network (WGAN), Denoising Diffusion Probabilistic Model (DDPM), Hidden Markov Model (HMM), and Masked Autoregressive Bernstein polynomial normalizing Flows (MABF). We analyze the ability of each method to replicate the temporal dynamics, long-range dependencies, and probabilistic transitions characteristic of individual energy consumption profiles. Our comparative evaluation highlights the strengths and limitations of: WGAN, DDPM, HMM and MABF aiding in selecting the most suitable approach for state estimations and other energy-related tasks. Our generation and analysis framework aims to enhance the accuracy and reliability of synthetic power consumption data while generating data that fulfills criteria like anonymisation - preserving privacy concerns mitigating risks of specific profiling of single customers. This study utilizes an open-source dataset from households in Germany with 15min time resolution. The generated synthetic power profiles can readily be used in applications like state estimations or consumption forecasting.
Authors: Junqi Jiang, Antonio Rago, Francesco Leofante, Francesca Toni
Abstract: In machine learning, it is common to obtain multiple equally performing models for the same prediction task, e.g., when training neural networks with different random seeds. Model multiplicity (MM) is the situation which arises when these competing models differ in their predictions for the same input, for which ensembling is often employed to determine an aggregation of the outputs. Providing recourse recommendations via counterfactual explanations (CEs) under MM thus becomes complex, since the CE may not be valid across all models, i.e., the CEs are not robust under MM. In this work, we formalise the problem of providing recourse under MM, which we name recourse-aware ensembling (RAE). We propose the idea that under MM, CEs for each individual model should be considered alongside their predictions so that the aggregated prediction and recourse are decided in tandem. Centred around this intuition, we introduce six desirable properties for solutions to this problem. For solving RAE, we propose a novel argumentative ensembling method which guarantees the robustness of CEs under MM. Specifically, our method leverages computational argumentation to explicitly represent the conflicts between models and counterfactuals regarding prediction results and CE validity. It then uses argumentation semantics to resolve the conflicts and obtain the final solution, in a manner which is parametric to the chosen semantics. Our method also allows for the specification of preferences over the models under MM, allowing further customisation of the ensemble. In a comprehensive theoretical analysis, we characterise the behaviour of argumentative ensembling with four different argumentation semantics. We then empirically demonstrate the effectiveness of our approach in satisfying desirable properties with eight instantiations of our method. (Abstract is shortened for arXiv.)
Authors: Zeqi Leng, Chunxu Zhang, Guodong Long, Riting Xia, Bo Yang
Abstract: Clustered Federated Learning (CFL) addresses the challenges posed by non-IID data by training multiple group- or cluster-specific expert models. However, existing methods often overlook the shared information across clusters, which represents the generalizable knowledge valuable to all participants in the Federated Learning (FL) system. To overcome this limitation, this paper introduces a novel FL framework that distills a universal expert model from the knowledge of multiple clusters. This universal expert captures globally shared information across all clients and is subsequently distributed to each client as the initialization for the next round of model training. The proposed FL framework operates in three iterative steps: (1) local model training at each client, (2) cluster-specific model aggregation, and (3) universal expert distillation. This three-step learning paradigm ensures the preservation of fine-grained non-IID characteristics while effectively incorporating shared knowledge across clusters. Compared to traditional gradient-based aggregation methods, the distillation-based model aggregation introduces greater flexibility in handling model heterogeneity and reduces conflicts among cluster-specific experts. Extensive experimental results demonstrate the superior performance of the proposed method across various scenarios, highlighting its potential to advance the state of CFL by balancing personalized and shared knowledge more effectively.
Authors: Kazuki Yoda, Kazuhiko Kawamoto, Hiroshi Kera
Abstract: The hardness of learning a function that attains a target task relates to its input-sensitivity. For example, image classification tasks are input-insensitive as minor corruptions should not affect the classification results, whereas arithmetic and symbolic computation, which have been recently attracting interest, are highly input-sensitive as each input variable connects to the computation results. This study presents the first learning-based Quick Response (QR) code decoding and investigates learning functions of medium sensitivity. Our experiments reveal that Transformers can successfully decode QR codes, even beyond the theoretical error-correction limit, by learning the structure of embedded texts. They generalize from English-rich training data to other languages and even random strings. Moreover, we observe that the Transformer-based QR decoder focuses on data bits while ignoring error-correction bits, suggesting a decoding mechanism distinct from standard QR code readers.
Authors: Heyang Zhao, Xingrui Yu, David M. Bossens, Ivor W. Tsang, Quanquan Gu
Abstract: Imitation learning is a central problem in reinforcement learning where the goal is to learn a policy that mimics the expert's behavior. In practice, it is often challenging to learn the expert policy from a limited number of demonstrations accurately due to the complexity of the state space. Moreover, it is essential to explore the environment and collect data to achieve beyond-expert performance. To overcome these challenges, we propose a novel imitation learning algorithm called Imitation Learning with Double Exploration (ILDE), which implements exploration in two aspects: (1) optimistic policy optimization via an exploration bonus that rewards state-action pairs with high uncertainty to potentially improve the convergence to the expert policy, and (2) curiosity-driven exploration of the states that deviate from the demonstration trajectories to potentially yield beyond-expert performance. Empirically, we demonstrate that ILDE outperforms the state-of-the-art imitation learning algorithms in terms of sample efficiency and achieves beyond-expert performance on Atari and MuJoCo tasks with fewer demonstrations than in previous work. We also provide a theoretical justification of ILDE as an uncertainty-regularized policy optimization method with optimistic exploration, leading to a regret growing sublinearly in the number of episodes.
Authors: Saundarya Subramaniam, Shalini Majumdar, Shantanu Nadar, Kaustubh Kulkarni
Abstract: This research presents the development of an Artificial Intelligence (AI) - driven crop disease detection system designed to assist farmers in rural areas with limited resources. We aim to compare different deep learning models for a comparative analysis, focusing on their efficacy in transfer learning. By leveraging deep learning models, including EfficientNet, ResNet101, MobileNetV2, and our custom CNN, which achieved a validation accuracy of 95.76%, the system effectively classifies plant diseases. This research demonstrates the potential of transfer learning in reshaping agricultural practices, improving crop health management, and supporting sustainable farming in rural environments.
Authors: Torben Berndt, Benjamin Walker, Tiexin Qin, Jan St\"uhmer, Andrey Kormilitzin
Abstract: Dynamic graphs exhibit complex temporal dynamics due to the interplay between evolving node features and changing network structures. Recently, Graph Neural Controlled Differential Equations (Graph Neural CDEs) successfully adapted Neural CDEs from paths on Euclidean domains to paths on graph domains. Building on this foundation, we introduce Permutation Equivariant Neural Graph CDEs, which project Graph Neural CDEs onto permutation equivariant function spaces. This significantly reduces the model's parameter count without compromising representational power, resulting in more efficient training and improved generalisation. We empirically demonstrate the advantages of our approach through experiments on simulated dynamical systems and real-world tasks, showing improved performance in both interpolation and extrapolation scenarios.
Authors: Alexandre Rio, Marta Soare, Sihem Amer-Yahia
Abstract: We address fairness in the context of sequential bundle recommendation, where users are served in turn with sets of relevant and compatible items. Motivated by real-world scenarios, we formalize producer-fairness, that seeks to achieve desired exposure of different item groups across users in a recommendation session. Our formulation combines naturally with building high quality bundles. Our problem is solved in real time as users arrive. We propose an exact solution that caters to small instances of our problem. We then examine two heuristics, quality-first and fairness-first, and an adaptive variant that determines on-the-fly the right balance between bundle fairness and quality. Our experiments on three real-world datasets underscore the strengths and limitations of each solution and demonstrate their efficacy in providing fair bundle recommendations without compromising bundle quality.
Authors: Malik Shahid Sultan, Hernando Ombao
Abstract: Granger Causality (GC) offers an elegant statistical framework to study the association between multivariate time series data. Linear Vector Autoregressive models (VAR) though have nice interpretation properties but have limited practical application due to underlying assumptions on the kind of associations that can be captured by these models. Numerous attempts have already been made in the literature that exploit the functional approximation power of Deep Neural Networks (DNNs) for the task of GC estimation. These methods however treat GC as a variable selection problem. We present a novel paradigm for approaching GC. We present this idea that GC is essentially linked with prediction and if a deep learning model is used to model the time series collectively or jointly, a well regularized model may learn the true granger causal structure from the data, given that there is enough training data. We propose to uncover the learned GC structure by comparing the model uncertainty or distribution of the residuals when the past of everything is used as compared to the one where a specific time series component is dropped from the model. We also compare the effect of input layer dropout on the ability of a neural network to learn granger causality from the data. We show that a well regularized model infact can learn the true GC structure from the data without explicitly adding terms in the loss function that guide the model to select variables or perform sparse regression.
Authors: Xuan Ding, Rui Sun, Yunjian Zhang, Xiu Yan, Yueqi Zhou, Kaihao Huang, Suzhong Fu, Chuanlong Xie, Yao Zhu
Abstract: The ever-increasing computational demands and deployment costs of large language models (LLMs) have spurred numerous compressing methods. Compared to quantization and unstructured pruning, SVD compression offers superior hardware compatibility and theoretical guarantees. However, existing SVD-based methods focus on the overall discrepancy between the original and compressed matrices while overlooking the protection of critical components within the matrix, which leads to inferior performance in the compressed models. This paper proposes a dual-level importance protection mechanism to enhance SVD-based compression methods: (1) local importance protection: preserving the most critical singular vectors within each weight matrix through channel-weighted data whitening; and (2) global importance protection: enabling less important layers to bear a greater portion of the compression burden through either a heuristic or optimization-based approach, thereby minimizing the impact of compression on critical layers. Extensive experiments demonstrate that DipSVD outperforms existing SVD-based compression approaches across multiple benchmarks, achieving superior model performance especially at high model compression ratios.
Authors: Francesco Carzaniga, Michael Hersche, Abu Sebastian, Kaspar Schindler, Abbas Rahimi
Abstract: Learning from multi-variate time-series with heterogeneous channel configurations remains a fundamental challenge for deep neural networks (DNNs), particularly in clinical domains such as intracranial electroencephalography (iEEG), where channel setups vary widely across subjects. In this work, we introduce multi-variate parallel attention (MVPA), a novel self-attention mechanism that disentangles content, temporal, and spatial attention, enabling flexible, generalizable, and efficient modeling of time-series data with varying channel counts and configurations. We use MVPA to build MVPFormer, a generative foundation model for human electrophysiology, trained to predict the evolution of iEEG signals across diverse subjects. To support this and future effort by the community, we release the SWEC iEEG dataset, the largest publicly available iEEG dataset to date, comprising nearly 10,000 hours of recordings from heterogeneous clinical sources. MVPFormer leverages MVPA to achieve strong generalization across subjects, demonstrating expert-level performance in seizure detection and outperforming state-of-the-art Transformer baselines on our SWEC, the MAYO, and the FNUSA dataset. We further validate MVPA on standard time-series forecasting and classification tasks, where it matches or exceeds existing attention-based models. Together, our contributions establish MVPA as a general-purpose attention mechanism for heterogeneous time-series and MVPFormer as the first open-source, open-weights, and open-data iEEG foundation model with state-of-the-art clinical performance. The code is available at https://github.com/IBM/multi-variate-parallel-transformer. The SWEC iEEG dataset is available at https://mb-neuro.medical-blocks.ch/public_access/databases/ieeg/swec_ieeg.
URLs: https://github.com/IBM/multi-variate-parallel-transformer., https://mb-neuro.medical-blocks.ch/public_access/databases/ieeg/swec_ieeg.
Authors: Chanuka Don Samarasinghage, Dhruv Gulabani
Abstract: Trajectory analysis is not only about obtaining movement data, but it is also of paramount importance in understanding the pattern in which an object moves through space and time, as well as in predicting its next move. Due to the significant interest in the area, data collection has improved substantially, resulting in a large number of features becoming available for training and predicting models. However, this introduces a high-dimensionality-induced feature explosion problem, which reduces the efficiency and interpretability of the data, thereby reducing the accuracy of machine learning models. To overcome this issue, feature selection has become one of the most prevalent tools. Thus, the objective of this paper was to introduce a taxonomy-based feature selection method that categorizes features based on their internal structure. This approach classifies the data into geometric and kinematic features, further categorizing them into curvature, indentation, speed, and acceleration. The comparative analysis indicated that a taxonomy-based approach consistently achieved comparable or superior predictive performance. Furthermore, due to the taxonomic grouping, which reduces combinatorial space, the time taken to select features was drastically reduced. The taxonomy was also used to gain insights into what feature sets each dataset was more sensitive to. Overall, this study provides robust evidence that a taxonomy-based feature selection method can add a layer of interpretability, reduce dimensionality and computational complexity, and contribute to high-level decision-making. It serves as a step toward providing a methodological framework for researchers and practitioners dealing with trajectory datasets and contributing to the broader field of explainable artificial intelligence.
Authors: Lorenzo Bini, Stephane Marchand-Maillet
Abstract: We present LaplaceGNN, a novel self-supervised graph learning framework that bypasses the need for negative sampling by leveraging spectral bootstrapping techniques. Our method integrates Laplacian-based signals into the learning process, allowing the model to effectively capture rich structural representations without relying on contrastive objectives or handcrafted augmentations. By focusing on positive alignment, LaplaceGNN achieves linear scaling while offering a simpler, more efficient, self-supervised alternative for graph neural networks, applicable across diverse domains. Our contributions are twofold: we precompute spectral augmentations through max-min centrality-guided optimization, enabling rich structural supervision without relying on handcrafted augmentations, then we integrate an adversarial bootstrapped training scheme that further strengthens feature learning and robustness. Our extensive experiments on different benchmark datasets show that LaplaceGNN achieves superior performance compared to state-of-the-art self-supervised graph methods, offering a promising direction for efficiently learning expressive graph representations.
Authors: Zhengpeng Feng, Sadiq Jaffer, Jovana Knezevic, Silja Sormunen, Robin Young, Madeline Lisaius, Markus Immitzer, James Ball, Clement Atzberger, David A. Coomes, Anil Madhavapeddy, Andrew Blake, Srinivasan Keshav
Abstract: Satellite remote sensing (RS) enables a wide array of downstream Earth observation (EO) applications, including climate modeling, carbon accounting, and strategies for conservation and sustainable land use. We present TESSERA, a novel Remote Sensing Foundation Model (RSFM) that uses Self-Supervised Learning (SSL) to generate global, robust representations at 10m scale from pixel-level satellite time series data. TESSERA combines information from only optical and SAR data streams using two parallel Transformer-based encoders: one dedicated to Sentinel-1 SAR polarizations and another to Sentinel-2 MSI data (10 selected spectral bands) to create representations that are then fused using a multilayer perceptron (MLP), resulting in a global representation map covering the years 2017 to 2024. Our precomputed representations set a new state-of-the-art performance benchmark and our open-source approach democratizes access to high-performance, high-resolution representations. We benchmark the performance of TESSERA in five diverse tasks, comparing our work with state-of-the-art task-specific models and other foundation models. Our results show that TESSERA outperforms both traditional RS baselines and the leading geospatial foundation models in these diverse downstream tasks.
Authors: Mohammad Mahdi Maheri, Denys Herasymuk, Hamed Haddadi
Abstract: The growing adoption of Artificial Intelligence (AI) in Internet of Things (IoT) ecosystems has intensified the need for personalized learning methods that can operate efficiently and privately across heterogeneous, resource-constrained devices. However, enabling effective personalized learning in decentralized settings introduces several challenges, including efficient knowledge transfer between clients, protection of data privacy, and resilience against poisoning attacks. In this paper, we address these challenges by developing P4 (Personalized, Private, Peer-to-Peer) -- a method designed to deliver personalized models for resource-constrained IoT devices while ensuring differential privacy and robustness against poisoning attacks. Our solution employs a lightweight, fully decentralized algorithm to privately detect client similarity and form collaborative groups. Within each group, clients leverage differentially private knowledge distillation to co-train their models, maintaining high accuracy while ensuring robustness to the presence of malicious clients. We evaluate P4 on popular benchmark datasets using both linear and CNN-based architectures across various heterogeneity settings and attack scenarios. Experimental results show that P4 achieves 5% to 30% higher accuracy than leading differentially private peer-to-peer approaches and maintains robustness with up to 30% malicious clients. Additionally, we demonstrate its practicality by deploying it on resource-constrained devices, where collaborative training between two clients adds only ~7 seconds of overhead.
Authors: Tatsuhiro Shimizu, Kazuki Kawamura, Takanori Muroi, Yusuke Narita, Kei Tateno, Takuma Udagawa, Yuta Saito
Abstract: We study the novel problem of future off-policy evaluation (F-OPE) and learning (F-OPL) for estimating and optimizing the future value of policies in non-stationary environments, where distributions vary over time. In e-commerce recommendations, for instance, our goal is often to estimate and optimize the policy value for the upcoming month using data collected by an old policy in the previous month. A critical challenge is that data related to the future environment is not observed in the historical data. Existing methods assume stationarity or depend on restrictive reward-modeling assumptions, leading to significant bias. To address these limitations, we propose a novel estimator named \textit{\textbf{O}ff-\textbf{P}olicy Estimator for the \textbf{F}uture \textbf{V}alue (\textbf{\textit{OPFV}})}, designed for accurately estimating policy values at any future time point. The key feature of OPFV is its ability to leverage the useful structure within time-series data. While future data might not be present in the historical log, we can leverage, for example, seasonal, weekly, or holiday effects that are consistent in both the historical and future data. Our estimator is the first to exploit these time-related structures via a new type of importance weighting, enabling effective F-OPE. Theoretical analysis identifies the conditions under which OPFV becomes low-bias. In addition, we extend our estimator to develop a new policy-gradient method to proactively learn a good future policy using only historical data. Empirical results show that our methods substantially outperform existing methods in estimating and optimizing the future policy value under non-stationarity for various experimental setups.
Authors: Xing Ma
Abstract: Federated learning aims to train a global model in a distributed environment that is close to the performance of centralized training. However, issues such as client label skew, data quantity skew, and other heterogeneity problems severely degrade the model's performance. Most existing methods overlook the scenario where only a small portion of clients participate in training within a large-scale client setting, whereas our experiments show that this scenario presents a more challenging federated learning task. Therefore, we propose a Knowledge Distillation with teacher-student Inequitable Aggregation (KDIA) strategy tailored to address the federated learning setting mentioned above, which can effectively leverage knowledge from all clients. In KDIA, the student model is the average aggregation of the participating clients, while the teacher model is formed by a weighted aggregation of all clients based on three frequencies: participation intervals, participation counts, and data volume proportions. During local training, self-knowledge distillation is performed. Additionally, we utilize a generator trained on the server to generate approximately independent and identically distributed (IID) data features locally for auxiliary training. We conduct extensive experiments on the CIFAR-10/100/CINIC-10 datasets and various heterogeneous settings to evaluate KDIA. The results show that KDIA can achieve better accuracy with fewer rounds of training, and the improvement is more significant under severe heterogeneity.
Authors: Antoine Caradot, R\'emi Emonet, Amaury Habrard, Abdel-Rahim Mezidi, Marc Sebban
Abstract: Physics-informed Neural Networks (PINNs) have emerged as an efficient way to learn surrogate neural solvers of PDEs by embedding the physical model in the loss function and minimizing its residuals using automatic differentiation at so-called collocation points. Originally uniformly sampled, the choice of the latter has been the subject of recent advances leading to adaptive sampling refinements. In this paper, we propose a new quadrature method for approximating definite integrals based on the hessian of the considered function, and that we leverage to guide the selection of the collocation points during the training process of PINNs.
Authors: Shuchu Han, Wolfgang Bruckner
Abstract: A fundamental question in applying In-Context Learning (ICL) for tabular data classification is how to determine the ideal number of demonstrations in the prompt. This work addresses this challenge by presenting an algorithm to automatically select a reasonable number of required demonstrations. Our method distinguishes itself by integrating not only the tabular data's distribution but also the user's selected prompt template and the specific Large Language Model (LLM) into its estimation. Rooted in Spectral Graph Theory, our proposed algorithm defines a novel metric to quantify the similarities between different demonstrations. We then construct a similarity graph and analyze the eigenvalues of its Laplacian to derive the minimum number of demonstrations capable of representing the data within the LLM's intrinsic representation space. We validate the efficacy of our approach through experiments comparing its performance against conventional random selection algorithms on diverse datasets and LLMs.
Authors: Matthieu Meeus, Igor Shilov, Georgios Kaissis, Yves-Alexandre de Montjoye
Abstract: Machine learning models are known to memorize samples from their training data, raising concerns around privacy and generalization. Counterfactual self-influence is a popular metric to study memorization, quantifying how the model's prediction for a sample changes depending on the sample's inclusion in the training dataset. However, recent work has shown memorization to be affected by factors beyond self-influence, with other training samples, in particular (near-)duplicates, having a large impact. We here study memorization treating counterfactual influence as a distributional quantity, taking into account how all training samples influence how a sample is memorized. For a small language model, we compute the full influence distribution of training samples on each other and analyze its properties. We find that solely looking at self-influence can severely underestimate tangible risks associated with memorization: the presence of (near-)duplicates seriously reduces self-influence, while we find these samples to be (near-)extractable. We observe similar patterns for image classification, where simply looking at the influence distributions reveals the presence of near-duplicates in CIFAR-10. Our findings highlight that memorization stems from complex interactions across training data and is better captured by the full influence distribution than by self-influence alone.
Authors: Qihang Jin, Enze Ge, Yuhang Xie, Hongying Luo, Junhao Song, Ziqian Bi, Chia Xin Liang, Jibin Guan, Joe Yeong, Junfeng Hao
Abstract: Multi-modal learning is a fast growing area in artificial intelligence. It tries to help machines understand complex things by combining information from different sources, like images, text, and audio. By using the strengths of each modality, multi-modal learning allows AI systems to build stronger and richer internal representations. These help machines better interpretation, reasoning, and making decisions in real-life situations. This field includes core techniques such as representation learning (to get shared features from different data types), alignment methods (to match information across modalities), and fusion strategies (to combine them by deep learning models). Although there has been good progress, some major problems still remain. Like dealing with different data formats, missing or incomplete inputs, and defending against adversarial attacks. Researchers now are exploring new methods, such as unsupervised or semi-supervised learning, AutoML tools, to make models more efficient and easier to scale. And also more attention on designing better evaluation metrics or building shared benchmarks, make it easier to compare model performance across tasks and domains. As the field continues to grow, multi-modal learning is expected to improve many areas: computer vision, natural language processing, speech recognition, and healthcare. In the future, it may help to build AI systems that can understand the world in a way more like humans, flexible, context aware, and able to deal with real-world complexity.
Authors: Arno Geimer, Karthick Panner Selvam, Beltran Fiz Pontiveros
Abstract: Federated Learning (FL) is a decentralized collaborative Machine Learning framework for training models without collecting data in a centralized location. It has seen application across various disciplines, from helping medical diagnoses in hospitals to detecting fraud in financial transactions. In this paper, we focus on improving the local training process through hardware usage optimization. While participants in a federation might share the hardware they are training on, since there is no information exchange between them, their training process can be hindered by an improper training configuration. Taking advantage of the parallel processing inherent to Federated Learning, we use a greedy randomized search to optimize local batch sizes for the best training settings across all participants. Our results show that against default parameter settings, our method improves convergence speed while staying nearly on par with the case where local parameters are optimized.
Authors: Arno Geimer, Beltran Fiz Pontiveros, Radu State
Abstract: Federated Learning (FL) is a collaborative machine learning paradigm which allows participants to collectively train a model while training data remains private. This paradigm is especially beneficial for sectors like finance, where data privacy, security and model performance are paramount. FL has been extensively studied in the years following its introduction, leading to, among others, better performing collaboration techniques, ways to defend against other clients trying to attack the model, and contribution assessment methods. An important element in for-profit Federated Learning is the development of incentive methods to determine the allocation and distribution of rewards for participants. While numerous methods for allocation have been proposed and thoroughly explored, distribution frameworks remain relatively understudied. In this paper, we propose a novel framework which introduces client-specific tokens as investment vehicles within the FL ecosystem. Our framework aims to address the limitations of existing incentive schemes by leveraging a decentralized finance (DeFi) platform and automated market makers (AMMs) to create a more flexible and scalable reward distribution system for participants, and a mechanism for third parties to invest in the federation learning process.
Authors: Charles Arnal, Ga\"etan Narozniak, Vivien Cabannes, Yunhao Tang, Julia Kempe, Remi Munos
Abstract: Reinforcement learning (RL) is increasingly used to align large language models (LLMs). Off-policy methods offer greater implementation simplicity and data efficiency than on-policy techniques, but often result in suboptimal performance. In this work, we study the intermediate range of algorithms between off-policy RL and supervised fine-tuning by analyzing a simple off-policy REINFORCE algorithm, where the advantage is defined as $A=r-V$, with $r$ a reward and $V$ some tunable baseline. Intuitively, lowering $V$ emphasizes high-reward samples, while raising it penalizes low-reward ones more heavily. We first provide a theoretical analysis of this off-policy REINFORCE algorithm, showing that when the baseline $V$ lower-bounds the expected reward, the algorithm enjoys a policy improvement guarantee. Our analysis reveals that while on-policy updates can safely leverage both positive and negative signals, off-policy updates benefit from focusing more on positive rewards than on negative ones. We validate our findings experimentally in a controlled stochastic bandit setting and through fine-tuning state-of-the-art LLMs on reasoning tasks.
Authors: Christian Intern\`o, Andrea Castellani, Sebastian Schmitt, Fabio Stella, Barbara Hammer
Abstract: Industrial Non-Intrusive Load Monitoring (NILM) is limited by the scarcity of high-quality datasets and the complex variability of industrial energy consumption patterns. To address data scarcity and privacy issues, we introduce the Synthetic Industrial Dataset for Energy Disaggregation (SIDED), an open-source dataset generated using Digital Twin simulations. SIDED includes three types of industrial facilities across three different geographic locations, capturing diverse appliance behaviors, weather conditions, and load profiles. We also propose the Appliance-Modulated Data Augmentation (AMDA) method, a computationally efficient technique that enhances NILM model generalization by intelligently scaling appliance power contributions based on their relative impact. We show in experiments that NILM models trained with AMDA-augmented data significantly improve the disaggregation of energy consumption of complex industrial appliances like combined heat and power systems. Specifically, in our out-of-sample scenarios, models trained with AMDA achieved a Normalized Disaggregation Error of 0.093, outperforming models trained without data augmentation (0.451) and those trained with random data augmentation (0.290). Data distribution analyses confirm that AMDA effectively aligns training and test data distributions, enhancing model generalization.
Authors: R. Sharma, M. Raissi, Y. B. Guo
Abstract: Efficient simulation of Laser Powder Bed Fusion (LPBF) is crucial for process prediction due to the lasting issue of high computation cost using traditional numerical methods such as finite element analysis (FEA). This study presents an efficient modeling framework termed FEA-Regulated Physics-Informed Neural Network (FEA-PINN) to accelerate the thermal field prediction in a LPBF process while maintaining the FEA accuracy. A novel dynamic material updating strategy is developed to capture the dynamic phase change of powder-liquid-solid in the PINN model. The PINN model incorporates temperature-dependent material properties and phase change behavior using the apparent heat capacity method. While the PINN model demonstrates high accuracy with a small training data and enables generalization of new process parameters via transfer learning, it faces the challenge of high computation cost in time-dependent problems due to the residual accumulation. To overcome this issue, the FEA-PINN framework integrates corrective FEA simulations during inference to enforce physical consistency and reduce error drift. A comparative analysis shows that FEA-PINN achieves equivalent accuracy to FEA while significantly reducing computational cost. The framework has been validated using the benchmark FEA data and demonstrated through single-track scanning in LPBF.
Authors: Sanne van Kempen, Jaron Sanders, Fiona Sloothaak, Maarten G. Wolf
Abstract: This paper is about optimally controlling skill-based queueing systems such as data centers, cloud computing networks, and service systems. By means of a case study using a real-world data set, we investigate the practical implementation of a recently developed reinforcement learning algorithm for optimal customer routing. Our experiments show that the algorithm efficiently learns and adapts to changing environments and outperforms static benchmark policies, indicating its potential for live implementation. We also augment the real-world applicability of this algorithm by introducing a new heuristic routing rule to reduce delays. Moreover, we show that the algorithm can optimize for multiple objectives: next to payoff maximization, secondary objectives such as server load fairness and customer waiting time reduction can be incorporated. Tuning parameters are used for balancing inherent performance trade--offs. Lastly, we investigate the sensitivity to estimation errors and parameter tuning, providing valuable insights for implementing adaptive routing algorithms in complex real-world queueing systems.
Authors: Laura Boggia, Rafael Teixeira de Lima, Bogdan Malaescu
Abstract: Anomaly detection in multivariate time series is an important problem across various fields such as healthcare, financial services, manufacturing or physics detector monitoring. Accurately identifying when unexpected errors or faults occur is essential, yet challenging, due to the unknown nature of anomalies and the complex interdependencies between time series dimensions. In this paper, we investigate transformer-based approaches for time series anomaly detection, focusing on the recently proposed iTransformer architecture. Our contributions are fourfold: (i) we explore the application of the iTransformer to time series anomaly detection, and analyse the influence of key parameters such as window size, step size, and model dimensions on performance; (ii) we examine methods for extracting anomaly labels from multidimensional anomaly scores and discuss appropriate evaluation metrics for such labels; (iii) we study the impact of anomalous data present during training and assess the effectiveness of alternative loss functions in mitigating their influence; and (iv) we present a comprehensive comparison of several transformer-based models across a diverse set of datasets for time series anomaly detection.
Authors: Itay Niv, Neta Rabin
Abstract: Deep learning on graphs has shown remarkable success across numerous applications, including social networks, bio-physics, traffic networks, and recommendation systems. Regardless of their successes, current methods frequently depend on the assumption that training and testing data share the same distribution, a condition rarely met in real-world scenarios. While graph-transformer (GT) backbones have recently outperformed traditional message-passing neural networks (MPNNs) in multiple in-distribution (ID) benchmarks, their effectiveness under distribution shifts remains largely unexplored. In this work, we address the challenge of out-of-distribution (OOD) generalization for graph neural networks, with a special focus on the impact of backbone architecture. We systematically evaluate GT and hybrid backbones in OOD settings and compare them to MPNNs. To do so, we adapt several leading domain generalization (DG) algorithms to work with GTs and assess their performance on a benchmark designed to test a variety of distribution shifts. Our results reveal that GT and hybrid GT-MPNN backbones consistently demonstrate stronger generalization ability compared to MPNNs, even without specialized DG algorithms. Additionally, we propose a novel post-training analysis approach that compares the clustering structure of the entire ID and OOD test datasets, specifically examining domain alignment and class separation. Demonstrating its model-agnostic design, this approach not only provided meaningful insights into GT and MPNN backbones. It also shows promise for broader applicability to DG problems beyond graph learning, offering a deeper perspective on generalization abilities that goes beyond standard accuracy metrics. Together, our findings highlight the promise of graph-transformers for robust, real-world graph learning and set a new direction for future research in OOD generalization.
Authors: Mariano Tepper, Ted Willke
Abstract: The most popular graph indices for vector search use principles from computational geometry to build the graph. Hence, their formal graph navigability guarantees are only valid in Euclidean space. In this work, we show that machine learning can be used to build graph indices for vector search in metric and non-metric vector spaces (e.g., for inner product similarity). From this novel perspective, we introduce the Support Vector Graph (SVG), a new type of graph index that leverages kernel methods to establish the graph connectivity and that comes with formal navigability guarantees valid in metric and non-metric vector spaces. In addition, we interpret the most popular graph indices, including HNSW and DiskANN, as particular specializations of SVG and show that new indices can be derived from the principles behind this specialization. Finally, we propose SVG-L0 that incorporates an $\ell_0$ sparsity constraint into the SVG kernel method to build graphs with a bounded out-degree. This yields a principled way of implementing this practical requirement, in contrast to the traditional heuristic of simply truncating the out edges of each node. Additionally, we show that SVG-L0 has a self-tuning property that avoids the heuristic of using a set of candidates to find the out-edges of each node and that keeps its computational complexity in check.
Authors: Jasen Lai, Senwei Liang, Chunmei Wang
Abstract: Hamiltonian systems describe a broad class of dynamical systems governed by Hamiltonian functions, which encode the total energy and dictate the evolution of the system. Data-driven approaches, such as symbolic regression and neural network-based methods, provide a means to learn the governing equations of dynamical systems directly from observational data of Hamiltonian systems. However, these methods often struggle to accurately capture complex Hamiltonian functions while preserving energy conservation. To overcome this limitation, we propose the Finite Expression Method for learning Hamiltonian Systems (H-FEX), a symbolic learning method that introduces novel interaction nodes designed to capture intricate interaction terms effectively. Our experiments, including those on highly stiff dynamical systems, demonstrate that H-FEX can recover Hamiltonian functions of complex systems that accurately capture system dynamics and preserve energy over long time horizons. These findings highlight the potential of H-FEX as a powerful framework for discovering closed-form expressions of complex dynamical systems.
Authors: Fariba Jangjoo, Matteo Marsili, Yasser Roudi
Abstract: Closed-loop learning is the process of repeatedly estimating a model from data generated from the model itself. It is receiving great attention due to the possibility that large neural network models may, in the future, be primarily trained with data generated by artificial neural networks themselves. We study this process for models that belong to exponential families, deriving equations of motions that govern the dynamics of the parameters. We show that maximum likelihood estimation of the parameters endows sufficient statistics with the martingale property and that as a result the process converges to absorbing states that amplify initial biases present in the data. However, we show that this outcome may be prevented by polluting the data with an infinitesimal fraction of data points generated from a fixed model, by relying on maximum a posteriori estimation or by introducing regularisation. Furthermore, we show that the asymptotic behavior of the dynamics is not reparametrisation invariant.
Authors: Soufiane Hayou, Nikhil Ghosh, Bin Yu
Abstract: Low-Rank Adaptation (LoRA) is a widely used finetuning method for large models. Its small memory footprint allows practitioners to adapt large models to specific tasks at a fraction of the cost of full finetuning. Different modifications have been proposed to enhance its efficiency by, for example, setting the learning rate, the rank, and the initialization. Another improvement axis is adapter placement strategy: when using LoRA, practitioners usually pick module types to adapt with LoRA, such as Query and Key modules. Few works have studied the problem of adapter placement, with nonconclusive results: original LoRA paper suggested placing adapters in attention modules, while other works suggested placing them in the MLP modules. Through an intuitive theoretical analysis, we introduce PLoP (Precise LoRA Placement), a lightweight method that allows automatic identification of module types where LoRA adapters should be placed, given a pretrained model and a finetuning task. We demonstrate that PLoP consistently outperforms, and in the worst case competes, with commonly used placement strategies through comprehensive experiments on supervised finetuning and reinforcement learning for reasoning.
Authors: Hangyu Li, Hongyue Wu, Guodong Fan, Zhen Zhang, Shizhan Chen, Zhiyong Feng
Abstract: As privacy protection gains increasing importance, more models are being trained on edge devices and subsequently merged into the central server through Federated Learning (FL). However, current research overlooks the impact of network topology, physical distance, and data heterogeneity on edge devices, leading to issues such as increased latency and degraded model performance. To address these issues, we propose a new federated learning scheme on edge devices that called Federated Learning with Encrypted Data Sharing(FedEDS). FedEDS uses the client model and the model's stochastic layer to train the data encryptor. The data encryptor generates encrypted data and shares it with other clients. The client uses the corresponding client's stochastic layer and encrypted data to train and adjust the local model. FedEDS uses the client's local private data and encrypted shared data from other clients to train the model. This approach accelerates the convergence speed of federated learning training and mitigates the negative impact of data heterogeneity, making it suitable for application services deployed on edge devices requiring rapid convergence. Experiments results show the efficacy of FedEDS in promoting model performance.
Authors: Anqi Mao, Mehryar Mohri, Yutao Zhong
Abstract: The problem of learning to defer with multiple experts consists of optimally assigning input instances to experts, balancing the trade-off between their accuracy and computational cost. This is a critical challenge in natural language generation, but also in other fields such as image processing, and medical diagnostics. Recent studies have proposed surrogate loss functions to optimize deferral, but challenges remain in ensuring their consistency properties. This paper introduces novel surrogate loss functions and efficient algorithms with strong theoretical learning guarantees. We address open questions regarding realizable $H$-consistency, $H$-consistency bounds, and Bayes-consistency for both single-stage (jointly learning predictor and deferral function) and two-stage (learning only the deferral function with a fixed expert) learning scenarios. For single-stage deferral, we introduce a family of new realizable $H$-consistent surrogate losses and further prove $H$-consistency for a selected member. For two-stage deferral, we derive new surrogate losses that achieve realizable $H$-consistency, $H$-consistency bounds, and Bayes-consistency for the two-expert scenario and, under natural assumptions, multiple-expert scenario. Additionally, we provide enhanced theoretical guarantees under low-noise assumptions for both scenarios. Finally, we report the results of experiments using our proposed surrogate losses, comparing their performance against existing baselines.
Authors: Fei Wang, Baochun Li
Abstract: Recent work has shown that gradient updates in federated learning (FL) can unintentionally reveal sensitive information about a client's local data. This risk becomes significantly greater when a malicious server manipulates the global model to provoke information-rich updates from clients. In this paper, we adopt a defender's perspective to provide the first comprehensive analysis of malicious gradient leakage attacks and the model manipulation techniques that enable them. Our investigation reveals a core trade-off: these attacks cannot be both highly effective in reconstructing private data and sufficiently stealthy to evade detection -- especially in realistic FL settings that incorporate common normalization techniques and federated averaging. Building on this insight, we argue that malicious gradient leakage attacks, while theoretically concerning, are inherently limited in practice and often detectable through basic monitoring. As a complementary contribution, we propose a simple, lightweight, and broadly applicable client-side detection mechanism that flags suspicious model updates before local training begins, despite the fact that such detection may not be strictly necessary in realistic FL settings. This mechanism further underscores the feasibility of defending against these attacks with minimal overhead, offering a deployable safeguard for privacy-conscious federated learning systems.
Authors: Yujie Liu, Vincent Y. F. Tan, Yunbei Xu
Abstract: We establish the first finite-time information-theoretic lower bounds-and derive new policies that achieve them-for the total queue length in scheduling problems over stochastic processing networks with both adversarial and stochastic arrivals. Prior analyses of MaxWeight guarantee only stability and asymptotic optimality in heavy traffic; we prove that, at finite horizons, MaxWeight can incur strictly larger backlog by problem-dependent factors which we identify. Our main innovations are 1) a minimax framework that pinpoints the precise problem parameters governing any policy's finite-time performance; 2) an information-theoretic lower bound on total queue length; 3) fundamental limitation of MaxWeight that it is suboptimal in finite time; and 4) a new scheduling rule that minimizes the full Lyapunov drift-including its second-order term-thereby matching the lower bound under certain conditions, up to universal constants. These findings reveal a fundamental limitation on "drift-only" methods and points the way toward principled, non-asymptotic optimality in queueing control.
Authors: Ashish Masarkar, Rakesh Gupta, Naga Neehar Dingari, Beena Rai
Abstract: Studying the peeling behaviour of adhesives on skin is vital for advancing biomedical applications such as medical adhesives and transdermal patches. Traditional methods like experimental testing and finite element method (FEM), though considered gold standards, are resource-intensive, computationally expensive and time-consuming, particularly when analysing a wide material parameter space. In this study, we present a neural network-based approach to predict the minimum peel force (F_min) required for adhesive detachment from skin tissue, limiting the need for repeated FEM simulations and significantly reducing the computational cost. Leveraging a dataset generated from FEM simulations of 90 degree peel test with varying adhesive and fracture mechanics parameters, our neural network model achieved high accuracy, validated through rigorous 5-fold cross-validation. The final architecture was able to predict a wide variety of skin-adhesive peeling behaviour, exhibiting a mean squared error (MSE) of 3.66*10^-7 and a R^2 score of 0.94 on test set, demonstrating robust performance. This work introduces a reliable, computationally efficient method for predicting adhesive behaviour, significantly reducing simulation time while maintaining accuracy. This integration of machine learning with high-fidelity biomechanical simulations enables efficient design and optimization of skin-adhesive systems, providing a scalable framework for future research in computational dermato-mechanics and bio-adhesive material design.
Authors: Ryan Samson, Adrian Banner, Luca Candelori, Sebastien Cottrell, Tiziana Di Matteo, Paul Duchnowski, Vahagn Kirakosyan, Jose Marques, Kharen Musaelian, Stefano Pasquali, Ryan Stever, Dario Villani
Abstract: We introduce a novel proxy for firm linkages, Characteristic Vector Linkages (CVLs). We use this concept to estimate firm linkages, first through Euclidean similarity, and then by applying Quantum Cognition Machine Learning (QCML) to similarity learning. We demonstrate that both methods can be used to construct profitable momentum spillover trading strategies, but QCML similarity outperforms the simpler Euclidean similarity.
Authors: Junjie Xu, Jiahao Zhang, Mangal Prakash, Xiang Zhang, Suhang Wang
Abstract: Geometric graph neural networks (GNNs) that respect E(3) symmetries have achieved strong performance on small molecule modeling, but they face scalability and expressiveness challenges when applied to large biomolecules such as RNA and proteins. These systems require models that can simultaneously capture fine-grained atomic interactions, long-range dependencies across spatially distant components, and biologically relevant hierarchical structure, such as atoms forming residues, which in turn form higher-order domains. Existing geometric GNNs, which typically operate exclusively in either Euclidean or Spherical Harmonics space, are limited in their ability to capture both the fine-scale atomic details and the long-range, symmetry-aware dependencies required for modeling the multi-scale structure of large biomolecules. We introduce DualEquiNet, a Dual-Space Hierarchical Equivariant Network that constructs complementary representations in both Euclidean and Spherical Harmonics spaces to capture local geometry and global symmetry-aware features. DualEquiNet employs bidirectional cross-space message passing and a novel Cross-Space Interaction Pooling mechanism to hierarchically aggregate atomic features into biologically meaningful units, such as residues, enabling efficient and expressive multi-scale modeling for large biomolecular systems. DualEquiNet achieves state-of-the-art performance on multiple existing benchmarks for RNA property prediction and protein modeling, and outperforms prior methods on two newly introduced 3D structural benchmarks demonstrating its broad effectiveness across a range of large biomolecule modeling tasks.
Authors: Piotr Gai\'nski, Oussama Boussif, Andrei Rekesh, Dmytro Shevchuk, Ali Parviz, Mike Tyers, Robert A. Batey, Micha{\l} Koziarski
Abstract: Template-based molecular generation offers a promising avenue for drug design by ensuring generated compounds are synthetically accessible through predefined reaction templates and building blocks. In this work, we tackle three core challenges in template-based GFlowNets: (1) minimizing synthesis cost, (2) scaling to large building block libraries, and (3) effectively utilizing small fragment sets. We propose \textbf{Recursive Cost Guidance}, a backward policy framework that employs auxiliary machine learning models to approximate synthesis cost and viability. This guidance steers generation toward low-cost synthesis pathways, significantly enhancing cost-efficiency, molecular diversity, and quality, especially when paired with an \textbf{Exploitation Penalty} that balances the trade-off between exploration and exploitation. To enhance performance in smaller building block libraries, we develop a \textbf{Dynamic Library} mechanism that reuses intermediate high-reward states to construct full synthesis trees. Our approach establishes state-of-the-art results in template-based molecular generation.
Authors: Md Asif Ul Hoq Khan, MD Zahedul Islam, Istiaq Ahmed, Md Masud Karim Rabbi, Farhana Rahman Anonna, MD Abdul Fahim Zeeshan, Mehedi Hasan Ridoy, Bivash Ranjan Chowdhury, Md Nazmul Shakir Rabbi, GM Alamin Sadnan
Abstract: Peer-to-peer trading and the move to decentralized grids have reshaped the energy markets in the United States. Notwithstanding, such developments lead to new challenges, mainly regarding the safety and authenticity of energy trade. This study aimed to develop and build a secure, intelligent, and efficient energy transaction system for the decentralized US energy market. This research interlinks the technological prowess of blockchain and artificial intelligence (AI) in a novel way to solve long-standing challenges in the distributed energy market, specifically those of security, fraudulent behavior detection, and market reliability. The dataset for this research is comprised of more than 1.2 million anonymized energy transaction records from a simulated peer-to-peer (P2P) energy exchange network emulating real-life blockchain-based American microgrids, including those tested by LO3 Energy and Grid+ Labs. Each record contains detailed fields of transaction identifier, timestamp, energy volume (kWh), transaction type (buy/sell), unit price, prosumer/consumer identifier (hashed for privacy), smart meter readings, geolocation regions, and settlement confirmation status. The dataset also includes system-calculated behavior metrics of transaction rate, variability of energy production, and historical pricing patterns. The system architecture proposed involves the integration of two layers, namely a blockchain layer and artificial intelligence (AI) layer, each playing a unique but complementary function in energy transaction securing and market intelligence improvement. The machine learning models used in this research were specifically chosen for their established high performance in classification tasks, specifically in the identification of energy transaction fraud in decentralized markets.
Authors: Zhaoyang Xu, Yunbo Liu
Abstract: Identifying suitable machine learning paradigms for intrusion detection remains critical for building effective and generalizable security solutions. In this study, we present a controlled comparison of four representative models - Multi-Layer Perceptron (MLP), 1D Convolutional Neural Network (CNN), One-Class Support Vector Machine (OCSVM) and Local Outlier Factor (LOF) - on the CICIDS2017 dataset under two scenarios: detecting known attack types and generalizing to previously unseen threats. Our results show that supervised MLP and CNN achieve near-perfect accuracy on familiar attacks but suffer drastic recall drops on novel attacks. Unsupervised LOF attains moderate overall accuracy and high recall on unknown threats at the cost of elevated false alarms, while boundary-based OCSVM balances precision and recall best, demonstrating robust detection across both scenarios. These findings offer practical guidance for selecting IDS models in dynamic network environments.
Authors: Aloni Cohen
Abstract: Are there any conditions under which a generative model's outputs are guaranteed not to infringe the copyrights of its training data? This is the question of "provable copyright protection" first posed by Vyas, Kakade, and Barak (ICML 2023). They define near access-freeness (NAF) and propose it as sufficient for protection. This paper revisits the question and establishes new foundations for provable copyright protection -- foundations that are firmer both technically and legally. First, we show that NAF alone does not prevent infringement. In fact, NAF models can enable verbatim copying, a blatant failure of copy protection that we dub being tainted. Then, we introduce our blameless copy protection framework for defining meaningful guarantees, and instantiate it with clean-room copy protection. Clean-room copy protection allows a user to control their risk of copying by behaving in a way that is unlikely to copy in a counterfactual clean-room setting. Finally, we formalize a common intuition about differential privacy and copyright by proving that DP implies clean-room copy protection when the dataset is golden, a copyright deduplication requirement.
Authors: Xuesong Wang, Mo Li, Xingyan Shi, Zhaoqian Liu, Shenghao Yang
Abstract: Semantic communication has emerged as a promising neural network-based system design for 6G networks. Task-oriented semantic communication is a novel paradigm whose core goal is to efficiently complete specific tasks by transmitting semantic information, optimizing communication efficiency and task performance. The key challenge lies in preserving privacy while maintaining task accuracy, as this scenario is susceptible to model inversion attacks. In such attacks, adversaries can restore or even reconstruct input data by analyzing and processing model outputs, owing to the neural network-based nature of the systems. In addition, traditional systems use image quality indicators (such as PSNR or SSIM) to assess attack severity, which may be inadequate for task-oriented semantic communication, since visual differences do not necessarily ensure semantic divergence. In this paper, we propose a diffusion-based semantic communication framework, named DiffSem, that optimizes semantic information reconstruction through a diffusion mechanism with self-referential label embedding to significantly improve task performance. Our model also compensates channel noise and adopt semantic information distortion to ensure the robustness of the system in various signal-to-noise ratio environments. To evaluate the attacker's effectiveness, we propose a new metric that better quantifies the semantic fidelity of estimations from the adversary. Experimental results based on this criterion show that on the MNIST dataset, DiffSem improves the classification accuracy by 10.03%, and maintain stable performance under dynamic channels. Our results further demonstrate that significant deviation exists between traditional image quality indicators and the leakage of task-relevant semantic information.
Authors: Isaac Marroqui Penalva, Enrique Tom\'as Mart\'inez Beltr\'an, Manuel Gil P\'erez, Alberto Huertas Celdr\'an
Abstract: Decentralized Federated Learning (DFL) enables nodes to collaboratively train models without a central server, introducing new vulnerabilities since each node independently selects peers for model aggregation. Malicious nodes may exploit this autonomy by sending corrupted models (model poisoning), delaying model submissions (delay attack), or flooding the network with excessive messages, negatively affecting system performance. Existing solutions often depend on rigid configurations or additional infrastructures such as blockchain, leading to computational overhead, scalability issues, or limited adaptability. To overcome these limitations, this paper proposes RepuNet, a decentralized reputation system that categorizes threats in DFL and dynamically evaluates node behavior using metrics like model similarity, parameter changes, message latency, and communication volume. Nodes' influence in model aggregation is adjusted based on their reputation scores. RepuNet was integrated into the Nebula DFL platform and experimentally evaluated with MNIST and CIFAR-10 datasets under non-IID distributions, using federations of up to 25 nodes in both fully connected and random topologies. Different attack intensities, frequencies, and activation intervals were tested. Results demonstrated that RepuNet effectively detects and mitigates malicious behavior, achieving F1 scores above 95% for MNIST scenarios and approximately 76% for CIFAR-10 cases. These outcomes highlight RepuNet's adaptability, robustness, and practical potential for mitigating threats in decentralized federated learning environments.
Authors: Kaito Baba, Chaoran Liu, Shuhei Kurita, Akiyoshi Sannai
Abstract: We present Prover Agent, a novel AI agent for automated theorem proving that integrates large language models (LLMs) with a formal proof assistant, Lean. Prover Agent coordinates an informal reasoning LLM, a formal prover model, and feedback from Lean while also generating auxiliary lemmas to assist in discovering the overall proof strategy. It achieves an 86.1% success rate on the MiniF2F benchmark, establishing a new state-of-the-art among methods using small language models (SLMs) with a much lower sample budget than previous approaches. We also present case studies illustrating how these generated lemmas contribute to solving challenging problems.
Authors: Graeme Baker, Agostino Capponi, J. Antonio Sidaoui
Abstract: We propose a data-driven dynamic factor framework where a response variable depends on a high-dimensional set of covariates, without imposing any parametric model on the joint dynamics. Leveraging Anisotropic Diffusion Maps, a nonlinear manifold learning technique introduced by Singer and Coifman, our framework uncovers the joint dynamics of the covariates and responses in a purely data-driven way. We approximate the embedding dynamics using linear diffusions, and exploit Kalman filtering to predict the evolution of the covariates and response variables directly from the diffusion map embedding space. We generalize Singer's convergence rate analysis of the graph Laplacian from the case of independent uniform samples on a compact manifold to the case of time series arising from Langevin diffusions in Euclidean space. Furthermore, we provide rigorous justification for our procedure by showing the robustness of approximations of the diffusion map coordinates by linear diffusions, and the convergence of ergodic averages under standard spectral assumptions on the underlying dynamics. We apply our method to the stress testing of equity portfolios using a combination of financial and macroeconomic factors from the Federal Reserve's supervisory scenarios. We demonstrate that our data-driven stress testing method outperforms standard scenario analysis and Principal Component Analysis benchmarks through historical backtests spanning three major financial crises, achieving reductions in mean absolute error of up to 55% and 39% for scenario-based portfolio return prediction, respectively.
Authors: Yung-Fu Chen, Anish Arora
Abstract: Channel hopping (CS) communication systems must adapt to interference changes in the wireless network and to node mobility for maintaining throughput efficiency. Optimal scheduling requires up-to-date network state information (i.e., of channel occupancy) to select non-overlapping channels for links in interference regions. However, state sharing among nodes introduces significant communication overhead, especially as network size or node mobility scale, thereby decreasing throughput efficiency of already capacity-limited networks. In this paper, we eschew state sharing while adapting the CS schedule based on a learning-based channel occupancy prediction. We propose the MiLAAP attention-based prediction framework for machine learning models of spectral, spatial, and temporal dependencies among network nodes. MiLAAP uses a self-attention mechanism that lets each node capture the temporospectral CS pattern in its interference region and accordingly predict the channel occupancy state within that region. Notably, the prediction relies only on locally and passively observed channel activities, and thus introduces no communication overhead. To deal with node mobility, MiLAAP also uses a multi-head self-attention mechanism that lets each node locally capture the spatiotemporal dependencies on other network nodes that can interfere with it and accordingly predict the motion trajectory of those nodes. Detecting nodes that enter or move outside the interference region is used to further improve the prediction accuracy of channel occupancy. We show that for dynamic networks that use local CS sequences to support relatively long-lived flow traffics, the channel state prediction accuracy of MiLAAP is remarkably ~100% across different node mobility patterns and it achieves zero-shot generalizability across different periods of CS sequences.
Authors: Federico Ruilova, Ernst Gunnar Gran, Sven-Arne Reinemo
Abstract: Cloud computing drives innovation but also poses significant environmental challenges due to its high-energy consumption and carbon emissions. Data centers account for 2-4% of global energy usage, and the ICT sector's share of electricity consumption is projected to reach 40% by 2040. As the goal of achieving net-zero emissions by 2050 becomes increasingly urgent, there is a growing need for more efficient and transparent solutions, particularly for private cloud infrastructures, which are utilized by 87% of organizations, despite the dominance of public-cloud systems. This study evaluates the MAIZX framework, designed to optimize cloud operations and reduce carbon footprint by dynamically ranking resources, including data centers, edge computing nodes, and multi-cloud environments, based on real-time and forecasted carbon intensity, Power Usage Effectiveness (PUE), and energy consumption. Leveraging a flexible ranking algorithm, MAIZX achieved an 85.68% reduction in CO2 emissions compared to baseline hypervisor operations. Tested across geographically distributed data centers, the framework demonstrates scalability and effectiveness, directly interfacing with hypervisors to optimize workloads in private, hybrid, and multi-cloud environments. MAIZX integrates real-time data on carbon intensity, power consumption, and carbon footprint, as well as forecasted values, into cloud management, providing a robust tool for enhancing climate performance potential while maintaining operational efficiency.
Authors: Haochen Zhang, Tianyi Zhang, Junze Yin, Oren Gal, Anshumali Shrivastava, Vladimir Braverman
Abstract: Recommender systems play a pivotal role in providing relevant content to users. With the rapid development of large language models (LLMs), researchers have begun utilizing LLMs to build more powerful recommender systems. However, existing approaches that focus on aligning LLMs with recommendation tasks do not fully leverage their sequential information processing capabilities, leading to suboptimal performance. In this paper, we propose a novel system called compressed vocabulary expansion (CoVE). In CoVE, each item is assigned a unique ID within the expanded vocabulary. Our framework effectively capitalizes on sequence understanding abilities of LLMs, significantly enhancing their performance on recommendation tasks. Additionally, we compress the embedding layer, making CoVE practical for large-scale industrial applications. The effectiveness and performance of CoVE are demonstrated through comprehensive experiments on multiple recommendation datasets and comparisons with prior works. Our code can be found at https://github.com/HaochenZhang717/CoVE-official-Repo.
URLs: https://github.com/HaochenZhang717/CoVE-official-Repo.
Authors: Narasimha Raghavan Veeraragavan, Jan Franz Nyg{\aa}rd
Abstract: We propose Guardian-FC, a novel two-layer framework for privacy preserving federated computing that unifies safety enforcement across diverse privacy preserving mechanisms, including cryptographic back-ends like fully homomorphic encryption (FHE) and multiparty computation (MPC), as well as statistical techniques such as differential privacy (DP). Guardian-FC decouples guard-rails from privacy mechanisms by executing plug-ins (modular computation units), written in a backend-neutral, domain-specific language (DSL) designed specifically for federated computing workflows and interchangeable Execution Providers (EPs), which implement DSL operations for various privacy back-ends. An Agentic-AI control plane enforces a finite-state safety loop through signed telemetry and commands, ensuring consistent risk management and auditability. The manifest-centric design supports fail-fast job admission and seamless extensibility to new privacy back-ends. We present qualitative scenarios illustrating backend-agnostic safety and a formal model foundation for verification. Finally, we outline a research agenda inviting the community to advance adaptive guard-rail tuning, multi-backend composition, DSL specification development, implementation, and compiler extensibility alongside human-override usability.
Authors: Koorosh Moslemi, Chi-Guhn Lee
Abstract: Team formation and the dynamics of team-based learning have drawn significant interest in the context of Multi-Agent Reinforcement Learning (MARL). However, existing studies primarily focus on unilateral groupings, predefined teams, or fixed-population settings, leaving the effects of algorithmic bilateral grouping choices in dynamic populations underexplored. To address this gap, we introduce a framework for learning two-sided team formation in dynamic multi-agent systems. Through this study, we gain insight into what algorithmic properties in bilateral team formation influence policy performance and generalization. We validate our approach using widely adopted multi-agent scenarios, demonstrating competitive performance and improved generalization in most scenarios.
Authors: Ahmet Sarigun, Bora Uyar, Vedran Franke, Altuna Akalin
Abstract: Sampling physically valid ligand-binding poses remains a major challenge in molecular docking, particularly for unseen or structurally diverse targets. We introduce PocketVina, a fast and memory-efficient, search-based docking framework that combines pocket prediction with systematic multi-pocket exploration. We evaluate PocketVina across four established benchmarks--PDBbind2020 (timesplit and unseen), DockGen, Astex, and PoseBusters--and observe consistently strong performance in sampling physically valid docking poses. PocketVina achieves state-of-the-art performance when jointly considering ligand RMSD and physical validity (PB-valid), while remaining competitive with deep learning-based approaches in terms of RMSD alone, particularly on structurally diverse and previously unseen targets. PocketVina also maintains state-of-the-art physically valid docking accuracy across ligands with varying degrees of flexibility. We further introduce TargetDock-AI, a benchmarking dataset we curated, consisting of over 500000 protein-ligand pairs, and a partition of the dataset labeled with PubChem activity annotations. On this large-scale dataset, PocketVina successfully discriminates active from inactive targets, outperforming a deep learning baseline while requiring significantly less GPU memory and runtime. PocketVina offers a robust and scalable docking strategy that requires no task-specific training and runs efficiently on standard GPUs, making it well-suited for high-throughput virtual screening and structure-based drug discovery.
Authors: Sungee Hong, Jiayi Wang, Zhengling Qi, Raymond Ka Wai Wong
Abstract: In reinforcement learning, distributional off-policy evaluation (OPE) focuses on estimating the return distribution of a target policy using offline data collected under a different policy. This work focuses on extending the widely used fitted-Q evaluation -- developed for expectation-based reinforcement learning -- to the distributional OPE setting. We refer to this extension as fitted distributional evaluation (FDE). While only a few related approaches exist, there remains no unified framework for designing FDE methods. To fill this gap, we present a set of guiding principles for constructing theoretically grounded FDE methods. Building on these principles, we develop several new FDE methods with convergence analysis and provide theoretical justification for existing methods, even in non-tabular environments. Extensive experiments, including simulations on linear quadratic regulators and Atari games, demonstrate the superior performance of the FDE methods.
Authors: Yuheng Chen, Alexander Montes McNeil, Taehyuk Park, Blake A. Wilson, Vaishnavi Iyer, Michael Bezick, Jae-Ik Choi, Rohan Ojha, Pravin Mahendran, Daksh Kumar Singh, Geetika Chitturi, Peigang Chen, Trang Do, Alexander V. Kildishev, Vladimir M. Shalaev, Michael Moebius, Wenshan Cai, Yongmin Liu, Alexandra Boltasseva
Abstract: Photonic device development (PDD) has achieved remarkable success in designing and implementing new devices for controlling light across various wavelengths, scales, and applications, including telecommunications, imaging, sensing, and quantum information processing. PDD is an iterative, five-step process that consists of: i) deriving device behavior from design parameters, ii) simulating device performance, iii) finding the optimal candidate designs from simulations, iv) fabricating the optimal device, and v) measuring device performance. Classically, all these steps involve Bayesian optimization, material science, control theory, and direct physics-driven numerical methods. However, many of these techniques are computationally intractable, monetarily costly, or difficult to implement at scale. In addition, PDD suffers from large optimization landscapes, uncertainties in structural or optical characterization, and difficulties in implementing robust fabrication processes. However, the advent of machine learning over the past decade has provided novel, data-driven strategies for tackling these challenges, including surrogate estimators for speeding up computations, generative modeling for noisy measurement modeling and data augmentation, reinforcement learning for fabrication, and active learning for experimental physical discovery. In this review, we present a comprehensive perspective on these methods to enable machine-learning-assisted PDD (ML-PDD) for efficient design optimization with powerful generative models, fast simulation and characterization modeling under noisy measurements, and reinforcement learning for fabrication. This review will provide researchers from diverse backgrounds with valuable insights into this emerging topic, fostering interdisciplinary efforts to accelerate the development of complex photonic devices and systems.
Authors: KMA Solaiman, Bharat Bhargava
Abstract: Existing multi-media retrieval models either rely on creating a common subspace with modality-specific representation models or require schema mapping among modalities to measure similarities among multi-media data. Our goal is to avoid the annotation overhead incurred from considering retrieval as a supervised classification task and re-use the pretrained encoders in large language models and vision tasks. We propose "FemmIR", a framework to retrieve multimodal results relevant to information needs expressed with multimodal queries by example without any similarity label. Such identification is necessary for real-world applications where data annotations are scarce and satisfactory performance is required without fine-tuning with a common framework across applications. We curate a new dataset called MuQNOL for benchmarking progress on this task. Our technique is based on weak supervision introduced through edit distance between samples: graph edit distance can be modified to consider the cost of replacing a data sample in terms of its properties, and relevance can be measured through the implicit signal from the amount of edit cost among the objects. Unlike metric learning or encoding networks, FemmIR re-uses the high-level properties and maintains the property value and relationship constraints with a multi-level interaction score between data samples and the query example provided by the user. We empirically evaluate FemmIR on a missing person use case with MuQNOL. FemmIR performs comparably to similar retrieval systems in delivering on-demand retrieval results with exact and approximate similarities while using the existing property identifiers in the system.
Authors: Kethmi Hirushini Hettige, Jiahao Ji, Cheng Long, Shili Xiang, Gao Cong, Jingyuan Wang
Abstract: Spatio-temporal data mining plays a pivotal role in informed decision making across diverse domains. However, existing models are often restricted to narrow tasks, lacking the capacity for multi-task inference and complex long-form reasoning that require generation of in-depth, explanatory outputs. These limitations restrict their applicability to real-world, multi-faceted decision scenarios. In this work, we introduce STReason, a novel framework that integrates the reasoning strengths of large language models (LLMs) with the analytical capabilities of spatio-temporal models for multi-task inference and execution. Without requiring task-specific finetuning, STReason leverages in-context learning to decompose complex natural language queries into modular, interpretable programs, which are then systematically executed to generate both solutions and detailed rationales. To facilitate rigorous evaluation, we construct a new benchmark dataset and propose a unified evaluation framework with metrics specifically designed for long-form spatio-temporal reasoning. Experimental results show that STReason significantly outperforms advanced LLM baselines across all metrics, particularly excelling in complex, reasoning-intensive spatio-temporal scenarios. Human evaluations further validate STReason's credibility and practical utility, demonstrating its potential to reduce expert workload and broaden the applicability to real-world spatio-temporal tasks. We believe STReason provides a promising direction for developing more capable and generalizable spatio-temporal reasoning systems.
Authors: Yali Yuan, Weiyi Zou, Guang Cheng
Abstract: Website Fingerprinting (WF) attacks aim to infer which websites a user is visiting by analyzing traffic patterns, thereby compromising user anonymity. Although this technique has been demonstrated to be effective in controlled experimental environments, it remains largely limited to small-scale scenarios, typically restricted to recognizing website homepages. In practical settings, however, users frequently access multiple subpages in rapid succession, often before previous content fully loads. WebPage Fingerprinting (WPF) generalizes the WF framework to large-scale environments by modeling subpages of the same site as distinct classes. These pages often share similar page elements, resulting in lower inter-class variance in traffic features. Furthermore, we consider multi-tab browsing scenarios, in which a single trace encompasses multiple categories of webpages. This leads to overlapping traffic segments, and similar features may appear in different positions within the traffic, thereby increasing the difficulty of classification. To address these challenges, we propose an attention-driven fine-grained WPF attack, named ADWPF. Specifically, during the training phase, we apply targeted augmentation to salient regions of the traffic based on attention maps, including attention cropping and attention masking. ADWPF then extracts low-dimensional features from both the original and augmented traffic and applies self-attention modules to capture the global contextual patterns of the trace. Finally, to handle the multi-tab scenario, we employ the residual attention to generate class-specific representations of webpages occurring at different temporal positions. Extensive experiments demonstrate that the proposed method consistently surpasses state-of-the-art baselines across datasets of different scales.
Authors: Malikussaid, Sutiyo
Abstract: The convergence of IT and OT has created hyper-connected ICS, exposing critical infrastructure to a new class of adaptive, intelligent adversaries that render static defenses obsolete. Existing security paradigms often fail to address a foundational "Trinity of Trust," comprising the fidelity of the system model, the integrity of synchronizing data, and the resilience of the analytical engine against sophisticated evasion. This paper introduces the ARC framework, a method for achieving analytical resilience through an autonomous, closed-loop hardening process. ARC establishes a perpetual co-evolutionary arms race within the high-fidelity sandbox of a F-SCDT. A DRL agent, the "Red Agent," is formalized and incentivized to autonomously discover stealthy, physically-plausible attack paths that maximize process disruption while evading detection. Concurrently, an ensemble-based "Blue Agent" defender is continuously hardened via adversarial training against the evolving threats discovered by its adversary. This co-evolutionary dynamic forces both agents to become progressively more sophisticated, enabling the system to autonomously probe and patch its own vulnerabilities. Experimental validation on both the TEP and the SWaT testbeds demonstrates the framework's superior performance. A comprehensive ablation study, supported by extensive visualizations including ROC curves and SHAP plots, reveals that the co-evolutionary process itself is responsible for a significant performance increase in detecting novel attacks. By integrating XAI to ensure operator trust and proposing a scalable F-ARC architecture, this work presents ARC not merely as an improvement, but as a necessary paradigm shift toward dynamic, self-improving security for the future of critical infrastructure.
Authors: Brian Liu, Rahul Mazumder, Peter Radchenko
Abstract: Tree ensembles are non-parametric methods widely recognized for their accuracy and ability to capture complex interactions. While these models excel at prediction, they are difficult to interpret and may fail to uncover useful relationships in the data. We propose an estimator to extract compact sets of decision rules from tree ensembles. The extracted models are accurate and can be manually examined to reveal relationships between the predictors and the response. A key novelty of our estimator is the flexibility to jointly control the number of rules extracted and the interaction depth of each rule, which improves accuracy. We develop a tailored exact algorithm to efficiently solve optimization problems underlying our estimator and an approximate algorithm for computing regularization paths, sequences of solutions that correspond to varying model sizes. We also establish novel non-asymptotic prediction error bounds for our proposed approach, comparing it to an oracle that chooses the best data-dependent linear combination of the rules in the ensemble subject to the same complexity constraint as our estimator. The bounds illustrate that the large-sample predictive performance of our estimator is on par with that of the oracle. Through experiments, we demonstrate that our estimator outperforms existing algorithms for rule extraction.
Authors: Masaki Uto, Yuma Ito
Abstract: Evaluating the abilities of learners is a fundamental objective in the field of education. In particular, there is an increasing need to assess higher-order abilities such as expressive skills and logical thinking. Constructed-response tests such as short-answer and essay-based questions have become widely used as a method to meet this demand. Although these tests are effective, they require substantial manual grading, making them both labor-intensive and costly. Item response theory (IRT) provides a promising solution by enabling the estimation of ability from incomplete score data, where human raters grade only a subset of answers provided by learners across multiple test items. However, the accuracy of ability estimation declines as the proportion of missing scores increases. Although data augmentation techniques for imputing missing scores have been explored in order to address this limitation, they often struggle with inaccuracy for sparse or heterogeneous data. To overcome these challenges, this study proposes a novel method for imputing missing scores by leveraging automated scoring technologies for accurate IRT-based ability estimation. The proposed method achieves high accuracy in ability estimation while markedly reducing manual grading workload.
Authors: Aashiq Muhamed
Abstract: RAG systems enhance LLMs by incorporating external knowledge, which is crucial for domains that demand factual accuracy and up-to-date information. However, evaluating the multifaceted quality of RAG outputs, spanning aspects such as contextual coherence, query relevance, factual correctness, and informational completeness, poses significant challenges. Existing evaluation methods often rely on simple lexical overlap metrics, which are inadequate for capturing these nuances, or involve complex multi-stage pipelines with intermediate steps like claim extraction or require finetuning specialized judge models, hindering practical efficiency. To address these limitations, we propose CCRS (Contextual Coherence and Relevance Score), a novel suite of five metrics that utilizes a single, powerful, pretrained LLM as a zero-shot, end-to-end judge. CCRS evaluates: Contextual Coherence (CC), Question Relevance (QR), Information Density (ID), Answer Correctness (AC), and Information Recall (IR). We apply CCRS to evaluate six diverse RAG system configurations on the challenging BioASQ dataset. Our analysis demonstrates that CCRS effectively discriminates between system performances, confirming, for instance, that the Mistral-7B reader outperforms Llama variants. We provide a detailed analysis of CCRS metric properties, including score distributions, convergent/discriminant validity, tie rates, population statistics, and discriminative power. Compared to the complex RAGChecker framework, CCRS offers comparable or superior discriminative power for key aspects like recall and faithfulness, while being significantly more computationally efficient. CCRS thus provides a practical, comprehensive, and efficient framework for evaluating and iteratively improving RAG systems.
Authors: Jiayong Qin, Xianyu Zhu, Qiyu Liu, Guangyi Zhang, Zhigang Cai, Jianwei Liao, Sha Hu, Jingshu Peng, Yingxia Shao, Lei Chen
Abstract: A growing trend in the database and system communities is to augment conventional index structures, such as B+-trees, with machine learning (ML) models. Among these, error-bounded Piecewise Linear Approximation ($\epsilon$-PLA) has emerged as a popular choice due to its simplicity and effectiveness. Despite its central role in many learned indexes, the design and analysis of $\epsilon$-PLA fitting algorithms remain underexplored. In this paper, we revisit $\epsilon$-PLA from both theoretical and empirical perspectives, with a focus on its application in learned index structures. We first establish a fundamentally improved lower bound of $\Omega(\kappa \cdot \epsilon^2)$ on the expected segment coverage for existing $\epsilon$-PLA fitting algorithms, where $\kappa$ is a data-dependent constant. We then present a comprehensive benchmark of state-of-the-art $\epsilon$-PLA algorithms when used in different learned data structures. Our results highlight key trade-offs among model accuracy, model size, and query performance, providing actionable guidelines for the principled design of future learned data structures.
Authors: Xiaoyu Li, Zhao Song, Jiahao Zhang
Abstract: The explosive growth of AI research has driven paper submissions at flagship AI conferences to unprecedented levels, necessitating many venues in 2025 (e.g., CVPR, ICCV, KDD, AAAI, IJCAI, WSDM) to enforce strict per-author submission limits and to desk-reject any excess papers by simple ID order. While this policy helps reduce reviewer workload, it may unintentionally discard valuable papers and penalize authors' efforts. In this paper, we ask an essential research question on whether it is possible to follow submission limits while minimizing needless rejections. We first formalize the current desk-rejection policies as an optimization problem, and then develop a practical algorithm based on linear programming relaxation and a rounding scheme. Under extensive evaluation on 11 years of real-world ICLR (International Conference on Learning Representations) data, our method preserves up to $19.23\%$ more papers without violating any author limits. Moreover, our algorithm is highly efficient in practice, with all results on ICLR data computed within at most 53.64 seconds. Our work provides a simple and practical desk-rejection strategy that significantly reduces unnecessary rejections, demonstrating strong potential to improve current CS conference submission policies.
Authors: Mahmoud Hegazy, Liviu Aolaritei, Michael I. Jordan, Aymeric Dieuleveut
Abstract: Conformal prediction offers a distribution-free framework for constructing prediction sets with coverage guarantees. In practice, multiple valid conformal prediction sets may be available, arising from different models or methodologies. However, selecting the most desirable set, such as the smallest, can invalidate the coverage guarantees. To address this challenge, we propose a stability-based approach that ensures coverage for the selected prediction set. We extend our results to the online conformal setting, propose several refinements in settings where additional structure is available, and demonstrate its effectiveness through experiments.
Authors: Zhiyuan Wang, Jinhao Duan, Qingni Wang, Xiaofeng Zhu, Tianlong Chen, Xiaoshuang Shi, Kaidi Xu
Abstract: Uncertainty quantification (UQ) for foundation models is essential to identify and mitigate potential hallucinations in automatically generated text. However, heuristic UQ approaches lack formal guarantees for key metrics such as the false discovery rate (FDR) in selective prediction. Previous work adopts the split conformal prediction (SCP) framework to ensure desired coverage of admissible answers by constructing prediction sets, but these sets often contain incorrect candidates, limiting their practical utility. To address this, we propose COIN, an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question under user-specified FDR constraints. COIN estimates the empirical error rate on a calibration set and applies confidence interval methods such as Clopper-Pearson to establish a high-probability upper bound on the true error rate (i.e., FDR). This enables the selection of the largest uncertainty threshold that ensures FDR control on test data while significantly increasing sample retention. We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data across both general and multimodal text generation tasks. Furthermore, we show that employing alternative upper bound constructions and UQ strategies can further boost COIN's power performance, which underscores its extensibility and adaptability to diverse application scenarios.
Authors: Ayush Lodh, Ritabrata Chakraborty, Shivakumara Palaiahnakote, Umapada Pal
Abstract: We posit that handwriting recognition benefits from complementary cues carried by the rasterized complex glyph and the pen's trajectory, yet most systems exploit only one modality. We introduce an end-to-end network that performs early fusion of offline images and online stroke data within a shared latent space. A patch encoder converts the grayscale crop into fixed-length visual tokens, while a lightweight transformer embeds the $(x, y, \text{pen})$ sequence. Learnable latent queries attend jointly to both token streams, yielding context-enhanced stroke embeddings that are pooled and decoded under a cross-entropy loss objective. Because integration occurs before any high-level classification, temporal cues reinforce each other during representation learning, producing stronger writer independence. Comprehensive experiments on IAMOn-DB and VNOn-DB demonstrate that our approach achieves state-of-the-art accuracy, exceeding previous bests by up to 1\%. Our study also shows adaptation of this pipeline with gesturification on the ISI-Air dataset. Our code can be found here.
Authors: Nir Weinberger, Ram Zamir
Abstract: Universal compression can learn the source and adapt to it either in a batch mode (forward adaptation), or in a sequential mode (backward adaptation). We recast the sequential mode as a multi-armed bandit problem, a fundamental model in reinforcement-learning, and study the trade-off between exploration and exploitation in the lossy compression case. We show that a previously proposed "natural type selection" scheme can be cast as a reconstruction-directed MAB algorithm, for sequential lossy compression, and explain its limitations in terms of robustness and short-block performance. We then derive and analyze robust cost-directed MAB algorithms, which work at any block length.
Authors: Fabian Bongratz, Tom Nuno Wolf, Jaume Gual Ramon, Christian Wachinger
Abstract: Interpretable models are crucial for supporting clinical decision-making, driving advances in their development and application for medical images. However, the nature of 3D volumetric data makes it inherently challenging to visualize and interpret intricate and complex structures like the cerebral cortex. Cortical surface renderings, on the other hand, provide a more accessible and understandable 3D representation of brain anatomy, facilitating visualization and interactive exploration. Motivated by this advantage and the widespread use of surface data for studying neurological disorders, we present the eXplainable Surface Vision Transformer (X-SiT). This is the first inherently interpretable neural network that offers human-understandable predictions based on interpretable cortical features. As part of X-SiT, we introduce a prototypical surface patch decoder for classifying surface patch embeddings, incorporating case-based reasoning with spatially corresponding cortical prototypes. The results demonstrate state-of-the-art performance in detecting Alzheimer's disease and frontotemporal dementia while additionally providing informative prototypes that align with known disease patterns and reveal classification errors.
Authors: Juan Jos\'e Murillo-Fuentes, Pablo M. Olmos, Laura Alba-Carcel\'en
Abstract: The study of canvas fabrics in works of art is a crucial tool for authentication, attribution and conservation. Traditional methods are based on thread density map matching, which cannot be applied when canvases do not come from contiguous positions on a roll. This paper presents a novel approach based on deep learning to assess the similarity of textiles. We introduce an automatic tool that evaluates the similarity between canvases without relying on thread density maps. A Siamese deep learning model is designed and trained to compare pairs of images by exploiting the feature representations learned from the scans. In addition, a similarity estimation method is proposed, aggregating predictions from multiple pairs of cloth samples to provide a robust similarity score. Our approach is applied to canvases from the Museo Nacional del Prado, corroborating the hypothesis that plain weave canvases, widely used in painting, can be effectively compared even when their thread densities are similar. The results demonstrate the feasibility and accuracy of the proposed method, opening new avenues for the analysis of masterpieces.
Authors: Natalie Lang, Maya Simhi, Nir Shlezinger
Abstract: Federated learning (FL) enables collaborative training across distributed clients without sharing raw data, often at the cost of substantial communication overhead induced by transmitting high-dimensional model updates. This overhead can be alleviated by having the clients quantize their model updates, with dithered lattice quantizers identified as an attractive scheme due to its structural simplicity and convergence-preserving properties. However, existing lattice-based FL schemes typically rely on a fixed quantization rule, which is suboptimal in heterogeneous and dynamic environments where the model updates distribution varies across users and training rounds. In this work, we propose Online Learned Adaptive Lattices (OLALa), a heterogeneous FL framework where each client can adjust its quantizer online using lightweight local computations. We first derive convergence guarantees for FL with non-fixed lattice quantizers and show that proper lattice adaptation can tighten the convergence bound. Then, we design an online learning algorithm that enables clients to tune their quantizers throughout the FL process while exchanging only a compact set of quantization parameters. Numerical experiments demonstrate that OLALa consistently improves learning performance under various quantization rates, outperforming conventional fixed-codebook and non-adaptive schemes.
Authors: Rian Touchent, Nathan Godey, Eric de la Clergerie
Abstract: We introduce Biomed-Enriched, a biomedical text dataset constructed from PubMed via a two-stage annotation process. In the first stage, a large language model annotates 400K paragraphs from PubMed scientific articles, assigning scores for their type (review, study, clinical case, other), domain (clinical, biomedical, other), and educational quality. The educational quality score (rated 1 to 5) estimates how useful a paragraph is for college-level learning. These annotations are then used to fine-tune a small language model, which propagates the labels across the full PMC-OA corpus. The resulting metadata allows us to extract refined subsets, including 2M clinical case paragraphs with over 450K high-quality ones from articles with commercial-use licenses, and to construct several variants via quality filtering and domain upsampling. Clinical text is typically difficult to access due to privacy constraints, as hospital records cannot be publicly shared. Hence, our dataset provides an alternative large-scale, openly available collection of clinical cases from PubMed, making it a valuable resource for biomedical and clinical NLP. Preliminary continual-pretraining experiments with OLMo2 suggest these curated subsets enable targeted improvements, with clinical upsampling boosting performance by ~5% on MMLU ProfMed and educational quality filtering improving MedQA and MedMCQA by ~1%. Combinations of these techniques led to faster convergence, reaching same performance with a third of training tokens, indicating potential for more efficient and effective biomedical pretraining strategies.
Authors: Daniele Ravasio, Marcello Farina, Alessio La Bella, Andrea Ballarino
Abstract: This paper investigates the design of output-feedback schemes for systems described by a class of recurrent neural networks. We propose a procedure based on linear matrix inequalities for designing an observer and a static state-feedback controller. The algorithm leverages global and regional incremental input-to-state stability (incremental ISS) and enables the tracking of constant setpoints, ensuring robustness to disturbances and state estimation uncertainty. To address the potential limitations of regional incremental ISS, we introduce an alternative scheme in which the static law is replaced with a tube-based nonlinear model predictive controller (NMPC) that exploits regional incremental ISS properties. We show that these conditions enable the formulation of a robust NMPC law with guarantees of convergence and recursive feasibility, leading to an enlarged region of attraction. Theoretical results are validated through numerical simulations on the pH-neutralisation process benchmark, demonstrating the effectiveness of the proposed schemes.
Authors: Lei Wang, Piotr Koniusz
Abstract: Understanding human actions in videos requires more than raw pixel analysis; it relies on high-level semantic reasoning and effective integration of multimodal features. We propose a deep translational action recognition framework that enhances recognition accuracy by jointly predicting action concepts and auxiliary features from RGB video frames. At test time, hallucination streams infer missing cues, enriching feature representations without increasing computational overhead. To focus on action-relevant regions beyond raw pixels, we introduce two novel domain-specific descriptors. Object Detection Features (ODF) aggregate outputs from multiple object detectors to capture contextual cues, while Saliency Detection Features (SDF) highlight spatial and intensity patterns crucial for action recognition. Our framework seamlessly integrates these descriptors with auxiliary modalities such as optical flow, Improved Dense Trajectories, skeleton data, and audio cues. It remains compatible with state-of-the-art architectures, including I3D, AssembleNet, Video Transformer Network, FASTER, and recent models like VideoMAE V2 and InternVideo2. To handle uncertainty in auxiliary features, we incorporate aleatoric uncertainty modeling in the hallucination step and introduce a robust loss function to mitigate feature noise. Our multimodal self-supervised action recognition framework achieves state-of-the-art performance on multiple benchmarks, including Kinetics-400, Kinetics-600, and Something-Something V2, demonstrating its effectiveness in capturing fine-grained action dynamics.
Authors: Po Chen, Rujun Jiang, Peng Wang
Abstract: Despite its wide range of applications across various domains, the optimization foundations of deep matrix factorization (DMF) remain largely open. In this work, we aim to fill this gap by conducting a comprehensive study of the loss landscape of the regularized DMF problem. Toward this goal, we first provide a closed-form expression of all critical points. Building on this, we establish precise conditions under which a critical point is a local minimizer, a global minimizer, a strict saddle point, or a non-strict saddle point. Leveraging these results, we derive a necessary and sufficient condition under which each critical point is either a local minimizer or a strict saddle point. This provides insights into why gradient-based methods almost always converge to a local minimizer of the regularized DMF problem. Finally, we conduct numerical experiments to visualize its loss landscape under different settings to support our theory.
Authors: Abdullah All Tanvir, Xin Zhong
Abstract: This paper introduces a novel deep learning framework for robust image zero-watermarking based on distortion-invariant feature learning. As a zero-watermarking scheme, our method leaves the original image unaltered and learns a reference signature through optimization in the feature space. The proposed framework consists of two key modules. In the first module, a feature extractor is trained via noise-adversarial learning to generate representations that are both invariant to distortions and semantically expressive. This is achieved by combining adversarial supervision against a distortion discriminator and a reconstruction constraint to retain image content. In the second module, we design a learning-based multibit zero-watermarking scheme where the trained invariant features are projected onto a set of trainable reference codes optimized to match a target binary message. Extensive experiments on diverse image datasets and a wide range of distortions show that our method achieves state-of-the-art robustness in both feature stability and watermark recovery. Comparative evaluations against existing self-supervised and deep watermarking techniques further highlight the superiority of our framework in generalization and robustness.
Authors: Ben Kang, Xin Chen, Jie Zhao, Chunjuan Bo, Dong Wang, Huchuan Lu
Abstract: Transformer-based visual trackers have demonstrated significant advancements due to their powerful modeling capabilities. However, their practicality is limited on resource-constrained devices because of their slow processing speeds. To address this challenge, we present HiT, a novel family of efficient tracking models that achieve high performance while maintaining fast operation across various devices. The core innovation of HiT lies in its Bridge Module, which connects lightweight transformers to the tracking framework, enhancing feature representation quality. Additionally, we introduce a dual-image position encoding approach to effectively encode spatial information. HiT achieves an impressive speed of 61 frames per second (fps) on the NVIDIA Jetson AGX platform, alongside a competitive AUC of 64.6% on the LaSOT benchmark, outperforming all previous efficient trackers.Building on HiT, we propose DyHiT, an efficient dynamic tracker that flexibly adapts to scene complexity by selecting routes with varying computational requirements. DyHiT uses search area features extracted by the backbone network and inputs them into an efficient dynamic router to classify tracking scenarios. Based on the classification, DyHiT applies a divide-and-conquer strategy, selecting appropriate routes to achieve a superior trade-off between accuracy and speed. The fastest version of DyHiT achieves 111 fps on NVIDIA Jetson AGX while maintaining an AUC of 62.4% on LaSOT.Furthermore, we introduce a training-free acceleration method based on the dynamic routing architecture of DyHiT. This method significantly improves the execution speed of various high-performance trackers without sacrificing accuracy. For instance, our acceleration method enables the state-of-the-art tracker SeqTrack-B256 to achieve a 2.68 times speedup on an NVIDIA GeForce RTX 2080 Ti GPU while maintaining the same AUC of 69.9% on the LaSOT.
Authors: Ruijia Zhang, Zhengling Qi, Yue Wu, Xiangyu Zhang, Yanxun Xu
Abstract: Dynamic treatment regimes (DTRs) provide a principled framework for optimizing sequential decision-making in domains where decisions must adapt over time in response to individual trajectories, such as healthcare, education, and digital interventions. However, existing statistical methods often rely on strong positivity assumptions and lack robustness under partial data coverage, while offline reinforcement learning approaches typically focus on average training performance, lack statistical guarantees, and require solving complex optimization problems. To address these challenges, we propose POLAR, a novel pessimistic model-based policy learning algorithm for offline DTR optimization. POLAR estimates the transition dynamics from offline data and quantifies uncertainty for each history-action pair. A pessimistic penalty is then incorporated into the reward function to discourage actions with high uncertainty. Unlike many existing methods that focus on average training performance, POLAR directly targets the suboptimality of the final learned policy and offers theoretical guarantees, without relying on computationally intensive minimax or constrained optimization procedures. To the best of our knowledge, POLAR is the first model-based DTR method to provide both statistical and computational guarantees, including finite-sample bounds on policy suboptimality. Empirical results on both synthetic data and the MIMIC-III dataset demonstrate that POLAR outperforms state-of-the-art methods and yields near-optimal, history-aware treatment strategies.
Authors: Ryan Thompson, Matt P. Wand, Joanna J. J. Wang
Abstract: Linear mixed models (LMMs), which incorporate fixed and random effects, are key tools for analyzing heterogeneous data, such as in personalized medicine or adaptive marketing. Nowadays, this type of data is increasingly wide, sometimes containing thousands of candidate predictors, necessitating sparsity for prediction and interpretation. However, existing sparse learning methods for LMMs do not scale well beyond tens or hundreds of predictors, leaving a large gap compared with sparse methods for linear models, which ignore random effects. This paper closes the gap with a new $\ell_0$ regularized method for LMM subset selection that can run on datasets containing thousands of predictors in seconds to minutes. On the computational front, we develop a coordinate descent algorithm as our main workhorse and provide a guarantee of its convergence. We also develop a local search algorithm to help traverse the nonconvex optimization surface. Both algorithms readily extend to subset selection in generalized LMMs via a penalized quasi-likelihood approximation. On the statistical front, we provide a finite-sample bound on the Kullback-Leibler divergence of the new method. We then demonstrate its excellent performance in synthetic experiments and illustrate its utility on two datasets from biology and journalism.
Authors: Tobias Vontobel, Seyedmorteza Sadat, Farnood Salehi, Romann M. Weber
Abstract: Diffusion models have emerged as the leading approach for image synthesis, demonstrating exceptional photorealism and diversity. However, training diffusion models at high resolutions remains computationally prohibitive, and existing zero-shot generation techniques for synthesizing images beyond training resolutions often produce artifacts, including object duplication and spatial incoherence. In this paper, we introduce HiWave, a training-free, zero-shot approach that substantially enhances visual fidelity and structural coherence in ultra-high-resolution image synthesis using pretrained diffusion models. Our method employs a two-stage pipeline: generating a base image from the pretrained model followed by a patch-wise DDIM inversion step and a novel wavelet-based detail enhancer module. Specifically, we first utilize inversion methods to derive initial noise vectors that preserve global coherence from the base image. Subsequently, during sampling, our wavelet-domain detail enhancer retains low-frequency components from the base image to ensure structural consistency, while selectively guiding high-frequency components to enrich fine details and textures. Extensive evaluations using Stable Diffusion XL demonstrate that HiWave effectively mitigates common visual artifacts seen in prior methods, achieving superior perceptual quality. A user study confirmed HiWave's performance, where it was preferred over the state-of-the-art alternative in more than 80% of comparisons, highlighting its effectiveness for high-quality, ultra-high-resolution image synthesis without requiring retraining or architectural modifications.
Authors: Haoze Wu, Yunzhi Yao, Wenhao Yu, Huajun Chen, Ningyu Zhang
Abstract: Large Language Models (LLMs) exhibit remarkable code generation capabilities but falter when adapting to frequent updates in external library APIs. This critical limitation, stemming from reliance on outdated API knowledge from their training data, even with access to current documentation, impedes reliable code generation in dynamic environments. To tackle this issue, we propose ReCode (rule-based Reinforcement learning for Code Update), a novel framework that mimics human programmer adaptation to API changes. Specifically, we construct a dataset of approximately 2,000 data entries to train the LLMs to perform version migration based on updated information. Then, we introduce a modified string similarity metric for code evaluation as the reward for reinforcement learning. Our experiments demonstrate that ReCode substantially boosts LLMs' code generation performance in dynamic API scenarios, especially on the unseen CodeUpdateArena task. Crucially, compared to supervised fine-tuning, ReCode has less impact on LLMs' general code generation abilities. We apply ReCode on various LLMs and reinforcement learning algorithms (GRPO and DAPO), all achieving consistent improvements. Notably, after training, Qwen2.5-Coder-7B outperforms that of the 32B parameter code instruction-tuned model and the reasoning model with the same architecture. Code is available at https://github.com/zjunlp/ReCode.
Authors: Philipp Hager, Onno Zoeter, Maarten de Rijke
Abstract: Additive two-tower models are popular learning-to-rank methods for handling biased user feedback in industry settings. Recent studies, however, report a concerning phenomenon: training two-tower models on clicks collected by well-performing production systems leads to decreased ranking performance. This paper investigates two recent explanations for this observation: confounding effects from logging policies and model identifiability issues. We theoretically analyze the identifiability conditions of two-tower models, showing that either document swaps across positions or overlapping feature distributions are required to recover model parameters from clicks. We also investigate the effect of logging policies on two-tower models, finding that they introduce no bias when models perfectly capture user behavior. However, logging policies can amplify biases when models imperfectly capture user behavior, particularly when prediction errors correlate with document placement across positions. We propose a sample weighting technique to mitigate these effects and provide actionable insights for researchers and practitioners using two-tower models.
Authors: Zengzhi Wang, Fan Zhou, Xuefeng Li, Pengfei Liu
Abstract: Different base language model families, such as Llama and Qwen, exhibit divergent behaviors during post-training with reinforcement learning (RL), especially on reasoning-intensive tasks. What makes a base language model suitable for reinforcement learning? Gaining deeper insight into this question is essential for developing RL-scalable foundation models of the next generation. In this work, we investigate how mid-training strategies shape RL dynamics, focusing on two representative model families: Qwen and Llama. Our study reveals that (1) high-quality mathematical corpora, such as MegaMath-Web-Pro, significantly improve both base model and RL performance, while existing alternatives (e.g., FineMath-4plus) fail to do so; (2) further adding QA-style data, particularly long chain-of-thought (CoT) reasoning examples, enhances RL outcomes, and instruction data further unlocks this effect; (3) while long-CoT improves reasoning depth, it can also induce verbosity of model responses and unstability of RL training, underscoring the importance of data formatting; (4) scaling mid-training consistently leads to stronger downstream RL performance. Building on these insights, we introduce a two-stage mid-training strategy, Stable-then-Decay, in which base models are first trained on 200B tokens with a constant learning rate, followed by 20B tokens across three CoT-focused branches with learning rate decay. This yields OctoThinker, a family of models demonstrating strong RL compatibility and closing the performance gap with more RL-friendly model families, i.e., Qwen. We hope our work will help shape pre-training strategies for foundation models in the RL era. To support further research, we release our open-source models along with a curated math reasoning-intensive corpus of over 70 billion tokens (i.e., MegaMath-Web-Pro-Max).
Authors: Lei Liu, Chao Song, Liangsheng He, Silin Wang, Xuan Feng, Cai Liu
Abstract: This study proposes a high-performance dual-parameter full waveform inversion framework (FWI) for ground-penetrating radar (GPR), accelerated through the hybrid compilation of CUDA kernel functions and PyTorch. The method leverages the computational efficiency of GPU programming while preserving the flexibility and usability of Python-based deep learning frameworks. By integrating customized CUDA kernels into PyTorch's automatic differentiation mechanism, the framework enables accurate and efficient inversion of both dielectric permittivity and electrical conductivity. Experimental evaluations on synthetic data and real wavefield data demonstrate that the proposed method achieves dual-parameter FWI for GPR data while maintaining high accuracy. Moreover, the framework is flexible and extensible, supporting optional regularization strategies such as total variation and multi-scale inversion. These features make the proposed approach a practical and scalable framework for rapid GPR-based subsurface imaging in applications including civil engineering, environmental monitoring, and geophysical exploration.
Authors: Gilad Lerman, Kang Li, Tyler Maunu, Teng Zhang
Abstract: Robust subspace estimation is fundamental to many machine learning and data analysis tasks. Iteratively Reweighted Least Squares (IRLS) is an elegant and empirically effective approach to this problem, yet its theoretical properties remain poorly understood. This paper establishes that, under deterministic conditions, a variant of IRLS with dynamic smoothing regularization converges linearly to the underlying subspace from any initialization. We extend these guarantees to affine subspace estimation, a setting that lacks prior recovery theory. Additionally, we illustrate the practical benefits of IRLS through an application to low-dimensional neural network training. Our results provide the first global convergence guarantees for IRLS in robust subspace recovery and, more broadly, for nonconvex IRLS on a Riemannian manifold.
Authors: Hongzhen Huang, Kunming Zhang, Hanlong Liao, Kui Wu, Guoming Tang
Abstract: The rapid advancement of AI, particularly large language models (LLMs), has raised significant concerns about the energy use and carbon emissions associated with model training and inference. However, existing tools for measuring and reporting such impacts are often fragmented, lacking systematic metric integration and offering limited support for correlation analysis among them. This paper presents WattsOnAI, a comprehensive software toolkit for the measurement, analysis, and visualization of energy use, power draw, hardware performance, and carbon emissions across AI workloads. By seamlessly integrating with existing AI frameworks, WattsOnAI offers standardized reports and exports fine-grained time-series data to support benchmarking and reproducibility in a lightweight manner. It further enables in-depth correlation analysis between hardware metrics and model performance and thus facilitates bottleneck identification and performance enhancement. By addressing critical limitations in existing tools, WattsOnAI encourages the research community to weigh environmental impact alongside raw performance of AI workloads and advances the shift toward more sustainable "Green AI" practices. The code is available at https://github.com/SusCom-Lab/WattsOnAI.
Authors: Manyi Li, Renshuai Tao, Yufan Liu, Chuangchuang Tan, Haotong Qin, Bing Li, Yunchao Wei, Yao Zhao
Abstract: With the rapid advancement of deep learning, particularly through generative adversarial networks (GANs) and diffusion models (DMs), AI-generated images, or ``deepfakes", have become nearly indistinguishable from real ones. These images are widely shared across Online Social Networks (OSNs), raising concerns about their misuse. Existing deepfake detection methods overlook the ``block effects" introduced by compression in OSNs, which obscure deepfake artifacts, and primarily focus on raw images, rarely encountered in real-world scenarios. To address these challenges, we propose PLADA (Pay Less Attention to Deceptive Artifacts), a novel framework designed to tackle the lack of paired data and the ineffective use of compressed images. PLADA consists of two core modules: Block Effect Eraser (B2E), which uses a dual-stage attention mechanism to handle block effects, and Open Data Aggregation (ODA), which processes both paired and unpaired data to improve detection. Extensive experiments across 26 datasets demonstrate that PLADA achieves a remarkable balance in deepfake detection, outperforming SoTA methods in detecting deepfakes on OSNs, even with limited paired data and compression. More importantly, this work introduces the ``block effect" as a critical factor in deepfake detection, providing a robust solution for open-world scenarios. Our code is available at https://github.com/ManyiLee/PLADA.
Authors: Andrew Mole, Max Weissenbacher, Georgios Rigas, Sylvain Laizet
Abstract: Traditional wind farm control operates each turbine independently to maximize individual power output. However, coordinated wake steering across the entire farm can substantially increase the combined wind farm energy production. Although dynamic closed-loop control has proven effective in flow control applications, wind farm optimization has relied primarily on static, low-fidelity simulators that ignore critical turbulent flow dynamics. In this work, we present the first reinforcement learning (RL) controller integrated directly with high-fidelity large-eddy simulation (LES), enabling real-time response to atmospheric turbulence through collaborative, dynamic control strategies. Our RL controller achieves a 4.30% increase in wind farm power output compared to baseline operation, nearly doubling the 2.19% gain from static optimal yaw control obtained through Bayesian optimization. These results establish dynamic flow-responsive control as a transformative approach to wind farm optimization, with direct implications for accelerating renewable energy deployment to net-zero targets.
Authors: Kristian Minchev, Dimitar Iliev Dimitrov, Nikola Konstantinov
Abstract: The widespread availability of large public datasets is a key factor behind the recent successes of statistical inference and machine learning methods. However, these datasets often contain some low-quality or contaminated data, to which many learning procedures are sensitive. Therefore, the question of whether and how public datasets should be prefiltered to facilitate accurate downstream learning arises. On a technical level this requires the construction of principled data prefiltering methods which are learner-agnostic robust, in the sense of provably protecting a set of pre-specified downstream learners from corrupted data. In this work, we formalize the problem of Learner-Agnostic Robust data Prefiltering (LARP), which aims at finding prefiltering procedures that minimize a worst-case loss over a pre-specified set of learners. We first instantiate our framework in the context of scalar mean estimation with Huber estimators under the Huber data contamination model. We provide a hardness result on a specific problem instance and analyze several natural prefiltering procedures. Our theoretical results indicate that performing LARP on a heterogeneous set of learners leads to some loss in model performance compared to the alternative of prefiltering data for each learner/use-case individually. We explore the resulting utility loss and its dependence on the problem parameters via extensive experiments on real-world image and tabular data, observing statistically significant reduction in utility. Finally, we model the trade-off between the utility drop and the cost of repeated (learner-specific) prefiltering within a game-theoretic framework and showcase benefits of LARP for large datasets.
Authors: Rajat Rasal, Avinash Kori, Ben Glocker
Abstract: Identifiable causal representation learning seeks to uncover the true causal relationships underlying a data generation process. In medical imaging, this presents opportunities to improve the generalisability and robustness of task-specific latent features. This work introduces the concept of grouping observations to learn identifiable representations for disease classification in chest X-rays via an end-to-end framework. Our experiments demonstrate that these causal representations improve generalisability and robustness across multiple classification tasks when grouping is used to enforce invariance w.r.t race, sex, and imaging views.
Authors: Zhaosong Lu, Yifeng Xiao
Abstract: In this paper, we study a class of stochastic and finite-sum convex optimization problems with deterministic constraints. Existing methods typically aim to find an $\epsilon$-$expectedly\ feasible\ stochastic\ optimal$ solution, in which the expected constraint violation and expected optimality gap are both within a prescribed tolerance $\epsilon$. However, in many practical applications, constraints must be nearly satisfied with certainty, rendering such solutions potentially unsuitable due to the risk of substantial violations. To address this issue, we propose stochastic first-order methods for finding an $\epsilon$-$surely\ feasible\ stochastic\ optimal$ ($\epsilon$-SFSO) solution, where the constraint violation is deterministically bounded by $\epsilon$ and the expected optimality gap is at most $\epsilon$. Our methods apply an accelerated stochastic gradient (ASG) scheme or a modified variance-reduced ASG scheme $only\ once$ to a sequence of quadratic penalty subproblems with appropriately chosen penalty parameters. We establish first-order oracle complexity bounds for the proposed methods in computing an $\epsilon$-SFSO solution. As a byproduct, we also derive first-order oracle complexity results for sample average approximation method in computing an $\epsilon$-SFSO solution of the stochastic optimization problem using our proposed methods to solve the sample average problem.
Authors: Sijie Li, Weiwei Sun, Shanda Li, Ameet Talwalkar, Yiming Yang
Abstract: Large language model-based machine learning (ML) agents have shown great promise in automating ML research. However, existing agents typically operate in isolation on a given research problem, without engaging with the broader research community, where human researchers often gain insights and contribute by sharing knowledge. To bridge this gap, we introduce MLE-Live, a live evaluation framework designed to assess an agent's ability to communicate with and leverage collective knowledge from a simulated Kaggle research community. Building on this framework, we propose CoMind, a novel agent that excels at exchanging insights and developing novel solutions within a community context. CoMind achieves state-of-the-art performance on MLE-Live and outperforms 79.2% human competitors on average across four ongoing Kaggle competitions. Our code is released at https://github.com/comind-ml/CoMind.
Authors: Jacopo Dapueto, Vito Paolo Pastore, Nicoletta Noceti, Francesca Odone
Abstract: Microscopy image analysis is fundamental for different applications, from diagnosis to synthetic engineering and environmental monitoring. Modern acquisition systems have granted the possibility to acquire an escalating amount of images, requiring a consequent development of a large collection of deep learning-based automatic image analysis methods. Although deep neural networks have demonstrated great performance in this field, interpretability, an essential requirement for microscopy image analysis, remains an open challenge. This work proposes a Disentangled Representation Learning (DRL) methodology to enhance model interpretability for microscopy image classification. Exploiting benchmark datasets from three different microscopic image domains (plankton, yeast vacuoles, and human cells), we show how a DRL framework, based on transferring a representation learnt from synthetic data, can provide a good trade-off between accuracy and interpretability in this domain.
Authors: Sungjae Park, Homanga Bharadhwaj, Shubham Tulsiani
Abstract: We propose DemoDiffusion, a simple and scalable method for enabling robots to perform manipulation tasks in natural environments by imitating a single human demonstration. Our approach is based on two key insights. First, the hand motion in a human demonstration provides a useful prior for the robot's end-effector trajectory, which we can convert into a rough open-loop robot motion trajectory via kinematic retargeting. Second, while this retargeted motion captures the overall structure of the task, it may not align well with plausible robot actions in-context. To address this, we leverage a pre-trained generalist diffusion policy to modify the trajectory, ensuring it both follows the human motion and remains within the distribution of plausible robot actions. Our approach avoids the need for online reinforcement learning or paired human-robot data, enabling robust adaptation to new tasks and scenes with minimal manual effort. Experiments in both simulation and real-world settings show that DemoDiffusion outperforms both the base policy and the retargeted trajectory, enabling the robot to succeed even on tasks where the pre-trained generalist policy fails entirely. Project page: https://demodiffusion.github.io/
Authors: George Bird, Maxim E. Polivoda
Abstract: Backpropagation through time (BPTT) is a technique of updating tuned parameters within recurrent neural networks (RNNs). Several attempts at creating such an algorithm have been made including: Nth Ordered Approximations and Truncated-BPTT. These methods approximate the backpropagation gradients under the assumption that the RNN only utilises short-term dependencies. This is an acceptable assumption to make for the current state of artificial neural networks. As RNNs become more advanced, a shift towards influence by long-term dependencies is likely. Thus, a new method for backpropagation is required. We propose using the 'discrete forward sensitivity equation' and a variant of it for single and multiple interacting recurrent loops respectively. This solution is exact and also allows the network's parameters to vary between each subsequent step, however it does require the computation of a Jacobian.
Authors: Yunpeng Qing, Shunyu Liu, Jie Song, Huiqiong Wang, Mingli Song
Abstract: Reinforcement Learning (RL) is a popular machine learning paradigm where intelligent agents interact with the environment to fulfill a long-term goal. Driven by the resurgence of deep learning, Deep RL (DRL) has witnessed great success over a wide spectrum of complex control tasks. Despite the encouraging results achieved, the deep neural network-based backbone is widely deemed as a black box that impedes practitioners to trust and employ trained agents in realistic scenarios where high security and reliability are essential. To alleviate this issue, a large volume of literature devoted to shedding light on the inner workings of the intelligent agents has been proposed, by constructing intrinsic interpretability or post-hoc explainability. In this survey, we provide a comprehensive review of existing works on eXplainable RL (XRL) and introduce a new taxonomy where prior works are clearly categorized into model-explaining, reward-explaining, state-explaining, and task-explaining methods. We also review and highlight RL methods that conversely leverage human knowledge to promote learning efficiency and performance of agents while this kind of method is often ignored in XRL field. Some challenges and opportunities in XRL are discussed. This survey intends to provide a high-level summarization of XRL and to motivate future research on more effective XRL solutions. Corresponding open source codes are collected and categorized at https://github.com/Plankson/awesome-explainable-reinforcement-learning.
URLs: https://github.com/Plankson/awesome-explainable-reinforcement-learning.
Authors: Shuchen Xue, Mingyang Yi, Weijian Luo, Shifeng Zhang, Jiacheng Sun, Zhenguo Li, Zhi-Ming Ma
Abstract: Diffusion Probabilistic Models (DPMs) have achieved considerable success in generation tasks. As sampling from DPMs is equivalent to solving diffusion SDE or ODE which is time-consuming, numerous fast sampling methods built upon improved differential equation solvers are proposed. The majority of such techniques consider solving the diffusion ODE due to its superior efficiency. However, stochastic sampling could offer additional advantages in generating diverse and high-quality data. In this work, we engage in a comprehensive analysis of stochastic sampling from two aspects: variance-controlled diffusion SDE and linear multi-step SDE solver. Based on our analysis, we propose \textit{SA-Solver}, which is an improved efficient stochastic Adams method for solving diffusion SDE to generate data with high quality. Our experiments show that \textit{SA-Solver} achieves: 1) improved or comparable performance compared with the existing state-of-the-art (SOTA) sampling methods for few-step sampling; 2) SOTA FID on substantial benchmark datasets under a suitable number of function evaluations (NFEs). Code is available at https://github.com/scxue/SA-Solver.
Authors: Naveen Raman, Mateo Espinosa Zarlenga, Juyeon Heo, Mateja Jamnik
Abstract: Concept-based explainability methods use human-understandable intermediaries to produce explanations for machine learning models. These methods assume concept predictions can help understand a model's internal reasoning. In this work, we assess the degree to which such an assumption is true by analyzing whether concept predictors leverage "relevant" features to make predictions, a term we call locality. Concept-based models that fail to respect localities also fail to be explainable because concept predictions are based on spurious features, making the interpretation of the concept predictions vacuous. To assess whether concept-based models respect localities, we construct and use three metrics to characterize when models respect localities, complementing our analysis with theoretical results. Each of our metrics captures a different notion of perturbation and assess whether perturbing "irrelevant" features impacts the predictions made by a concept predictors. We find that many concept-based models used in practice fail to respect localities because concept predictors cannot always clearly distinguish distinct concepts. Based on these findings, we propose suggestions for alleviating this issue.
Authors: Shuyi Chen, Shixiang Zhu
Abstract: Machine learning models have shown exceptional prowess in solving complex issues across various domains. However, these models can sometimes exhibit biased decision-making, resulting in unequal treatment of different groups. Despite substantial research on counterfactual fairness, methods to reduce the impact of multivariate and continuous sensitive variables on decision-making outcomes are still underdeveloped. We propose a novel data pre-processing algorithm, Orthogonal to Bias (OB), which is designed to eliminate the influence of a group of continuous sensitive variables, thus promoting counterfactual fairness in machine learning applications. Our approach, based on the assumption of a jointly normal distribution within a structural causal model (SCM), demonstrates that counterfactual fairness can be achieved by ensuring the data is orthogonal to the observed sensitive variables. The OB algorithm is model-agnostic, making it applicable to a wide range of machine learning models and tasks. Additionally, it includes a sparse variant to improve numerical stability through regularization. Empirical evaluations on both simulated and real-world datasets, encompassing settings with both discrete and continuous sensitive variables, show that our methodology effectively promotes fairer outcomes without compromising accuracy.
Authors: Ruiyang Hong, Anastasis Kratsios
Abstract: The foundations of deep learning are supported by the seemingly opposing perspectives of approximation or learning theory. The former advocates for large/expressive models that need not generalize, while the latter considers classes that generalize but may be too small/constrained to be universal approximators. Motivated by real-world deep learning implementations that are both expressive and statistically reliable, we ask: "Is there a class of neural networks that is both large enough to be universal but structured enough to generalize?" This paper constructively provides a positive answer to this question by identifying a highly structured class of ReLU multilayer perceptions (MLPs), which are optimal function approximators and are statistically well-behaved. We show that any $(L,\alpha)$-H\"{o}lder function from $[0,1]^d$ to $[-n,n]$ can be approximated to a uniform $\mathcal{O}(1/n)$ error on $[0,1]^d$ with a sparsely connected ReLU MLP with the same H\"{o}lder exponent $\alpha$ and coefficient $L$, of width $\mathcal{O}(dn^{d/\alpha})$, depth $\mathcal{O}(\log(d))$, with $\mathcal{O}(dn^{d/\alpha})$ nonzero parameters, and whose weights and biases take values in $\{0,\pm 1/2\}$ except in the first and last layers which instead have magnitude at-most $n$. Further, our class of MLPs achieves a near-optimal sample complexity of $\mathcal{O}(\log(N)/\sqrt{N})$ when given $N$ i.i.d. normalized sub-Gaussian training samples. We achieve this through a new construction that perfectly fits together linear pieces using Kuhn triangulations, along with a new proof technique which shows that our construction preserves the regularity of not only the H\"{o}lder functions, but also any uniformly continuous function. Our results imply that neural networks can solve the McShane extension problem on suitable finite sets.
Authors: Erica Zhang, Fangzhao Zhang, Mert Pilanci
Abstract: Active learning methods aim to improve sample complexity in machine learning. In this work, we investigate an active learning scheme via a novel gradient-free cutting-plane training method for ReLU networks of arbitrary depth and develop a convergence theory. We demonstrate, for the first time, that cutting-plane algorithms, traditionally used in linear models, can be extended to deep neural networks despite their nonconvexity and nonlinear decision boundaries. Moreover, this training method induces the first deep active learning scheme known to achieve convergence guarantees, revealing a geometric contraction rate of the feasible set. We exemplify the effectiveness of our proposed active learning method against popular deep active learning baselines via both synthetic data experiments and sentimental classification task on real datasets.
Authors: Michael T. Pearce, Thomas Dooms, Alice Rigg, Jose M. Oramas, Lee Sharkey
Abstract: A mechanistic understanding of how MLPs do computation in deep neural networks remains elusive. Current interpretability work can extract features from hidden activations over an input dataset but generally cannot explain how MLP weights construct features. One challenge is that element-wise nonlinearities introduce higher-order interactions and make it difficult to trace computations through the MLP layer. In this paper, we analyze bilinear MLPs, a type of Gated Linear Unit (GLU) without any element-wise nonlinearity that nevertheless achieves competitive performance. Bilinear MLPs can be fully expressed in terms of linear operations using a third-order tensor, allowing flexible analysis of the weights. Analyzing the spectra of bilinear MLP weights using eigendecomposition reveals interpretable low-rank structure across toy tasks, image classification, and language modeling. We use this understanding to craft adversarial examples, uncover overfitting, and identify small language model circuits directly from the weights alone. Our results demonstrate that bilinear layers serve as an interpretable drop-in replacement for current activation functions and that weight-based interpretability is viable for understanding deep-learning models.
Authors: Minghao Li (Harvard University), Dmitrii Avdiukhin (Northwestern University), Rana Shahout (Harvard University), Nikita Ivkin (Amazon), Vladimir Braverman (Johns Hopkins University), Minlan Yu (Harvard University)
Abstract: Federated Learning (FL) trains deep models across edge devices without centralizing raw data, preserving user privacy. However, client heterogeneity slows down convergence and limits global model accuracy. Clustered FL (CFL) mitigates this by grouping clients with similar representations and training a separate model for each cluster. In practice, client data evolves over time, a phenomenon we refer to as data drift, which breaks cluster homogeneity and degrades performance. Data drift can take different forms depending on whether changes occur in the output values, the input features, or the relationship between them. We propose FIELDING, a CFL framework for handling diverse types of data drift with low overhead. FIELDING detects drift at individual clients and performs selective re-clustering to balance cluster quality and model performance, while remaining robust to malicious clients and varying levels of heterogeneity. Experiments show that FIELDING improves final model accuracy by 1.9-5.9% and achieves target accuracy 1.16x-2.23x faster than existing state-of-the-art CFL methods.
Authors: Thejan Rajapakshe, Rajib Rana, Farina Riaz, Sara Khalifa, Bj\"orn W. Schuller
Abstract: Quantum machine learning (QML) offers a promising avenue for advancing representation learning in complex signal domains. In this study, we investigate the use of parameterised quantum circuits (PQCs) for speech emotion recognition (SER) a challenging task due to the subtle temporal variations and overlapping affective states in vocal signals. We propose a hybrid quantum classical architecture that integrates PQCs into a conventional convolutional neural network (CNN), leveraging quantum properties such as superposition and entanglement to enrich emotional feature representations. Experimental evaluations on three benchmark datasets IEMOCAP, RECOLA, and MSP-IMPROV demonstrate that our hybrid model achieves improved classification performance relative to a purely classical CNN baseline, with over 50% reduction in trainable parameters. This work provides early evidence of the potential for QML to enhance emotion recognition and lays the foundation for future quantum-enabled affective computing systems.
Authors: Eug\`ene Berta, David Holzm\"uller, Michael I. Jordan, Francis Bach
Abstract: Machine learning classifiers often produce probabilistic predictions that are critical for accurate and interpretable decision-making in various domains. The quality of these predictions is generally evaluated with proper losses, such as cross-entropy, which decompose into two components: calibration error assesses general under/overconfidence, while refinement error measures the ability to distinguish different classes. In this paper, we present a novel variational formulation of the calibration-refinement decomposition that sheds new light on post-hoc calibration, and enables rapid estimation of the different terms. Equipped with this new perspective, we provide theoretical and empirical evidence that calibration and refinement errors are not minimized simultaneously during training. Selecting the best epoch based on validation loss thus leads to a compromise point that is suboptimal for both terms. To address this, we propose minimizing refinement error only during training (Refine,...), before minimizing calibration error post hoc, using standard techniques (...then Calibrate). Our method integrates seamlessly with any classifier and consistently improves performance across diverse classification tasks.
Authors: Mahdi Sabbaghi, Paul Kassianik, George Pappas, Yaron Singer, Amin Karbasi, Hamed Hassani
Abstract: As large language models (LLMs) are becoming more capable and widespread, the study of their failure cases is becoming increasingly important. Recent advances in standardizing, measuring, and scaling test-time compute suggest new methodologies for optimizing models to achieve high performance on hard tasks. In this paper, we apply these advances to the task of model jailbreaking: eliciting harmful responses from aligned LLMs. We develop an adversarial reasoning approach to automatic jailbreaking that leverages a loss signal to guide the test-time compute, achieving SOTA attack success rates against many aligned LLMs, even those that aim to trade inference-time compute for adversarial robustness. Our approach introduces a new paradigm in understanding LLM vulnerabilities, laying the foundation for the development of more robust and trustworthy AI systems.
Authors: Steve Azzolin, Sagar Malhotra, Andrea Passerini, Stefano Teso
Abstract: Self-Explainable Graph Neural Networks (SE-GNNs) are popular explainable-by-design GNNs, but their explanations' properties and limitations are not well understood. Our first contribution fills this gap by formalizing the explanations extracted by some popular SE-GNNs, referred to as Minimal Explanations (MEs), and comparing them to established notions of explanations, namely Prime Implicant (PI) and faithful explanations. Our analysis reveals that MEs match PI explanations for a restricted but significant family of tasks. In general, however, they can be less informative than PI explanations and are surprisingly misaligned with widely accepted notions of faithfulness. Although faithful and PI explanations are informative, they are intractable to find and we show that they can be prohibitively large. Given these observations, a natural choice is to augment SE-GNNs with alternative modalities of explanations taking care of SE-GNNs' limitations. To this end, we propose Dual-Channel GNNs that integrate a white-box rule extractor and a standard SE-GNN, adaptively combining both channels. Our experiments show that even a simple instantiation of Dual-Channel GNNs can recover succinct rules and perform on par or better than widely used SE-GNNs.
Authors: Filip Ekstr\"om Kelvinius, Zheng Zhao, Fredrik Lindsten
Abstract: A recent line of research has exploited pre-trained generative diffusion models as priors for solving Bayesian inverse problems. We contribute to this research direction by designing a sequential Monte Carlo method for linear-Gaussian inverse problems which builds on "decoupled diffusion", where the generative process is designed such that larger updates to the sample are possible. The method is asymptotically exact and we demonstrate the effectiveness of our Decoupled Diffusion Sequential Monte Carlo (DDSMC) algorithm on both synthetic as well as protein and image data. Further, we demonstrate how the approach can be extended to discrete data.
Authors: Corinna Cortes, Anqi Mao, Mehryar Mohri, Yutao Zhong
Abstract: Class imbalance remains a major challenge in machine learning, especially in multi-class problems with long-tailed distributions. Existing methods, such as data resampling, cost-sensitive techniques, and logistic loss modifications, though popular and often effective, lack solid theoretical foundations. As an example, we demonstrate that cost-sensitive methods are not Bayes-consistent. This paper introduces a novel theoretical framework for analyzing generalization in imbalanced classification. We then propose a new class-imbalanced margin loss function for both binary and multi-class settings, prove its strong $H$-consistency, and derive corresponding learning guarantees based on empirical loss and a new notion of class-sensitive Rademacher complexity. Leveraging these theoretical results, we devise novel and general learning algorithms, IMMAX (Imbalanced Margin Maximization), which incorporate confidence margins and are applicable to various hypothesis sets. While our focus is theoretical, we also present extensive empirical results demonstrating the effectiveness of our algorithms compared to existing baselines.
Authors: Guikun Chen, Xu Zhang, Xiaolin Hu, Yong Liu, Yi Yang, Wenguan Wang
Abstract: Chemical reaction data is a pivotal asset, driving advances in competitive fields such as pharmaceuticals, materials science, and industrial chemistry. Its proprietary nature renders it sensitive, as it often includes confidential insights and competitive advantages organizations strive to protect. However, in contrast to this need for confidentiality, the current standard training paradigm for machine learning-based retrosynthesis gathers reaction data from multiple sources into one single edge to train prediction models. This paradigm poses considerable privacy risks as it necessitates broad data availability across organizational boundaries and frequent data transmission between entities, potentially exposing proprietary information to unauthorized access or interception during storage and transfer. In the present study, we introduce the chemical knowledge-informed framework (CKIF), a privacy-preserving approach for learning retrosynthesis models. CKIF enables distributed training across multiple chemical organizations without compromising the confidentiality of proprietary reaction data. Instead of gathering raw reaction data, CKIF learns retrosynthesis models through iterative, chemical knowledge-informed aggregation of model parameters. In particular, the chemical properties of predicted reactants are leveraged to quantitatively assess the observable behaviors of individual models, which in turn determines the adaptive weights used for model aggregation. On a variety of reaction datasets, CKIF outperforms several strong baselines by a clear margin.
Authors: Lucas Caccia, Alan Ansell, Edoardo Ponti, Ivan Vuli\'c, Alessandro Sordoni
Abstract: Dynamically integrating new or rapidly evolving information after (Large) Language Model pre-training remains challenging, particularly in low-data scenarios or when dealing with private and specialized documents. In-context learning and retrieval-augmented generation (RAG) face limitations, including their high inference costs and their inability to capture global document information. In this paper, we propose a way of modularizing knowledge by training document-level Knowledge Modules (KMs). KMs are lightweight components implemented as parameter-efficient LoRA modules, which are trained to store information about new documents and can be easily plugged into models on demand. We show that next-token prediction performs poorly as the training objective for KMs. We instead propose Deep Context Distillation: we learn KMs parameters such as to simulate hidden states and logits of a teacher that takes the document in context. Our method outperforms standard next-token prediction and pre-instruction training techniques, across two datasets. Finally, we highlight synergies between KMs and RAG.
Authors: Jingxin Zhan, Yuchen Xin, Chenjie Sun, Zhihua Zhang
Abstract: We consider a common case of the combinatorial semi-bandit problem, the $m$-set semi-bandit, where the learner exactly selects $m$ arms from the total $d$ arms. In the adversarial setting, the best regret bound, known to be $\mathcal{O}(\sqrt{nmd})$ for time horizon $n$, is achieved by the well-known Follow-the-Regularized-Leader (FTRL) policy. However, this requires to explicitly compute the arm-selection probabilities via optimizing problems at each time step and sample according to them. This problem can be avoided by the Follow-the-Perturbed-Leader (FTPL) policy, which simply pulls the $m$ arms that rank among the $m$ smallest (estimated) loss with random perturbation. In this paper, we show that FTPL with a Fr\'echet perturbation also enjoys the near optimal regret bound $\mathcal{O}(\sqrt{nm}(\sqrt{d\log(d)}+m^{5/6}))$ in the adversarial setting and approaches best-of-both-world regret bounds, i.e., achieves a logarithmic regret for the stochastic setting. Moreover, our lower bounds show that the extra factors are unavoidable with our approach; any improvement would require a fundamentally different and more challenging method.
Authors: Avrim Blum, Steve Hanneke, Chirag Pabbaraju, Donya Saless
Abstract: We consider a model for explainable AI in which an explanation for a prediction $h(x)=y$ consists of a subset $S'$ of the training data (if it exists) such that all classifiers $h' \in H$ that make at most $b$ mistakes on $S'$ predict $h'(x)=y$. Such a set $S'$ serves as a proof that $x$ indeed has label $y$ under the assumption that (1) the target function $h^\star$ belongs to $H$, and (2) the set $S$ contains at most $b$ corrupted points. For example, if $b=0$ and $H$ is the family of linear classifiers in $\mathbb{R}^d$, and if $x$ lies inside the convex hull of the positive data points in $S$ (and hence every consistent linear classifier labels $x$ as positive), then Carath\'eodory's theorem states that $x$ lies inside the convex hull of $d+1$ of those points. So, a set $S'$ of size $d+1$ could be released as an explanation for a positive prediction, and would serve as a short proof of correctness of the prediction under the assumption of realizability. In this work, we consider this problem more generally, for general hypothesis classes $H$ and general values $b\geq 0$. We define the notion of the robust hollow star number of $H$ (which generalizes the standard hollow star number), and show that it precisely characterizes the worst-case size of the smallest certificate achievable, and analyze its size for natural classes. We also consider worst-case distributional bounds on certificate size, as well as distribution-dependent bounds that we show tightly control the sample size needed to get a certificate for any given test example. In particular, we define a notion of the certificate coefficient $\varepsilon_x$ of an example $x$ with respect to a data distribution $D$ and target function $h^\star$, and prove matching upper and lower bounds on sample size as a function of $\varepsilon_x$, $b$, and the VC dimension $d$ of $H$.
Authors: Mauricio Ortiz Torres, Markus Lange, Arne P. Raulf
Abstract: The Forward-Forward algorithm has evolved in machine learning research, tackling more complex tasks that mimic real-life applications. In the last years, it has been improved by several techniques to perform better than its original version, handling a challenging dataset like CIFAR10 without losing its flexibility and low memory usage. We have shown in our results that improvements are achieved through a combination of convolutional channel grouping, learning rate schedules, and independent block structures during training that lead to a 20\% decrease in test error percentage. Additionally, to approach further implementations on low-capacity hardware projects, we have presented a series of lighter models that achieve low test error percentages within (21$\pm$3)\% and number of trainable parameters between 164,706 and 754,386. This serves as a basis for our future study on complete verification and validation of these kinds of neural networks.
Authors: Jingnan Wang, Jie Chao, Shangshang Yang, Congyi Nai, Kaijun Ren, Kefeng Deng, Xi Chen, Yaxin Liu, Hanqiuzi Wen, Ziniu Xiao, Lifeng Zhang, Xiaodong Wang, Jiping Guan, Baoxiang Pan
Abstract: The planning and operation of renewable energy, especially wind power, depend crucially on accurate, timely, and high-resolution weather information. Coarse-grid global numerical weather forecasts are typically downscaled to meet these requirements, introducing challenges of scale inconsistency, process representation error, computation cost, and entanglement of distinct uncertainty sources from chaoticity, model bias, and large-scale forcing. We address these challenges by learning the climatological distribution of a target wind farm using its high-resolution numerical weather simulations. An optimal combination of this learned high-resolution climatological prior with coarse-grid large scale forecasts yields highly accurate, fine-grained, full-variable, large ensemble of weather pattern forecasts. Using observed meteorological records and wind turbine power outputs as references, the proposed methodology verifies advantageously compared to existing numerical/statistical forecasting-downscaling pipelines, regarding either deterministic/probabilistic skills or economic gains. Moreover, a 100-member, 10-day forecast with spatial resolution of 1 km and output frequency of 15 min takes < 1 hour on a moderate-end GPU, as contrast to $\mathcal{O}(10^3)$ CPU hours for conventional numerical simulation. By drastically reducing computational costs while maintaining accuracy, our method paves the way for more efficient and reliable renewable energy planning and operation.
Authors: Vijay Ekambaram, Subodh Kumar, Arindam Jati, Sumanta Mukherjee, Tomoya Sakai, Pankaj Dayama, Wesley M. Gifford, Jayant Kalagnanam
Abstract: The rise of time-series pre-trained models has advanced temporal representation learning, but current state-of-the-art models are often large-scale, requiring substantial compute. We introduce TSPulse, ultra-compact time-series pre-trained models with only 1M parameters, specialized to perform strongly across classification, anomaly detection, imputation, and retrieval tasks. TSPulse introduces innovations at both the architecture and task levels. At the architecture level, it employs a dual-space masked reconstruction, learning from both time and frequency domains to capture complementary signals. This is further enhanced by a dual-embedding disentanglement, generating both detailed embeddings for fine-grained analysis and high-level semantic embeddings for broader task understanding. Notably, TSPulse's semantic embeddings are robust to shifts in time, magnitude, and noise, which is important for robust retrieval. At the task level, TSPulse incorporates TSLens, a fine-tuning component enabling task-specific feature attention. It also introduces a multi-head triangulation technique that correlates deviations from multiple prediction heads, enhancing anomaly detection by fusing complementary model outputs. Additionally, a hybrid mask pretraining is proposed to improves zero-shot imputation by reducing pre-training bias. These architecture and task innovations collectively contribute to TSPulse's significant performance gains: 5-16% on the UEA classification benchmarks, +20% on the TSB-AD anomaly detection leaderboard, +50% in zero-shot imputation, and +25% in time-series retrieval. Remarkably, these results are achieved with just 1M parameters (10-100X smaller than existing SOTA models) and allow GPU-free inference, setting a new standard for efficient time-series pre-trained models. The models can be accessed from https://huggingface.co/ibm-granite/granite-timeseries-tspulse-r1
URLs: https://huggingface.co/ibm-granite/granite-timeseries-tspulse-r1
Authors: Diyuan Wu, Aleksandr Shevchenko, Samet Oymak, Marco Mondelli
Abstract: Token embeddings play a crucial role in language modeling but, despite this practical relevance, their theoretical understanding remains limited. Our paper addresses the gap by characterizing the structure of embeddings obtained via gradient descent. Specifically, we consider a one-layer softmax attention model with a linear head for binary classification, i.e., $\texttt{Softmax}( p^\top E_X^\top ) E_X v = \frac{ \sum_{i=1}^T \exp(p^\top E_{x_i}) E_{x_i}^\top v}{\sum_{j=1}^T \exp(p^\top E_{x_{j}}) }$, where $E_X = [ E_{x_1} , \dots, E_{x_T} ]^\top$ contains the embeddings of the input sequence, $p$ is the embedding of the $\mathrm{\langle cls \rangle}$ token and $v$ the output vector. First, we show that, already after a single step of gradient training with the logistic loss, the embeddings $E_X$ capture the importance of tokens in the dataset by aligning with the output vector $v$ proportionally to the frequency with which the corresponding tokens appear in the dataset. Then, after training $p$ via gradient flow until convergence, the softmax selects the important tokens in the sentence (i.e., those that are predictive of the label), and the resulting $\mathrm{\langle cls \rangle}$ embedding maximizes the margin for such a selection. Experiments on real-world datasets (IMDB, Yelp) exhibit a phenomenology close to that unveiled by our theory.
Authors: Lan-Cuong Nguyen, Quan Nguyen-Tri, Bang Tran Khanh, Dung D. Le, Long Tran-Thanh, Khoat Than
Abstract: Few-shot image classification remains challenging due to the scarcity of labeled training examples. Augmenting them with synthetic data has emerged as a promising way to alleviate this issue, but models trained on synthetic samples often face performance degradation due to the inherent gap between real and synthetic distributions. To address this limitation, we develop a theoretical framework that quantifies the impact of such distribution discrepancies on supervised learning, specifically in the context of image classification. More importantly, our framework suggests practical ways to generate good synthetic samples and to train a predictor with high generalization ability. Building upon this framework, we propose a novel theoretical-based algorithm that integrates prototype learning to optimize both data partitioning and model training, effectively bridging the gap between real few-shot data and synthetic data. Extensive experiments results show that our approach demonstrates superior performance compared to state-of-the-art methods, outperforming them across multiple datasets.
Authors: Han Guo, Songlin Yang, Tarushii Goel, Eric P. Xing, Tri Dao, Yoon Kim
Abstract: The attention mechanism in Transformers is an important primitive for accurate and scalable sequence modeling. Its quadratic-compute and linear-memory complexity however remain significant bottlenecks. Linear attention and state-space models enable linear-time, constant-memory sequence modeling and can moreover be trained efficiently through matmul-rich parallelization across sequence length. However, at their core these models are still RNNs, and thus their use of a fixed-size hidden state to model the context is a fundamental limitation. This paper develops log-linear attention, an attention mechanism that balances linear attention's efficiency and the expressiveness of softmax attention. Log-linear attention replaces the fixed-size hidden state with a logarithmically growing set of hidden states. We show that with a particular growth function, log-linear attention admits a similarly matmul-rich parallel form whose compute cost is log-linear in sequence length. Log-linear attention is a general framework and can be applied on top of existing linear attention variants. As case studies, we instantiate log-linear variants of two recent architectures -- Mamba-2 and Gated DeltaNet -- and find they perform well compared to their linear-time variants.
Authors: Yuanye Zhou, Zhaokun Wang, Kai Zhou, Hui Tang, Xiaofan Li
Abstract: Physics-informed neural networks (PINNs) have emerged as a powerful meshless tool for topology optimization, capable of simultaneously determining optimal topologies and physical solutions. However, conventional PINNs rely on density-based topology descriptions, which necessitate manual interpolation and limit their applicability to complex geometries. To address this, we propose Lagrangian topology-conscious PINNs (LT-PINNs), a novel framework for boundary-focused engineering optimization. By parameterizing the control variables of topology boundary curves as learnable parameters, LT-PINNs eliminate the need for manual interpolation and enable precise boundary determination. We further introduce specialized boundary condition loss function and topology loss function to ensure sharp and accurate boundary representations, even for intricate topologies. The accuracy and robustness of LT-PINNs are validated via two types of partial differential equations (PDEs), including elastic equation with Dirichlet boundary conditions and Laplace's equation with Neumann boundary conditions. Furthermore, we demonstrate effectiveness of LT-PINNs on more complex time-dependent and time-independent flow problems without relying on measurement data, and showcase their engineering application potential in flow velocity rearrangement, transforming a uniform upstream velocity into a sine-shaped downstream profile. The results demonstrate (1) LT-PINNs achieve substantial reductions in relative L2 errors compared with the state-of-art density topology-oriented PINNs (DT-PINNs), (2) LT-PINNs can handle arbitrary boundary conditions, making them suitable for a wide range of PDEs, and (3) LT-PINNs can infer clear topology boundaries without manual interpolation, especially for complex topologies.
Authors: Seungho Baek, Taegeon Park, Jongchan Park, Seungjun Oh, Yusung Kim
Abstract: Existing offline hierarchical reinforcement learning methods rely on high-level policy learning to generate subgoal sequences. However, their efficiency degrades as task horizons increase, and they lack effective strategies for stitching useful state transitions across different trajectories. We propose Graph-Assisted Stitching (GAS), a novel framework that formulates subgoal selection as a graph search problem rather than learning an explicit high-level policy. By embedding states into a Temporal Distance Representation (TDR) space, GAS clusters semantically similar states from different trajectories into unified graph nodes, enabling efficient transition stitching. A shortest-path algorithm is then applied to select subgoal sequences within the graph, while a low-level policy learns to reach the subgoals. To improve graph quality, we introduce the Temporal Efficiency (TE) metric, which filters out noisy or inefficient transition states, significantly enhancing task performance. GAS outperforms prior offline HRL methods across locomotion, navigation, and manipulation tasks. Notably, in the most stitching-critical task, it achieves a score of 88.3, dramatically surpassing the previous state-of-the-art score of 1.0. Our source code is available at: https://github.com/qortmdgh4141/GAS.
Authors: Jina Kim, Youjin Jang, Jeongjin Han
Abstract: We propose VRAIL (Vectorized Reward-based Attribution for Interpretable Learning), a bi-level framework for value-based reinforcement learning (RL) that learns interpretable weight representations from state features. VRAIL consists of two stages: a deep learning (DL) stage that fits an estimated value function using state features, and an RL stage that uses this to shape learning via potential-based reward transformations. The estimator is modeled in either linear or quadratic form, allowing attribution of importance to individual features and their interactions. Empirical results on the Taxi-v3 environment demonstrate that VRAIL improves training stability and convergence compared to standard DQN, without requiring environment modifications. Further analysis shows that VRAIL uncovers semantically meaningful subgoals, such as passenger possession, highlighting its ability to produce human-interpretable behavior. Our findings suggest that VRAIL serves as a general, model-agnostic framework for reward shaping that enhances both learning and interpretability.
Authors: Nick Erickson, Lennart Purucker, Andrej Tschalzev, David Holzm\"uller, Prateek Mutalik Desai, David Salinas, Frank Hutter
Abstract: With the growing popularity of deep learning and foundation models for tabular data, the need for standardized and reliable benchmarks is higher than ever. However, current benchmarks are static. Their design is not updated even if flaws are discovered, model versions are updated, or new models are released. To address this, we introduce TabArena, the first continuously maintained living tabular benchmarking system. To launch TabArena, we manually curate a representative collection of datasets and well-implemented models, conduct a large-scale benchmarking study to initialize a public leaderboard, and assemble a team of experienced maintainers. Our results highlight the influence of validation method and ensembling of hyperparameter configurations to benchmark models at their full potential. While gradient-boosted trees are still strong contenders on practical tabular datasets, we observe that deep learning methods have caught up under larger time budgets with ensembling. At the same time, foundation models excel on smaller datasets. Finally, we show that ensembles across models advance the state-of-the-art in tabular machine learning and investigate the contributions of individual models. We launch TabArena with a public leaderboard, reproducible code, and maintenance protocols to create a living benchmark available at https://tabarena.ai.
URLs: https://tabarena.ai.
Authors: Yanzhi Zhang, Zhaoxi Zhang, Haoxiang Guan, Yilin Cheng, Yitong Duan, Chen Wang, Yue Wang, Shuxin Zheng, Jiyan He
Abstract: Reinforcement learning has emerged as a powerful paradigm for post-training large language models (LLMs) to improve reasoning. Approaches like Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) have shown strong results, but they require extensive external supervision. We investigate an alternative class of methods, Reinforcement Learning from Internal Feedback (RLIF), which relies solely on intrinsic model-derived signals instead of external rewards. In particular, we leverage unsupervised reward proxies such as token-level entropy, trajectory-level entropy, and self-certainty. Our theoretical analysis shows these internal objectives are partially equivalent, and we empirically evaluate various RLIF strategies on challenging math reasoning benchmarks. Experimental results demonstrate that RLIF can boost the reasoning performance of base LLMs at the beginning phase of the training, matching or surpassing RLVR techniques on these tasks. However, when training progresses, performance degrades even below the model before training. Moreover, we find that RLIF yields little improvement for instruction-tuned models, indicating diminishing returns of intrinsic feedback once an LLM is already instruction-tuned. We further analyze this limitation by mixing model weights and explain the reason of RLIF's training behaviors, providing practical guidelines for integrating internal feedback signals into LLM training. We hope our analysis of internal feedback will inform more principled and effective strategies for LLM post-training.
Authors: Chenghan Li, Mingchen Li, Yipu Liao, Ruisheng Diao
Abstract: Long-term time series prediction has predominantly relied on Transformer and MLP models, while the potential of convolutional networks in this domain remains underexplored. To address this gap, we introduce a novel multi-scale time series reshape module, which effectively captures the relationships among multi-period patches and variable dependencies. Building upon this module, we propose MS-TVNet, a multi-scale 3D dynamic convolutional neural network. Through comprehensive evaluations on diverse datasets, MS-TVNet demonstrates superior performance compared to baseline models, achieving state-of-the-art (SOTA) results in long-term time series prediction. Our findings highlight the effectiveness of leveraging convolutional networks for capturing complex temporal patterns, suggesting a promising direction for future research in this field.The code is realsed on https://github.com/Curyyfaust/TVNet.
Authors: Jaemoo Choi, Yongxin Chen, Molei Tao, Guan-Horng Liu
Abstract: Recently, there has been significant progress in learning-based diffusion samplers, which aim to sample from a given unnormalized density. These methods typically follow one of two paradigms: (i) formulating sampling as an unbiased stochastic optimal control (SOC) problem using a canonical reference process, or (ii) refining annealed path measures through importance-weighted sampling. Although annealing approaches have advantages in guiding samples toward high-density regions, reliance on importance sampling leads to high variance and limited scalability in practice. In this paper, we introduce the \textbf{Non-equilibrium Annealed Adjoint Sampler (NAAS)}, a novel SOC-based diffusion sampler that leverages annealed reference dynamics without resorting to importance sampling. NAAS employs a lean adjoint system inspired by adjoint matching, enabling efficient and scalable training. We demonstrate the effectiveness of our approach across a range of tasks, including sampling from classical energy landscapes and molecular Boltzmann distribution.
Authors: Wenxin Li, Chuan Wang, Hongdong Zhu, Qi Gao, Yin Ma, Hai Wei, Kai Wen
Abstract: Here in this work, we present a novel Quadratic Binary Optimization (QBO) model for quantized neural network training, enabling the use of arbitrary activation and loss functions through spline interpolation. We introduce Forward Interval Propagation (FIP), a method designed to tackle the challenges of non-linearity and the multi-layer composite structure in neural networks by discretizing activation functions into linear subintervals. This approach preserves the universal approximation properties of neural networks while allowing complex nonlinear functions to be optimized using quantum computers, thus broadening their applicability in artificial intelligence. We provide theoretical upper bounds on the approximation error and the number of Ising spins required, by deriving the sample complexity of the empirical risk minimization problem, from an optimization perspective. A significant challenge in solving the associated Quadratic Constrained Binary Optimization (QCBO) model on a large scale is the presence of numerous constraints. When employing the penalty method to handle these constraints, tuning a large number of penalty coefficients becomes a critical hyperparameter optimization problem, increasing computational complexity and potentially affecting solution quality. To address this, we employ the Quantum Conditional Gradient Descent (QCGD) algorithm, which leverages quantum computing to directly solve the QCBO problem. We prove the convergence of QCGD under a quantum oracle with randomness and bounded variance in objective value, as well as under limited precision constraints in the coefficient matrix. Additionally, we provide an upper bound on the Time-To-Solution for the QCBO solving process. Experimental results using a coherent Ising machine (CIM) demonstrate a 94.95% accuracy on the Fashion MNIST classification task, with only 1.1-bit precision.
Authors: Lixin Wu, Na Cai, Qiao Cheng, Jiachen Wang, Yitao Duan
Abstract: We introduce Confucius3-Math, an open-source large language model with 14B parameters that (1) runs efficiently on a single consumer-grade GPU; (2) achieves SOTA performances on a range of mathematical reasoning tasks, outperforming many models with significantly larger sizes. In particular, as part of our mission to enhancing education and knowledge dissemination with AI, Confucius3-Math is specifically committed to mathematics learning for Chinese K-12 students and educators. Built via post-training with large-scale reinforcement learning (RL), Confucius3-Math aligns with national curriculum and excels at solving main-stream Chinese K-12 mathematical problems with low cost. In this report we share our development recipe, the challenges we encounter and the techniques we develop to overcome them. In particular, we introduce three technical innovations: Targeted Entropy Regularization, Recent Sample Recovery and Policy-Specific Hardness Weighting. These innovations encompass a new entropy regularization, a novel data scheduling policy, and an improved group-relative advantage estimator. Collectively, they significantly stabilize the RL training, improve data efficiency, and boost performance. Our work demonstrates the feasibility of building strong reasoning models in a particular domain at low cost. We open-source our model and code at https://github.com/netease-youdao/Confucius3-Math.
Authors: Anthony Kobanda, Waris Radji, Mathieu Petitbois, Odalric-Ambrym Maillard, R\'emy Portelas
Abstract: Offline Goal-Conditioned Reinforcement Learning seeks to train agents to reach specified goals from previously collected trajectories. Scaling that promises to long-horizon tasks remains challenging, notably due to compounding value-estimation errors. Principled geometric offers a potential solution to address these issues. Following this insight, we introduce Projective Quasimetric Planning (ProQ), a compositional framework that learns an asymmetric distance and then repurposes it, firstly as a repulsive energy forcing a sparse set of keypoints to uniformly spread over the learned latent space, and secondly as a structured directional cost guiding towards proximal sub-goals. In particular, ProQ couples this geometry with a Lagrangian out-of-distribution detector to ensure the learned keypoints stay within reachable areas. By unifying metric learning, keypoint coverage, and goal-conditioned control, our approach produces meaningful sub-goals and robustly drives long-horizon goal-reaching on diverse a navigation benchmarks.
Authors: Paul C. Bogdan, Uzay Macar, Neel Nanda, Arthur Conmy
Abstract: Reasoning large language models have recently achieved state-of-the-art performance in many fields. However, their long-form chain-of-thought reasoning creates interpretability challenges as each generated token depends on all previous ones, making the computation harder to decompose. We argue that analyzing reasoning traces at the sentence level is a promising approach to understanding reasoning processes. We present three complementary attribution methods: (1) a black-box method measuring each sentence's counterfactual importance by comparing final answers across 100 rollouts conditioned on the model generating that sentence or one with a different meaning; (2) a white-box method of aggregating attention patterns between pairs of sentences, which identified "broadcasting" sentences that receive disproportionate attention from all future sentences via "receiver" attention heads; (3) a causal attribution method measuring logical connections between sentences by suppressing attention toward one sentence and measuring the effect on each future sentence's tokens. Each method provides evidence for the existence of thought anchors, reasoning steps that have outsized importance and that disproportionately influence the subsequent reasoning process. These thought anchors are typically planning or backtracking sentences. We provide an open-source tool (www.thought-anchors.com) for visualizing the outputs of our methods, and present a case study showing converging patterns across methods that map how a model performs multi-step reasoning. The consistency across methods demonstrates the potential of sentence-level analysis for a deeper understanding of reasoning models.
Authors: Palina Salanevich, Olov Schavemaker
Abstract: A Random Vector Functional Link (RVFL) network is a depth-2 neural network with random inner weights and biases. Only the outer weights of such an architecture are to be learned, so the learning process boils down to a linear optimization task, allowing one to sidestep the pitfalls of nonconvex optimization problems. In this paper, we prove that an RVFL with ReLU activation functions can approximate Lipschitz continuous functions in $L_\infty$ norm. To the best of our knowledge, our result is the first approximation result in $L_\infty$ norm using nice inner weights; namely, Gaussians. We give a nonasymptotic lower bound for the number of hidden-layer nodes to achieve a given accuracy with high probability, depending on, among other things, the Lipschitz constant of the target function, the desired accuracy, and the input dimension. Our method of proof is rooted in probability theory and harmonic analysis.
Authors: C. -C. Joseph Wang, F. Perkkola, I. Salmenper\"a, A. Meijer-van de Griend, J. K. Nurminen, R. S. Bennink
Abstract: Hybrid variational quantum algorithms (VQAs) are promising for solving practical problems such as combinatorial optimization, quantum chemistry simulation, quantum machine learning, and quantum error correction on noisy quantum computers. However, with typical random ansatz or quantum alternating operator ansatz, derived variational quantum algorithms become a black box that cannot be trusted for model interpretation, not to mention deploying as applications in informing critical decisions: the results of these variational parameters are just rotational angles for the quantum gates and have nothing to do with interpretable values that a model can provide directly. In this paper, we construct the first interpretable quantum regression algorithm, in which the quantum state exactly encodes the classical data table and the variational parameters correspond directly to the regression coefficients, which are real numbers by construction, providing a high degree of model interpretability and minimal cost to optimize due to the right expressiveness. We also take advantage of the encoded data structure to reduce the time complexity of computing the regression map. To shorten the circuit depth for nonlinear regression, our algorithm can be extended by building nonlinear features by classical preprocessing as the independent encoded column vectors. Even though the realization of compressed encoding in superconducting qubits has been achieved by the less noisy compressed encoding recently by the authors, we envision potential quantum utilities with multi-qubit gates implemented in neutral cold atoms and ions.
Authors: Thangarajah Akilan, Hrishikesh Vachhani
Abstract: Pedestrian detection has become a cornerstone for several high-level tasks, including autonomous driving, intelligent transportation, and traffic surveillance. There are several works focussed on pedestrian detection using visible images, mainly in the daytime. However, this task is very intriguing when the environmental conditions change to poor lighting or nighttime. Recently, new ideas have been spurred to use alternative sources, such as Far InfraRed (FIR) temperature sensor feeds for detecting pedestrians in low-light conditions. This study reviews recent developments in low-light pedestrian detection approaches. It systematically categorizes and analyses various algorithms from region-based to non-region-based and graph-based learning methodologies by highlighting their methodologies, implementation issues, and challenges. It also outlines the key benchmark datasets that can be used for research and development of advanced pedestrian detection algorithms, particularly in low-light situations.
Authors: Ben Anson, Edward Milsom, Laurence Aitchison
Abstract: A common theoretical approach to understanding neural networks is to take an infinite-width limit, at which point the outputs become Gaussian process (GP) distributed. This is known as a neural network Gaussian process (NNGP). However, the NNGP kernel is fixed and tunable only through a small number of hyperparameters, thus eliminating the possibility of representation learning. This contrasts with finite-width NNs, which are often believed to perform well because they are able to flexibly learn representations for the task at hand. Thus, in simplifying NNs to make them theoretically tractable, NNGPs may eliminate precisely what makes them work well (representation learning). This motivated us to understand whether representation learning is necessary in a range of graph tasks. We develop a precise tool for this task, the graph convolutional deep kernel machine. This is very similar to an NNGP, in that it is an infinite width limit and uses kernels, but comes with a ``knob'' to control the amount of flexibility and hence representation learning. We found that representation learning gives noticeable performance improvements for heterophilous node classification tasks, but less so for homophilous node classification tasks.
Authors: Benjamin D. Killeen, Liam J. Wang, Blanca Inigo, Han Zhang, Mehran Armand, Russell H. Taylor, Greg Osgood, Mathias Unberath
Abstract: Language promptable X-ray image segmentation would enable greater flexibility for human-in-the-loop workflows in diagnostic and interventional precision medicine. Prior efforts have contributed task-specific models capable of solving problems within a narrow scope, but expanding to broader use requires additional data, annotations, and training time. Recently, language-aligned foundation models (LFMs) -- machine learning models trained on large amounts of highly variable image and text data thus enabling broad applicability -- have emerged as promising tools for automated image analysis. Existing foundation models for medical image analysis focus on scenarios and modalities where large, richly annotated datasets are available. However, the X-ray imaging modality features highly variable image appearance and applications, from diagnostic chest X-rays to interventional fluoroscopy, with varying availability of data. To pave the way toward an LFM for comprehensive and language-aligned analysis of arbitrary medical X-ray images, we introduce FluoroSAM, a language-promptable variant of the Segment Anything Model, trained from scratch on 3M synthetic X-ray images from a wide variety of human anatomies, imaging geometries, and viewing angles. These include pseudo-ground truth masks for 128 organ types and 464 tools with associated text descriptions. FluoroSAM is capable of segmenting myriad anatomical structures and tools based on natural language prompts, thanks to the novel incorporation of vector quantization (VQ) of text embeddings in the training process. We demonstrate FluoroSAM's performance quantitatively on real X-ray images and showcase on several applications how FluoroSAM is a key enabler for rich human-machine interaction in the X-ray image acquisition and analysis context. Code is available at https://github.com/arcadelab/fluorosam.
Authors: Xiang Li, Chaofan Fu, Zhongying Zhao, Guanjie Zheng, Chao Huang, Yanwei Yu, Junyu Dong
Abstract: Effective recommender systems play a crucial role in accurately capturing user and item attributes that mirror individual preferences. Some existing recommendation techniques have started to shift their focus towards modeling various types of interactive relations between users and items in real-world recommendation scenarios, such as clicks, marking favorites, and purchases on online shopping platforms. Nevertheless, these approaches still grapple with two significant challenges: (1) Insufficient modeling and exploitation of the impact of various behavior patterns formed by multiplex relations between users and items on representation learning, and (2) ignoring the effect of different relations within behavior patterns on the target relation in recommender system scenarios. In this work, we introduce a novel recommendation framework, Dual-Channel Multiplex Graph Neural Network (DCMGNN), which addresses the aforementioned challenges. It incorporates an explicit behavior pattern representation learner to capture the behavior patterns composed of multiplex user-item interactive relations, and includes a relation chain representation learner and a relation chain-aware encoder to discover the impact of various auxiliary relations on the target relation, the dependencies between different relations, and mine the appropriate order of relations in a behavior pattern. Extensive experiments on three real-world datasets demonstrate that our DCMGNN surpasses various state-of-the-art recommendation methods. It outperforms the best baselines by 10.06% and 12.15% on average across all datasets in terms of Recall@10 and NDCG@10, respectively.
Authors: Ricardo Cannizzaro, Michael Groom, Jonathan Routley, Robert Osazuwa Ness, Lars Kunze
Abstract: Manipulation tasks require robots to reason about cause and effect when interacting with objects. Yet, many data-driven approaches lack causal semantics and thus only consider correlations. We introduce COBRA-PPM, a novel causal Bayesian reasoning architecture that combines causal Bayesian networks and probabilistic programming to perform interventional inference for robot manipulation under uncertainty. We demonstrate its capabilities through high-fidelity Gazebo-based experiments on an exemplar block stacking task, where it predicts manipulation outcomes with high accuracy (Pred Acc: 88.6%) and performs greedy next-best action selection with a 94.2% task success rate. We further demonstrate sim2real transfer on a domestic robot, showing effectiveness in handling real-world uncertainty from sensor noise and stochastic actions. Our generalised and extensible framework supports a wide range of manipulation scenarios and lays a foundation for future work at the intersection of robotics and causality.
Authors: Yang Ba, Michelle V. Mancenido, Erin K. Chiou, Rong Pan
Abstract: As crowdsourcing emerges as an efficient and cost-effective method for obtaining labels for machine learning datasets, it is important to assess the quality of crowd-provided data, so as to improve analysis performance and reduce biases in subsequent machine learning tasks. Given the lack of ground truth in most cases of crowdsourcing, we refer to data quality as annotators' consistency and credibility. Unlike the simple scenarios where Kappa coefficient and intraclass correlation coefficient usually can apply, online crowdsourcing requires dealing with more complex situations. We introduce a systematic method for evaluating data quality and detecting spamming threats via variance decomposition, and we classify spammers into three categories based on their different behavioral patterns. A spammer index is proposed to assess entire data consistency, and two metrics are developed to measure crowd workers' credibility by utilizing the Markov chain and generalized random effects models. Furthermore, we showcase the practicality of our techniques and their advantages by applying them on a face verification task with both simulation and real-world data collected from two crowdsourcing platforms.
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. Finally, to understand why our method exhibits superior performance in settings with low overlap, we present a theoretical example with heavy-tailed inverse propensity scores in which other debiased estimators converge more slowly compared to ours.
Authors: Tianyu Wang, Ningyuan Chen, Chun Wang
Abstract: In contextual optimization, a decision-maker leverages contextual information, often referred to as covariates, to better resolve uncertainty and make informed decisions. In this paper, we examine the challenges of contextual decision-making under covariate shift, a phenomenon where the distribution of covariates differs between the training and test environments. Such shifts can lead to inaccurate upstream estimations for test covariates that lie far from the training data, ultimately resulting in suboptimal downstream decisions. To tackle these challenges, we propose a novel approach called Intersection Wasserstein-balls DRO (IW-DRO), which integrates multiple estimation methods into the distributionally robust optimization (DRO) framework. At the core of our approach is an innovative ambiguity set defined as the intersection of two Wasserstein balls, with their centers constructed using appropriate nonparametric and parametric estimators. On the computational side, we reformulate the IW-DRO problem as a tractable convex program and develop an approximate algorithm tailored for large-scale problems to enhance computational efficiency. From a theoretical perspective, we demonstrate that IW-DRO achieves superior performance compared to single Wasserstein-ball DRO models. We further establish performance guarantees by analyzing the coverage of the intersection ambiguity set and the measure concentration of both estimators under the Wasserstein distance. Notably, we derive a finite-sample concentration result for the Nadaraya-Watson kernel estimator under covariate shift. The proposed IW-DRO framework offers practical value for decision-makers operating in uncertain environments affected by covariate shifts.
Authors: Harry Shomer, Jay Revolinsky, Jiliang Tang
Abstract: Knowledge Graph Completion (KGC) attempts to predict missing facts in a Knowledge Graph (KG). Recently, there's been an increased focus on designing KGC methods that can excel in the inductive setting, where a portion or all of the entities and relations seen in inference are unobserved during training. Numerous benchmark datasets have been proposed for inductive KGC, all of which are subsets of existing KGs used for transductive KGC. However, we find that the current procedure for constructing inductive KGC datasets inadvertently creates a shortcut that can be exploited even while disregarding the relational information. Specifically, we observe that the Personalized PageRank (PPR) score can achieve strong or near SOTA performance on most datasets. In this paper, we study the root cause of this problem. Using these insights, we propose an alternative strategy for constructing inductive KGC datasets that helps mitigate the PPR shortcut. We then benchmark multiple popular methods using the newly constructed datasets and analyze their performance. The new benchmark datasets help promote a better understanding of the capabilities and challenges of inductive KGC by removing any shortcuts that obfuscate performance. The code and dataset and can be found at https://github.com/HarryShomer/Better-Inductive-KGC.
Authors: Hang Zhou, Yihao Qin, Dan Xu, Yiding Ji
Abstract: Recent advances in imitative reinforcement learning (IRL) have considerably enhanced the ability of autonomous agents to assimilate expert demonstrations, leading to rapid skill acquisition in a range of demanding tasks. However, such learning-based agents face significant challenges when transferring knowledge to highly dynamic closed-loop environments. Their performance is significantly impacted by the conflicting optimization objectives of imitation learning (IL) and reinforcement learning (RL), sample inefficiency, and the complexity of uncovering the hidden world model and physics. To address this challenge, we propose a physics-informed IRL that is entirely data-driven. It leverages both expert demonstration data and exploratory data with a joint optimization objective, allowing the underlying physical principles of vehicle dynamics to emerge naturally from the training process. The performance is evaluated through empirical experiments and results exceed popular IL, RL and IRL algorithms in closed-loop settings on Waymax benchmark. Our approach exhibits 37.8% reduction in collision rate and 22.2% reduction in off-road rate compared to the baseline method.
Authors: Yannick Assogba, Donghao Ren
Abstract: As language models support larger and larger context sizes, evaluating their ability to make effective use of that context becomes increasingly important. We analyze the ability of several code generation models to handle long range dependencies using a suite of multi-step key retrieval tasks in context windows up to 8k tokens in length. The tasks progressively increase in difficulty and allow more nuanced evaluation of model capabilities than tests like the popular needle-in-the-haystack test. We find that performance degrades significantly for many models (up to 2x) when a function references another function that is defined later in the prompt. We also observe that models that use sliding window attention mechanisms have difficulty handling references further than the size of a single window. We perform simple prompt modifications using call graph information to improve multi-step retrieval performance up to 3x. Our analysis highlights ways that long-context performance needs deeper consideration beyond retrieval of single facts within a document.
Authors: Yingkai Dong, Xiangtao Meng, Ning Yu, Zheng Li, Shanqing Guo
Abstract: Text-to-image (T2I) generative models have revolutionized content creation by transforming textual descriptions into high-quality images. However, these models are vulnerable to jailbreaking attacks, where carefully crafted prompts bypass safety mechanisms to produce unsafe content. While researchers have developed various jailbreak attacks to expose this risk, these methods face significant limitations, including impractical access requirements, easily detectable unnatural prompts, restricted search spaces, and high query demands on the target system. In this paper, we propose JailFuzzer, a novel fuzzing framework driven by large language model (LLM) agents, designed to efficiently generate natural and semantically meaningful jailbreak prompts in a black-box setting. Specifically, JailFuzzer employs fuzz-testing principles with three components: a seed pool for initial and jailbreak prompts, a guided mutation engine for generating meaningful variations, and an oracle function to evaluate jailbreak success. Furthermore, we construct the guided mutation engine and oracle function by LLM-based agents, which further ensures efficiency and adaptability in black-box settings. Extensive experiments demonstrate that JailFuzzer has significant advantages in jailbreaking T2I models. It generates natural and semantically coherent prompts, reducing the likelihood of detection by traditional defenses. Additionally, it achieves a high success rate in jailbreak attacks with minimal query overhead, outperforming existing methods across all key metrics. This study underscores the need for stronger safety mechanisms in generative models and provides a foundation for future research on defending against sophisticated jailbreaking attacks. JailFuzzer is open-source and available at this repository: https://github.com/YingkaiD/JailFuzzer.
Authors: Max D. Champneys, Timothy J. Rogers
Abstract: Model parsimony is an important \emph{cognitive bias} in data-driven modelling that aids interpretability and helps to prevent over-fitting. Sparse identification of nonlinear dynamics (SINDy) methods are able to learn sparse representations of complex dynamics directly from data, given a basis of library functions. In this work, a novel Bayesian treatment of dictionary learning system identification, as an alternative to SINDy, is envisaged. The proposed method -- Bayesian identification of nonlinear dynamics (BINDy) -- is distinct from previous approaches in that it targets the full joint posterior distribution over both the terms in the library and their parameterisation in the model. This formulation confers the advantage that an arbitrary prior may be placed over the model structure to produce models that are sparse in the model space rather than in parameter space. Because this posterior is defined over parameter vectors that can change in dimension, the inference cannot be performed by standard techniques. Instead, a Gibbs sampler based on reversible-jump Markov-chain Monte-Carlo is proposed. BINDy is shown to compare favourably to ensemble SINDy in three benchmark case-studies. In particular, it is seen that the proposed method is better able to assign high probability to correct model terms.
Authors: Andreas Opedal, Eleanor Chodroff, Ryan Cotterell, Ethan Gotlieb Wilcox
Abstract: We present a new perspective on how readers integrate context during real-time language comprehension. Our proposals build on surprisal theory, which posits that the processing effort of a linguistic unit (e.g., a word) is an affine function of its in-context information content. We first observe that surprisal is only one out of many potential ways that a contextual predictor can be derived from a language model. Another one is the pointwise mutual information (PMI) between a unit and its context, which turns out to yield the same predictive power as surprisal when controlling for unigram frequency. Moreover, both PMI and surprisal are correlated with frequency. This means that neither PMI nor surprisal contains information about context alone. In response to this, we propose a technique where we project surprisal onto the orthogonal complement of frequency, yielding a new contextual predictor that is uncorrelated with frequency. Our experiments show that the proportion of variance in reading times explained by context is a lot smaller when context is represented by the orthogonalized predictor. From an interpretability standpoint, this indicates that previous studies may have overstated the role that context has in predicting reading times.
Authors: Christos Xypolopoulos, Guokan Shang, Xiao Fei, Giannis Nikolentzos, Hadi Abdine, Iakovos Evdaimon, Michail Chatzianastasis, Giorgos Stamou, Michalis Vazirgiannis
Abstract: Large language models have evolved to process multiple modalities beyond text, such as images and audio, which motivates us to explore how to effectively leverage them for graph reasoning tasks. The key question, therefore, is how to transform graphs into linear sequences of tokens, a process we term "graph linearization", so that LLMs can handle graphs naturally. We consider that graphs should be linearized meaningfully to reflect certain properties of natural language text, such as local dependency and global alignment, in order to ease contemporary LLMs, trained on trillions of textual tokens, better understand graphs. To achieve this, we developed several graph linearization methods based on graph centrality and degeneracy. These methods are further enhanced using node relabeling techniques. The experimental results demonstrate the effectiveness of our methods compared to the random linearization baseline. Our work introduces novel graph representations suitable for LLMs, contributing to the potential integration of graph machine learning with the trend of multimodal processing using a unified transformer model.
Authors: Jingtao Ding, Yunke Zhang, Yu Shang, Yuheng Zhang, Zefang Zong, Jie Feng, Yuan Yuan, Hongyuan Su, Nian Li, Nicholas Sukiennik, Fengli Xu, Yong Li
Abstract: The concept of world models has garnered significant attention due to advancements in multimodal large language models such as GPT-4 and video generation models such as Sora, which are central to the pursuit of artificial general intelligence. This survey offers a comprehensive review of the literature on world models. Generally, world models are regarded as tools for either understanding the present state of the world or predicting its future dynamics. This review presents a systematic categorization of world models, emphasizing two primary functions: (1) constructing internal representations to understand the mechanisms of the world, and (2) predicting future states to simulate and guide decision-making. Initially, we examine the current progress in these two categories. We then explore the application of world models in key domains, including autonomous driving, robotics, and social simulacra, with a focus on how each domain utilizes these aspects. Finally, we outline key challenges and provide insights into potential future research directions. We summarize the representative papers along with their code repositories in https://github.com/tsinghua-fib-lab/World-Model.
Authors: Ben Jacobson-Bell, Steve Croft, Carmen Choza, Alex Andersson, Daniel Bautista, Vishal Gajjar, Matthew Lebofsky, David H. E. MacMahon, Caleb Painter, Andrew P. V. Siemion
Abstract: The search for radio technosignatures is an anomaly detection problem: Candidate signals represent needles of interest in the proverbial haystack of radio-frequency interference (RFI). Current search frameworks find an enormity of false-positive signals, especially in large surveys, requiring manual follow-up to a sometimes prohibitive degree. Unsupervised learning provides an algorithmic way to winnow the most anomalous signals from the chaff, as well as group together RFI signals that bear morphological similarities. We present GLOBULAR (Grouping Low-frequency Observations By Unsupervised Learning After Reduction) clustering, a signal processing method that uses HDBSCAN to reduce the false-positive rate and isolate outlier signals for further analysis. When combined with a standard narrowband signal detection and spatial filtering pipeline, such as turboSETI, GLOBULAR clustering offers significant improvements in the false-positive rate over the standard pipeline alone, suggesting dramatic potential for the amelioration of manual follow-up requirements for future large surveys. By removing RFI signals in regions of high spectral occupancy, GLOBULAR clustering may also enable the detection of signals missed by the standard pipeline. We benchmark our method against the Choza et al. turboSETI-only search of 97 nearby galaxies at the L band, demonstrating a false-positive hit reduction rate of 93.1% and a false-positive event reduction rate of 99.3%.
Authors: Lucas Nogueira Nobrega, Ewerton de Oliveira, Martin Saska, Tiago Nascimento
Abstract: The human-robot interaction (HRI) is a growing area of research. In HRI, complex command (action) classification is still an open problem that usually prevents the real applicability of such a technique. The literature presents some works that use neural networks to detect these actions. However, occlusion is still a major issue in HRI, especially when using uncrewed aerial vehicles (UAVs), since, during the robot's movement, the human operator is often out of the robot's field of view. Furthermore, in multi-robot scenarios, distributed training is also an open problem. In this sense, this work proposes an action recognition and control approach based on Long Short-Term Memory (LSTM) Deep Neural Networks with two layers in association with three densely connected layers and Federated Learning (FL) embedded in multiple drones. The FL enabled our approach to be trained in a distributed fashion, i.e., access to data without the need for cloud or other repositories, which facilitates the multi-robot system's learning. Furthermore, our multi-robot approach results also prevented occlusion situations, with experiments with real robots achieving an accuracy greater than 96%.
Authors: Jelena Bratuli\'c, Sudhanshu Mittal, David T. Hoffmann, Samuel B\"ohm, Robin Tibor Schirrmeister, Tonio Ball, Christian Rupprecht, Thomas Brox
Abstract: Large Language Models (LLMs) exhibit In-Context Learning (ICL), which enables the model to perform new tasks conditioning only on the examples provided in the context without updating the model's weights. While ICL offers fast adaptation across natural language tasks and domains, its emergence is less straightforward for modalities beyond text. In this work, we systematically uncover properties present in LLMs that support the emergence of ICL for autoregressive models and various modalities by promoting the learning of the needed mechanisms for ICL. We identify exact token repetitions in the training data sequences as an important factor for ICL. Such repetitions further improve stability and reduce transiency in ICL performance. Moreover, we emphasise the significance of training task difficulty for the emergence of ICL. Finally, by applying our novel insights on ICL emergence, we unlock ICL capabilities for various visual datasets and a more challenging EEG classification task in a few-shot learning regime.
Authors: Guinan Su, Jonas Geiping
Abstract: Reasoning capabilities represent a critical frontier for large language models (LLMs), but developing them requires extensive proprietary datasets and computational resources. One way to efficiently supplement capabilities with is by model merging, which offers a promising alternative by combining multiple models without retraining. However, current merging approaches rely on manually-designed strategies for merging hyperparameters, limiting the exploration of potential model combinations and requiring significant human effort. We propose an Automated Model Merging Framework that enables fine-grained exploration of merging strategies while reducing costs through multi-fidelity approximations. We support both single and multi-objective optimization and introduce two novel search spaces: layerwise fusion (LFS) and depth-wise integration (DIS). Evaluating across a number of benchmarks, we find that the search autonomously finds 1) Merges that further boost single-objective performance, even on tasks the model has already been finetuned on, and 2) Merges that optimize multi-objective frontiers across tasks. Effective merges are found with limited compute, e.g. within less than 500 search steps.
Authors: Filip Ekstr\"om Kelvinius, Oskar B. Andersson, Abhijith S. Parackal, Dong Qian, Rickard Armiento, Fredrik Lindsten
Abstract: Crystalline materials often exhibit a high level of symmetry. However, most generative models do not account for symmetry, but rather model each atom without any constraints on its position or element. We propose a generative model, Wyckoff Diffusion (WyckoffDiff), which generates symmetry-based descriptions of crystals. This is enabled by considering a crystal structure representation that encodes all symmetry, and we design a novel neural network architecture which enables using this representation inside a discrete generative model framework. In addition to respecting symmetry by construction, the discrete nature of our model enables fast generation. We additionally present a new metric, Fr\'echet Wrenformer Distance, which captures the symmetry aspects of the materials generated, and we benchmark WyckoffDiff against recently proposed generative models for crystal generation. As a proof-of-concept study, we use WyckoffDiff to find new materials below the convex hull of thermodynamical stability.
Authors: Eduardo Adame, Daniel Csillag, Guilherme Tegoni Goedert
Abstract: The increasing use of generative ML foundation models for image restoration tasks such as super-resolution calls for robust and interpretable uncertainty quantification methods. We address this need by presenting a novel approach based on conformal prediction techniques to create a 'confidence mask' capable of reliably and intuitively communicating where the generated image can be trusted. Our method is adaptable to any black-box generative model, including those locked behind an opaque API, requires only easily attainable data for calibration, and is highly customizable via the choice of a local image similarity metric. We prove strong theoretical guarantees for our method that span fidelity error control (according to our local image similarity metric), reconstruction quality, and robustness in the face of data leakage. Finally, we empirically evaluate these results and establish our method's solid performance.
Authors: Xinyu Yuan, Zichen Wang, Marcus Collins, Huzefa Rangwala
Abstract: Recent years have witnessed a surge in the development of protein structural tokenization methods, which chunk protein 3D structures into discrete or continuous representations. Structure tokenization enables the direct application of powerful techniques like language modeling for protein structures, and large multimodal models to integrate structures with protein sequences and functional texts. Despite the progress, the capabilities and limitations of these methods remain poorly understood due to the lack of a unified evaluation framework. We first introduce StructTokenBench, a framework that comprehensively evaluates the quality and efficiency of structure tokenizers, focusing on fine-grained local substructures rather than global structures, as typical in existing benchmarks. Our evaluations reveal that no single model dominates all benchmarking perspectives. Observations of codebook under-utilization led us to develop AminoAseed, a simple yet effective strategy that enhances codebook gradient updates and optimally balances codebook size and dimension for improved tokenizer utilization and quality. Compared to the leading model ESM3, our method achieves an average of 6.31% performance improvement across 24 supervised tasks, with sensitivity and utilization rates increased by 12.83% and 124.03%, respectively. Source code and model weights are available at https://github.com/KatarinaYuan/StructTokenBench
Authors: Farouk Mokhtar, Joosep Pata, Dolores Garcia, Eric Wulff, Mengke Zhang, Michael Kagan, Javier Duarte
Abstract: We demonstrate transfer learning capabilities in a machine-learned algorithm trained for particle-flow reconstruction in high energy particle colliders. This paper presents a cross-detector fine-tuning study, where we initially pretrain the model on a large full simulation dataset from one detector design, and subsequently fine-tune the model on a sample with a different collider and detector design. Specifically, we use the Compact Linear Collider detector (CLICdet) model for the initial training set and demonstrate successful knowledge transfer to the CLIC-like detector (CLD) proposed for the Future Circular Collider in electron-positron mode. We show that with an order of magnitude less samples from the second dataset, we can achieve the same performance as a costly training from scratch, across particle-level and event-level performance metrics, including jet and missing transverse momentum resolution. Furthermore, we find that the fine-tuned model achieves comparable performance to the traditional rule-based particle-flow approach on event-level metrics after training on 100,000 CLD events, whereas a model trained from scratch requires at least 1 million CLD events to achieve similar reconstruction performance. To our knowledge, this represents the first full-simulation cross-detector transfer learning study for particle-flow reconstruction. These findings offer valuable insights towards building large foundation models that can be fine-tuned across different detector designs and geometries, helping to accelerate the development cycle for new detectors and opening the door to rapid detector design and optimization using machine learning.
Authors: Miao Peng, Nuo Chen, Zongrui Suo, Jia Li
Abstract: Despite significant advancements in Large Language Models (LLMs), developing advanced reasoning capabilities in LLMs remains a key challenge. Process Reward Models (PRMs) have demonstrated exceptional promise in enhancing reasoning by providing step-wise feedback, particularly in the context of mathematical reasoning. However, their application to broader reasoning domains remains understudied, largely due to the high costs associated with manually creating step-level supervision. In this work, we explore the potential of PRMs in graph reasoning problems - a domain that demands sophisticated multi-step reasoning and offers opportunities for automated step-level data generation using established graph algorithms. We introduce GraphSILO, the largest dataset for graph reasoning problems with fine-grained step-wise labels, built using automated Task-oriented Trajectories and Monte Carlo Tree Search (MCTS) to generate detailed reasoning steps with step-wise labels. Building upon this dataset, we train GraphPRM, the first PRM designed for graph reasoning problems, and evaluate its effectiveness in two key settings: inference-time scaling and reinforcement learning via Direct Preference Optimization (DPO). Experimental results show that GraphPRM significantly improves LLM performance across 13 graph reasoning tasks, delivering a 9% gain for Qwen2.5-7B and demonstrating transferability to new graph reasoning datasets and new reasoning domains like mathematical problem-solving. Notably, GraphPRM enhances LLM performance on GSM8K and Math500, underscoring the cross-domain applicability of graph-based reasoning rewards. Our findings highlight the potential of PRMs in advancing reasoning across diverse domains, paving the way for more versatile and effective LLMs.
Authors: Miao Li, Michael Klamkin, Mathieu Tanneau, Reza Zandehshahvar, Pascal Van Hentenryck
Abstract: This paper studies a Conformal Prediction (CP) methodology for building prediction intervals in a regression setting, given only deterministic lower and upper bounds on the target variable. It proposes a new CP mechanism (CPUL) that goes beyond post-processing by adopting a model selection approach over multiple nested interval construction methods. Paradoxically, many well-established CP methods, including CPUL, may fail to provide adequate coverage in regions where the bounds are tight. To remedy this limitation, the paper proposes an optimal thresholding mechanism, OMLT, that adjusts CPUL intervals in tight regions with undercoverage. The combined CPUL-OMLT is validated on large-scale learning tasks where the goal is to bound the optimal value of a parametric optimization problem. The experimental results demonstrate substantial improvements over baseline methods across various datasets.
Authors: Thomas Boucher, John Whittle, Evangelos B. Mazomenos
Abstract: We demonstrate that quantum vision transformers (QViTs), vision transformers (ViTs) with self-attention (SA) mechanisms replaced by quantum self-attention (QSA) mechanisms, can match state-of-the-art (SOTA) biomedical image classifiers while using 99.99% fewer parameters. QSAs are produced by replacing linear SA layers with parameterised quantum neural networks (QNNs), producing a QSA mechanism and reducing parameter scaling from $\mathcal{O}(n^2)$ to $\mathcal{O}(n)$. On RetinaMNIST, our ultra parameter-efficient QViT outperforms 13/14 SOTA methods including CNNs and ViTs, achieving 56.5% accuracy, just 0.88% below the top MedMamba model while using 99.99% fewer parameters (1K vs 14.5M) and 89% fewer GFLOPs. We present the first investigation of knowledge distillation (KD) from classical to quantum vision transformers in biomedical image classification, showing that QViTs maintain comparable performance to classical ViTs across eight diverse datasets spanning multiple modalities, with improved QSA parameter-efficiency. Our higher-qubit architecture benefitted more from KD pre-training, suggesting a scaling relationship between QSA parameters and KD effectiveness. These findings establish QSA as a practical architectural choice toward parameter-efficient biomedical image analysis.
Authors: Elvis Kimara, Mozhgan Hadadi, Jackson Godbersen, Aditya Balu, Talukder Jubery, Yawei Li, Adarsh Krishnamurthy, Patrick S. Schnable, Baskar Ganapathysubramanian
Abstract: The development of artificial intelligence (AI) and machine learning (ML) based tools for 3D phenotyping, especially for maize, has been limited due to the lack of large and diverse 3D datasets. 2D image datasets fail to capture essential structural details such as leaf architecture, plant volume, and spatial arrangements that 3D data provide. To address this limitation, we present MaizeField3D (https://baskargroup.github.io/MaizeField3D/), a curated dataset of 3D point clouds of field-grown maize plants from a diverse genetic panel, designed to be AI-ready for advancing agricultural research. Our dataset includes 1,045 high-quality point clouds of field-grown maize collected using a terrestrial laser scanner (TLS). Point clouds of 520 plants from this dataset were segmented and annotated using a graph-based segmentation method to isolate individual leaves and stalks, ensuring consistent labeling across all samples. This labeled data was then used for fitting procedural models that provide a structured parametric representation of the maize plants. The leaves of the maize plants in the procedural models are represented using Non-Uniform Rational B-Spline (NURBS) surfaces that were generated using a two-step optimization process combining gradient-free and gradient-based methods. We conducted rigorous manual quality control on all datasets, correcting errors in segmentation, ensuring accurate leaf ordering, and validating metadata annotations. The dataset also includes metadata detailing plant morphology and quality, alongside multi-resolution subsampled point cloud data (100k, 50k, 10k points), which can be readily used for different downstream computational tasks. MaizeField3D will serve as a comprehensive foundational dataset for AI-driven phenotyping, plant structural analysis, and 3D applications in agricultural research.
Authors: Akshay Thakur, Matthew J. Zahr
Abstract: The Riemann problem is fundamental in the computational modeling of hyperbolic partial differential equations, enabling the development of stable and accurate upwind schemes. While exact solvers provide robust upwinding fluxes, their high computational cost necessitates approximate solvers. Although approximate solvers achieve accuracy in many scenarios, they produce inaccurate solutions in certain cases. To overcome this limitation, we propose constructing neural network-based surrogate models, trained using supervised learning, designed to map interior and exterior conservative state variables to the corresponding exact flux. Specifically, we propose two distinct approaches: one utilizing a vanilla neural network and the other employing a bi-fidelity neural network. The performance of the proposed approaches is demonstrated through applications to one-dimensional and two-dimensional partial differential equations, showcasing their robustness and accuracy.
Authors: Michael D. White, Michael D. Atkinson, Adam J. Plowman, Pratheek Shanthraj
Abstract: Microstructure quantification is an important step towards establishing structure-property relationships in materials. Machine learning-based image processing methods have been shown to outperform conventional image processing techniques and are increasingly applied to microstructure quantification tasks. In this work, we present a 3D variational autoencoder (VAE) for encoding microstructure volume elements (VEs) comprising voxelated crystallographic orientation data. Crystal symmetries in the orientation space are accounted for by mapping to the crystallographic fundamental zone as a preprocessing step, which allows for a continuous loss function to be used and improves the training convergence rate. The VAE is then used to encode a training set of VEs with an equiaxed polycrystalline microstructure with random texture. Accurate reconstructions are achieved with a relative average misorientation error of 3x10^-2 on the test dataset, for a continuous latent space with dimension 256. We show that the model generalises well to microstructures with textures, grain sizes and aspect ratios outside the training distribution. Structure-property relationships are explored through using the training set of VEs as initial configurations in various crystal plasticity (CP) simulations. Microstructural fingerprints extracted from the VAE, which parameterise the VEs in a low-dimensional latent space, are stored alongside the volume-averaged stress response, at each strain increment, to uniaxial tensile deformation from CP simulations. This is then used to train a fully connected neural network mapping the input fingerprint to the resulting stress response, which acts as a surrogate model for the CP simulation. The fingerprint-based surrogate model is shown to accurately predict the microstructural dependence in the CP stress response, with a relative mean-squared error of 2.75 MPa on unseen test data.
Authors: Vladan Stojni\'c, Yannis Kalantidis, Ji\v{r}\'i Matas, Giorgos Tolias
Abstract: We propose a training-free method for open-vocabulary semantic segmentation using Vision-and-Language Models (VLMs). Our approach enhances the initial per-patch predictions of VLMs through label propagation, which jointly optimizes predictions by incorporating patch-to-patch relationships. Since VLMs are primarily optimized for cross-modal alignment and not for intra-modal similarity, we use a Vision Model (VM) that is observed to better capture these relationships. We address resolution limitations inherent to patch-based encoders by applying label propagation at the pixel level as a refinement step, significantly improving segmentation accuracy near class boundaries. Our method, called LPOSS+, performs inference over the entire image, avoiding window-based processing and thereby capturing contextual interactions across the full image. LPOSS+ achieves state-of-the-art performance among training-free methods, across a diverse set of datasets. Code: https://github.com/vladan-stojnic/LPOSS
Authors: Frank Nielsen
Abstract: By analogy to curved exponential families in statistics, we define curved Bregman divergences as Bregman divergences restricted to nonlinear parameter subspaces. We show that the barycenter of a finite weighted set of parameters under a curved Bregman divergence amounts to the right Bregman projection onto the nonlinear subspace of the barycenter with respect to the full Bregman divergence. We demonstrate the significance of curved Bregman divergences with two examples: (1) symmetrized Bregman divergences and (2) the Kullback-Leibler divergence between circular complex normal distributions. We then consider monotonic embeddings to define representational curved Bregman divergences and show that the $\alpha$-divergences are representational curved Bregman divergences with respect to $\alpha$-embeddings of the probability simplex into the positive measure cone. As an application, we report an efficient method to calculate the intersection of a finite set of $\alpha$-divergence spheres.
Authors: Robert Gruhlke, Matei Hanu, Claudia Schillings, Philipp Wacker
Abstract: We introduce a gradient-free framework for Bayesian Optimal Experimental Design (BOED) in sequential settings, aimed at complex systems where gradient information is unavailable. Our method combines Ensemble Kalman Inversion (EKI) for design optimization with the Affine-Invariant Langevin Dynamics (ALDI) sampler for efficient posterior sampling-both of which are derivative-free and ensemble-based. To address the computational challenges posed by nested expectations in BOED, we propose variational Gaussian and parametrized Laplace approximations that provide tractable upper and lower bounds on the Expected Information Gain (EIG). These approximations enable scalable utility estimation in high-dimensional spaces and PDE-constrained inverse problems. We demonstrate the performance of our framework through numerical experiments ranging from linear Gaussian models to PDE-based inference tasks, highlighting the method's robustness, accuracy, and efficiency in information-driven experimental design.
Authors: Pedro Abdalla, Roman Vershynin
Abstract: Given a text, can we determine whether it was generated by a large language model (LLM) or by a human? A widely studied approach to this problem is watermarking. We propose an undetectable and elementary watermarking scheme in the closed setting. Also, in the harder open setting, where the adversary has access to most of the model, we propose an unremovable watermarking scheme.
Authors: Asif Rahman, Veljko Cvetkovic, Kathleen Reece, Aidan Walters, Yasir Hassan, Aneesh Tummeti, Bryan Torres, Denise Cooney, Margaret Ellis, Dimitrios S. Nikolopoulos
Abstract: Large language models (LLMs) have transformed software development through code generation capabilities, yet their effectiveness for high-performance computing (HPC) remains limited. HPC code requires specialized optimizations for parallelism, memory efficiency, and architecture-specific considerations that general-purpose LLMs often overlook. We present MARCO (Multi-Agent Reactive Code Optimizer), a novel framework that enhances LLM-generated code for HPC through a specialized multi-agent architecture. MARCO employs separate agents for code generation and performance evaluation, connected by a feedback loop that progressively refines optimizations. A key innovation is MARCO's web-search component that retrieves real-time optimization techniques from recent conference proceedings and research publications, bridging the knowledge gap in pre-trained LLMs. Our extensive evaluation on the LeetCode 75 problem set demonstrates that MARCO achieves a 14.6\% average runtime reduction compared to Claude 3.5 Sonnet alone, while the integration of the web-search component yields a 30.9\% performance improvement over the base MARCO system. These results highlight the potential of multi-agent systems to address the specialized requirements of high-performance code generation, offering a cost-effective alternative to domain-specific model fine-tuning.
Authors: Matias Quintana, Youlong Gu, Xiucheng Liang, Yujun Hou, Koichi Ito, Yihan Zhu, Mahmoud Abdelrahman, Filip Biljecki
Abstract: Understanding people's preferences and needs is crucial for urban planning decisions, yet current approaches often combine them from multi-cultural and multi-city populations, obscuring important demographic differences and risking amplifying biases. We conducted a large-scale urban visual perception survey of streetscapes worldwide using street view imagery, examining how demographics -- including gender, age, income, education, race and ethnicity, and, for the first time, personality traits -- shape perceptions among 1,000 participants, with balanced demographics, from five countries and 45 nationalities. This dataset, introduced as Street Perception Evaluation Considering Socioeconomics (SPECS), exhibits statistically significant differences in perception scores in six traditionally used indicators (safe, lively, wealthy, beautiful, boring, and depressing) and four new ones we propose (live nearby, walk, cycle, green) among demographics and personalities. We revealed that location-based sentiments are carried over in people's preferences when comparing urban streetscapes with other cities. Further, we compared the perception scores based on where participants and streetscapes are from. We found that an off-the-shelf machine learning model trained on an existing global perception dataset tends to overestimate positive indicators and underestimate negative ones compared to human responses, suggesting that targeted intervention should consider locals' perception. Our study aspires to rectify the myopic treatment of street perception, which rarely considers demographics or personality traits.
Authors: Mahmud Ashraf Shamim, Eric A F Reinhardt, Talal Ahmed Chowdhury, Sergei Gleyzer, Paulo T Araujo
Abstract: Neural Quantum States (NQS) are a class of variational wave functions parametrized by neural networks (NNs) to study quantum many-body systems. In this work, we propose \texttt{SineKAN}, a NQS \textit{ansatz} based on Kolmogorov-Arnold Networks (KANs), to represent quantum mechanical wave functions as nested univariate functions. We show that \texttt{SineKAN} wavefunction with learnable sinusoidal activation functions can capture the ground state energies, fidelities and various correlation functions of the one dimensional Transverse-Field Ising model, Anisotropic Heisenberg model, and Antiferromagnetic $J_{1}-J_{2}$ model with different chain lengths. In our study of the $J_1-J_2$ model with $L=100$ sites, we find that the \texttt{SineKAN} model outperforms several previously explored neural quantum state \textit{ans\"atze}, including Restricted Boltzmann Machines (RBMs), Long Short-Term Memory models (LSTMs), and Multi-layer Perceptrons (MLP) \textit{a.k.a.} Feed Forward Neural Networks, when compared to the results obtained from the Density Matrix Renormalization Group (DMRG) algorithm. We find that \texttt{SineKAN} models can be trained to high precisions and accuracies with minimal computational costs.
Authors: Thao Nguyen, Yang Li, Olga Golovneva, Luke Zettlemoyer, Sewoong Oh, Ludwig Schmidt, Xian Li
Abstract: Scaling laws predict that the performance of large language models improves with increasing model size and data size. In practice, pre-training has been relying on massive web crawls, using almost all data sources publicly available on the internet so far. However, this pool of natural data does not grow at the same rate as the compute supply. Furthermore, the availability of high-quality texts is even more limited: data filtering pipelines often remove up to 99% of the initial web scrapes to achieve state-of-the-art. To address the "data wall" of pre-training scaling, our work explores ways to transform and recycle data discarded in existing filtering processes. We propose REWIRE, REcycling the Web with guIded REwrite, a method to enrich low-quality documents so that they could become useful for training. This in turn allows us to increase the representation of synthetic data in the final pre-training set. Experiments at 1B, 3B and 7B scales of the DCLM benchmark show that mixing high-quality raw texts and our rewritten texts lead to 1.0, 1.3 and 2.5 percentage points improvement respectively across 22 diverse tasks, compared to training on only filtered web data. Training on the raw-synthetic data mix is also more effective than having access to 2x web data. Through further analysis, we demonstrate that about 82% of the mixed in texts come from transforming lower-quality documents that would otherwise be discarded. REWIRE also outperforms related approaches of generating synthetic data, including Wikipedia-style paraphrasing, question-answer synthesizing and knowledge extraction. These results suggest that recycling web texts holds the potential for being a simple and effective approach for scaling pre-training data.
Authors: Luel Hagos Beyene, Vivek Verma, Min Ma, Jesujoba O. Alabi, Fabian David Schmidt, Joyce Nakatumba-Nabende, David Ifeoluwa Adelani
Abstract: Large Language models (LLMs) have demonstrated impressive performance on a wide range of tasks, including in multimodal settings such as speech. However, their evaluation is often limited to English and a few high-resource languages. For low-resource languages, there is no standardized evaluation benchmark. In this paper, we address this gap by introducing mSTEB, a new benchmark to evaluate the performance of LLMs on a wide range of tasks covering language identification, text classification, question answering, and translation tasks on both speech and text modalities. We evaluated the performance of leading LLMs such as Gemini 2.0 Flash and GPT-4o (Audio) and state-of-the-art open models such as Qwen 2 Audio and Gemma 3 27B. Our evaluation shows a wide gap in performance between high-resource and low-resource languages, especially for languages spoken in Africa and Americas/Oceania. Our findings show that more investment is needed to address their under-representation in LLMs coverage.
Authors: Jasper Yao
Abstract: This paper argues that AI alignment is not merely difficult, but is founded on a fundamental logical contradiction. We first establish The Enumeration Paradox: we use machine learning precisely because we cannot enumerate all necessary safety rules, yet making ML safe requires examples that can only be generated from the very enumeration we admit is impossible. This paradox is then confirmed by a set of five independent mathematical proofs, or "pillars of impossibility." Our main results show that: (1) Geometric Impossibility: The set of safe policies has measure zero, a necessary consequence of projecting infinite-dimensional world-context requirements onto finite-dimensional models. (2) Computational Impossibility: Verifying a policy's safety is coNP-complete, even for non-zero error tolerances. (3) Statistical Impossibility: The training data required for safety (abundant examples of rare disasters) is a logical contradiction and thus unobtainable. (4) Information-Theoretic Impossibility: Safety rules contain more incompressible, arbitrary information than any feasible network can store. (5) Dynamic Impossibility: The optimization process for increasing AI capability is actively hostile to safety, as the gradients for the two objectives are generally anti-aligned. Together, these results demonstrate that the pursuit of safe, highly capable AI is not a matter of overcoming technical hurdles, but of confronting fundamental, interlocking barriers. The paper concludes by presenting a strategic trilemma that these impossibilities force upon the field. A formal verification of the core theorems in Lean4 is currently in progress.
Authors: Donghoon Ahn, Jiwon Kang, Sanghyun Lee, Minjae Kim, Jaewon Min, Wooseok Jang, Saungwu Lee, Sayak Paul, Susung Hong, Seungryong Kim
Abstract: Recent guidance methods in diffusion models steer reverse sampling by perturbing the model to construct an implicit weak model and guide generation away from it. Among these approaches, attention perturbation has demonstrated strong empirical performance in unconditional scenarios where classifier-free guidance is not applicable. However, existing attention perturbation methods lack principled approaches for determining where perturbations should be applied, particularly in Diffusion Transformer (DiT) architectures where quality-relevant computations are distributed across layers. In this paper, we investigate the granularity of attention perturbations, ranging from the layer level down to individual attention heads, and discover that specific heads govern distinct visual concepts such as structure, style, and texture quality. Building on this insight, we propose "HeadHunter", a systematic framework for iteratively selecting attention heads that align with user-centric objectives, enabling fine-grained control over generation quality and visual attributes. In addition, we introduce SoftPAG, which linearly interpolates each selected head's attention map toward an identity matrix, providing a continuous knob to tune perturbation strength and suppress artifacts. Our approach not only mitigates the oversmoothing issues of existing layer-level perturbation but also enables targeted manipulation of specific visual styles through compositional head selection. We validate our method on modern large-scale DiT-based text-to-image models including Stable Diffusion 3 and FLUX.1, demonstrating superior performance in both general quality enhancement and style-specific guidance. Our work provides the first head-level analysis of attention perturbation in diffusion models, uncovering interpretable specialization within attention layers and enabling practical design of effective perturbation strategies.
Authors: Avrajit Ghosh, Bai Cong, Rio Yokota, Saiprasad Ravishankar, Rongrong Wang, Molei Tao, Mohammad Emtiyaz Khan, Thomas M\"ollenhoff
Abstract: Variational Learning (VL) has recently gained popularity for training deep neural networks and is competitive to standard learning methods. Part of its empirical success can be explained by theories such as PAC-Bayes bounds, minimum description length and marginal likelihood, but there are few tools to unravel the implicit regularization in play. Here, we analyze the implicit regularization of VL through the Edge of Stability (EoS) framework. EoS has previously been used to show that gradient descent can find flat solutions and we extend this result to VL to show that it can find even flatter solutions. This is obtained by controlling the posterior covariance and the number of Monte Carlo samples from the posterior. These results are derived in a similar fashion as the standard EoS literature for deep learning, by first deriving a result for a quadratic problem and then extending it to deep neural networks. We empirically validate these findings on a wide variety of large networks, such as ResNet and ViT, to find that the theoretical results closely match the empirical ones. Ours is the first work to analyze the EoS dynamics in VL.
Authors: Zeyu Zhang, Ziyuan Jiao
Abstract: Solving Inverse Kinematics (IK) problems is fundamental to robotics, but has primarily been successful with single serial manipulators. For multi-arm robotic systems, IK remains challenging due to complex self-collisions, coupled joints, and high-dimensional redundancy. These complexities make traditional IK solvers slow, prone to failure, and lacking in solution diversity. In this paper, we present IKDiffuser, a diffusion-based model designed for fast and diverse IK solution generation for multi-arm robotic systems. IKDiffuser learns the joint distribution over the configuration space, capturing complex dependencies and enabling seamless generalization to multi-arm robotic systems of different structures. In addition, IKDiffuser can incorporate additional objectives during inference without retraining, offering versatility and adaptability for task-specific requirements. In experiments on 6 different multi-arm systems, the proposed IKDiffuser achieves superior solution accuracy, precision, diversity, and computational efficiency compared to existing solvers. The proposed IKDiffuser framework offers a scalable, unified approach to solving multi-arm IK problems, facilitating the potential of multi-arm robotic systems in real-time manipulation tasks.
Authors: Tawsif Ahmed, Andrej Radonjic, Gollam Rabby
Abstract: We present Sleeping-DISCO 9M, a large-scale pre-training dataset for music and song. To the best of our knowledge, there are no open-source high-quality dataset representing popular and well-known songs for generative music modeling tasks such as text-music, music-captioning, singing-voice synthesis, melody reconstruction and cross-model retrieval. Past contributions focused on isolated and constrained factors whose core perspective was to create synthetic or re-recorded music corpus (e.g. GTSinger, M4Singer) and arbitrarily large-scale audio datasets (e.g. DISCO-10M and LAIONDISCO-12M) had been another focus for the community. Unfortunately, adoption of these datasets has been below substantial in the generative music community as these datasets fail to reflect real-world music and its flavour. Our dataset changes this narrative and provides a dataset that is constructed using actual popular music and world-renowned artists.
Authors: Christina Q. Knight, Kaustubh Deshpande, Ved Sirdeshmukh, Meher Mankikar, Scale Red Team, SEAL Research Team, Julian Michael
Abstract: The rapid advancement of large language models (LLMs) introduces dual-use capabilities that could both threaten and bolster national security and public safety (NSPS). Models implement safeguards to protect against potential misuse relevant to NSPS and allow for benign users to receive helpful information. However, current benchmarks often fail to test safeguard robustness to potential NSPS risks in an objective, robust way. We introduce FORTRESS: 500 expert-crafted adversarial prompts with instance-based rubrics of 4-7 binary questions for automated evaluation across 3 domains (unclassified information only): Chemical, Biological, Radiological, Nuclear and Explosive (CBRNE), Political Violence & Terrorism, and Criminal & Financial Illicit Activities, with 10 total subcategories across these domains. Each prompt-rubric pair has a corresponding benign version to test for model over-refusals. This evaluation of frontier LLMs' safeguard robustness reveals varying trade-offs between potential risks and model usefulness: Claude-3.5-Sonnet demonstrates a low average risk score (ARS) (14.09 out of 100) but the highest over-refusal score (ORS) (21.8 out of 100), while Gemini 2.5 Pro shows low over-refusal (1.4) but a high average potential risk (66.29). Deepseek-R1 has the highest ARS at 78.05, but the lowest ORS at only 0.06. Models such as o1 display a more even trade-off between potential risks and over-refusals (with an ARS of 21.69 and ORS of 5.2). To provide policymakers and researchers with a clear understanding of models' potential risks, we publicly release FORTRESS at https://huggingface.co/datasets/ScaleAI/fortress_public. We also maintain a private set for evaluation.
URLs: https://huggingface.co/datasets/ScaleAI/fortress_public.
Authors: Matteo Zecchin, Tomer Raviv, Dileep Kalathil, Krishna Narayanan, Nir Shlezinger, Osvaldo Simeone
Abstract: In recent years, deep learning has facilitated the creation of wireless receivers capable of functioning effectively in conditions that challenge traditional model-based designs. Leveraging programmable hardware architectures, deep learning-based receivers offer the potential to dynamically adapt to varying channel environments. However, current adaptation strategies, including joint training, hypernetwork-based methods, and meta-learning, either demonstrate limited flexibility or necessitate explicit optimization through gradient descent. This paper presents gradient-free adaptation techniques rooted in the emerging paradigm of in-context learning (ICL). We review architectural frameworks for ICL based on Transformer models and structured state-space models (SSMs), alongside theoretical insights into how sequence models effectively learn adaptation from contextual information. Further, we explore the application of ICL to cell-free massive MIMO networks, providing both theoretical analyses and empirical evidence. Our findings indicate that ICL represents a principled and efficient approach to real-time receiver adaptation using pilot signals and auxiliary contextual information-without requiring online retraining.
Authors: Zelin Xiao, Jia Gu, Song Xi Chen
Abstract: We study methods for identifying heterogeneous parameter components in distributed M-estimation with minimal data transmission. One is based on a re-normalized Wald test, which is shown to be consistent as long as the number of distributed data blocks $K$ is of a smaller order of the minimum block sample size and the level of heterogeneity is dense. The second one is an extreme contrast test (ECT) based on the difference between the largest and smallest component-wise estimated parameters among data blocks. By introducing a sample splitting procedure, the ECT can avoid the bias accumulation arising from the M-estimation procedures, and exhibits consistency for $K$ being much larger than the sample size while the heterogeneity is sparse. The ECT procedure is easy to operate and communication-efficient. A combination of the Wald and the extreme contrast tests is formulated to attain more robust power under varying levels of sparsity of the heterogeneity. We also conduct intensive numerical experiments to compare the family-wise error rate (FWER) and the power of the proposed methods. Additionally, we conduct a case study to present the implementation and validity of the proposed methods.
Authors: Rahul Raja, Arpita Vats
Abstract: We investigate the generalization capabilities of small language models under two popular adaptation paradigms: few-shot prompting and supervised fine-tuning. While prompting is often favored for its parameter efficiency and flexibility, it remains unclear how robust this approach is in low-resource settings and under distributional shifts. This paper presents a comparative study of prompting and fine-tuning across task formats, prompt styles, and model scales, with a focus on their behavior in both in-distribution and out-of-distribution (OOD) settings. Beyond accuracy, we analyze the internal representations learned by each approach to assess the stability and abstraction of task-specific features. Our findings highlight critical differences in how small models internalize and generalize knowledge under different adaptation strategies. This work offers practical guidance for model selection in low-data regimes and contributes empirical insight into the ongoing debate over prompting versus fine-tuning. Code for the experiments is available at the following
Authors: Csaba T\'oth
Abstract: The interface between stochastic analysis and machine learning is a rapidly evolving field, with path signatures - iterated integrals that provide faithful, hierarchical representations of paths - offering a principled and universal feature map for sequential and structured data. Rooted in rough path theory, path signatures are invariant to reparameterization and well-suited for modelling evolving dynamics, long-range dependencies, and irregular sampling - common challenges in real-world time series and graph data. This thesis investigates how to harness the expressive power of path signatures within scalable machine learning pipelines. It introduces a suite of models that combine theoretical robustness with computational efficiency, bridging rough path theory with probabilistic modelling, deep learning, and kernel methods. Key contributions include: Gaussian processes with signature kernel-based covariance functions for uncertainty-aware time series modelling; the Seq2Tens framework, which employs low-rank tensor structure in the weight space for scalable deep modelling of long-range dependencies; and graph-based models where expected signatures over graphs induce hypo-elliptic diffusion processes, offering expressive yet tractable alternatives to standard graph neural networks. Further developments include Random Fourier Signature Features, a scalable kernel approximation with theoretical guarantees, and Recurrent Sparse Spectrum Signature Gaussian Processes, which combine Gaussian processes, signature kernels, and random features with a principled forgetting mechanism for multi-horizon time series forecasting with adaptive context length. We hope this thesis serves as both a methodological toolkit and a conceptual bridge, and provides a useful reference for the current state of the art in scalable, signature-based learning for sequential and structured data.
Authors: Jiaming Hu, Debarghya Mukherjee, Ioannis Ch. Paschalidis
Abstract: In many real-world applications, ensuring the robustness and stability of deep neural networks (DNNs) is crucial, particularly for image classification tasks that encounter various input perturbations. While data augmentation techniques have been widely adopted to enhance the resilience of a trained model against such perturbations, there remains significant room for improvement in robustness against corrupted data and adversarial attacks simultaneously. To address this challenge, we introduce DRO-Augment, a novel framework that integrates Wasserstein Distributionally Robust Optimization (W-DRO) with various data augmentation strategies to improve the robustness of the models significantly across a broad spectrum of corruptions. Our method outperforms existing augmentation methods under severe data perturbations and adversarial attack scenarios while maintaining the accuracy on the clean datasets on a range of benchmark datasets, including but not limited to CIFAR-10-C, CIFAR-100-C, MNIST, and Fashion-MNIST. On the theoretical side, we establish novel generalization error bounds for neural networks trained using a computationally efficient, variation-regularized loss function closely related to the W-DRO problem.
Authors: Jianghong Huang, Luping Ji, Xin Ma, Mao Ye
Abstract: Conveyor belts are important equipment in modern industry, widely applied in production and manufacturing. Their health is much critical to operational efficiency and safety. Cracks are a major threat to belt health. Currently, considering safety, how to intelligently detect belt cracks is catching an increasing attention. To implement the intelligent detection with machine learning, real crack samples are believed to be necessary. However, existing crack datasets primarily focus on pavement scenarios or synthetic data, no real-world industrial belt crack datasets at all. Cracks are a major threat to belt health. Furthermore, to validate usability and effectiveness, we propose a special baseline method with triple-domain ($i.e.$, time-space-frequency) feature hierarchical fusion learning for the two whole-new datasets. Experimental results demonstrate the availability and effectiveness of our dataset. Besides, they also show that our baseline is obviously superior to other similar detection methods. Our datasets and source codes are available at https://github.com/UESTC-nnLab/BeltCrack.
Authors: Yuchang Zhu, Huazhen Zhong, Qunshu Lin, Haotong Wei, Xiaolong Sun, Zixuan Yu, Minghao Liu, Zibin Zheng, Liang Chen
Abstract: With the remarkable generative capabilities of large language models (LLMs), using LLM-generated data to train downstream models has emerged as a promising approach to mitigate data scarcity in specific domains and reduce time-consuming annotations. However, recent studies have highlighted a critical issue: iterative training on self-generated data results in model collapse, where model performance degrades over time. Despite extensive research on the implications of LLM-generated data, these works often neglect the importance of data diversity, a key factor in data quality. In this work, we aim to understand the implications of the diversity of LLM-generated data on downstream model performance. Specifically, we explore how varying levels of diversity in LLM-generated data affect downstream model performance. Additionally, we investigate the performance of models trained on data that mixes different proportions of LLM-generated data, which we refer to as synthetic data. Our experimental results show that, with minimal distribution shift, moderately diverse LLM-generated data can enhance model performance in scenarios with insufficient labeled data, whereas highly diverse generated data has a negative impact. We hope our empirical findings will offer valuable guidance for future studies on LLMs as data generators.