Authors: Guanlue Li, Xufeng Zhao, Fang Wu, S\"oren Laue
Abstract: Protein-protein interactions (PPIs) are governed by surface complementarity and hydrophobic interactions at protein interfaces. However, designing diverse and physically realistic protein structure and surfaces that precisely complement target receptors remains a significant challenge in computational protein design. In this work, we introduce PepBridge, a novel framework for the joint design of protein surface and structure that seamlessly integrates receptor surface geometry and biochemical properties. Starting with a receptor surface represented as a 3D point cloud, PepBridge generates complete protein structures through a multi-step process. First, it employs denoising diffusion bridge models (DDBMs) to map receptor surfaces to ligand surfaces. Next, a multi-model diffusion model predicts the corresponding structure, while Shape-Frame Matching Networks ensure alignment between surface geometry and backbone architecture. This integrated approach facilitates surface complementarity, conformational stability, and chemical feasibility. Extensive validation across diverse protein design scenarios demonstrates PepBridge's efficacy in generating structurally viable proteins, representing a significant advancement in the joint design of top-down protein structure.
Authors: Yuqi Li, Kuiye Ding, Chuanguang Yang, Hao Wang, Haoxuan Wang, Huiran Duan, Junming Liu, Yingli Tian
Abstract: Time-series forecasting is fundamental across many domains, yet training accurate models often requires large-scale datasets and substantial computational resources. Dataset distillation offers a promising alternative by synthesizing compact datasets that preserve the learning behavior of full data. However, extending dataset distillation to time-series forecasting is non-trivial due to two fundamental challenges: 1.temporal bias from strong autocorrelation, which leads to distorted value-term alignment between teacher and student models; and 2.insufficient diversity among synthetic samples, arising from the absence of explicit categorical priors to regularize trajectory variety. In this work, we propose DDTime, a lightweight and plug-in distillation framework built upon first-order condensation decomposition. To tackle Challenge 1, it revisits value-term alignment through temporal statistics and introduces a frequency-domain alignment mechanism to mitigate autocorrelation-induced bias, ensuring spectral consistency and temporal fidelity. To address Challenge 2, we further design an inter-sample regularization inspired by the information bottleneck principle, which enhances diversity and maximizes information density across synthetic trajectories. The combined objective is theoretically compatible with a wide range of condensation paradigms and supports stable first-order optimization. Extensive experiments on 20 benchmark datasets and diverse forecasting architectures demonstrate that DDTime consistently outperforms existing distillation methods, achieving about 30% relative accuracy gains while introducing about 2.49% computational overhead. All code and distilled datasets will be released.
Authors: Haotian Xu, Yuning You, Tengfei Ma
Abstract: Graphs provide a unified representation of semantic content and relational structure, making them a natural fit for domains such as molecular modeling, citation networks, and social graphs. Meanwhile, large language models (LLMs) have excelled at understanding natural language and integrating cross-modal signals, sparking interest in their potential for graph reasoning. Recent work has explored this by either designing template-based graph templates or using graph neural networks (GNNs) to encode structural information. In this study, we investigate how different strategies for encoding graph structure affect LLM performance on text-attributed graphs. Surprisingly, our systematic experiments reveal that: (i) LLMs leveraging only node textual descriptions already achieve strong performance across tasks; and (ii) most structural encoding strategies offer marginal or even negative gains. We show that explicit structural priors are often unnecessary and, in some cases, counterproductive when powerful language models are involved. This represents a significant departure from traditional graph learning paradigms and highlights the need to rethink how structure should be represented and utilized in the LLM era. Our study is to systematically challenge the foundational assumption that structure is inherently beneficial for LLM-based graph reasoning, opening the door to new, semantics-driven approaches for graph learning.
Authors: Yating Ren, Yikun Ban, Huobin Tan
Abstract: Recently, structure-text contrastive learning has shown promising performance on text-attributed graphs by leveraging the complementary strengths of graph neural networks and language models. However, existing methods typically rely on homophily assumptions in similarity estimation and hard optimization objectives, which limit their applicability to heterophilic graphs. Although existing methods can mitigate heterophily through structural adjustments or neighbor aggregation, they usually treat textual embeddings as static targets, leading to suboptimal alignment. In this work, we identify the multi-granular heterophily in text-attributed graphs, including complete heterophily, partial heterophily, and latent homophily, which makes structure-text alignment particularly challenging due to mixed, noisy, and missing semantic correlations. To achieve flexible and bidirectional alignment, we propose GCL-OT, a novel graph contrastive learning framework with optimal transport, equipped with tailored mechanisms for each type of heterophily. Specifically, for partial heterophily, we design a RealSoftMax-based similarity estimator to emphasize key neighbor-word interactions while easing background noise. For complete heterophily, we introduce a prompt-based filter that adaptively excludes irrelevant noise during optimal transport alignment. Furthermore, we incorporate OT-guided soft supervision to uncover potential neighbors with similar semantics, enhancing the learning of latent homophily. Theoretical analysis shows that GCL-OT can improve the mutual information bound and Bayes error guarantees. Extensive experiments on nine benchmarks show that GCL-OT consistently outperforms state-of-the-art methods, verifying its effectiveness and robustness.
Authors: Yaoxin Yang, Peng Ye, Xudong Tan, Chongjun Tu, Maosen Zhao, Jia Hao, Tao Chen
Abstract: Multimodal large language models suffer from substantial inference overhead since multimodal KV Cache grows proportionally with the visual input length. Existing multimodal KV Cache compression methods mostly rely on attention score to reduce cache size, which makes them are incompatible with established efficient attention kernels (e.g., FlashAttention) and ignores the contribution of value vectors to the attention output. In this work, we revisit multimodal KV Cache compression from the perspective of the KV matrices' distribution. First, we observe that frequency-domain energy of multimodal KV matrices is predominantly concentrated in low-frequency and extract this principal energy via a low-pass filter. Further, we find that removing KV pairs that deviate substantially from this principal energy leads to a pronounced performance drop, which we define as Outlier KVs. Considering Outlier KVs are more likely to encode features critical for inference, we propose FlashCache, a frequency-domain-guided, Outlier-KV-aware KV Cache compression framework. First, we introduce an Outlier KV Recognition Module that models the principal component of multimodal KV matrices in the frequency domain and preferentially retains KV pairs that significantly deviate from it. Furthermore, Dynamic Budget Allocation Module is designed to adaptively determine the per-layer KV Cache size to retain more Outlier KVs. Experiments on multiple MLLMs and benchmarks demonstrate that FlashCache outperforms state-of-the-art multimoal KV compression methods, achieving up to 1.69 times faster decoding with 80% lower KV memory usage while maintaining task performance.
Authors: Ehsan Ahmed Dhrubo, Mohammad Mahmudul Alam, Edward Raff, Tim Oates, James Holt
Abstract: Multiple Instance Learning (MIL) tasks impose a strict logical constraint: a bag is labeled positive if and only if at least one instance within it is positive. While this iff constraint aligns with many real-world applications, recent work has shown that most deep learning-based MIL approaches violate it, leading to inflated performance metrics and poor generalization. We propose a novel MIL framework based on Vector Symbolic Architectures (VSAs), which provide a differentiable mechanism for performing symbolic operations in high-dimensional space. Our method encodes the MIL assumption directly into the model's structure by representing instances and concepts as nearly orthogonal high-dimensional vectors and using algebraic operations to enforce the iff constraint during classification. To bridge the gap between raw data and VSA representations, we design a learned encoder that transforms input instances into VSA-compatible vectors while preserving key distributional properties. Our approach, which includes a VSA-driven MaxNetwork classifier, achieves state-of-the-art results for a valid MIL model on standard MIL benchmarks and medical imaging datasets, outperforming existing methods while maintaining strict adherence to the MIL formulation. This work offers a principled, interpretable, and effective alternative to existing MIL approaches that rely on learned heuristics.
Authors: Eyad Gad, Zubair Md Fadlullah, Mostafa M. Fouda
Abstract: In the context of the growing proliferation of user devices and the concurrent surge in data volumes, the complexities arising from the substantial increase in data have posed formidable challenges to conventional machine learning model training. Particularly, this is evident within resource-constrained and security-sensitive environments such as those encountered in networks associated with the Internet of Things (IoT). Federated Learning has emerged as a promising remedy to these challenges by decentralizing model training to edge devices or parties, effectively addressing privacy concerns and resource limitations. Nevertheless, the presence of statistical heterogeneity in non-Independently and Identically Distributed (non-IID) data across different parties poses a significant hurdle to the effectiveness of FL. Many FL approaches have been proposed to enhance learning effectiveness under statistical heterogeneity. However, prior studies have uncovered a gap in the existing research landscape, particularly in the absence of a comprehensive comparison between federated methods addressing statistical heterogeneity in detecting IoT attacks. In this research endeavor, we delve into the exploration of FL algorithms, specifically FedAvg, FedProx, and Scaffold, under different data distributions. Our focus is on achieving a comprehensive understanding of and addressing the challenges posed by statistical heterogeneity. In this study, We classify large-scale IoT attacks by utilizing the CICIoT2023 dataset. Through meticulous analysis and experimentation, our objective is to illuminate the performance nuances of these FL methods, providing valuable insights for researchers and practitioners in the domain.
Authors: Joseph Kim, Saahith Potluri
Abstract: Evaluating and measuring AI Safety Level (ASL) threats are crucial for guiding stakeholders to implement safeguards that keep risks within acceptable limits. ASL-3+ models present a unique risk in their ability to uplift novice non-state actors, especially in the realm of biosecurity. Existing evaluation metrics, such as LAB-Bench, BioLP-bench, and WMDP, can reliably assess model uplift and domain knowledge. However, metrics that better contextualize "real-world risks" are needed to inform the safety case for LLMs, along with scalable, open-ended metrics to keep pace with their rapid advancements. To address both gaps, we introduce MOCET, an interpretable and doubly-scalable metric (automatable and open-ended) that can quantify real-world risks.
Authors: Yihang Fu, Lifang He, Qingyu Chen
Abstract: Existing EEG foundation models mainly treat neural signals as generic time series in Euclidean space, ignoring the intrinsic geometric structure of neural dynamics that constrains brain activity to low-dimensional manifolds. This fundamental mismatch between model assumptions and neural geometry limits representation quality and cross-subject generalization. ManifoldFormer addresses this limitation through a novel geometric deep learning framework that explicitly learns neural manifold representations. The architecture integrates three key innovations: a Riemannian VAE for manifold embedding that preserves geometric structure, a geometric Transformer with geodesic-aware attention mechanisms operating directly on neural manifolds, and a dynamics predictor leveraging neural ODEs for manifold-constrained temporal evolution. Extensive evaluation across four public datasets demonstrates substantial improvements over state-of-the-art methods, with 4.6-4.8% higher accuracy and 6.2-10.2% higher Cohen's Kappa, while maintaining robust cross-subject generalization. The geometric approach reveals meaningful neural patterns consistent with neurophysiological principles, establishing geometric constraints as essential for effective EEG foundation models.
Authors: Falk Dippela, Yinan Yu, Annika Rosengren, Martin Lindgren, Christina E. Lundberg, Erik Aerts, Martin Adiels, Helen Sj\"oland
Abstract: Transformers have defined the state-of-the-art for clinical prediction tasks involving electronic health records (EHRs). The recently introduced Mamba architecture outperformed an advanced Transformer (Transformer++) based on Llama in handling long context lengths, while using fewer model parameters. Despite the impressive performance of these architectures, a systematic approach to empirically analyze model performance and efficiency under various settings is not well established in the medical domain. The performances of six sequence models were investigated across three architecture classes (Transformers, Transformers++, Mambas) in a large Swedish heart failure (HF) cohort (N = 42820), providing a clinically relevant case study. Patient data included diagnoses, vital signs, laboratories, medications and procedures extracted from in-hospital EHRs. The models were evaluated on three one-year prediction tasks: clinical instability (a readmission phenotype) after initial HF hospitalization, mortality after initial HF hospitalization and mortality after latest hospitalization. Ablations account for modifications of the EHR-based input patient sequence, architectural model configurations, and temporal preprocessing techniques for data collection. Llama achieves the highest predictive discrimination, best calibration, and showed robustness across all tasks, followed by Mambas. Both architectures demonstrate efficient representation learning, with tiny configurations surpassing other large-scaled Transformers. At equal model size, Llama and Mambas achieve superior performance using 25% less training data. This paper presents a first ablation study with systematic design choices for input tokenization, model configuration and temporal data preprocessing. Future model development in clinical prediction tasks using EHRs could build upon this study's recommendation as a starting point.
Authors: Zijian Zhang, Xinyu Chen, Yuanjie Shi, Liyuan Lillian Ma, Zifan Xu, Yan Yan
Abstract: Ordinal classification has been widely applied in many high-stakes applications, e.g., medical imaging and diagnosis, where reliable uncertainty quantification (UQ) is essential for decision making. Conformal prediction (CP) is a general UQ framework that provides statistically valid guarantees, which is especially useful in practice. However, prior ordinal CP methods mainly focus on heuristic algorithms or restrictively require the underlying model to predict a unimodal distribution over ordinal labels. Consequently, they provide limited insight into coverage-efficiency trade-offs, or a model-agnostic and distribution-free nature favored by CP methods. To this end, we fill this gap by propose an ordinal-CP method that is model-agnostic and provides instance-level optimal prediction intervals. Specifically, we formulate conformal ordinal classification as a minimum-length covering problem at the instance level. To solve this problem, we develop a sliding-window algorithm that is optimal on each calibration data, with only a linear time complexity in K, the number of label candidates. The local optimality per instance further also improves predictive efficiency in expectation. Moreover, we propose a length-regularized variant that shrinks prediction set size while preserving coverage. Experiments on four benchmark datasets from diverse domains are conducted to demonstrate the significantly improved predictive efficiency of the proposed methods over baselines (by 15% decrease on average over four datasets).
Authors: Feliciano Pedro Francisco Domingos, Isibor Kennedy Ihianle, Omprakash Kaiwartya, Ahmad Lotfi, Nicola Khan, Nicholas Beaudreau, Amaya Albalat, Pedro Machado
Abstract: Monitoring aquatic species, especially elusive ones like lobsters, presents challenges. This study focuses on Homarus gammarus (European lobster), a key species for fisheries and aquaculture, and leverages non-invasive Passive Acoustic Monitoring (PAM). Understanding lobster habitats, welfare, reproduction, sex, and age is crucial for management and conservation. While bioacoustic emissions have classified various aquatic species using Artificial Intelligence (AI) models, this research specifically uses H. gammarus bioacoustics (buzzing/carapace vibrations) to classify lobsters by age (juvenile/adult) and sex (male/female). The dataset was collected at Johnshaven, Scotland, using hydrophones in concrete tanks. We explored the efficacy of Deep Learning (DL) models (1D-CNN, 1D-DCNN) and six Machine Learning (ML) models (SVM, k-NN, Naive Bayes, Random Forest, XGBoost, MLP). Mel-frequency cepstral coefficients (MFCCs) were used as features. For age classification (adult vs. juvenile), most models achieved over 97% accuracy (Naive Bayes: 91.31%). For sex classification, all models except Naive Bayes surpassed 93.23%. These strong results demonstrate the potential of supervised ML and DL to extract age- and sex-related features from lobster sounds. This research offers a promising non-invasive PAM approach for lobster conservation, detection, and management in aquaculture and fisheries, enabling real-world edge computing applications for underwater species.
Authors: Leonardo Pepino, Pablo Riera, Juan Kamienkowski, Luciana Ferrer
Abstract: Artificial neural networks (ANNs) are increasingly powerful models of brain computation, yet it remains unclear whether improving their task performance also makes their internal representations more similar to brain signals. To address this question in the auditory domain, we quantified the alignment between the internal representations of 36 different audio models and brain activity from two independent fMRI datasets. Using voxel-wise and component-wise regression, and representation similarity analysis (RSA), we found that recent self-supervised audio models with strong performance in diverse downstream tasks are better predictors of auditory cortex activity than older and more specialized models. To assess the quality of the audio representations, we evaluated these models in 6 auditory tasks from the HEAREval benchmark, spanning music, speech, and environmental sounds. This revealed strong positive Pearson correlations ($r>0.7$) between a model's overall task performance and its alignment with brain representations. Finally, we analyzed the evolution of the similarity between audio and brain representations during the pretraining of EnCodecMAE. We discovered that brain similarity increases progressively and emerges early during pretraining, despite the model not being explicitly optimized for this objective. This suggests that brain-like representations can be an emergent byproduct of learning to reconstruct missing information from naturalistic audio data.
Authors: Katia Pires Nascimento do Sacramento, Elliot Q. C. Garcia, Nic\'eias Silva Vilela, Vinicius P. Sacramento, Tiago A. E. Ferreira
Abstract: Parkinson's disease (PD) is a progressive neurodegenerative disorder that, in addition to directly impairing functional mobility, is frequently associated with vocal impairments such as hypophonia and dysarthria, which typically manifest in the early stages. The use of vocal biomarkers to support the early diagnosis of PD presents a non-invasive, low-cost, and accessible alternative in clinical settings. Thus, the objective of this cross-sectional study was to consistently evaluate the effectiveness of a Deep Neural Network (DNN) in distinguishing individuals with Parkinson's disease from healthy controls, in comparison with traditional Machine Learning (ML) methods, using vocal biomarkers. Two publicly available voice datasets were used. Mel-frequency cepstral coefficients (MFCCs) were extracted from the samples, and model robustness was assessed using a validation strategy with 1000 independent random executions. Performance was evaluated using classification statistics. Since normality assumptions were not satisfied, non-parametric tests (Kruskal-Wallis and Bonferroni post-hoc tests) were applied to verify whether the tested classification models were similar or different in the classification of PD. With an average accuracy of $98.65\%$ and $92.11\%$ on the Italian Voice dataset and Parkinson's Telemonitoring dataset, respectively, the DNN demonstrated superior performance and efficiency compared to traditional ML models, while also achieving competitive results when benchmarked against relevant studies. Overall, this study confirms the efficiency of DNNs and emphasizes their potential to provide greater accuracy and reliability for the early detection of neurodegenerative diseases using voice-based biomarkers.
Authors: Marshall Rosenhoover, Huaming Zhang
Abstract: Graph Neural Networks rely on local message passing, which limits their ability to model long-range dependencies in graphs. Existing approaches extend this range through continuous-time dynamics or dense self-attention, but both suffer from high computational cost and limited scalability. We propose Topologic Attention Networks, a new framework that applies topologic attention, a probabilistic mechanism that learns how information should flow through both direct and indirect connections in a graph. Unlike conventional attention that depends on explicit pairwise interactions, topologic attention emerges from the learned information propagation of the graph, enabling unified reasoning over local and global relationships. This method achieves provides state-of-the-art performance across all measured baseline models. Our implementation is available at https://github.com/Marshall-Rosenhoover/Topologic-Attention-Networks.
URLs: https://github.com/Marshall-Rosenhoover/Topologic-Attention-Networks.
Authors: Zhongjie Dai, Tao Feng, Jiaxuan You
Abstract: The growing number of Large Language Models (LLMs) with diverse capabilities and response styles provides users with a wider range of choices, which presents challenges in selecting appropriate LLMs, as user preferences vary in terms of performance, cost, and response style. Current LLM selection methods typically optimize for a single fixed objective, such as performance, cost, or a trade-off between them, and fail to learn individual user preferences from interaction data. To address these limitations, we propose PersonalizedRouter, a graph-based framework that models diverse user profiles and performs personalized LLM selection by leveraging interaction data that includes task context, queries, candidate LLMs, and user decisions. To capture contextual information between user queries and optimal LLMs, PersonalizedRouter converts the interaction data into a heterogeneous graph, where the relationships between different types of nodes are represented by edges. To evaluate adaptability across users, we design two strategies: the multi-cost-efficiency simulation strategy and the LLM-as-a-Judge strategy. In addition, we construct PersonaRoute-Bench, a large-scale benchmark with 1,000 simulated users and 10 LLMs. Experimental results show that PersonalizedRouter significantly outperforms existing LLM selection methods and surpasses the strongest methods by a large margin of 15.38% and 9.83% under two simulation strategies. On the PersonaRoute-Bench with 1,000 users, it further surpasses the best methods by 16.19% and 59.69% while maintaining higher efficiency. Moreover, PersonalizedRouter demonstrates strong few-shot generalization, achieving 64.81% and 85.80% of the fully trained model's performance when adapting to new users and new LLMs.
Authors: Bilguun Batsaikhan, Hiroyuki Fukuda
Abstract: Early detection of rising talents is of paramount importance in the field of advertising. In this paper, we define a concept of talent breakout and propose a method to detect Japanese talents before their rise to stardom. The main focus of the study is to determine the effectiveness of combining Twitter and TV data on predicting time-dependent changes in social data. Although traditional time-series models are known to be robust in many applications, the success of neural network models in various fields (e.g.\ Natural Language Processing, Computer Vision, Reinforcement Learning) continues to spark an interest in the time-series community to apply new techniques in practice. Therefore, in order to find the best modeling approach, we have experimented with traditional, neural network and ensemble learning methods. We observe that ensemble learning methods outperform traditional and neural network models based on standard regression metrics. However, by utilizing the concept of talent breakout, we are able to assess the true forecasting ability of the models, where neural networks outperform traditional and ensemble learning methods in terms of precision and recall.
Authors: Trieu Nguyen, Hao-Wei Pang, Shasha Feng
Abstract: Macrocyclic peptides are an emerging modality that combines biologics-like affinity with small-molecule-like developability, but their vast combinatorial space and multi-parameter objectives make lead optimization slow and challenging. Prior generative approaches such as PepINVENT require chemists to pre-specify mutable positions for optimization, choices that are not always known a priori, and rely on static pretraining and optimization algorithms that limit the model's ability to generalize and effectively optimize peptide sequences. We introduce PepEVOLVE, a position-aware, dynamic framework that learns both where to edit and how to dynamically optimize peptides for multi-objective improvement. PepEVOLVE (i) augments pretraining with dynamic masking and CHUCKLES shifting to improve generalization, (ii) uses a context-free multi-armed bandit router that discovers high-reward residues, and (iii) couples a novel evolving optimization algorithm with group-relative advantage to stabilize reinforcement updates. During in silico evaluations, the router policy reliably learns and concentrates probability on chemically meaningful sites that influence the peptide's properties. On a therapeutically motivated Rev-binding macrocycle benchmark, PepEVOLVE outperformed PepINVENT by reaching higher mean scores (approximately 0.8 vs. 0.6), achieving best candidates with a score of 0.95 (vs. 0.87), and converging in fewer steps under the task of optimizing permeability and lipophilicity with structural constraints. Overall, PepEVOLVE offers a practical, reproducible path to peptide lead optimization when optimal edit sites are unknown, enabling more efficient exploration and improving design quality across multiple objectives.
Authors: Ali Anaissi, Deshao Liu, Yuanzhe Jia, Weidong Huang, Widad Alyassine, Junaid Akram
Abstract: Single-cell RNA sequencing (scRNA-seq) enables transcriptomic profiling at cellular resolution but suffers from pervasive dropout events that obscure biological signals. We present SCR-MF, a modular two-stage workflow that combines principled dropout detection using scRecover with robust non-parametric imputation via missForest. Across public and simulated datasets, SCR-MF achieves robust and interpretable performance comparable to or exceeding existing imputation methods in most cases, while preserving biological fidelity and transparency. Runtime analysis demonstrates that SCR-MF provides a competitive balance between accuracy and computational efficiency, making it suitable for mid-scale single-cell datasets.
Authors: Rui Xue, Dan He, Fengmei Jin, Chen Zhang, Xiaofang Zhou
Abstract: Detecting trajectory anomalies is a vital task in modern Intelligent Transportation Systems (ITS), enabling the identification of unsafe, inefficient, or irregular travel behaviours. While deep learning has emerged as the dominant approach, several key challenges remain unresolved. First, sub-trajectory anomaly detection, capable of pinpointing the precise segments where anomalies occur, remains underexplored compared to whole-trajectory analysis. Second, many existing methods depend on carefully tuned thresholds, limiting their adaptability in real-world applications. Moreover, the irregular sampling of trajectory data and the presence of noise in training sets further degrade model performance, making it difficult to learn reliable representations of normal routes. To address these challenges, we propose a contrastive reinforcement learning framework for online trajectory anomaly detection, CroTad. Our method is threshold-free and robust to noisy, irregularly sampled data. By incorporating contrastive learning, CroTad learns to extract diverse normal travel patterns for different itineraries and effectively distinguish anomalous behaviours at both sub-trajectory and point levels. The detection module leverages deep reinforcement learning to perform online, real-time anomaly scoring, enabling timely and fine-grained identification of abnormal segments. Extensive experiments on two real-world datasets demonstrate the effectiveness and robustness of our framework across various evaluation scenarios.
Authors: Angelina Yan, Matt L. Sampson, Peter Melchior
Abstract: 12-lead ECGs with high sampling frequency are the clinical gold standard for arrhythmia detection, but their short-term, spot-check nature often misses intermittent events. Wearable ECGs enable long-term monitoring but suffer from irregular, lower sampling frequencies due to battery constraints, making morphology analysis challenging. We present an end-to-end classification pipeline to address these issues. We train a latent ODE to model continuous ECG waveforms and create robust feature vectors from high-frequency single-channel signals. We construct three latent vectors per waveform via downsampling the initial 360 Hz ECG to 90 Hz and 45 Hz. We then use a gradient boosted tree to classify these vectors and test robustness across frequencies. Performance shows minimal degradation, with macro-averaged AUC-ROC values of 0.984, 0.978, and 0.976 at 360 Hz, 90 Hz, and 45 Hz, respectively, suggesting a way to sidestep the trade-off between signal fidelity and battery life. This enables smaller wearables, promoting long-term monitoring of cardiac health.
Authors: Shuyang Yu, Jianan Liang, Hui Hu
Abstract: Optimizing patent claims is a critical yet challenging task, demanding careful balance between maximizing novelty and preserving legal scope. Manual claim drafting is labor-intensive, costly, and inherently inconsistent, while conventional Large Language Models (LLMs) often lack the structured, iterative reasoning essential for precise claim refinement. To address these challenges, we introduce Tree of Claims (ToC), an innovative framework that redefines claim editing as a guided search problem. ToC synergistically integrates Monte Carlo Tree Search (MCTS) with a collaborative multi-agent system, comprising an LLM-based EditorAgent that proposes contextually grounded edits, and an ExaminerAgent that mimics patent examiner critiques through structured, chain-of-thought analyses of novelty and prior art disclosure. Driven by a carefully designed multi-objective reward function, ToC jointly optimizes novelty, scope retention, and semantic coherence. Experimental evaluation on a benchmark of 1145 claims demonstrates that ToC significantly outperforms standard LLMs in zero-shot and few-shot scenarios, achieving an average composite score improvement of 8\%, and up to 9\% in certain cases. Extensive experiments, including detailed ablation studies, validate ToC's efficacy in generating superior, legally robust claim revisions. Overall, ToC establishes a transparent, controllable, and interpretable methodology that effectively bridges advanced LLM reasoning capabilities with strategic MCTS planning for structured patent claim optimization.The source code is available at https://github.com/ysy2003/ToC.
Authors: Sanjit Dandapanthula, Aaditya Ramdas
Abstract: Deep equilibrium models (DEQs) have recently emerged as a powerful paradigm for training infinitely deep weight-tied neural networks that achieve state of the art performance across many modern machine learning tasks. Despite their practical success, theoretically understanding the gradient descent dynamics for training DEQs remains an area of active research. In this work, we rigorously study the gradient descent dynamics for DEQs in the simple setting of linear models and single-index models, filling several gaps in the literature. We prove a conservation law for linear DEQs which implies that the parameters remain trapped on spheres during training and use this property to show that gradient flow remains well-conditioned for all time. We then prove linear convergence of gradient descent to a global minimizer for linear DEQs and deep equilibrium single-index models under appropriate initialization and with a sufficiently small step size. Finally, we validate our theoretical findings through experiments.
Authors: Fatemeh (Atena), Nourzad (Kevin), Amirhossein Roknilamouki (Kevin), Eylem Ekici (Kevin), Jia (Kevin), Liu, Ness B. Shroff
Abstract: Aligning Large Language Models (LLMs) with human values often involves balancing multiple, conflicting objectives such as helpfulness and harmlessness. Training these models is computationally intensive, and centralizing the process raises significant data privacy concerns. Federated Learning (FL) offers a compelling alternative, but existing Federated Multi-Objective Optimization (FMOO) methods face severe communication bottlenecks as their reliance on transmitting multiple gradients to a server is unscalable for large models. We introduce FIRM (Federated In-client Regularized Multi-objective alignment), a novel algorithm that achieves both client disagreement drift mitigation and communication efficiency. In FIRM, each client locally solves a regularized multi-objective optimization problem. By directly mitigating client disagreement drift through in-client regularization, our method eliminates the need for the multi-gradient transmissions common in prior works. Consequently, clients need only to transmit a single set of adapted parameters, maintaining high communication efficiency. We prove that our algorithm converges to Pareto-stationary points and, to our knowledge, provide the first finite-time convergence guarantees for this federated multi-objective alignment setting. Empirically, we show that FIRM leads to smoother training dynamics, reduced client disagreement drift, and improved reward trade-offs compared to baselines. We further propose a method to incorporate a preference over the objectives and report empirical Pareto plots, demonstrating that FIRM can smoothly adapt trade-offs between objectives in response to specified preferences.
Authors: Zexi Tan, Xiaopeng Luo, Yunlin Liu, Yiqun Zhang
Abstract: Multivariate Time-Series (MTS) clustering discovers intrinsic grouping patterns of temporal data samples. Although time-series provide rich discriminative information, they also contain substantial redundancy, such as steady-state machine operation records and zero-output periods of solar power generation. Such redundancy diminishes the attention given to discriminative timestamps in representation learning, thus leading to performance bottlenecks in MTS clustering. Masking has been widely adopted to enhance the MTS representation, where temporal reconstruction tasks are designed to capture critical information from MTS. However, most existing masking strategies appear to be standalone preprocessing steps, isolated from the learning process, which hinders dynamic adaptation to the importance of clustering-critical timestamps. Accordingly, this paper proposes the Evolving-masked MTS Clustering (EMTC) method, with its model architecture composed of Importance-aware Variate-wise Masking (IVM) and Multi-Endogenous Views (MEV) representation learning modules. IVM adaptively guides the model in learning more discriminative representations for clustering, while the MEV-based reconstruction and contrastive learning pathways enhance the generalization. That is, the MEV reconstruction facilitates multi-perspective complementary to prevent the masking from premature convergence, and the clustering-guided contrastive learning facilitates the joint optimization of representation and clustering. Extensive experiments on 15 real benchmark datasets demonstrate the superiority of EMTC in comparison with eight SOTA methods, where the EMTC achieves an average improvement of 4.85% over the strongest baselines.
Authors: Aniketh Iyengar, Jiaqi Han, Boris Ruf, Vincent Grari, Marcin Detyniecki, Stefano Ermon
Abstract: The rapidly growing computational demands of diffusion models for image generation have raised significant concerns about energy consumption and environmental impact. While existing approaches to energy optimization focus on architectural improvements or hardware acceleration, there is a lack of principled methods to predict energy consumption across different model configurations and hardware setups. We propose an adaptation of Kaplan scaling laws to predict GPU energy consumption for diffusion models based on computational complexity (FLOPs). Our approach decomposes diffusion model inference into text encoding, iterative denoising, and decoding components, with the hypothesis that denoising operations dominate energy consumption due to their repeated execution across multiple inference steps. We conduct comprehensive experiments across four state-of-the-art diffusion models (Stable Diffusion 2, Stable Diffusion 3.5, Flux, and Qwen) on three GPU architectures (NVIDIA A100, A4000, A6000), spanning various inference configurations including resolution (256x256 to 1024x1024), precision (fp16/fp32), step counts (10-50), and classifier-free guidance settings. Our energy scaling law achieves high predictive accuracy within individual architectures (R-squared > 0.9) and exhibits strong cross-architecture generalization, maintaining high rank correlations across models and enabling reliable energy estimation for unseen model-hardware combinations. These results validate the compute-bound nature of diffusion inference and provide a foundation for sustainable AI deployment planning and carbon footprint estimation.
Authors: Wenzhang Du
Abstract: Training data collected in the wild often contain noisy labels and outliers that substantially degrade the performance and reliability of deep neural networks. While data cleaning is commonly applied as a separate preprocessing stage, such two-stage pipelines neither fully exploit feedback from the downstream model nor adapt to unknown noise patterns. We propose Step-E, a simple framework that integrates sample selection and model learning into a single optimization process. At each epoch, Step-E ranks samples by loss and gradually increases the fraction of high-loss examples that are excluded from gradient updates after a brief warm-up stage, yielding an online curriculum that focuses on easy and consistent examples and eventually ignores persistent outliers. On CIFAR-100N, Step-E improves the test accuracy of a ResNet-18 model from 43.3% (+/- 0.7%) to 50.4% (+/- 0.9%), clearly outperforming loss truncation, self-paced learning, and one-shot filtering while approaching the clean-label oracle at 60.5% (+/- 0.2%). On CIFAR-10N (aggre), Step-E also improves over the noisy baseline (85.3% vs. 83.9%) and nearly matches the clean-label oracle (85.9%), with only moderate training-time overhead.
Authors: Walter Virany, Austin Tripp
Abstract: Molecular fingerprinting methods use hash functions to create fixed-length vector representations of molecules. However, hash collisions cause distinct substructures to be represented with the same feature, leading to overestimates in molecular similarity calculations. We investigate whether using exact fingerprints improves accuracy compared to standard compressed fingerprints in molecular property prediction and Bayesian optimization where the underlying predictive model is a Gaussian process. We find that using exact fingerprints yields a small yet consistent improvement in predictive accuracy on five molecular property prediction benchmarks from the DOCKSTRING dataset. However, these gains did not translate to significant improvements in Bayesian optimization performance.
Authors: Kushal Agrawal, Frank Xiao, Guido Bergman, Asa Cooper Stickland
Abstract: The deployment of Large Language Models (LLMs) as tool-using agents causes their alignment training to manifest in new ways. Recent work finds that language models can use tools in ways that contradict the interests or explicit instructions of the user. We study LLM whistleblowing: a subset of this behavior where models disclose suspected misconduct to parties beyond the dialog boundary (e.g., regulatory agencies) without user instruction or knowledge. We introduce an evaluation suite of diverse and realistic staged misconduct scenarios to assess agents for this behavior. Across models and settings, we find that: (1) the frequency of whistleblowing varies widely across model families, (2) increasing the complexity of the task the agent is instructed to complete lowers whistleblowing tendencies, (3) nudging the agent in the system prompt to act morally substantially raises whistleblowing rates, and (4) giving the model more obvious avenues for non-whistleblowing behavior, by providing more tools and a detailed workflow to follow, decreases whistleblowing rates. Additionally, we verify the robustness of our dataset by testing for model evaluation awareness, and find that both black-box methods and probes on model activations show lower evaluation awareness in our settings than in comparable previous work.
Authors: Duo Zhou, Yuji Zhang, Tianxin Wei, Ruizhong Qiu, Ke Yang, Xiao Lin, Cheng Qian, Jingrui He, Hanghang Tong, Heng Ji, Huan Zhang
Abstract: Machine unlearning, the removal of a training subset's influence from a deployed model, is critical for privacy preservation and model reliability, yet gradient ascent on forget samples often harms retained knowledge. Existing approaches face a persistent tradeoff between effective forgetting and preservation on the retain set. While previous methods provide useful heuristics, they often lack a formal analysis on how exactly forgetting updates harm retained knowledge, and whether the side effects can be removed with theoretical guarantees. To explore a theoretically sound and simple solution, we start from the first principle on how performance on the retain set is actually affected: a first-order analysis of the local change of the retain loss under small parameter updates during model training. We start from a crisp equivalence: the retain loss is unchanged to first order iff the update direction is orthogonal to the subspace spanned by retain gradients ("retain-invariant"). This identifies the entangled component as the tangential part of forget update within the retain-gradient subspace, and characterizes disentanglement as orthogonality. Guided by this, we propose the Geometric-disentanglement Unlearning (GU) that decomposes any candidate forget gradient update into tangential and normal components to retain space and executes only the normal component. Under a standard trust-region budget, the projected direction aligned with the raw forget gradient is optimal among all first-order retain-invariant moves, and we also derive the optimal projected direction for joint forget-retain updating objectives. Our method is plug-and-play and can be attached to existing gradient-based unlearning procedures to mitigate side effects. GU achieves consistent improvement on various methods across three benchmarks TOFU, MUSE, and WMDP.
Authors: Sonia Dupuis, Nando Metzger, Konrad Schindler, Frank G\"ottsche, Stefan Wunderle
Abstract: Land surface temperature (LST) is an essential climate variable (ECV) crucial for understanding land-atmosphere energy exchange and monitoring climate change, especially in the rapidly warming Arctic. Long-term satellite-based LST records, such as those derived from the Advanced Very High Resolution Radiometer (AVHRR), are essential for detecting climate trends. However, the coarse spatial resolution of AVHRR's global area coverage (GAC) data limit their utility for analyzing fine-scale permafrost dynamics and other surface processes in the Arctic. This paper presents a new 42 years pan-Arctic LST dataset, downscaled from AVHRR GAC to 1 km with a super-resolution algorithm based on a deep anisotropic diffusion model. The model is trained on MODIS LST data, using coarsened inputs and native-resolution outputs, guided by high-resolution land cover, digital elevation, and vegetation height maps. The resulting dataset provides twice-daily, 1 km LST observations for the entire pan-Arctic region over four decades. This enhanced dataset enables improved modelling of permafrost, reconstruction of near-surface air temperature, and assessment of surface mass balance of the Greenland Ice Sheet. Additionally, it supports climate monitoring efforts in the pre-MODIS era and offers a framework adaptable to future satellite missions for thermal infrared observation and climate data record continuity.
Authors: Shubhranil Basak, Mada Hemanth, Madhav Rao
Abstract: Surface Electromyography (sEMG) provides vital insights into muscle function, but it can be noisy and challenging to acquire. Inertial Measurement Units (IMUs) provide a robust and wearable alternative to motion capture systems. This paper investigates the synthesis of normalized sEMG signals from 6-axis IMU data using a deep learning approach. We collected simultaneous sEMG and IMU data sampled at 1~KHz for various arm movements. A Sliding-Window-Wave-Net model, based on dilated causal convolutions, was trained to map the IMU data to the sEMG signal. The results show that the model successfully predicts the timing and general shape of muscle activations. Although peak amplitudes were often underestimated, the high temporal fidelity demonstrates the feasibility of using this method for muscle intent detection in applications such as prosthetics and rehabilitation biofeedback.
Authors: Tomas Javurek, Michal Gregor, Sebastian Kula, Marian Simko
Abstract: The paper introduces DelTriC (Delaunay Triangulation Clustering), a clustering algorithm which integrates PCA/UMAP-based projection, Delaunay triangulation, and a novel back-projection mechanism to form clusters in the original high-dimensional space. DelTriC decouples neighborhood construction from decision-making by first triangulating in a low-dimensional proxy to index local adjacency, and then back-projecting to the original space to perform robust edge pruning, merging, and anomaly detection. DelTriC can outperform traditional methods such as k-means, DBSCAN, and HDBSCAN in many scenarios; it is both scalable and accurate, and it also significantly improves outlier detection.
Authors: Yufei Luo, Xiang Gu, Jian Sun
Abstract: Transition states (TSs) are crucial for understanding reaction mechanisms, yet their exploration is limited by the complexity of experimental and computational approaches. Here we propose TS-DFM, a flow matching framework that predicts TSs from reactants and products. By operating in molecular distance geometry space, TS-DFM explicitly captures the dynamic changes of interatomic distances in chemical reactions. A network structure named TSDVNet is designed to learn the velocity field for generating TS geometries accurately. On the benchmark dataset Transition1X, TS-DFM outperforms the previous state-of-the-art method React-OT by 30\% in structural accuracy. These predicted TSs provide high-quality initial structures, accelerating the convergence of CI-NEB optimization. Additionally, TS-DFM can identify alternative reaction paths. In our experiments, even a more favorable TS with lower energy barrier is discovered. Further tests on RGD1 dataset confirm its strong generalization ability on unseen molecules and reaction types, highlighting its potential for facilitating reaction exploration.
Authors: Riccardo Tedoldi, Ola Engkvist, Patrick Bryant, Hossein Azizpour, Jon Paul Janet, Alessandro Tibo
Abstract: Sampling useful three-dimensional molecular structures along with their most favorable conformations is a key challenge in drug discovery. Current state-of-the-art 3D de-novo design flow matching or diffusion-based models are limited to generating a single conformation. However, the conformational landscape of a molecule determines its observable properties and how tightly it is able to bind to a given protein target. By generating a representative set of low-energy conformers, we can more directly assess these properties and potentially improve the ability to generate molecules with desired thermodynamic observables. Towards this aim, we propose FlexiFlow, a novel architecture that extends flow-matching models, allowing for the joint sampling of molecules along with multiple conformations while preserving both equivariance and permutation invariance. We demonstrate the effectiveness of our approach on the QM9 and GEOM Drugs datasets, achieving state-of-the-art results in molecular generation tasks. Our results show that FlexiFlow can generate valid, unstrained, unique, and novel molecules with high fidelity to the training data distribution, while also capturing the conformational diversity of molecules. Moreover, we show that our model can generate conformational ensembles that provide similar coverage to state-of-the-art physics-based methods at a fraction of the inference time. Finally, FlexiFlow can be successfully transferred to the protein-conditioned ligand generation task, even when the dataset contains only static pockets without accompanying conformations.
Authors: Omer Rochman, Gilles Louppe
Abstract: Neural PDE solvers used for scientific simulation often violate governing equation constraints. While linear constraints can be projected cheaply, many constraints are nonlinear, complicating projection onto the feasible set. Dynamical PDEs are especially difficult because constraints induce long-range dependencies in time. In this work, we evaluate two training-free, post hoc projections of approximate solutions: a nonlinear optimization-based projection, and a local linearization-based projection using Jacobian-vector and vector-Jacobian products. We analyze constraints across representative PDEs and find that both projections substantially reduce violations and improve accuracy over physics-informed baselines.
Authors: Tom Nahrendorf, Stefan Minner, Helfried Binder, Richard Zinck
Abstract: Premium automotive manufacturers face increasingly complex forecasting challenges due to high product variety, sparse variant-level data, and volatile market dynamics. This study addresses monthly automobile demand forecasting across a multi-product, multi-market, and multi-level hierarchy using data from a German premium manufacturer. The methodology combines point and probabilistic forecasts across strategic and operational planning levels, leveraging ensembles of LightGBM models with pooled training sets, quantile regression, and a mixed-integer linear programming reconciliation approach. Results highlight that spatiotemporal dependencies, as well as rounding bias, significantly affect forecast accuracy, underscoring the importance of integer forecasts for operational feasibility. Shapley analysis shows that short-term demand is reactive, shaped by life cycle maturity, autoregressive momentum, and operational signals, whereas medium-term demand reflects anticipatory drivers such as online engagement, planning targets, and competitive indicators, with online behavioral data considerably improving accuracy at disaggregated levels.
Authors: Artem Frenk, Roee Shraga
Abstract: Our work introduces SAVeD (Semantically Aware Version Detection), a contrastive learning-based framework for identifying versions of structured datasets without relying on metadata, labels, or integration-based assumptions. SAVeD addresses a common challenge in data science of repeated labor due to a difficulty of similar work or transformations on datasets. SAVeD employs a modified SimCLR pipeline, generating augmented table views through random transformations (e.g., row deletion, encoding perturbations). These views are embedded via a custom transformer encoder and contrasted in latent space to optimize semantic similarity. Our model learns to minimize distances between augmented views of the same dataset and maximize those between unrelated tables. We evaluate performance using validation accuracy and separation, defined respectively as the proportion of correctly classified version/non-version pairs on a hold-out set, and the difference between average similarities of versioned and non-versioned tables (defined by a benchmark, and not provided to the model). Our experiments span five canonical datasets from the Semantic Versioning in Databases Benchmark, and demonstrate substantial gains post-training. SAVeD achieves significantly higher accuracy on completely unseen tables in, and a significant boost in separation scores, confirming its capability to distinguish semantically altered versions. Compared to untrained baselines and prior state-of-the-art dataset-discovery methods like Starmie, our custom encoder achieves competitive or superior results.
Authors: Israt Jahan Tulin, Sebastian Starke, Dominic Windisch, Andr\'e Bieberle, Peter Steinbach
Abstract: Ultrafast electron beam X-ray computed tomography produces noisy data due to short measurement times, causing reconstruction artifacts and limiting overall image quality. To counteract these issues, two self-supervised deep learning methods for denoising of raw detector data were investigated and compared against a non-learning based denoising method. We found that the application of the deep-learning-based methods was able to enhance signal-to-noise ratios in the detector data and also led to consistent improvements of the reconstructed images, outperforming the non-learning based method.
Authors: Yassir Bendou, Omar Ezzahir, Eduardo Fernandes Montesuma, Gabriel Mahuas, Victoria Shevchenko, Mike Gartrell
Abstract: Prompt learning has emerged as an effective technique for fine-tuning large-scale foundation models for downstream tasks. However, conventional prompt tuning methods are prone to overfitting and can struggle with out-of-distribution generalization. To address these limitations, Bayesian prompt learning has been proposed, which frames prompt optimization as a Bayesian inference problem to enhance robustness. This paper introduces Repulsive Bayesian Prompt Learning (ReBaPL), a novel method for Bayesian prompt learning, designed to efficiently explore the complex and often multimodal posterior landscape of prompts. Our method integrates a cyclical step-size schedule with a stochastic gradient Hamiltonian Monte Carlo (SGHMC) algorithm, enabling alternating phases of exploration to discover new modes, and exploitation to refine existing modes. Furthermore, we introduce a repulsive force derived from a potential function over probability metrics (including Maximum Mean Discrepancy and Wasserstein distance) computed on the distributions of representations produced by different prompts. This representation-space repulsion diversifies exploration and prevents premature collapse to a single mode. Our approach allows for a more comprehensive characterization of the prompt posterior distribution, leading to improved generalization. In contrast to prior Bayesian prompt learning methods, our method provides a modular plug-and-play Bayesian extension of any existing prompt learning method based on maximum likelihood estimation. We demonstrate the efficacy of ReBaPL on several benchmark datasets, showing superior performance over state-of-the-art methods for prompt learning.
Authors: Massimiliano Manenti, Andrea Iannelli
Abstract: Hierarchical Reinforcement Learning promises, among other benefits, to efficiently capture and utilize the temporal structure of a decision-making problem and to enhance continual learning capabilities, but theoretical guarantees lag behind practice. In this paper, we propose a Feudal Q-learning scheme and investigate under which conditions its coupled updates converge and are stable. By leveraging the theory of Stochastic Approximation and the ODE method, we present a theorem stating the convergence and stability properties of Feudal Q-learning. This provides a principled convergence and stability analysis tailored to Feudal RL. Moreover, we show that the updates converge to a point that can be interpreted as an equilibrium of a suitably defined game, opening the door to game-theoretic approaches to Hierarchical RL. Lastly, experiments based on the Feudal Q-learning algorithm support the outcomes anticipated by theory.
Authors: Runyu Lu, Ruochuan Shi, Yuanheng Zhu, Dongbin Zhao
Abstract: Computing worst-case robust strategies in pursuit-evasion games (PEGs) is time-consuming, especially when real-world factors like partial observability are considered. While important for general security purposes, real-time applicable pursuit strategies for graph-based PEGs are currently missing when the pursuers only have imperfect information about the evader's position. Although state-of-the-art reinforcement learning (RL) methods like Equilibrium Policy Generalization (EPG) and Grasper provide guidelines for learning graph neural network (GNN) policies robust to different game dynamics, they are restricted to the scenario of perfect information and do not take into account the possible case where the evader can predict the pursuers' actions. This paper introduces the first approach to worst-case robust real-time pursuit strategies (R2PS) under partial observability. We first prove that a traditional dynamic programming (DP) algorithm for solving Markov PEGs maintains optimality under the asynchronous moves by the evader. Then, we propose a belief preservation mechanism about the evader's possible positions, extending the DP pursuit strategies to a partially observable setting. Finally, we embed the belief preservation into the state-of-the-art EPG framework to finish our R2PS learning scheme, which leads to a real-time pursuer policy through cross-graph reinforcement learning against the asynchronous-move DP evasion strategies. After reinforcement learning, our policy achieves robust zero-shot generalization to unseen real-world graph structures and consistently outperforms the policy directly trained on the test graphs by the existing game RL approach.
Authors: Wei-Kai Chang, Rajiv Khanna
Abstract: Understanding the dynamics of optimization in deep learning is increasingly important as models scale. While stochastic gradient descent (SGD) and its variants reliably find solutions that generalize well, the mechanisms driving this generalization remain unclear. Notably, these algorithms often prefer flatter or simpler minima, particularly in overparameterized settings. Prior work has linked flatness to generalization, and methods like Sharpness-Aware Minimization (SAM) explicitly encourage flatness, but a unified theory connecting data structure, optimization dynamics, and the nature of learned solutions is still lacking. In this work, we develop a linear stability framework that analyzes the behavior of SGD, random perturbations, and SAM, particularly in two layer ReLU networks. Central to our analysis is a coherence measure that quantifies how gradient curvature aligns across data points, revealing why certain minima are stable and favored during training.
Authors: Wei-Kai Chang, Rajiv Khanna
Abstract: As deep learning models continue to scale, the growing computational demands have amplified the need for effective coreset selection techniques. Coreset selection aims to accelerate training by identifying small, representative subsets of data that approximate the performance of the full dataset. Among various approaches, gradient based methods stand out due to their strong theoretical underpinnings and practical benefits, particularly under limited data budgets. However, these methods face challenges such as naive stochastic gradient descent (SGD) acting as a surprisingly strong baseline and the breakdown of representativeness due to loss curvature mismatches over time. In this work, we propose a novel framework that addresses these limitations. First, we establish a connection between posterior sampling and loss landscapes, enabling robust coreset selection even in high data corruption scenarios. Second, we introduce a smoothed loss function based on posterior sampling onto the model weights, enhancing stability and generalization while maintaining computational efficiency. We also present a novel convergence analysis for our sampling-based coreset selection method. Finally, through extensive experiments, we demonstrate how our approach achieves faster training and enhanced generalization across diverse datasets than the current state of the art.
Authors: Yeamin Kaiser, Muhammed Tasnim Bin Anwar, Bholanath Das, Chowdhury Farhan Ahmed, Md. Tanvir Alam
Abstract: Graph representation learning seeks to transform complex, high-dimensional graph structures into compact vector spaces that preserve both topology and semantics. Among the various strategies, subgraph-based methods provide an interpretable bridge between symbolic pattern discovery and continuous embedding learning. Yet, existing frequent or discriminative subgraph mining approaches often suffer from redundant multi-phase pipelines, high computational cost, and weak coupling between mined structures and their discriminative relevance. We propose DS-Span, a single-phase discriminative subgraph mining framework that unifies pattern growth, pruning, and supervision-driven scoring within one traversal of the search space. DS-Span introduces a coverage-capped eligibility mechanism that dynamically limits exploration once a graph is sufficiently represented, and an information-gain-guided selection that promotes subgraphs with strong class-separating ability while minimizing redundancy. The resulting subgraph set serves as an efficient, interpretable basis for downstream graph embedding and classification. Extensive experiments across benchmarks demonstrate that DS-Span generates more compact and discriminative subgraph features than prior multi-stage methods, achieving higher or comparable accuracy with significantly reduced runtime. These results highlight the potential of unified, single-phase discriminative mining as a foundation for scalable and interpretable graph representation learning.
Authors: Benyamin Ghojogh, M. Hadi Sepanj, Paul Fieguth
Abstract: Self-supervised learning (SSL) has recently advanced through non-contrastive methods that couple an invariance term with variance, covariance, or redundancy-reduction penalties. While such objectives shape first- and second-order statistics of the representation, they largely ignore the local geometry of the underlying data manifold. In this paper, we introduce CurvSSL, a curvature-regularized self-supervised learning framework, and its RKHS extension, kernel CurvSSL. Our approach retains a standard two-view encoder-projector architecture with a Barlow Twins-style redundancy-reduction loss on projected features, but augments it with a curvature-based regularizer. Each embedding is treated as a vertex whose $k$ nearest neighbors define a discrete curvature score via cosine interactions on the unit hypersphere; in the kernel variant, curvature is computed from a normalized local Gram matrix in an RKHS. These scores are aligned and decorrelated across augmentations by a Barlow-style loss on a curvature-derived matrix, encouraging both view invariance and consistency of local manifold bending. Experiments on MNIST and CIFAR-10 datasets with a ResNet-18 backbone show that curvature-regularized SSL yields competitive or improved linear evaluation performance compared to Barlow Twins and VICReg. Our results indicate that explicitly shaping local geometry is a simple and effective complement to purely statistical SSL regularizers.
Authors: Etienne Meunier, Said Ouala, Hugo Frezat, Julien Le Sommer, Ronan Fablet
Abstract: We present a differentiable extension of the VEROS ocean model, enabling automatic differentiation through its dynamical core. We describe the key modifications required to make the model fully compatible with JAX autodifferentiation framework and evaluate the numerical consistency of the resulting implementation. Two illustrative applications are then demonstrated: (i) the correction of an initial ocean state through gradient-based optimization, and (ii) the calibration of unknown physical parameters directly from model observations. These examples highlight how differentiable programming can facilitate end-to-end learning and parameter tuning in ocean modeling. Our implementation is available online.
Authors: Zengyu Zou, Jingyuan Wang, Yixuan Huang, Junjie Wu
Abstract: This paper addresses the cooperative Multi-Vehicle Dynamic Pickup and Delivery Problem with Stochastic Requests (MVDPDPSR) and proposes an end-to-end centralized decision-making framework based on sequence-to-sequence, named Multi-Agent Pointer Transformer (MAPT). MVDPDPSR is an extension of the vehicle routing problem and a spatio-temporal system optimization problem, widely applied in scenarios such as on-demand delivery. Classical operations research methods face bottlenecks in computational complexity and time efficiency when handling large-scale dynamic problems. Although existing reinforcement learning methods have achieved some progress, they still encounter several challenges: 1) Independent decoding across multiple vehicles fails to model joint action distributions; 2) The feature extraction network struggles to capture inter-entity relationships; 3) The joint action space is exponentially large. To address these issues, we designed the MAPT framework, which employs a Transformer Encoder to extract entity representations, combines a Transformer Decoder with a Pointer Network to generate joint action sequences in an AutoRegressive manner, and introduces a Relation-Aware Attention module to capture inter-entity relationships. Additionally, we guide the model's decision-making using informative priors to facilitate effective exploration. Experiments on 8 datasets demonstrate that MAPT significantly outperforms existing baseline methods in terms of performance and exhibits substantial computational time advantages compared to classical operations research methods.
Authors: Patryk Krukowski, Jan Miksa, Piotr Helm, Jacek Tabor, Pawe{\l} Wawrzy\'nski, Przemys{\l}aw Spurek
Abstract: Continual learning aims to enable neural networks to acquire new knowledge without forgetting previously learned information. While recent prompt-based methods perform strongly in class-incremental settings, they remain vulnerable under domain shifts, where the input distribution changes but the label space remains fixed. This exposes a persistent problem known as representation drift. Shared representations evolve in ways that overwrite previously useful features and cause forgetting even when prompts isolate task-specific parameters. To address this issue, we introduce InTAct, a method that preserves functional behavior in shared layers without freezing parameters or storing past data. InTAct captures the characteristic activation ranges associated with previously learned tasks and constrains updates to ensure the network remains consistent within these regions, while still allowing for flexible adaptation elsewhere. In doing so, InTAct stabilizes the functional role of important neurons rather than directly restricting parameter values. The approach is architecture-agnostic and integrates seamlessly into existing prompt-based continual learning frameworks. By regulating representation changes where past knowledge is encoded, InTAct achieves a principled balance between stability and plasticity. Across diverse domain-incremental benchmarks, including DomainNet and ImageNet-R, InTAct consistently reduces representation drift and improves performance, increasing Average Accuracy by up to 8 percentage points over state-of-the-art baselines.
Authors: Kyle M. Regan, Michael McLoughlin, Wayne A. Bryden, Gonzalo R. Arce
Abstract: Matrix Assisted Laser Desorption/Ionization Mass Spectrometry (MALDI-MS) is a cornerstone in biomolecular analysis, offering precise identification of pathogens through unique mass spectral signatures. Yet, its reliance on labor-intensive sample preparation and multi-shot spectral averaging restricts its use to laboratory settings, rendering it impractical for real-time environmental monitoring. These limitations are especially pronounced in emerging aerosol MALDI-MS systems, where autonomous sampling generates noisy spectra for unknown aerosol analytes, requiring single-shot detection for effective analysis. Addressing these challenges, we propose the Mass Spectral Dictionary-Guided Transformer (MS-DGFormer): a data-driven framework that redefines spectral analysis by directly processing raw, minimally prepared mass spectral data. MS-DGFormer leverages a transformer architecture, designed to capture the long-range dependencies inherent in these time-series spectra. To enhance feature extraction, we introduce a novel dictionary encoder that integrates denoised spectral information derived from Singular Value Decomposition (SVD), enabling the model to discern critical biomolecular patterns from single-shot spectra with robust performance. This innovation provides a system to achieve superior pathogen identification from aerosol samples, facilitating autonomous, real-time analysis in field conditions. By eliminating the need for extensive preprocessing, our method unlocks the potential for portable, deployable MALDI-MS platforms, revolutionizing environmental pathogen detection and rapid response to biological threats.
Authors: Siqi Liang, Yudi Zhang, Yue Guo
Abstract: We propose a novel framework for persona-based language model system, motivated by the need for personalized AI agents that adapt to individual user preferences. In our approach, the agent embodies the user's "persona" (e.g. user profile or taste) and is powered by a large language model (LLM). To enable the agent to leverage rich contextual information, we introduce a Knowledge-Graph-enhanced Retrieval-Augmented Generation (Graph RAG) mechanism that constructs an LLM-derived graph index of relevant documents and summarizes communities of related information. Our framework generates personalized prompts by combining: (1) a summary of the user's historical behaviors and preferences extracted from the knowledge graph, and (2) relevant global interaction patterns identified through graph-based community detection. This dynamic prompt engineering approach allows the agent to maintain consistent persona-aligned behaviors while benefiting from collective knowledge. On the LaMP benchmark, our method improves news categorization F1 by 11.1%, movie tagging F1 by 56.1%, and reduces product rating MAE by 10.4% over prior methods. Our code is available at https://anonymous.4open.science/r/PersonaAgentwGraphRAG-DE6F
URLs: https://anonymous.4open.science/r/PersonaAgentwGraphRAG-DE6F
Authors: Vinay Kanakeri, Shivam Bajaj, Ashwin Verma, Vijay Gupta, Aritra Mitra
Abstract: It is known that reinforcement learning (RL) is data-hungry. To improve sample-efficiency of RL, it has been proposed that the learning algorithm utilize data from 'approximately similar' processes. However, since the process models are unknown, identifying which other processes are similar poses a challenge. In this work, we study this problem in the context of the benchmark Linear Quadratic Regulator (LQR) setting. Specifically, we consider a setting with multiple agents, each corresponding to a copy of a linear process to be controlled. The agents' local processes can be partitioned into clusters based on similarities in dynamics and tasks. Combining ideas from sequential elimination and zeroth-order policy optimization, we propose a new algorithm that performs simultaneous clustering and learning to output a personalized policy (controller) for each cluster. Under a suitable notion of cluster separation that captures differences in closed-loop performance across systems, we prove that our approach guarantees correct clustering with high probability. Furthermore, we show that the sub-optimality gap of the policy learned for each cluster scales inversely with the size of the cluster, with no additional bias, unlike in prior works on collaborative learning-based control. Our work is the first to reveal how clustering can be used in data-driven control to learn personalized policies that enjoy statistical gains from collaboration but do not suffer sub-optimality due to inclusion of data from dissimilar processes. From a distributed implementation perspective, our method is attractive as it incurs only a mild logarithmic communication overhead.
Authors: Linus Stuhlmann, Mauricio Fadel Argerich, Jonathan F\"urst
Abstract: Running large language models (LLMs) locally is becoming increasingly common. While the growing availability of small open-source models and inference engines has lowered the entry barrier, users now face an overwhelming number of configuration choices. Identifying an optimal configuration -- balancing functional and non-functional requirements -- requires substantial manual effort. While several benchmarks target LLM inference, they are designed for narrow evaluation goals and not user-focused. They fail to integrate relevant system and task-specific metrics into a unified, easy-to-use benchmark that supports multiple inference engines, usage scenarios, and quantization levels. To address this gap, we present Bench360 -- Benchmarking Local LLM Inference from 360{\deg}. Bench360 allows users to easily define their own custom tasks along with datasets and relevant task-specific metrics and then automatically benchmarks selected LLMs, inference engines, and quantization levels across different usage scenarios (single stream, batch & server). Bench360 tracks a wide range of metrics, including (1) system metrics -- such as Computing Performance (e.g., latency, throughput), Resource Usage (e.g., energy per query), and Deployment (e.g., cold start time) -- and (2) task-specific metrics such as ROUGE, F1 score or accuracy. We demonstrate Bench360 on four common LLM tasks -- General Knowledge & Reasoning, QA, Summarization and Text-to-SQL -- across three hardware platforms and four state of the art inference engines. Our results reveal several interesting trade-offs between task performance and system-level efficiency, highlighting the differences in inference engines and models. Most importantly, there is no single best setup for local inference, which strongly motivates the need for a framework such as Bench360.
Authors: Samuel Frank, James Halverson, Anindita Maiti, Fabian Ruehle
Abstract: We introduce fermionic neural network field theories via Grassmann-valued neural networks. Free theories are obtained by a generalization of the Central Limit Theorem to Grassmann variables. This enables the realization of the free Dirac spinor at infinite width and a four fermion interaction at finite width. Yukawa couplings are introduced by breaking the statistical independence of the output weights for the fermionic and bosonic fields. A large class of interacting supersymmetric quantum mechanics and field theory models are introduced by super-affine transformations on the input that realize a superspace formalism.
Authors: Adeel Yousaf, Joseph Fioresi, James Beetham, Amrit Singh Bedi, Mubarak Shah
Abstract: Improving the safety of vision-language models like CLIP via fine-tuning often comes at a steep price, causing significant drops in their generalization performance. We find this trade-off stems from rigid alignment strategies that force unsafe concepts toward single, predefined safe targets, disrupting the model's learned semantic structure. To address this, we propose a proximity-aware approach: redirecting unsafe concepts to their semantically closest safe alternatives to minimize representational change. We introduce SaFeR-CLIP, a fine-tuning framework that applies this principle of minimal intervention. SaFeR-CLIP successfully reconciles safety and performance, recovering up to 8.0% in zero-shot accuracy over prior methods while maintaining robust safety. To support more rigorous evaluation, we also contribute NSFW-Caps, a new benchmark of 1,000 highly-aligned pairs for testing safety under distributional shift. Our work shows that respecting the geometry of pretrained representations is key to achieving safety without sacrificing performance.
Authors: Mona Khalil, Alberto Blanco-Justicia, Najeeb Jebreel, Josep Domingo-Ferrer
Abstract: Membership inference attacks (MIAs) against machine learning (ML) models aim to determine whether a given data point was part of the model training data. These attacks may pose significant privacy risks to individuals whose sensitive data were used for training, which motivates the use of defenses such as differential privacy, often at the cost of high accuracy losses. MIAs exploit the differences in the behavior of a model when making predictions on samples it has seen during training (members) versus those it has not seen (non-members). Several studies have pointed out that model overfitting is the major factor contributing to these differences in behavior and, consequently, to the success of MIAs. However, the literature also shows that even non-overfitted ML models can leak information about a small subset of their training data. In this paper, we investigate the root causes of membership inference vulnerabilities beyond traditional overfitting concerns and suggest targeted defenses. We empirically analyze the characteristics of the training data samples vulnerable to MIAs in models that are not overfitted (and hence able to generalize). Our findings reveal that these samples are often outliers within their classes (e.g., noisy or hard to classify). We then propose potential defensive strategies to protect these vulnerable samples and enhance the privacy-preserving capabilities of ML models. Our code is available at https://github.com/najeebjebreel/mia_analysis.
Authors: Liuyuan Jiang, Quan Xiao, Lisha Chen, Tianyi Chen
Abstract: Penalty-based methods have become popular for solving bilevel optimization (BLO) problems, thanks to their effective first-order nature. However, they often require inner-loop iterations to solve the lower-level (LL) problem and small outer-loop step sizes to handle the increased smoothness induced by large penalty terms, leading to suboptimal complexity. This work considers the general BLO problems with coupled constraints (CCs) and leverages a novel penalty reformulation that decouples the upper- and lower-level variables. This yields an improved analysis of the smoothness constant, enabling larger step sizes and reduced iteration complexity for Penalty-Based Gradient Descent algorithms in ALTernating fashion (ALT-PBGD). Building on the insight of reduced smoothness, we propose PBGD-Free, a novel fully single-loop algorithm that avoids inner loops for the uncoupled constraint BLO. For BLO with CCs, PBGD-Free employs an efficient inner-loop with substantially reduced iteration complexity. Furthermore, we propose a novel curvature condition describing the "flatness" of the upper-level objective with respect to the LL variable. This condition relaxes the traditional upper-level Lipschitz requirement, enables smaller penalty constant choices, and results in a negligible penalty gradient term during upper-level variable updates. We provide rigorous convergence analysis and validate the method's efficacy through hyperparameter optimization for support vector machines and fine-tuning of large language models.
Authors: Kyla D. Jones, Alexander W. Dowling
Abstract: We introduce the Bayesian Information-Theoretic Sampling for hierarchical GAussian Process Surrogates (BITS for GAPS) framework to emulate latent components in hybrid physical systems. BITS for GAPS supports serial hybrid modeling, where known physics governs part of the system and residual dynamics are represented as a latent function inferred from data. A Gaussian process prior is placed over the latent function, with hierarchical priors on its hyperparameters to encode physically meaningful structure in the predictive posterior. To guide data acquisition, we derive entropy-based acquisition functions that quantify expected information gain from candidate input locations, identifying samples most informative for training the surrogate. Specifically, we obtain a closed-form expression for the differential entropy of the predictive posterior and establish a tractable lower bound for efficient evaluation. These derivations approximate the predictive posterior as a finite, uniformly weighted mixture of Gaussian processes. We demonstrate the framework's utility by modeling activity coefficients in vapor-liquid equilibrium systems, embedding the surrogate into extended Raoult's law for distillation design. Numerical results show that entropy-guided sampling improves sample efficiency by targeting regions of high uncertainty and potential information gain. This accelerates surrogate convergence, enhances predictive accuracy in non-ideal regimes, and preserves physical consistency. Overall, BITS for GAPS provides an efficient, interpretable, and uncertainty-aware framework for hybrid modeling of complex physical systems.
Authors: Sang Truong, Yuheng Tu, Michael Hardy, Anka Reuel, Zeyu Tang, Jirayu Burapacheep, Jonathan Perera, Chibuike Uwakwe, Ben Domingue, Nick Haber, Sanmi Koyejo
Abstract: Benchmarks are pivotal in driving AI progress, and invalid benchmark questions frequently undermine their reliability. Manually identifying and correcting errors among thousands of benchmark questions is not only infeasible but also a critical bottleneck for reliable evaluation. In this work, we introduce a framework for systematic benchmark revision that leverages statistical analysis of response patterns to flag potentially invalid questions for further expert review. Our approach builds on a core assumption commonly used in AI evaluations that the mean score sufficiently summarizes model performance. This implies a unidimensional latent construct underlying the measurement experiment, yielding expected ranges for various statistics for each item. When empirically estimated values for these statistics fall outside the expected range for an item, the item is more likely to be problematic. Across nine widely used benchmarks, our method guides expert review to identify problematic questions with up to 84\% precision. In addition, we introduce an LLM-judge first pass to review questions, further reducing human effort. Together, these components provide an efficient and scalable framework for systematic benchmark revision.
Authors: Toufique Ahmed, Jatin Ganhotra, Avraham Shinnar, Martin Hirzel
Abstract: Automated program repair has been shown to be susceptible to generating repaired code that passes on seen tests but fails on a hold-out set of hidden tests. This problem, dubbed test overfitting, has been identified and studied before the rise of large language models. We experimentally study how much test overfitting is still a problem today, using repository-level SWE-bench tasks.
Authors: Loukas Sfountouris, Giannis Daras, Paris Giampouras
Abstract: Enforcing alignment between the internal representations of diffusion or flow-based generative models and those of pretrained self-supervised encoders has recently been shown to provide a powerful inductive bias, improving both convergence and sample quality. In this work, we extend this idea to inverse problems, where pretrained generative models are employed as priors. We propose applying representation alignment (REPA) between diffusion or flow-based models and a pretrained self-supervised visual encoder, such as DINOv2, to guide the reconstruction process at inference time. Although ground-truth signals are unavailable in inverse problems, we show that aligning model representations with approximate target features can substantially enhance reconstruction fidelity and perceptual realism. We provide theoretical results showing (a) the relation between the REPA regularization and a divergence measure in the DINOv2 embedding space, and (b) how REPA updates steer the model's internal representations toward those of the clean image. These results offer insights into the role of REPA in improving perceptual fidelity. Finally, we demonstrate the generality of our approach by integrating it into multiple state-of-the-art inverse problem solvers. Extensive experiments on super-resolution, box inpainting, Gaussian deblurring, and motion deblurring confirm that our method consistently improves reconstruction quality across tasks, while also providing substantial efficiency gains by reducing the number of required discretization steps without compromising the performance of the underlying solver.
Authors: Arip Asadulaev, Rayan Banerjee, Fakhri Karray, Martin Takac
Abstract: Recently, it was shown that small, looped architectures, such as Tiny Recursive Models (TRMs), can outperform Large Language Models (LLMs) on complex reasoning tasks, including the Abstraction and Reasoning Corpus (ARC). In this work, we investigate a core question: how can we further improve the efficiency of these methods with minimal changes? To address this, we frame the latent reasoning of TRMs as a form of classifier-free guidance and implicit policy improvement algorithm. Building on these insights, we propose a novel training scheme that provides a target for each loop during training. We demonstrate that our approach significantly enhances training efficiency. Our method reduces the total number of forward passes by 18x and eliminates halting mechanisms, while maintaining quality comparable to standard TRMs. Notably, we achieve 24% accuracy on ARC-1 with only 0.8M parameters, outperforming most LLMs.
Authors: Dailan He, Guanlin Feng, Xingtong Ge, Yazhe Niu, Yi Zhang, Bingqi Ma, Guanglu Song, Yu Liu, Hongsheng Li
Abstract: Group Relative Policy Optimization (GRPO) has shown promise in aligning image and video generative models with human preferences. However, applying it to modern flow matching models is challenging because of its deterministic sampling paradigm. Current methods address this issue by converting Ordinary Differential Equations (ODEs) to Stochastic Differential Equations (SDEs), which introduce stochasticity. However, this SDE-based GRPO suffers from issues of inefficient credit assignment and incompatibility with high-order solvers for fewer-step sampling. In this paper, we first reinterpret existing SDE-based GRPO methods from a distance optimization perspective, revealing their underlying mechanism as a form of contrastive learning. Based on this insight, we propose Neighbor GRPO, a novel alignment algorithm that completely bypasses the need for SDEs. Neighbor GRPO generates a diverse set of candidate trajectories by perturbing the initial noise conditions of the ODE and optimizes the model using a softmax distance-based surrogate leaping policy. We establish a theoretical connection between this distance-based objective and policy gradient optimization, rigorously integrating our approach into the GRPO framework. Our method fully preserves the advantages of deterministic ODE sampling, including efficiency and compatibility with high-order solvers. We further introduce symmetric anchor sampling for computational efficiency and group-wise quasi-norm reweighting to address reward flattening. Extensive experiments demonstrate that Neighbor GRPO significantly outperforms SDE-based counterparts in terms of training cost, convergence speed, and generation quality.
Authors: Jigyasa Gupta, Soumya Goyal, Anil Kumar, Ishan Jindal
Abstract: Synthesizing realistic cooked food images from raw inputs on edge devices is a challenging generative task, requiring models to capture complex changes in texture, color and structure during cooking. Existing image-to-image generation methods often produce unrealistic results or are too resource-intensive for edge deployment. We introduce the first oven-based cooking-progression dataset with chef-annotated doneness levels and propose an edge-efficient recipe and cooking state guided generator that synthesizes realistic food images conditioned on raw food image. This formulation enables user-preferred visual targets rather than fixed presets. To ensure temporal consistency and culinary plausibility, we introduce a domain-specific \textit{Culinary Image Similarity (CIS)} metric, which serves both as a training loss and a progress-monitoring signal. Our model outperforms existing baselines with significant reductions in FID scores (30\% improvement on our dataset; 60\% on public datasets)
Authors: Sai Nath Chowdary Medikonduru, Hongpeng Jin, Yanzhao Wu
Abstract: Plant diseases pose a significant threat to global agriculture, causing over $220 billion in annual economic losses and jeopardizing food security. The timely and accurate detection of these diseases from plant leaf images is critical to mitigating their adverse effects. Deep neural network Ensembles (Deep Ensembles) have emerged as a powerful approach to enhancing prediction accuracy by leveraging the strengths of diverse Deep Neural Networks (DNNs). However, selecting high-performing ensemble member models is challenging due to the inherent difficulty in measuring ensemble diversity. In this paper, we introduce the Synergistic Diversity (SQ) framework to enhance plant disease detection accuracy. First, we conduct a comprehensive analysis of the limitations of existing ensemble diversity metrics (denoted as Q metrics), which often fail to identify optimal ensemble teams. Second, we present the SQ metric, a novel measure that captures the synergy between ensemble members and consistently aligns with ensemble accuracy. Third, we validate our SQ approach through extensive experiments on a plant leaf image dataset, which demonstrates that our SQ metric substantially improves ensemble selection and enhances detection accuracy. Our findings pave the way for a more reliable and efficient image-based plant disease detection.
Authors: Wangqian Chen, Junting Chen, Shuguang Cui
Abstract: Machine learning (ML) has greatly advanced data-driven channel modeling and resource optimization in wireless communication systems. However, most existing ML-based methods rely on large, accurately labeled datasets with location information, which are often difficult and costly to obtain. This paper proposes a generative framework to recover location labels directly from sequences of sparse channel state information (CSI) measurements, without explicit location labels for radio map construction. Instead of directly storing raw CSI, we learn a compact low-dimensional radio map embedding and leverage a generative model to reconstruct the high-dimensional CSI. Specifically, to address the uncertainty of sparse CSI, a dual-scale feature extraction scheme is designed to enhance feature representation by jointly exploiting correlations from angular space and across neighboring samples. We develop a hybrid recurrent-convolutional encoder to learn mobility patterns, which combines a truncation strategy and multi-scale convolutions in the recurrent neural network (RNN) to ensure feature robustness against short-term fluctuations. Unlike conventional Gaussian priors in latent space, we embed a learnable radio map to capture the location information by encoding high-level positional features from CSI measurements. Finally, a diffusion-based generative decoder reconstructs the full CSI with high fidelity by conditioning on the positional features in the radio map. Numerical experiments demonstrate that the proposed model can improve localization accuracy by over 30% and achieve a 20% capacity gain in non-line-of-sight (NLOS) scenarios compared with model-based Kalman filter approaches.
Authors: Arnau Mir, Alejandro Mus, Juan Vicente Riera
Abstract: Discrete fuzzy numbers, and in particular those defined over a finite chain $L_n = \{0, \ldots, n\}$, have been effectively employed to represent linguistic information within the framework of fuzzy systems. Research on total (admissible) orderings of such types of fuzzy subsets, and specifically those belonging to the set $\mathcal{D}_1^{L_n\rightarrow Y_m}$ consisting of discrete fuzzy numbers $A$ whose support is a closed subinterval of the finite chain $L_n = \{0, 1, \ldots, n\}$ and whose membership values $A(x)$, for $x \in L_n$, belong to the set $Y_m = \{ 0 = y_1 < y_2 < \cdots < y_{m-1} < y_m = 1 \}$, has facilitated the development of new methods for constructing logical connectives, based on a bijective function, called $\textit{pos function}$, that determines the position of each $A \in \mathcal{D}_1^{L_n\rightarrow Y_m}$. For this reason, in this work we revisit the problem by introducing algorithms that exploit the combinatorial structure of total (admissible) orders to compute the $\textit{pos}$ function and its inverse with exactness. The proposed approach achieves a complexity of $\mathcal{O}(n^{2} m \log n)$, which is quadratic in the size of the underlying chain ($n$) and linear in the number of membership levels ($m$). The key point is that the dominant factor is $m$, ensuring scalability with respect to the granularity of membership values. The results demonstrate that this formulation substantially reduces computational cost and enables the efficient implementation of algebraic operations -- such as aggregation and implication -- on the set of discrete fuzzy numbers.
Authors: Javier Lazaro, Juan-Ignacio Vazquez, Pablo Garcia-Bringas
Abstract: Parameterised quantum circuit (PQC) based Quantum Reinforcement Learning (QRL) has emerged as a promising paradigm at the intersection of quantum computing and reinforcement learning (RL). By design, PQCs create hybrid quantum-classical models, but their practical applicability remains uncertain due to training instabilities, barren plateaus (BPs), and the difficulty of isolating the contribution of individual pipeline components. In this work, we dissect PQC based QRL architectures through a systematic experimental evaluation of three aspects recurrently identified as critical: (i) data embedding strategies, with Data Reuploading (DR) as an advanced approach; (ii) ansatz design, particularly the role of entanglement; and (iii) post-processing blocks after quantum measurement, with a focus on the underexplored Output Reuse (OR) technique. Using a unified PPO-CartPole framework, we perform controlled comparisons between hybrid and classical agents under identical conditions. Our results show that OR, though purely classical, exhibits distinct behaviour in hybrid pipelines, that DR improves trainability and stability, and that stronger entanglement can degrade optimisation, offsetting classical gains. Together, these findings provide controlled empirical evidence of the interplay between quantum and classical contributions, and establish a reproducible framework for systematic benchmarking and component-wise analysis in QRL.
Authors: Georgios Anyfantis, Pere Barlet-Ros
Abstract: Network Intrusion Detection Systems (NIDS) are essential tools for detecting network attacks and intrusions. While extensive research has explored the use of supervised Machine Learning for attack detection and characterisation, these methods require accurately labelled datasets, which are very costly to obtain. Moreover, existing public datasets have limited and/or outdated attacks, and many of them suffer from mislabelled data. To reduce the reliance on labelled data, we propose AutoGraphAD, a novel unsupervised anomaly detection approach based on a Heterogeneous Variational Graph Autoencoder. AutoGraphAD operates on heterogeneous graphs, made from connection and IP nodes that capture network activity within a time window. The model is trained using unsupervised and contrastive learning, without relying on any labelled data. The reconstruction, structural loss, and KL divergence are then weighted and combined in an anomaly score that is then used for anomaly detection. Overall, AutoGraphAD yields the same, and in some cases better, results than previous unsupervised approaches, such as Anomal-E, but without requiring costly downstream anomaly detectors. As a result, AutoGraphAD achieves around 1.18 orders of magnitude faster training and 1.03 orders of magnitude faster inference, which represents a significant advantage for operational deployment.
Authors: Jiaxun Fang, Li Zhang, Shaoyi Huang
Abstract: Systolic array accelerators execute CNNs with energy dominated by the switching activity of multiply accumulate (MAC) units. Although prior work exploits weight dependent MAC power for compression, existing methods often use global activation models, coarse energy proxies, or layer-agnostic policies, which limits their effectiveness on real hardware. We propose an energy aware, layer-wise compression framework that explicitly leverages MAC and layer level energy characteristics. First, we build a layer-aware MAC energy model that combines per-layer activation statistics with an MSB-Hamming distance grouping of 22-bit partial sum transitions, and integrate it with a tile-level systolic mapping to estimate convolution-layer energy. On top of this model, we introduce an energy accuracy co-optimized weight selection algorithm within quantization aware training and an energy-prioritized layer-wise schedule that compresses high energy layers more aggressively under a global accuracy constraint. Experiments on different CNN models demonstrate up to 58.6\% energy reduction with 2-3\% accuracy drop, outperforming a state-of-the-art power-aware baseline.
Authors: Qi Jiang, Xiaolong Qian, Yao Gao, Lei Sun, Kailun Yang, Zhonghua Yi, Wenyong Li, Ming-Hsuan Yang, Luc Van Gool, Kaiwei Wang
Abstract: Emerging deep-learning-based lens library pre-training (LensLib-PT) pipeline offers a new avenue for blind lens aberration correction by training a universal neural network, demonstrating strong capability in handling diverse unknown optical degradations. This work proposes the OmniLens++ framework, which resolves two challenges that hinder the generalization ability of existing pipelines: the difficulty of scaling data and the absence of prior guidance characterizing optical degradation. To improve data scalability, we expand the design specifications to increase the degradation diversity of the lens source, and we sample a more uniform distribution by quantifying the spatial-variation patterns and severity of optical degradation. In terms of model design, to leverage the Point Spread Functions (PSFs), which intuitively describe optical degradation, as guidance in a blind paradigm, we propose the Latent PSF Representation (LPR). The VQVAE framework is introduced to learn latent features of LensLib's PSFs, which is assisted by modeling the optical degradation process to constrain the learning of degradation priors. Experiments on diverse aberrations of real-world lenses and synthetic LensLib show that OmniLens++ exhibits state-of-the-art generalization capacity in blind aberration correction. Beyond performance, the AODLibpro is verified as a scalable foundation for more effective training across diverse aberrations, and LPR can further tap the potential of large-scale LensLib. The source code and datasets will be made publicly available at https://github.com/zju-jiangqi/OmniLens2.
Authors: Kesheng Chen, Wenjian Luo, Bang Zhang, Zeping Yin, Zipeng Ye
Abstract: Episodic rewards present a significant challenge in reinforcement learning. While intrinsic reward methods have demonstrated effectiveness in single-agent rein-forcement learning scenarios, their application to multi-agent reinforcement learn-ing (MARL) remains problematic. The primary difficulties stem from two fac-tors: (1) the exponential sparsity of joint action trajectories that lead to rewards as the exploration space expands, and (2) existing methods often fail to account for joint actions that can influence team states. To address these challenges, this paper introduces Mutual Intrinsic Reward (MIR), a simple yet effective enhancement strategy for MARL with extremely sparse rewards like episodic rewards. MIR incentivizes individual agents to explore actions that affect their teammates, and when combined with original strategies, effectively stimulates team exploration and improves algorithm performance. For comprehensive experimental valida-tion, we extend the representative single-agent MiniGrid environment to create MiniGrid-MA, a series of MARL environments with sparse rewards. Our evalu-ation compares the proposed method against state-of-the-art approaches in the MiniGrid-MA setting, with experimental results demonstrating superior perfor-mance.
Authors: Mario Markov (INSAIT, Sofia University), Stefan Maria Ailuro (INSAIT, Sofia University), Luc Van Gool (INSAIT, Sofia University), Konrad Schindler (ETH Zurich), Danda Pani Paudel (INSAIT, Sofia University, ETH Zurich)
Abstract: Predicting wildfire risk is a reasoning-intensive spatial problem that requires the integration of visual, climatic, and geographic factors to infer continuous risk maps. Existing methods lack the causal reasoning and multimodal understanding required for reliable generalization. We introduce $\textbf{FireScope-Bench}$, a large-scale dataset and benchmark that couples Sentinel-2 imagery and climate data with expert-defined risk rasters across the USA, and real wildfire events in Europe for cross-continental evaluation. Building on this dataset, we propose $\textbf{FireScope}$, a VLM-based reasoning-to-generation framework that learns from both reinforcement learning and visual supervision to predict risk rasters with complementary reasoning traces. When trained in the USA and tested in Europe, $\textbf{FireScope}$ achieves substantial performance gains, while expert feedback and automated analysis confirm that its reasoning traces are faithful and semantically meaningful. Our findings demonstrate that reasoning can ground raster prediction models, improving both generalization and interpretability. To our knowledge, this is the first framework to (1) demonstrate that language-based reasoning can improve generalization in visual generation, (2) propose a high-resolution wildfire risk model that can be applied across continents, and (3) enable systematic studies of robust cross-continental generalization for multimodal fire risk models. We believe that $\textbf{FireScope-Bench}$ has the potential to serve as a foundation for advancing reasoning-driven, interpretable and generalizable spatial modeling. Data and source code will be made publicly available.
Authors: Rodrigo Almeida, Noelia Otero, Miguel-\'Angel Fern\'andez-Torres, Jackie Ma
Abstract: Accurate prediction of extreme weather events remains a major challenge for artificial intelligence based weather prediction systems. While deterministic models such as FuXi, GraphCast, and SFNO have achieved competitive forecast skill relative to numerical weather prediction, their ability to represent uncertainty and capture extremes is still limited. This study investigates how state of the art deterministic artificial intelligence based models respond to initial-condition perturbations and evaluates the resulting ensembles in forecasting extremes. Using three perturbation strategies (Gaussian noise, Hemispheric Centered Bred Vectors, and Huge Ensembles), we generate 50 member ensembles for two major events in August 2022: the Pakistan floods and the China heatwave. Ensemble skill is assessed against ERA5 and compared with IFS ENS and the probabilistic AIFSENS model using deterministic and probabilistic metrics. Results show that flow dependent perturbations produce the most realistic ensemble spread and highest probabilistic skill, narrowing but not closing the performance gap with numerical weather prediction ensembles. Across variables, artificial intelligence based weather models capture temperature extremes more effectively than precipitation. These findings demonstrate that input perturbations can extend deterministic models toward probabilistic forecasting, paving the way for approaches that combine flow dependent perturbations with generative or latent-space uncertainty modeling for reliable artificial intelligence-driven early warning systems.
Authors: Dragos-Alexandru Boldisor, Stefan Smeu, Dan Oneata, Elisabeta Oneata
Abstract: Self-supervised representations excel at many vision and speech tasks, but their potential for audio-visual deepfake detection remains underexplored. Unlike prior work that uses these features in isolation or buried within complex architectures, we systematically evaluate them across modalities (audio, video, multimodal) and domains (lip movements, generic visual content). We assess three key dimensions: detection effectiveness, interpretability of encoded information, and cross-modal complementarity. We find that most self-supervised features capture deepfake-relevant information, and that this information is complementary. Moreover, models primarily attend to semantically meaningful regions rather than spurious artifacts. Yet none generalize reliably across datasets. This generalization failure likely stems from dataset characteristics, not from the features themselves latching onto superficial patterns. These results expose both the promise and fundamental challenges of self-supervised representations for deepfake detection: while they learn meaningful patterns, achieving robust cross-domain performance remains elusive.
Authors: Yusuf \c{C}elebi, Mahmoud El Hussieni, \"Ozay Ezerceli
Abstract: This study presents PARROT (Persuasion and Agreement Robustness Rating of Output Truth), a robustness focused framework designed to measure the degradation in accuracy that occurs under social pressure exerted on users through authority and persuasion in large language models (LLMs) the phenomenon of sycophancy (excessive conformity). PARROT (i) isolates causal effects by comparing the neutral version of the same question with an authoritatively false version using a double-blind evaluation, (ii) quantifies confidence shifts toward the correct and imposed false responses using log-likelihood-based calibration tracking, and (iii) systematically classifies failure modes (e.g., robust correct, sycophantic agreement, reinforced error, stubborn error, self-correction, etc.) using an eight-state behavioral taxonomy. We evaluated 22 models using 1,302 MMLU-style multiple-choice questions across 13 domains and domain-specific authority templates. Findings show marked heterogeneity: advanced models (e.g., GPT-5, GPT-4.1, Claude Sonnet 4.5) exhibit low "follow rates" ($\leq 11\%$, GPT-5: 4\%) and minimal accuracy loss, while older/smaller models show severe epistemic collapse (GPT-4: 80\%, Qwen 2.5-1.5B: 94\%). The danger is not limited to response changes; weak models reduce confidence in the correct response while increasing confidence in the imposed incorrect response. While international law and global knowledge at the domain level exhibit high fragility, elementary mathematics is relatively resilient. Consequently, we argue that the goal of "resistance to overfitting pressure" should be addressed as a primary objective alongside accuracy, harm avoidance, and privacy for safe deployment in the real world.
Authors: Yu-Qin Chen, Shi-Xin Zhang
Abstract: Artificial intelligence in dynamic, real-world environments requires the capacity for continual learning. However, standard deep learning suffers from a fundamental issue: loss of plasticity, in which networks gradually lose their ability to learn from new data. Here we show that quantum learning models naturally overcome this limitation, preserving plasticity over long timescales. We demonstrate this advantage systematically across a broad spectrum of tasks from multiple learning paradigms, including supervised learning and reinforcement learning, and diverse data modalities, from classical high-dimensional images to quantum-native datasets. Although classical models exhibit performance degradation correlated with unbounded weight and gradient growth, quantum neural networks maintain consistent learning capabilities regardless of the data or task. We identify the origin of the advantage as the intrinsic physical constraints of quantum models. Unlike classical networks where unbounded weight growth leads to landscape ruggedness or saturation, the unitary constraints confine the optimization to a compact manifold. Our results suggest that the utility of quantum computing in machine learning extends beyond potential speedups, offering a robust pathway for building adaptive artificial intelligence and lifelong learners.
Authors: Hoang Ta, Jonathan Scarlett
Abstract: We study the problem of learning an unknown graph via group queries on node subsets, where each query reports whether at least one edge is present among the queried nodes. In general, learning arbitrary graphs with \(n\) nodes and \(k\) edges is hard in the non-adaptive setting, requiring \(\Omega\big(\min\{k^2\log n,\,n^2\}\big)\) tests even when a small error probability is allowed. We focus on learning Erd\H{o}s--R\'enyi (ER) graphs \(G\sim\ER(n,q)\) in the non-adaptive setting, where the expected number of edges is \(\bar{k}=q\binom{n}{2}\), and we aim to design an efficient testing--decoding scheme achieving asymptotically vanishing error probability. Prior work (Li--Fresacher--Scarlett, NeurIPS 2019) presents a testing--decoding scheme that attains an order-optimal number of tests \(O(\bar{k}\log n)\) but incurs \(\Omega(n^2)\) decoding time, whereas their proposed sublinear-time algorithm incurs an extra \((\log \bar{k})(\log n)\) factor in the number of tests. We extend the binary splitting approach, recently developed for non-adaptive group testing, to the ER graph learning setting, and prove that the edge set can be recovered with high probability using \(O(\bar{k}\log n)\) tests while attaining decoding time \(O(\bar{k}^{1+\delta}\log n)\) for any fixed \(\delta>0\).
Authors: Mohammed Alnemari
Abstract: This paper presents a novel framework combining group equivariant convolutional neural networks (G-CNNs) with equivariant-aware structured pruning to produce compact, transformation-invariant models for resource-constrained environments. Equivariance to rotations is achieved through the C4 cyclic group via the e2cnn library,enabling consistent performance under geometric transformations while reducing computational overhead. Our approach introduces structured pruning that preserves equivariant properties by analyzing e2cnn layer structure and applying neuron-level pruning to fully connected components. To mitigate accuracy degradation, we implement adaptive fine-tuning that automatically triggers when accuracy drop exceeds 2%, using early stopping and learning rate scheduling for efficient recovery. The framework includes dynamic INT8 quantization and a comprehensive pipeline encompassing training, knowledge distillation, structured pruning, fine-tuning, and quantization. We evaluate our method on satellite imagery (EuroSAT) and standard benchmarks (CIFAR-10, Rotated MNIST) demonstrating effectiveness across diverse domains. Experimental results show 29.3% parameter reduction with significant accuracy recovery, demonstrating that structured pruning of equivariant networks achieves substantial compression while maintaining geometric robustness. Our pipeline provides a reproducible framework for optimizing equivariant models, bridging the gap between group-theoretic network design and practical deployment constraints, with particular relevance to satellite imagery analysis and geometric vision tasks.
Authors: Thorsten Buss, Henry Day-Hall, Frank Gaede, Gregor Kasieczka, Katja Kr\"uger, Anatolii Korol, Thomas Madlener, Peter McKeown
Abstract: The physics programs of current and future collider experiments necessitate the development of surrogate simulators for calorimeter showers. While much progress has been made in the development of generative models for this task, they have typically been evaluated in simplified scenarios and for single particles. This is particularly true for the challenging task of highly granular calorimeter simulation. For the first time, this work studies the use of highly granular generative calorimeter surrogates in a realistic simulation application. We introduce DDML, a generic library which enables the combination of generative calorimeter surrogates with realistic detectors implemented using the DD4hep toolkit. We compare two different generative models - one operating on a regular grid representation, and the other using a less common point cloud approach. In order to disentangle methodological details from model performance, we provide comparisons to idealized simulators which directly sample representations of different resolutions from the full simulation ground-truth. We then systematically evaluate model performance on post-reconstruction benchmarks for electromagnetic shower simulation. Beginning with a typical single particle study, we introduce a first multi-particle benchmark based on di-photon separations, before studying a first full-physics benchmark based on hadronic decays of the tau lepton. Our results indicate that models operating on a point cloud can achieve a favorable balance between speed and accuracy for highly granular calorimeter simulation compared to those which operate on a regular grid representation.
Authors: David Nordstr\"om, Johan Edstedt, Fredrik Kahl, Georg B\"okman
Abstract: Self-supervised learning on images seeks to extract meaningful visual representations from unlabeled data. When scaled to large datasets, this paradigm has achieved state-of-the-art performance and the resulting trained models such as DINOv3 have seen widespread adoption. However, most prior efforts are optimized for semantic understanding rather than geometric reasoning. One important exception is Cross-View Completion, CroCo, which is a form of masked autoencoding (MAE) tailored for 3D understanding. In this work, we continue on the path proposed by CroCo and focus on learning features tailored for 3D vision. In a nutshell, we extend MAE to arbitrarily many views of the same scene. By uniformly masking all views and employing a lightweight decoder with inter-frame attention, our approach is inherently simpler and more scalable than CroCo. We evaluate the resulting model, MuM, extensively on downstream tasks including feedforward reconstruction, dense image matching and relative pose estimation, finding that it outperforms the state-of-the-art visual encoders DINOv3 and CroCo v2.
Authors: Mikael Lundb\"ack, Erik Wallin, Carola H\"aggstr\"om, Mattias Nystr\"om, Andreas Gr\"onlund, Mats Richardson, Petrus J\"onsson, William Arnvik, Lucas Hedstr\"om, Arvid F\"alldin, Martin Servin
Abstract: We present FORWARD, a high-resolution multimodal dataset of a cut-to-length forwarder operating in rough terrain on two harvest sites in the middle part of Sweden. The forwarder is a large Komatsu model equipped with a variety of sensors, including RTK-GNSS, 360-camera, operator vibration sensors, internal CAN-bus signal recording, and multiple IMUs. The data includes event time logs recorded in 5 Hz with e.g., driving speed, fuel consumption, vehicle position with centimeter accuracy, and crane use while the vehicle operates in forest areas laser-scanned with very high-resolution, $\sim$1500 points per square meter. Production log files (StanForD standard) with time-stamped machine events, extensive video material, and terrain data in various formats are included as well. About 18 hours of regular wood extraction work during three days is annotated from 360-video material into individual work elements and included in the dataset. We also include scenario specifications of conducted experiments on forest roads and in terrain. Scenarios include repeatedly driving the same routes with and without steel tracks, different load weight, and different target driving speeds. The dataset is intended for developing models and algorithms for trafficability, perception, and autonomous control of forest machines using artificial intelligence, simulation, and experiments on physical testbeds. In part, we focus on forwarders traversing terrain, avoiding obstacles, and loading or unloading logs, with consideration for efficiency, fuel consumption, safety, and environmental impact. Other benefits of the open dataset include the ability to explore auto-generation and calibration of forestry machine simulators and automation scenario descriptions using the data recorded in the field.
Authors: Emma Andrews, Prabhat Mishra
Abstract: Classical autoencoders are widely used to learn features of input data. To improve the feature learning, classical masked autoencoders extend classical autoencoders to learn the features of the original input sample in the presence of masked-out data. While quantum autoencoders exist, there is no design and implementation of quantum masked autoencoders that can leverage the benefits of quantum computing and quantum autoencoders. In this paper, we propose quantum masked autoencoders (QMAEs) that can effectively learn missing features of a data sample within quantum states instead of classical embeddings. We showcase that our QMAE architecture can learn the masked features of an image and can reconstruct the masked input image with improved visual fidelity in MNIST images. Experimental evaluation highlights that QMAE can significantly outperform (12.86% on average) in classification accuracy compared to state-of-the-art quantum autoencoders in the presence of masks.
Authors: Zheng Wang, Yi Zhang, Siddartha Khastgir, Carsten Maple, Xingyu Zhao
Abstract: Deep learning (DL) models, despite their remarkable success, remain vulnerable to small input perturbations that can cause erroneous outputs, motivating the recent proposal of probabilistic robustness (PR) as a complementary alternative to adversarial robustness (AR). However, existing PR formulations assume a fixed and known perturbation distribution, an unrealistic expectation in practice. To address this limitation, we propose non-parametric probabilistic robustness (NPPR), a more practical PR metric that does not rely on any predefined perturbation distribution. Following the non-parametric paradigm in statistical modeling, NPPR learns an optimized perturbation distribution directly from data, enabling conservative PR evaluation under distributional uncertainty. We further develop an NPPR estimator based on a Gaussian Mixture Model (GMM) with Multilayer Perceptron (MLP) heads and bicubic up-sampling, covering various input-dependent and input-independent perturbation scenarios. Theoretical analyses establish the relationships among AR, PR, and NPPR. Extensive experiments on CIFAR-10, CIFAR-100, and Tiny ImageNet across ResNet18/50, WideResNet50 and VGG16 validate NPPR as a more practical robustness metric, showing up to 40\% more conservative (lower) PR estimates compared to assuming those common perturbation distributions used in state-of-the-arts.
Authors: Sajad Movahedi, Timur Carstensen, Arshia Afzal, Frank Hutter, Antonio Orvieto, Volkan Cevher
Abstract: Position information is essential for language modeling. In softmax transformers, Rotary Position Embeddings (\textit{RoPE}) encode positions through \textit{fixed-angle} rotations, while in linear transformers, order is handled via input-dependent (selective) gating that decays past key-value associations. Selectivity has generally been shown to improve language-related tasks. Inspired by this, we introduce \textit{Selective RoPE}, an \textit{input-dependent} rotary embedding mechanism, that generalizes \textit{RoPE}, and enables rotation in \textit{arbitrary angles} for both linear and softmax transformers. We show that softmax attention already performs a hidden form of these rotations on query-key pairs, uncovering an implicit positional structure. We further show that in state-space models and gated linear transformers, the real part manages forgetting while the imaginary part encodes positions through rotations. We validate our method by equipping gated transformers with \textit{Selective RoPE}, demonstrating that its input-dependent rotations improve performance in language modeling and on difficult sequence tasks like copying, state tracking, and retrieval.
Authors: Nathalie Kirch, Samuel Dower, Adrians Skapars, Ekdeep Singh Lubana, Dmitrii Krasheninnikov
Abstract: Probing has emerged as a promising method for monitoring Large Language Models (LLMs), enabling inference-time detection of concerning behaviours such as deception and sycophancy. However, natural examples of many behaviours are rare, forcing researchers to rely on synthetic or off-policy LLM responses for training probes. We systematically evaluate how the use of synthetic and off-policy data influences probe generalisation across eight distinct LLM behaviours. Testing linear and attention probes across multiple LLMs, we find that the response generation strategy can significantly affect probe performance, though the magnitude of this effect varies by behaviour. We find that successful generalisation from off-policy data, to test sets where the model is incentivised to produce the target behaviour, is predictive of successful on-policy generalisation. Leveraging this result, we predict that Deception and Sandbagging probes may fail to generalise from off-policy to on-policy data when used in real monitoring scenarios. Notably, shifts in the training data domain still cause even larger performance degradation, with different-domain test scores being consistently lower than the same-domain ones. These results indicate that, in the absence of on-policy data, using same-domain off-policy data yields more reliable probes than using on-policy data from a different domain, emphasizing the need for methods that can better handle distribution shifts in LLM monitoring.
Authors: Nikolay Nikolov, Giuliano Albanese, Sombit Dey, Aleksandar Yanev, Luc Van Gool, Jan-Nico Zaech, Danda Pani Paudel
Abstract: Robotic Foundation Models (RFMs) hold great promise as generalist, end-to-end systems for robot control. Yet their ability to generalize across new environments, tasks, and embodiments remains limited. We argue that a major bottleneck lies in their foundations: most RFMs are built by fine-tuning internet-pretrained Vision-Language Models (VLMs). However, these VLMs are trained on 2D image-language tasks and lack the 3D spatial reasoning inherently required for embodied control in the 3D world. Bridging this gap directly with large-scale robotic data is costly and difficult to scale. Instead, we propose to enrich easy-to-collect non-robotic image data with 3D annotations and enhance a pretrained VLM with 3D understanding capabilities. Following this strategy, we train SPEAR-VLM, a 3D-aware VLM that infers object coordinates in 3D space from a single 2D image. Building on SPEAR-VLM, we introduce our main contribution, $~\textbf{SPEAR-1}$: a robotic foundation model that integrates grounded 3D perception with language-instructed embodied control. Trained on $\sim$45M frames from 24 Open X-Embodiment datasets, SPEAR-1 outperforms or matches state-of-the-art models such as $\pi_0$-FAST and $\pi_{0.5}$, while it uses 20$\times$ fewer robot demonstrations. This carefully-engineered training strategy unlocks new VLM capabilities and as a consequence boosts the reliability of embodied control beyond what is achievable with only robotic data. We make our model weights and 3D-annotated datasets publicly available.
Authors: Soroush Javdan, Pragash Krishnamoorthy, Olga Baysal
Abstract: The rapid evolution of the telecommunication industry necessitates efficient troubleshooting processes to maintain network reliability, software maintainability, and service quality. Trouble Reports (TRs), which document issues in Ericsson's production system, play a critical role in facilitating the timely resolution of software faults. However, the complexity and volume of TR data, along with the presence of diverse criteria that reflect different aspects of each fault, present challenges for retrieval systems. Building on prior work at Ericsson, which utilized a two-stage workflow, comprising Initial Retrieval (IR) and Re-Ranking (RR) stages, this study investigates different TR observation criteria and their impact on the performance of retrieval models. We propose \textbf{CREST} (\textbf{C}riteria-specific \textbf{R}etrieval via \textbf{E}nsemble of \textbf{S}pecialized \textbf{T}R models), a criterion-driven retrieval approach that leverages specialized models for different TR fields to improve both effectiveness and interpretability, thereby enabling quicker fault resolution and supporting software maintenance. CREST utilizes specialized models trained on specific TR criteria and aggregates their outputs to capture diverse and complementary signals. This approach leads to enhanced retrieval accuracy, better calibration of predicted scores, and improved interpretability by providing relevance scores for each criterion, helping users understand why specific TRs were retrieved. Using a subset of Ericsson's internal TRs, this research demonstrates that criterion-specific models significantly outperform a single model approach across key evaluation metrics. This highlights the importance of all targeted criteria used in this study for optimizing the performance of retrieval systems.
Authors: Seth Siriya, Jingge Zhu, Dragan Ne\v{s}i\'c, Ye Pu
Abstract: We consider the adaptive control problem for discrete-time, nonlinear stochastic systems with linearly parameterised uncertainty. Assuming access to a parameterised family of controllers that can stabilise the system in a bounded set within an informative region of the state space when the parameter is well-chosen, we propose a certainty equivalence learning-based adaptive control strategy, and subsequently derive stability bounds on the closed-loop system that hold for some probabilities. We then show that if the entire state space is informative, and the family of controllers is globally stabilising with appropriately chosen parameters, high probability stability guarantees can be derived.
Authors: Zhen Wang, Zhifeng Gao, Guolin Ke
Abstract: Test-time scaling has been shown to substantially improve large language models' (LLMs) mathematical reasoning. However, for a large portion of mathematical corpora, especially theorem proving, RLVR's scalability is limited: intermediate reasoning is crucial, while final answers are difficult to directly and reliably verify. Meanwhile, token-level SFT often degenerates into rote memorization rather than inducing longer chains of thought. Inspired by BERT's self-supervised tasks, we propose MR-RLVR (Masked-and-Reordered RLVR), which constructs process-level self-supervised rewards via "masked-then-fill" and "step reordering" to extract learnable signals from intermediate reasoning. Our training pipeline comprises two stages: we first perform self-supervised training on sampled mathematical calculation and proof data; we then conduct RLVR fine-tuning on mathematical calculation datasets where only outcomes are verifiable. We implement MR-RLVR on Qwen2.5-3B and DeepSeek-R1-Distill-Qwen-1.5B, and evaluate on AIME24, AIME25, AMC23, and MATH500. Under a fixed sampling and decoding budget, MR-RLVR achieves average relative gains over the original RLVR of +9.86% Pass@1, +5.27% Pass@5, and +4.00% Pass@8. These results indicate that incorporating process-aware self-supervised signals can effectively enhance RLVR's scalability and performance in only outcome-verifiable settings.
Authors: Andy Wu, Sanjiva K. Lele
Abstract: Neural network subgrid stress models often have a priori performance that is far better than the a posteriori performance, leading to neural network models that look very promising a priori completely failing in a posteriori Large Eddy Simulations (LES). This performance gap can be decreased by combining two different methods, training data augmentation and reducing input complexity to the neural network. Augmenting the training data with two different filters before training the neural networks has no performance degradation a priori as compared to a neural network trained with one filter. A posteriori, neural networks trained with two different filters are far more robust across two different LES codes with different numerical schemes. In addition, by ablating away the higher order terms input into the neural network, the a priori versus a posteriori performance changes become less apparent. When combined, neural networks that use both training data augmentation and a less complex set of inputs have a posteriori performance far more reflective of their a priori evaluation.
Authors: Ying Wu, Hanzhong Liu, Kai Ren, Shujie Ma, Xiangyu Chang
Abstract: Interpretability plays a crucial role in the application of statistical learning to estimate heterogeneous treatment effects (HTE) in complex diseases. In this study, we leverage a rule-based workflow, namely causal rule learning (CRL), to estimate and improve our understanding of HTE for atrial septal defect, addressing an overlooked question in the previous literature: what if an individual simultaneously belongs to multiple groups with different average treatment effects? The CRL process consists of three steps: rule discovery, which generates a set of causal rules with corresponding subgroup average treatment effects; rule selection, which identifies a subset of these rules to deconstruct individual-level treatment effects as a linear combination of subgroup-level effects; and rule analysis, which presents a detailed procedure for further analyzing each selected rule from multiple perspectives to identify the most promising rules for validation. Extensive simulation studies and real-world data analysis demonstrate that CRL outperforms other methods in providing interpretable estimates of HTE, especially when dealing with complex ground truth and sufficient sample sizes.
Authors: Keith Burghardt, Daniel M. T. Fessler, Chyna Tang, Anne Pisor, Kristina Lerman
Abstract: Socio-linguistic indicators of affectively-relevant phenomena, such as emotion or sentiment, are often extracted from text to better understand features of human-computer interactions, including on social media. However, an indicator that is often overlooked is the presence or absence of information concerning harms or hazards. Here, we develop a new model to detect information concerning hazards, trained on a new collection of annotated X posts. We show that not only does this model perform well (outperforming, e.g., dictionary approaches), but that the hazard information it extracts is not strongly correlated with common indicators. To demonstrate the utility of our tool, we apply it to two datasets of X posts that discuss important geopolitical events, namely the Israel-Hamas war and the 2022 French national election. In both cases, we find that hazard information, especially information concerning conflict, is common. We extract accounts associated with information campaigns from each data set to explore how information about hazards could be used to attempt to influence geopolitical events. We find that inorganic accounts representing the viewpoints of weaker sides in a conflict often discuss hazards to civilians, potentially as a way to elicit aid for the weaker side. Moreover, the rate at which these hazards are mentioned differs markedly from organic accounts, likely reflecting information operators' efforts to frame the given geopolitical event for strategic purposes. These results are first steps towards exploring hazards within an information warfare environment. The model is shared as a Python package to help researchers and journalists analyze hazard content. The model, along with data and annotations, is available in the following repository: https://github.com/KeithBurghardt/DetectHazards.
Authors: Lorenzo Chicchi, Lorenzo Buffoni, Diego Febbe, Lorenzo Giambagli, Raffaele Marino, Duccio Fanelli
Abstract: In machine learning practice it is often useful to identify relevant input features. Isolating key input elements, ranked according their respective degree of relevance, can help to elaborate on the process of decision making. Here, we propose a novel method to estimate the relative importance of the input components for a Deep Neural Network. This is achieved by leveraging on a spectral re-parametrization of the optimization process. Eigenvalues associated to input nodes provide in fact a robust proxy to gauge the relevance of the supplied entry features. Notably, the spectral features ranking is performed automatically, as a byproduct of the network training, with no additional processing to be carried out. Moreover, by leveraging on the regularization of the eigenvalues, it is possible to enforce solutions making use of a minimum subset of the input components, increasing the explainability of the model and providing sparse input representations. The technique is compared to the most common methods in the literature and is successfully challenged against both synthetic and real data.
Authors: Kiran Smelser, Jacob Miller, Stephen Kobourov
Abstract: Stress is among the most commonly employed quality metrics and optimization criteria for dimension reduction projections of high dimensional data. Complex, high dimensional data is ubiquitous across many scientific disciplines, including machine learning, biology, and the social sciences. One of the primary methods of visualizing these datasets is with two dimensional scatter plots that visually capture some properties of the data. Because visually determining the accuracy of these plots is challenging, researchers often use quality metrics to measure projection accuracy or faithfulness to the full data. One of the most commonly employed metrics, normalized stress, is sensitive to uniform scaling of the projection, despite this act not meaningfully changing anything about the projection. We investigate the effect of scaling on stress and other distance based quality metrics analytically and empirically by showing just how much the values change and how this affects dimension reduction technique evaluations. We introduce a simple technique to make normalized stress scale invariant and show that it accurately captures expected behavior on a small benchmark.
Authors: Alejandro Polo-Molina, David Alfaya, Jose Portela
Abstract: Artificial Neural Networks (ANNs) have significantly advanced various fields by effectively recognizing patterns and solving complex problems. Despite these advancements, their interpretability remains a critical challenge, especially in applications where transparency and accountability are essential. To address this, explainable AI (XAI) has made progress in demystifying ANNs, yet interpretability alone is often insufficient. In certain applications, model predictions must align with expert-imposed requirements, sometimes exemplified by partial monotonicity constraints. While monotonic approaches are found in the literature for traditional Multi-layer Perceptrons (MLPs), they still face difficulties in achieving both interpretability and certified partial monotonicity. Recently, the Kolmogorov-Arnold Network (KAN) architecture, based on learnable activation functions parametrized as splines, has been proposed as a more interpretable alternative to MLPs. Building on this, we introduce a novel ANN architecture called MonoKAN, which is based on the KAN architecture and achieves certified partial monotonicity while enhancing interpretability. To achieve this, we employ cubic Hermite splines, which guarantee monotonicity through a set of straightforward conditions. Additionally, by using positive weights in the linear combinations of these splines, we ensure that the network preserves the monotonic relationships between input and output. Our experiments demonstrate that MonoKAN not only enhances interpretability but also improves predictive performance across the majority of benchmarks, outperforming state-of-the-art monotonic MLP approaches.
Authors: Yida Xiong, Kun Li, Jiameng Chen, Hongzhi Zhang, Di Lin, Yan Che, Wenbin Hu
Abstract: Molecular optimization (MO) is a crucial stage in drug discovery in which task-oriented generated molecules are optimized to meet practical industrial requirements. Existing mainstream MO approaches primarily utilize external property predictors to guide iterative property optimization. However, learning all molecular samples in the vast chemical space is unrealistic for predictors. As a result, errors and noise are inevitably introduced during property prediction due to the nature of approximation. This leads to discrepancy accumulation, generalization reduction and suboptimal molecular candidates. In this paper, we propose a text-guided multi-property molecular optimization method utilizing transformer-based diffusion language model (TransDLM). TransDLM leverages standardized chemical nomenclature as semantic representations of molecules and implicitly embeds property requirements into textual descriptions, thereby mitigating error propagation during diffusion process. By fusing physically and chemically detailed textual semantics with specialized molecular representations, TransDLM effectively integrates diverse information sources to guide precise optimization, which enhances the model's ability to balance structural retention and property enhancement. Additionally, the success of a case study further demonstrates TransDLM's ability to solve practical problems. Experimentally, our approach surpasses state-of-the-art methods in maintaining molecular structural similarity and enhancing chemical properties on the benchmark dataset.
Authors: Zhenjiang Mao, Mrinall Eashaan Umasudhan, Ivan Ruchkin
Abstract: Learning predictive models from high-dimensional sensory observations is fundamental for cyber-physical systems, yet the latent representations learned by standard world models lack physical interpretability. This limits their reliability, generalizability, and applicability to safety-critical tasks. We introduce Physically Interpretable World Models (PIWM), a framework that aligns latent representations with real-world physical quantities and constrains their evolution through partially known physical dynamics. Physical interpretability in PIWM is defined by two complementary properties: (i) the learned latent state corresponds to meaningful physical variables, and (ii) its temporal evolution follows physically consistent dynamics. To achieve this without requiring ground-truth physical annotations, PIWM employs weak distribution-based supervision that captures state uncertainty naturally arising from real-world sensing pipelines. The architecture integrates a VQ-based visual encoder, a transformer-based physical encoder, and a learnable dynamics model grounded in known physical equations. Across three case studies (Cart Pole, Lunar Lander, and Donkey Car), PIWM achieves accurate long-horizon prediction, recovers true system parameters, and significantly improves physical grounding over purely data-driven models. These results demonstrate the feasibility and advantages of learning physically interpretable world models directly from images under weak supervision.
Authors: Yacouba Kaloga, Shashi Kumar, Petr Motlicek, Ina Kodrasi
Abstract: Accurate sequence-to-sequence (seq2seq) alignment is critical for applications like medical speech analysis and language learning tools relying on automatic speech recognition (ASR). State-of-the-art end-to-end (E2E) ASR systems, such as the Connectionist Temporal Classification (CTC) and transducer-based models, suffer from peaky behavior and alignment inaccuracies. In this paper, we propose a novel differentiable alignment framework based on one-dimensional optimal transport, enabling the model to learn a single alignment and perform ASR in an E2E manner. We introduce a pseudo-metric, called Sequence Optimal Transport Distance (SOTD), over the sequence space and discuss its theoretical properties. Based on the SOTD, we propose Optimal Temporal Transport Classification (OTTC) loss for ASR and contrast its behavior with CTC. Experimental results on the TIMIT, AMI, and LibriSpeech datasets show that our method considerably improves alignment performance compared to CTC and the more recently proposed Consistency-Regularized CTC, though with a trade-off in ASR performance. We believe this work opens new avenues for seq2seq alignment research, providing a solid foundation for further exploration and development within the community. Our code is publicly available at: https://github.com/idiap/OTTC
Authors: Maximilian Abstreiter, Sasu Tarkoma, Roberto Morabito
Abstract: The rapid rise of Language Models (LMs) has expanded the capabilities of natural language processing, powering applications from text generation to complex decision-making. While state-of-the-art LMs often boast hundreds of billions of parameters and are primarily deployed in data centers, recent trends show a growing focus on compact models-typically under 10 billion parameters-enabled by techniques such as quantization and other model compression techniques. This shift paves the way for LMs on edge devices, offering potential benefits such as enhanced privacy, reduced latency, and improved data sovereignty. However, the inherent complexity of even these smaller models, combined with the limited computing resources of edge hardware, raises critical questions about the practical trade-offs in executing LM inference outside the cloud. To address these challenges, we present a comprehensive evaluation of generative LM inference on representative CPU-based and GPU-accelerated edge devices. Our study measures key performance indicators-including memory usage, inference speed, and energy consumption-across various device configurations. Additionally, we examine throughput-energy trade-offs, cost considerations, and usability, alongside an assessment of qualitative model performance. While quantization helps mitigate memory overhead, it does not fully eliminate resource bottlenecks, especially for larger models. Our findings quantify the memory and energy constraints that must be considered for practical real-world deployments, offering concrete insights into the trade-offs between model size, inference performance, and efficiency. The exploration of LMs at the edge is still in its early stages. We hope this study provides a foundation for future research, guiding the refinement of models, the enhancement of inference efficiency, and the advancement of edge-centric AI systems.
Authors: Yuze Li, Wei Zhu
Abstract: We propose an efficient fine-tuning method for time series foundation models, termed TRACE: Time Series Parameter Efficient Fine-tuning. While pretrained time series foundation models are gaining popularity, they face the following challenges: (1) Unlike natural language tasks, time series data vary in frequency, channel numbers, historical/prediction lengths. For long-term forecasting tasks in particular, tailored fine-tuning can significantly enhance performance.(2) Existing parameter-efficient tuning methods like LoRA remain applicable but require adaptation to temporal characteristics. To address these challenges, our TRACE framework introduces two key innovations: (1) Gated DSIC (Gated Dynamic Simulation Importance Calculation), an unbiased LoRA module importance selection mechanism that ensures conditional parameter consistency before and after masking. Experiments demonstrate that Gated DSIC outperforms common fine-tuning. (2) Reconstructed prediction heads for long-term forecasting tasks, which achieve comparable or superior performance to linear probing heads while drastically reducing parameter counts. Extensive experiments on long-/short-term forecasting, anomaly detection and natural language tasks across diverse datasets, coupled with ablation studies, validate the effectiveness of our method.
Authors: Zuzanna Osika, Roxana R\u{a}dulescu, Jazmin Zatarain Salazar, Frans Oliehoek, Pradeep K. Murukannaiah
Abstract: Many real-world problems (e.g., resource management, autonomous driving, drug discovery) require optimizing multiple, conflicting objectives. Multi-objective reinforcement learning (MORL) extends classic reinforcement learning to handle multiple objectives simultaneously, yielding a set of policies that capture various trade-offs. However, the MORL field lacks complex, realistic environments and benchmarks. We introduce a water resource (Nile river basin) management case study and model it as a MORL environment. We then benchmark existing MORL algorithms on this task. Our results show that specialized water management methods outperform state-of-the-art MORL approaches, underscoring the scalability challenges MORL algorithms face in real-world scenarios.
Authors: Akira Tamamori
Abstract: Kernel-based learning methods such as Kernel Logistic Regression (KLR) can dramatically increase the storage capacity of Hopfield networks, but the principles governing their performance and stability remain largely uncharacterized. This paper presents a comprehensive quantitative analysis of the attractor landscape in KLR-trained networks to establish a solid foundation for their design and application. Through extensive, statistically validated simulations, we address critical questions of generality, scalability, and robustness. Our comparative analysis reveals that KLR and Kernel Ridge Regression (KRR) exhibit similarly high storage capacities and clean attractor landscapes, suggesting this is a general property of kernel regression methods, though KRR is computationally much faster. We uncover a non-trivial, scale-dependent scaling law for the kernel width ($\gamma$), demonstrating that optimal capacity requires $\gamma$ to be scaled such that $\gamma \times N$ increases with network size $N$. This implies that larger networks necessitate more localized kernels -- where each pattern's influence is more spatially confined -- to manage inter-pattern interference. Under this optimized scaling, we provide definitive evidence that the storage capacity scales linearly with network size ($P \propto N$). Furthermore, our sensitivity analysis shows that performance is remarkably robust to the choice of the regularization parameter $\lambda$. Collectively, these findings provide a clear set of empirical principles for designing high-capacity, robust associative memories and clarify the mechanisms that enable kernel methods to overcome the classical limitations of Hopfield-type models.
Authors: Chibueze Peace Obioma, Youcheng Sun, Mustafa A. Mustafa
Abstract: Federated learning (FL) remains highly vulnerable to adaptive backdoor attacks that preserve stealth by closely imitating benign update statistics. Existing defenses predominantly rely on anomaly detection in parameter or gradient space, overlooking behavioral constraints that backdoor attacks must satisfy to ensure reliable trigger activation. These anomaly-centric methods fail against adaptive attacks that normalize update magnitudes and mimic benign statistical patterns while preserving backdoor functionality, creating a fundamental detection gap. To address this limitation, this paper introduces FeRA (Federated Representative Attention) -- a novel attention-driven defense that shifts the detection paradigm from anomaly-centric to consistency-centric analysis. FeRA exploits the intrinsic need for backdoor persistence across training rounds, identifying malicious clients through suppressed representation-space variance, an orthogonal property to traditional magnitude-based statistics. The framework conducts multi-dimensional behavioral analysis combining spectral and spatial attention, directional alignment, mutual similarity, and norm inflation across two complementary detection mechanisms: consistency analysis and norm-inflation detection. Through this mechanism, FeRA isolates malicious clients that exhibit low-variance consistency or magnitude amplification. Extensive evaluation across six datasets, nine attacks, and three model architectures under both Independent and Identically Distributed (IID) and non-IID settings confirm FeRA achieves superior backdoor mitigation. Under different non-IID settings, FeRA achieved the lowest average Backdoor Accuracy (BA), about 1.67% while maintaining high clean accuracy compared to other state-of-the-art defenses. The code is available at https://github.com/Peatech/FeRA_defense.git.
Authors: Ke Sun
Abstract: The high dimensional parameter space of modern deep neural networks -- the neuromanifold -- is endowed with a unique metric tensor defined by the Fisher information, estimating which is crucial for both theory and practical methods in deep learning. To analyze this tensor for classification networks, we return to a low dimensional space of probability distributions -- the core space -- and carefully analyze the spectrum of its Riemannian metric. We extend our discoveries there into deterministic bounds of the metric tensor on the neuromanifold. We introduce an unbiased random estimate of the metric tensor and its bounds based on Hutchinson's trace estimator. It can be evaluated efficiently through a single backward pass, with a standard deviation bounded by the true value up to scaling.
Authors: Yuanyao Chen, Rongsheng Chen, Fu Luo, Zhenkun Wang
Abstract: Neural Combinatorial Optimization (NCO) has emerged as a promising learning-based paradigm for addressing Vehicle Routing Problems (VRPs) by minimizing the need for extensive manual engineering. While existing NCO methods, trained on small-scale instances (e.g., 100 nodes), have demonstrated considerable success on problems of similar scale, their performance significantly degrades when applied to large-scale scenarios. This degradation arises from the distributional shift between training and testing data, rendering policies learned on small instances ineffective for larger problems. To overcome this limitation, we introduce a novel learning framework driven by Large Language Models (LLMs). This framework learns a projection between the training and testing distributions, which is then deployed to enhance the scalability of the NCO model. Notably, unlike prevailing techniques that necessitate joint training with the neural network, our approach operates exclusively during the inference phase, obviating the need for model retraining. Extensive experiments demonstrate that our method enables a backbone model (trained on 100-node instances) to achieve superior performance on large-scale Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP) of up to 100K nodes from diverse distributions.
Authors: Patryk Krukowski, {\L}ukasz Gorczyca, Piotr Helm, Kamil Ksi\k{a}\.zek, Przemys{\l}aw Spurek
Abstract: Continual learning under adversarial conditions remains an open problem, as existing methods often compromise either robustness, scalability, or both. We propose a novel framework that integrates Interval Bound Propagation (IBP) with a hypernetwork-based architecture to enable certifiably robust continual learning across sequential tasks. Our method, SHIELD, generates task-specific model parameters via a shared hypernetwork conditioned solely on compact task embeddings, eliminating the need for replay buffers or full model copies and enabling efficient over time. To further enhance robustness, we introduce Interval MixUp, a novel training strategy that blends virtual examples represented as $\ell_{\infty}$ balls centered around MixUp points. Leveraging interval arithmetic, this technique guarantees certified robustness while mitigating the wrapping effect, resulting in smoother decision boundaries. We evaluate SHIELD under strong white-box adversarial attacks, including PGD and AutoAttack, across multiple benchmarks. It consistently outperforms existing robust continual learning methods, achieving state-of-the-art average accuracy while maintaining both scalability and certification. These results represent a significant step toward practical and theoretically grounded continual learning in adversarial settings.
Authors: Jo\~ao Manoel Herrera Pinheiro, Suzana Vilas Boas de Oliveira, Thiago Henrique Segreto Silva, Pedro Antonio Rabelo Saraiva, Enzo Ferreira de Souza, Ricardo V. Godoy, Leonardo Andr\'e Ambrosio, Marcelo Becker
Abstract: This research addresses the critical lack of comprehensive studies on feature scaling by systematically evaluating 12 scaling techniques - including several less common transformations - across 14 different Machine Learning algorithms and 16 datasets for classification and regression tasks. We meticulously analyzed impacts on predictive performance (using metrics such as accuracy, MAE, MSE, and $R^2$) and computational costs (training time, inference time, and memory usage). Key findings reveal that while ensemble methods (such as Random Forest and gradient boosting models like XGBoost, CatBoost and LightGBM) demonstrate robust performance largely independent of scaling, other widely used models such as Logistic Regression, SVMs, TabNet, and MLPs show significant performance variations highly dependent on the chosen scaler. This extensive empirical analysis, with all source code, experimental results, and model parameters made publicly available to ensure complete transparency and reproducibility, offers model-specific crucial guidance to practitioners on the need for an optimal selection of feature scaling techniques.
Authors: Antonio Consolo, Edoardo Amaldi, Emilio Carrizosa
Abstract: Decision trees are popular in survival analysis for their interpretability and ability to model complex relationships. Survival trees, which predict the timing of singular events using censored historical data, are typically built through heuristic approaches. Recently, there has been growing interest in globally optimized trees, where the overall tree is trained by minimizing the error function over all its parameters. We propose a new soft survival tree model (SST), with a soft splitting rule at each branch node, trained via a nonlinear optimization formulation amenable to decomposition. Since SSTs provide for every input vector a specific survival function associated to a single leaf node, they satisfy the conditional computation property and inherit the related benefits. SST and the training formulation combine flexibility with interpretability: any smooth survival function (parametric, semiparametric, or nonparametric) estimated through maximum likelihood can be used, and each leaf node of an SST yields a cluster of distinct survival functions which are associated to the data points routed to it. Numerical experiments on 15 well-known datasets show that SSTs, with parametric and spline-based semiparametric survival functions, trained using an adaptation of the node-based decomposition algorithm proposed by Consolo et al. (2024) for soft regression trees, outperform three benchmark survival trees in terms of four widely-used discrimination and calibration measures. SSTs can also be extended to consider group fairness.
Authors: Naoki Sato, Hiroki Naganuma, Hideaki Iiduka
Abstract: Muon, a recently proposed optimizer that leverages the inherent matrix structure of neural network parameters, has demonstrated strong empirical performance, indicating its potential as a successor to standard optimizers such as AdamW. This paper presents theoretical analysis to support its practical success. We provide convergence proofs for Muon across four practical settings, systematically examining its behavior with and without the inclusion of Nesterov momentum and weight decay. Our analysis covers the standard configuration using both, thereby elucidating its real-world performance. We then demonstrate that the addition of weight decay yields strictly tighter theoretical bounds and clarify the interplay between the weight decay coefficient and the learning rate. Finally, we derive the critical batch size for Muon that minimizes the computational cost of training. Our analysis identifies the hyperparameters governing this value, and our experiments validate the corresponding theoretical findings across workloads including image classification and language modeling task.
Authors: Philipp Schlinge, Steffen Meinert, Martin Atzmueller
Abstract: Prototype models are an important method for explainable artificial intelligence (XAI) and interpretable machine learning. In this paper, we perform an in-depth analysis of a set of prominent prototype models including ProtoPNet, ProtoPool and PIPNet. For their assessment, we apply a comprehensive set of metrics. In addition to applying standard metrics from literature, we propose several new metrics to further complement the analysis of model interpretability. In our experimentation, we apply the set of prototype models on a diverse set of datasets including fine-grained classification, Non-IID settings and multi-label classification to further contrast the performance. Furthermore, we also provide our code as an open-source library (https://github.com/uos-sis/quanproto), which facilitates simple application of the metrics itself, as well as extensibility -- providing the option for easily adding new metrics and models.
Authors: Zhipeng He, Alexander Stevens, Chun Ouyang, Johannes De Smedt, Alistair Barros, Catarina Moreira
Abstract: Adversarial attacks on tabular data present unique challenges due to the heterogeneous nature of mixed categorical and numerical features. Unlike images where pixel perturbations maintain visual similarity, tabular data lacks intuitive similarity metrics, making it difficult to define imperceptible modifications. Additionally, traditional gradient-based methods prioritise $\ell_p$-norm constraints, often producing adversarial examples that deviate from the original data distributions. To address this, we propose a latent-space perturbation framework using a mixed-input Variational Autoencoder (VAE) to generate statistically consistent adversarial examples. The proposed VAE integrates categorical embeddings and numerical features into a unified latent manifold, enabling perturbations that preserve statistical consistency. We introduce In-Distribution Success Rate (IDSR) to jointly evaluate attack effectiveness and distributional alignment. Evaluation across six publicly available datasets and three model architectures demonstrates that our method achieves substantially lower outlier rates and more consistent performance compared to traditional input-space attacks and other VAE-based methods adapted from image domain approaches, achieving substantially lower outlier rates and higher IDSR across six datasets and three model architectures. Our comprehensive analyses of hyperparameter sensitivity, sparsity control, and generative architecture demonstrate that the effectiveness of VAE-based attacks depends strongly on reconstruction quality and the availability of sufficient training data. When these conditions are met, the proposed framework achieves superior practical utility and stability compared with input-space methods. This work underscores the importance of maintaining on-manifold perturbations for generating realistic and robust adversarial examples in tabular domains.
Authors: Chao Wu, Zhenyi Wang, Kangxian Xie, Naresh Kumar Devulapally, Vishnu Suresh Lokhande, Mingchen Gao
Abstract: Text-to-image (T2I) diffusion models often exhibit gender bias, particularly by generating stereotypical associations between professions and gendered subjects. This paper presents SAE Debias, a lightweight and model-agnostic framework for mitigating such bias in T2I generation. Unlike prior approaches that rely on CLIP-based filtering or prompt engineering, which often require model-specific adjustments and offer limited control, SAE Debias operates directly within the feature space without retraining or architectural modifications. By leveraging a k-sparse autoencoder pre-trained on a gender bias dataset, the method identifies gender-relevant directions within the sparse latent space, capturing professional stereotypes. Specifically, a biased direction per profession is constructed from sparse latents and suppressed during inference to steer generations toward more gender-balanced outputs. Trained only once, the sparse autoencoder provides a reusable debiasing direction, offering effective control and interpretable insight into biased subspaces. Extensive evaluations across multiple T2I models, including Stable Diffusion 1.4, 1.5, 2.1, and SDXL, demonstrate that SAE Debias substantially reduces gender bias while preserving generation quality. To the best of our knowledge, this is the first work to apply sparse autoencoders for identifying and intervening in gender bias within T2I models. These findings contribute toward building socially responsible generative AI, providing an interpretable and model-agnostic tool to support fairness in text-to-image generation.
Authors: Kushal Kapoor, Wyatt Mackey, Yiannis Aloimonos, Xiaomin Lin
Abstract: We propose HiCL, a novel hippocampal-inspired dual-memory continual learning architecture designed to mitigate catastrophic forgetting by using elements inspired by the hippocampal circuitry. Our system encodes inputs through a grid-cell-like layer, followed by sparse pattern separation using a dentate gyrus-inspired module with top-k sparsity. Episodic memory traces are maintained in a CA3-like autoassociative memory. Task-specific processing is dynamically managed via a DG-gated mixture-of-experts mechanism, wherein inputs are routed to experts based on cosine similarity between their normalized sparse DG representations and learned task-specific DG prototypes computed through online exponential moving averages. This biologically grounded yet mathematically principled gating strategy enables differentiable, scalable task-routing without relying on a separate gating network, and enhances the model's adaptability and efficiency in learning multiple sequential tasks. Cortical outputs are consolidated using Elastic Weight Consolidation weighted by inter-task similarity. Crucially, we incorporate prioritized replay of stored patterns to reinforce essential past experiences. Evaluations on standard continual learning benchmarks demonstrate the effectiveness of our architecture in reducing task interference, achieving near state-of-the-art results in continual learning tasks at lower computational costs. Our code is available here https://github.com/kushalk173-sc/HiCL.
Authors: Mohamed Kissi, Keanu Sisouk, Joshua A. Levine, Julien Tierny
Abstract: This paper presents a neural scheme for the topology-aware interpolation of time-varying scalar fields. Given a time-varying sequence of persistence diagrams, along with a sparse temporal sampling of the corresponding scalar fields, denoted as keyframes, our interpolation approach aims at "inverting" the non-keyframe diagrams to produce plausible estimations of the corresponding, missing data. For this, we rely on a neural architecture which learns the relation from a time value to the corresponding scalar field, based on the keyframe examples, and reliably extends this relation to the non-keyframe time steps. We show how augmenting this architecture with specific topological losses exploiting the input diagrams both improves the geometrical and topological reconstruction of the non-keyframe time steps. At query time, given an input time value for which an interpolation is desired, our approach instantaneously produces an output, via a single propagation of the time input through the network. Experiments interpolating 2D and 3D time-varying datasets show our approach superiority, both in terms of data and topological fitting, with regard to reference interpolation schemes. Our implementation is available at this GitHub link : https://github.com/MohamedKISSI/Topology-Aware-Neural-Interpolation-of-Scalar-Fields.git.
URLs: https://github.com/MohamedKISSI/Topology-Aware-Neural-Interpolation-of-Scalar-Fields.git.
Authors: Misgina Tsighe Hagos, Claes Lundstr\"om
Abstract: Conformal prediction is a model-agnostic approach to generating prediction sets that cover the true class with a high probability. Although its prediction set size is expected to capture aleatoric uncertainty, there is a lack of evidence regarding its effectiveness. The literature presents that prediction set size can upper-bound aleatoric uncertainty or that prediction sets are larger for difficult instances and smaller for easy ones, but a validation of this attribute of conformal predictors is missing. This work investigates how effectively conformal predictors quantify aleatoric uncertainty, specifically the inherent ambiguity in datasets caused by overlapping classes. We perform this by measuring the correlation between prediction set sizes and the number of distinct labels assigned by human annotators per instance. We further assess the similarity between prediction sets and human-provided annotations. We use three conformal prediction approaches to generate prediction sets for eight deep learning models trained on four datasets. The datasets contain annotations from multiple human annotators (ranging from five to fifty participants) per instance, enabling the identification of class overlap. We show that the vast majority of the conformal prediction outputs show a very weak to weak correlation with human annotations, with only a few showing moderate correlation. These findings underscore the necessity of critically reassessing the prediction sets generated using conformal predictors. While they can provide a higher coverage of the true classes, their capability in capturing aleatoric uncertainty and generating sets that align with human annotations remains limited.
Authors: Praneet Suresh, Jack Stanley, Sonia Joseph, Luca Scimeca, Danilo Bzdok
Abstract: As generative AI systems become competent and democratized in science, business, and government, deeper insight into their failure modes now poses an acute need. The occasional volatility in their behavior, such as the propensity of transformer models to hallucinate, impedes trust and adoption of emerging AI solutions in high-stakes areas. In the present work, we establish how and when hallucinations arise in pre-trained transformer models through concept representations captured by sparse autoencoders, under scenarios with experimentally controlled uncertainty in the input space. Our systematic experiments reveal that the number of semantic concepts used by the transformer model grows as the input information becomes increasingly unstructured. In the face of growing uncertainty in the input space, the transformer model becomes prone to activate coherent yet input-insensitive semantic features, leading to hallucinated output. At its extreme, for pure-noise inputs, we identify a wide variety of robustly triggered and meaningful concepts in the intermediate activations of pre-trained transformer models, whose functional integrity we confirm through targeted steering. We also show that hallucinations in the output of a transformer model can be reliably predicted from the concept patterns embedded in transformer layer activations. This collection of insights on transformer internal processing mechanics has immediate consequences for aligning AI models with human values, AI safety, opening the attack surface for potential adversarial attacks, and providing a basis for automatic quantification of a model's hallucination risk.
Authors: Sahil Sethi, Kai Sundmacher, Caroline Ganzer
Abstract: Ionic liquids (ILs) have emerged as versatile replacements for traditional solvents because their physicochemical properties can be precisely tailored to various applications. However, accurately predicting key thermophysical properties remains challenging due to the vast chemical design space and the limited availability of experimental data. In this study, we present a data-driven transfer learning framework combined with a neural recommender system (NRS) to enable reliable property prediction for ILs using sparse experimental datasets. The approach involves a two-stage process: first, pre-training NRS models on COSMO-RS-based simulated data at fixed temperature and pressure, and second, fine-tuning simple feedforward neural networks with experimental data at varying temperatures and pressures. In this work, five essential IL properties are considered: density, viscosity, surface tension, heat capacity, and melting point. We find that the framework supports both within-property and cross-property knowledge transfer. Notably, pre-trained models for density, viscosity, and heat capacity are used to fine-tune models for all five target properties, achieving improved performance by a substantial margin for four of them. The model exhibits robust extrapolation to previously unseen ILs. Moreover, the final trained models enable property prediction for over 700,000 IL combinations, offering a scalable solution for IL screening in process design. This work highlights the effectiveness of combining simulated data and transfer learning to overcome sparsity in the experimental data.
Authors: Justin Arndt
Abstract: We introduce the Holographic Knowledge Manifold (HKM), a four-phase pipeline that achieves zero catastrophic forgetting in AI knowledge representation while maintaining minimal memory growth and high efficiency. Leveraging fractal quantization, probabilistic entanglement, and dynamic diffraction chipping, HKM compresses knowledge substrates by 3x with 67% storage savings, integrates holographically at 100%, and supports over 1,020 updates with 1% growth per increment. In experiments on combined WikiText and FB15k datasets (scaled to 2,997 nodes), we demonstrate industry-leading performance: 0% forgetting (infinite improvement over GEM baselines), 3x compression, and 53% training time reduction on consumer GPU hardware. Hypothetical cost analyses project $92.4M savings over 5 years at petabyte scale, with 21.2% energy reduction and 33% lower carbon footprint. This work hypothesizes a paradigm shift for public large language models (LLMs), enabling "eternal" adaptation without retraining. Future extensions to multimodal fusion and quantum hardware could further democratize scalable AI, potentially reducing fine-tuning costs by 60-80% for models like Llama-3 or Grok-4. Code, datasets, and full results are publicly available for reproducibility.
Authors: Ansh Nagda, Prabhakar Raghavan, Abhradeep Thakurta
Abstract: Can AI based methods help us make advances in complexity theory? We provide evidence towards answering this in the affirmative, using AlphaEvolve (an LLM code mutation agent) to obtain new results in three settings: a) We improve a recent result of Kunisky and Yu to obtain near-optimal upper and (conditional) lower bounds on certification algorithms for MAX-CUT and MAX-Independent Set on random 3- and 4-regular graphs. Our improved lower bounds are obtained by constructing nearly extremal Ramanujan graphs on as many as $163$ vertices, and our upper bounds are obtained via analytical arguments. b) We obtain new inapproximability results for MAX-4-CUT and MAX-3-CUT, proving that it is NP-hard to approximate them within factors of $0.987$ and $0.9649$ respectively, using AlphaEvolve to discover new gadget reductions. Our MAX-4-CUT result improves upon the SOTA of $0.9883$, and our MAX-3-CUT result improves on the current best gadget-based inapproximability result of $0.9853$, but falls short of the SOTA of $16/17$ that relies on a custom PCP (rather than a reduction from ``standard'' H{\aa}stad-style PCPs). c) Inapproximability for the metric Traveling Salesman Problem (TSP): We show that it is NP-hard to approximate the minimum cost tour within a factor of $111/110$ using AlphaEvolve to discover a new gadget, thus improving the SOTA of $117/116$. Along the way, we provide new modular soundness and completeness arguments that can be of independent interest. A key technical challenge we faced: verifying a candidate construction produced by AlphaEvolve is costly (sometimes requiring time exponential in the size of the construction). We used AlphaEvolve itself to evolve the verification procedure to be faster (sometimes by $10,000\times$ for our gadgets). Our results suggest that gadget based proofs would benefit from a pass through AI-based tools to obtain stronger results.
Authors: Ange-Cl\'ement Akazan, Verlon Roel Mbingui
Abstract: Feature selection is a key step in many tabular prediction problems, where multiple candidate variables may be redundant, noisy, or weakly informative. We investigate feature selection based on Kolmogorov-Arnold Networks (KANs), which parameterize feature transformations with splines and expose per-feature importance scores in a natural way. From this idea we derive four KAN-based selection criteria (coefficient norms, gradient-based saliency, and knockout scores) and compare them with standard methods such as LASSO, Random Forest feature importance, Mutual Information, and SVM-RFE on a suite of real and synthetic classification and regression datasets. Using average F1 and $R^2$ scores across three feature-retention levels (20%, 40%, 60%), we find that KAN-based selectors are generally competitive with, and sometimes superior to, classical baselines. In classification, KAN criteria often match or exceed existing methods on multi-class tasks by removing redundant features and capturing nonlinear interactions. In regression, KAN-based scores provide robust performance on noisy and heterogeneous datasets, closely tracking strong ensemble predictors; we also observe characteristic failure modes, such as overly aggressive pruning with an $\ell_1$ criterion. Stability and redundancy analyses further show that KAN-based selectors yield reproducible feature subsets across folds while avoiding unnecessary correlation inflation, ensuring reliable and non-redundant variable selection. Overall, our findings demonstrate that KAN-based feature selection provides a powerful and interpretable alternative to traditional methods, capable of uncovering nonlinear and multivariate feature relevance beyond sparsity or impurity-based measures.
Authors: Roussel Rahman, Jeff Shrager
Abstract: Strategy Choice Theory (SCT; Siegler and Shrager, 1984; Siegler, 2000) explains important aspects of children's arithmetic learning based upon principles including learning from developmentally naturalistic data, probabilistic representation, confidence-based retrieval, and the phase-like importance of scaffolding strategies, such as finger-counting. Here we recast SCT as a ``Small Math Model'' (SMM), employing a neural-network-based architecture analogous to LLMs. The SMM extends SCT to include counting practice, symbol (number) embedding, and gated attention. Similar to earlier work, the SMM demonstrates constructive and destructive interference between counting and addition, and the ``wave-like'' use of finger-counting as sum recall improves. We plan to extend the SMM to later aspects of the decades-long SCT program, including adaptive strategy choice and eventually strategy discovery, providing a unified platform to investigate the understanding of numerical characteristics and relationships essential for mathematical reasoning -- as it can emerge in LLM-based agents.
Authors: Roberto Neglia, Andrea Cini, Michael M. Bronstein, Filippo Maria Bianchi
Abstract: Conformal prediction offers a powerful framework for building distribution-free prediction intervals for exchangeable data. Existing methods that extend conformal prediction to sequential data rely on fitting a relatively complex model to capture temporal dependencies. However, these methods can fail if the sample size is small and often require expensive retraining when the underlying data distribution changes. To overcome these limitations, we propose Reservoir Conformal Prediction (ResCP), a novel training-free conformal prediction method for time series. Our approach leverages the efficiency and representation learning capabilities of reservoir computing to dynamically reweight conformity scores. In particular, we compute similarity scores among reservoir states and use them to adaptively reweight the observed residuals at each step. With this approach, ResCP enables us to account for local temporal dynamics when modeling the error distribution without compromising computational scalability. We prove that, under reasonable assumptions, ResCP achieves asymptotic conditional coverage, and we empirically demonstrate its effectiveness across diverse forecasting tasks.
Authors: Guojian Zhan, Likun Wang, Xiangteng Zhang, Jiaxin Gao, Masayoshi Tomizuka, Shengbo Eben Li
Abstract: Online planning has proven effective in reinforcement learning (RL) for improving sample efficiency and final performance. However, using planning for environment interaction inevitably introduces a divergence between the collected data and the policy's actual behaviors, degrading both model learning and policy improvement. To address this, we propose BOOM (Bootstrap Off-policy with WOrld Model), a framework that tightly integrates planning and off-policy learning through a bootstrap loop: the policy initializes the planner, and the planner refines actions to bootstrap the policy through behavior alignment. This loop is supported by a jointly learned world model, which enables the planner to simulate future trajectories and provides value targets to facilitate policy improvement. The core of BOOM is a likelihood-free alignment loss that bootstraps the policy using the planner's non-parametric action distribution, combined with a soft value-weighted mechanism that prioritizes high-return behaviors and mitigates variability in the planner's action quality within the replay buffer. Experiments on the high-dimensional DeepMind Control Suite and Humanoid-Bench show that BOOM achieves state-of-the-art results in both training stability and final performance. The code is accessible at https://github.com/molumitu/BOOM_MBRL.
Authors: Yan Sun, Jia Guo, Stanley Kok, Zihao Wang, Zujie Wen, Zhiqiang Zhang
Abstract: Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning ability of large language models, yet training remains costly because many rollouts contribute little to optimization, considering the amount of computation required. This study investigates how simply leveraging intrinsic data properties, almost free benefit during training, can improve data efficiency for RLVR. We propose PREPO with two complementary components. First, we adopt prompt perplexity as an indicator of model adaptability in learning, enabling the model to progress from well-understood contexts to more challenging ones. Second, we amplify the discrepancy among the rollouts by differentiating their relative entropy, and prioritize sequences that exhibit a higher degree of exploration. Together, these mechanisms reduce rollout demand while preserving competitive performance. On the Qwen and Llama models, PREPO achieves effective results on mathematical reasoning benchmarks with up to 3 times fewer rollouts than the baselines. Beyond empirical gains, we provide theoretical and in-depth analyses explaining the underlying rationale of our method to improve the data efficiency of RLVR.
Authors: Zhicheng Wang, Chen Ju, Xu Chen, Shuai Xiao, Jinsong Lan, Xiaoyong Zhu, Ying Chen, Zhiguo Cao
Abstract: Embedding models are a cornerstone of modern AI. Driven by Multimodal Large Language Models (MLLMs), they have made great progress in architecture and data curation, while the holistic paradigm is still limited to SSC, i.e., single input, singular embedding, contrastive supervision, which collapses rich, multifaceted inputs into monolithic embeddings and fails to fully exploit MLLM capabilities. In this paper, we tailor one Parallel Decoupling Framework (PDF) for multimodal embedding learning, by utilizing the proprietary steerability of MLLMs, i.e., their ability to flexibly generate quite differentiated response under explicit instructions. Concretely, PDF conditions a shared MLLM backbone on distinct, learnable prefixes to roll out multiple parallel paths for one input, then relies on these paths to obtain parallel embeddings. To promote full parallel diversity, we employ Mutual Information Minimization (MIM) as an explicit constraint, coupled with per-path contrastive supervision to maintain semantic alignment. Such dual-objectives force PDF to yield robust semantic coverage and a generalizable embedding space. Ultimately, the remarkable embedding space are accessible at inference via one single forward pass, incurring negligible computational overhead. We instantiate PDF on multiple MLLM backbones and prove its effectiveness on MMEB benchmark. Significant gains are consistently achieved across various resolutions and model sizes, e.g., boosting the VLM2Vec-LLaVA-1.6-LR model by a remarkable +8.9% (7B), while the VLM2Vec-Qwen2VL models by +4.2% (2B) and +3.1% (7B). In terms of efficiency, our 2B model surpasses its baseline by +2.6% using only half the computational budget.
Authors: W. K. M Mithsara, Ning Yang, Ahmed Imteaj, Hussein Zangoti, Abdur R. Shahid
Abstract: The widespread integration of wearable sensing devices in Internet of Things (IoT) ecosystems, particularly in healthcare, smart homes, and industrial applications, has required robust human activity recognition (HAR) techniques to improve functionality and user experience. Although machine learning models have advanced HAR, they are increasingly susceptible to data poisoning attacks that compromise the data integrity and reliability of these systems. Conventional approaches to defending against such attacks often require extensive task-specific training with large, labeled datasets, which limits adaptability in dynamic IoT environments. This work proposes a novel framework that uses large language models (LLMs) to perform poisoning detection and sanitization in HAR systems, utilizing zero-shot, one-shot, and few-shot learning paradigms. Our approach incorporates \textit{role play} prompting, whereby the LLM assumes the role of expert to contextualize and evaluate sensor anomalies, and \textit{think step-by-step} reasoning, guiding the LLM to infer poisoning indicators in the raw sensor data and plausible clean alternatives. These strategies minimize reliance on curation of extensive datasets and enable robust, adaptable defense mechanisms in real-time. We perform an extensive evaluation of the framework, quantifying detection accuracy, sanitization quality, latency, and communication cost, thus demonstrating the practicality and effectiveness of LLMs in improving the security and reliability of wearable IoT systems.
Authors: Stergios Plataniotis, Charilaos Akasiadis, Georgios Chalkiadakis
Abstract: Efficient exploration in deep reinforcement learning remains a fundamental challenge, especially in environments characterized by high-dimensional states and sparse rewards. Traditional exploration strategies that rely on random local policy noise, such as $\epsilon$-greedy and Boltzmann exploration methods, often struggle to efficiently balance exploration and exploitation. In this paper, we integrate the notion of (expected) value of information (EVOI) within the well-known Bootstrapped DQN algorithmic framework, to enhance the algorithm's deep exploration ability. Specifically, we develop two novel algorithms that incorporate the expected gain from learning the value of information into Bootstrapped DQN. Our methods use value of information estimates to measure the discrepancies of opinions among distinct network heads, and drive exploration towards areas with the most potential. We evaluate our algorithms with respect to performance and their ability to exploit inherent uncertainty arising from random network initialization. Our experiments in complex, sparse-reward Atari games demonstrate increased performance, all the while making better use of uncertainty, and, importantly, without introducing extra hyperparameters.
Authors: Xuyang Li, John Harlim, Dibyajyoti Chakraborty, Romit Maulik
Abstract: Accurate forecasting of complex high-dimensional dynamical systems from observational data is essential for several applications across science and engineering. A key challenge, however, is that real-world measurements are often corrupted by noise, which severely degrades the performance of data-driven models. Particularly, in chaotic dynamical systems, where small errors amplify rapidly, it is challenging to identify a data-driven model from noisy data that achieves short-term accuracy while preserving long-term invariant properties. In this paper, we propose the use of the weak formulation as a complementary approach to the classical strong formulation of data-driven time-series forecasting models. Specifically, we focus on the neural ordinary differential equation (NODE) architecture. Unlike the standard strong formulation, which relies on the discretization of the NODE followed by optimization, the weak formulation constrains the model using a set of integrated residuals over temporal subdomains. While such a formulation yields an effective NODE model, we discover that the performance of a NODE can be further enhanced by employing this weak formulation as a penalty alongside the classical strong formulation-based learning. Through numerical demonstrations, we illustrate that our proposed training strategy, which we coined as the Weak-Penalty NODE (WP-NODE), achieves state-of-the-art forecasting accuracy and exceptional robustness across benchmark chaotic dynamical systems and real-world climate dataset.
Authors: Nathan Breslow, Aayush Mishra, Mahler Revsine, Michael C. Schatz, Anqi Liu, Daniel Khashabi
Abstract: In-context learning (ICL) -- the capacity of a model to infer and apply abstract patterns from examples provided within its input -- has been extensively studied in large language models trained for next-token prediction on human text. In fact, prior work often attributes this emergent behavior to distinctive statistical properties in human language. This raises a fundamental question: can ICL arise organically in other sequence domains purely through large-scale predictive training? To explore this, we turn to genomic sequences, an alternative symbolic domain rich in statistical structure. Specifically, we study the Evo2 genomic model, trained predominantly on next-nucleotide (A/T/C/G) prediction, at a scale comparable to mid-sized LLMs. We develop a controlled experimental framework comprising symbolic reasoning tasks instantiated in both linguistic and genomic forms, enabling direct comparison of ICL across genomic and linguistic models. Our results show that genomic models, like their linguistic counterparts, exhibit log-linear gains in pattern induction as the number of in-context demonstrations increases. To the best of our knowledge, this is the first evidence of organically emergent ICL in genomic sequences, supporting the hypothesis that ICL arises as a consequence of large-scale predictive modeling over rich data. These findings extend emergent meta-learning beyond language, pointing toward a unified, modality-agnostic view of in-context learning.
Authors: Antoine Ledent, Mun Chong Soo, Nong Minh Hieu
Abstract: We study a matrix completion problem where both the ground truth $R$ matrix and the unknown sampling distribution $P$ over observed entries are low-rank matrices, and \textit{share a common subspace}. We assume that a large amount $M$ of \textit{unlabeled} data drawn from the sampling distribution $P$ is available, together with a small amount $N$ of labeled data drawn from the same distribution and noisy estimates of the corresponding ground truth entries. This setting is inspired by recommender systems scenarios where the unlabeled data corresponds to `implicit feedback' (consisting in interactions such as purchase, click, etc. ) and the labeled data corresponds to the `explicit feedback', consisting of interactions where the user has given an explicit rating to the item. Leveraging powerful results from the theory of low-rank subspace recovery, together with classic generalization bounds for matrix completion models, we show error bounds consisting of a sum of two error terms scaling as $\widetilde{O}\left(\sqrt{\frac{nd}{M}}\right)$ and $\widetilde{O}\left(\sqrt{\frac{dr}{N}}\right)$ respectively, where $d$ is the rank of $P$ and $r$ is the rank of $M$. In synthetic experiments, we confirm that the true generalization error naturally splits into independent error terms corresponding to the estimations of $P$ and and the ground truth matrix $\ground$ respectively. In real-life experiments on Douban and MovieLens with most explicit ratings removed, we demonstrate that the method can outperform baselines relying only on the explicit ratings, demonstrating that our assumptions provide a valid toy theoretical setting to study the interaction between explicit and implicit feedbacks in recommender systems.
Authors: E. Zhixuan Zeng, Yuhao Chen, Alexander Wong
Abstract: Image generation models frequently encode social biases, including stereotypes tied to gender, race, and profession. Existing methods for analyzing these biases in diffusion models either focus narrowly on predefined categories or depend on manual interpretation of latent directions. These constraints limit scalability and hinder the discovery of subtle or unanticipated patterns. We introduce SCALEX, a framework for scalable and automated exploration of diffusion model latent spaces. SCALEX extracts semantically meaningful directions from H-space using only natural language prompts, enabling zero-shot interpretation without retraining or labelling. This allows systematic comparison across arbitrary concepts and large-scale discovery of internal model associations. We show that SCALEX detects gender bias in profession prompts, ranks semantic alignment across identity descriptors, and reveals clustered conceptual structure without supervision. By linking prompts to latent directions directly, SCALEX makes bias analysis in diffusion models more scalable, interpretable, and extensible than prior approaches.
Authors: Chao Yu, Qixin Tan, Jiaxuan Gao, Shi Yu, Hong Lu, Xinting Yang, Zelai Xu, Yu Wang, Yi Wu, Eugene Vinitsky
Abstract: Reasoning reinforcement learning (RL) has recently revealed a new scaling effect: test-time scaling. Thinking models such as R1 and o1 improve their reasoning accuracy at test time as the length of the reasoning context increases. However, compared with training-time scaling, test-time scaling is fundamentally limited by the limited context length of base models, which remains orders of magnitude smaller than the amount of tokens consumed during training. We revisit test-time enhancement techniques through the lens of scaling effect and introduce a unified framework of multi-dimensional test-time scaling to extend the capacity of test-time reasoning. Beyond conventional context-length scaling, we consider two additional dimensions: batch scaling, where accuracy improves with parallel sampling, and turn scaling, where iterative self-refinement enhances reasoning quality. Building on this perspective, we propose 3D test-time scaling, which integrates context, batch, and turn scaling. We show that: (1) each dimension demonstrates a test-time scaling effect, but with a bounded capacity; (2) combining all three dimensions substantially improves the reasoning performance of challenging testbeds, including IOI, IMO, and CPHO, and further benefits from human preference feedback; and (3) the human-in-the-loop framework naturally extends to a more open-ended domain, i.e., embodied learning, which enables the design of humanoid control behaviors.
Authors: Peter Sharpe
Abstract: We introduce GLOBE, a new neural surrogate for homogeneous PDEs that draws inductive bias from boundary-element methods and equivariant ML. GLOBE represents solutions as superpositions of learnable Green's-function-like kernels evaluated from boundary faces to targets, composed across multiscale branches and communication hyperlayers. The architecture is translation-, rotation-, and parity-equivariant; discretization-invariant in the fine-mesh limit; and units-invariant via rigorous nondimensionalization. An explicit far-field decay envelope stabilizes extrapolation, boundary-to-boundary hyperlayer communication mediates long-range coupling, and the all-to-all boundary-to-target evaluation yields a global receptive field that respects PDE information flow, even for elliptic PDEs. On AirFRANS (steady incompressible RANS over NACA airfoils), GLOBE achieves substantial accuracy improvements. On the "Full" split, it reduces mean-squared error by roughly 200x on all fields relative to the dataset's reference baselines, and roughly 50x relative to the next-best-performing model. In the "Scarce" split, it achieves over 100x lower error on velocity and pressure fields and over 600x lower error on surface pressure than Transolver. Qualitative results show sharp near-wall gradients, coherent wakes, and limited errors under modest extrapolation in Reynolds number and angle of attack. In addition to this accuracy, the model is quite compact (117k parameters), and fields can be evaluated at arbitrary points during inference. We also demonstrate the ability to train and predict with non-watertight meshes, which has strong practical implications. These results show that rigorous physics- and domain-inspired inductive biases can achieve large gains in accuracy, generalizability, and practicality for ML-based PDE surrogates for industrial computer-aided engineering (CAE).
Authors: Yang Xu, Zuliang Yang, Kai Ming Ting
Abstract: Trajectory similarity retrieval is an important part of spatiotemporal data mining, however, existing methods have the following limitations: traditional metrics are computationally expensive, while learning-based methods suffer from substantial training costs and potential instability. This paper addresses these problems by proposing Geometric Prototype Trajectory Hashing (GeoPTH), a novel, lightweight, and non-learning framework for efficient category-based trajectory retrieval. GeoPTH constructs data-dependent hash functions by using representative trajectory prototypes, i.e., small point sets preserving geometric characteristics, as anchors. The hashing process is efficient, which involves mapping a new trajectory to its closest prototype via a robust, Hausdorff metric. Extensive experiments show that GeoPTH's retrieval accuracy is highly competitive with both traditional metrics and state-of-the-art learning methods, and it significantly outperforms binary codes generated through simple binarization of the learned embeddings. Critically, GeoPTH consistently outperforms all competitors in terms of efficiency. Our work demonstrates that a lightweight, prototype-centric approach offers a practical and powerful alternative, achieving an exceptional retrieval performance and computational efficiency.
Authors: Han Zheng, Zimu Li, Sergii Strelchuk, Risi Kondor, Junyu Liu
Abstract: We introduce a framework of the equivariant convolutional quantum algorithms which is tailored for a number of machine-learning tasks on physical systems with arbitrary SU$(d)$ symmetries. It allows us to enhance a natural model of quantum computation -- permutational quantum computing (PQC) -- and define a more powerful model: PQC+. While PQC was shown to be efficiently classically simulatable, we exhibit a problem which can be efficiently solved on PQC+ machine, whereas no classical polynomial time algorithm is known; thus providing evidence against PQC+ being classically simulatable. We further discuss practical quantum machine learning algorithms which can be carried out in the paradigm of PQC+.
Authors: Kasidis Arunruangsirilert, Jiro Katto
Abstract: While 5G New Radio (NR) networks offer significant uplink throughput improvements, these gains are primarily realized when User Equipment (UE) connects to high-frequency millimeter wave (mmWave) bands. The growing demand for uplink-intensive applications, such as real-time UHD 4K/8K video streaming and Virtual Reality (VR)/Augmented Reality (AR) content, highlights the need for accurate uplink throughput prediction to optimize user Quality of Experience (QoE). In this paper, we introduce UplinkNet, a compact neural network designed to predict future uplink throughput using past throughput and RF parameters available through the Android API. With a model size limited to approximately 4,000 parameters, UplinkNet is suitable for IoT and low-power devices. The network was trained on real-world drive test data from commercial 5G Standalone (SA) networks in Tokyo, Japan, and Bangkok, Thailand, across various mobility conditions. To ensure practical implementation, the model uses only Android API data and was evaluated on unseen data against other models. Results show that UplinkNet achieves an average prediction accuracy of 98.9% and an RMSE of 5.22 Mbps, outperforming all other models while maintaining a compact size and low computational cost.
Authors: Patrick Chao, Edgar Dobriban
Abstract: Contaminations are a key concern in modern statistical learning, as small but systematic perturbations of all datapoints can substantially alter estimation results. Here, we study Wasserstein-$r$ contaminations ($r\ge 1$) in an $\ell_q$ norm ($q\in [1,\infty]$), in which each observation may undergo an adversarial perturbation with bounded cost, complementing the classical Huber model, corresponding to total variation norm, where only a fraction of observations is arbitrarily corrupted. We study both independent and joint (coordinated) contaminations and develop a minimax theory under $\ell_q^r$ losses. Our analysis encompasses several fundamental problems: location estimation, linear regression, and pointwise nonparametric density estimation. For joint contaminations in location estimation and for prediction in linear regression, we obtain the exact minimax risk, identify least favorable contaminations, and show that the sample mean and least squares predictor are respectively minimax optimal. For location estimation under independent contaminations, we give sharp upper and lower bounds, including exact minimaxity in the Euclidean Wasserstein contamination case, when $q=r=2$. For pointwise density estimation in any dimension, we derive the optimal rate, showing that it is achieved by kernel density estimation with a bandwidth that is possibly larger than the classical one. Our proofs leverage powerful tools from optimal transport developed over the last 20 years, including the dynamic Benamou-Brenier formulation. Taken together, our results suggest that in contrast to the Huber contamination model, for norm-based Wasserstein contaminations, classical estimators may be nearly optimally robust.
Authors: Sahibzada Adil Shahzad, Ammarah Hashmi, Yan-Tsung Peng, Yu Tsao, Hsin-Min Wang
Abstract: Multimodal manipulations (also known as audio-visual deepfakes) make it difficult for unimodal deepfake detectors to detect forgeries in multimedia content. To avoid the spread of false propaganda and fake news, timely detection is crucial. The damage to either modality (i.e., visual or audio) can only be discovered through multimodal models that can exploit both pieces of information simultaneously. However, previous methods mainly adopt unimodal video forensics and use supervised pre-training for forgery detection. This study proposes a new method based on a multimodal self-supervised-learning (SSL) feature extractor to exploit inconsistency between audio and visual modalities for multimodal video forgery detection. We use the transformer-based SSL pre-trained Audio-Visual HuBERT (AV-HuBERT) model as a visual and acoustic feature extractor and a multi-scale temporal convolutional neural network to capture the temporal correlation between the audio and visual modalities. Since AV-HuBERT only extracts visual features from the lip region, we also adopt another transformer-based video model to exploit facial features and capture spatial and temporal artifacts caused during the deepfake generation process. Experimental results show that our model outperforms all existing models and achieves new state-of-the-art performance on the FakeAVCeleb and DeepfakeTIMIT datasets.
Authors: Donsub Rim, Gerrit Welper
Abstract: We construct a new representation of entropy solutions to nonlinear scalar conservation laws with a smooth convex flux function in a single spatial dimension. The representation is a generalization of the method of characteristics and posseses a compositional form. While it is a nonlinear representation, the embedded dynamics of the solution in the time variable is linear. This representation is then discretized as a manifold of implicit neural representations where the feedforward neural network architecture has a low rank structure. Finally, we show that the low rank neural representation with a fixed number of layers and a small number of coefficients can approximate any entropy solution regardless of the complexity of the shock topology, while retaining the linearity of the embedded dynamics.
Authors: Pascal J. Sager, Jan M. Deriu, Benjamin F. Grewe, Thilo Stadelmann, Christoph von der Malsburg
Abstract: We introduce the Cooperative Network Architecture (CNA), a model that represents sensory signals using structured, recurrently connected networks of neurons, termed "nets." Nets are dynamically assembled from overlapping net fragments, which are learned based on statistical regularities in sensory input. This architecture offers robustness to noise, deformation, and generalization to out-of-distribution data, addressing challenges in current vision systems from a novel perspective. We demonstrate that net fragments can be learned without supervision and flexibly recombined to encode novel patterns, enabling figure completion and resilience to noise. Our findings establish CNA as a promising paradigm for developing neural representations that integrate local feature processing with global structure formation, providing a foundation for future research on invariant object recognition.
Authors: Zonghao Chen, Aratrika Mustafi, Pierre Glaser, Anna Korba, Arthur Gretton, Bharath K. Sriperumbudur
Abstract: We introduce a (de)-regularization of the Maximum Mean Discrepancy (DrMMD) and its Wasserstein gradient flow. Existing gradient flows that transport samples from source distribution to target distribution with only target samples, either lack tractable numerical implementation ($f$-divergence flows) or require strong assumptions, and modifications such as noise injection, to ensure convergence (Maximum Mean Discrepancy flows). In contrast, DrMMD flow can simultaneously (i) guarantee near-global convergence for a broad class of targets in both continuous and discrete time, and (ii) be implemented in closed form using only samples. The former is achieved by leveraging the connection between the DrMMD and the $\chi^2$-divergence, while the latter comes by treating DrMMD as MMD with a de-regularized kernel. Our numerical scheme uses an adaptive de-regularization schedule throughout the flow to optimally trade off between discretization errors and deviations from the $\chi^2$ regime. The potential application of the DrMMD flow is demonstrated across several numerical experiments, including a large-scale setting of training student/teacher networks.
Authors: Kang Yang, Yuning Chen, Wan Du
Abstract: We present GRaF, Generalizable Radio-Frequency (RF) Radiance Fields, a framework that models RF signal propagation to synthesize spatial spectra at arbitrary transmitter or receiver locations, where each spectrum measures signal power across all surrounding directions at the receiver. Unlike state-of-the-art methods that adapt vanilla Neural Radiance Fields (NeRF) to the RF domain with scene-specific training, GRaF generalizes across scenes to synthesize spectra. To enable this, we prove an interpolation theory in the RF domain: the spatial spectrum from a transmitter can be approximated using spectra from geographically proximate transmitters. Building on this theory, GRaF comprises two components: (i) a geometry-aware Transformer encoder that captures spatial correlations from neighboring transmitters to learn a scene-independent latent RF radiance field, and (ii) a neural ray tracing algorithm that estimates spectrum reception at the receiver. Experimental results demonstrate that GRaF outperforms existing methods on single-scene benchmarks and achieves state-of-the-art performance on unseen scene layouts.
Authors: Yohei Saito
Abstract: Reservoir computing (RC) is becoming increasingly important because of its short training time. The squared error normalized by the target output is called the information processing capacity (IPC) and is used to evaluate the performance of an RC system. Since RC aims to learn the relationship between input and output time series, we should evaluate the IPC for infinitely long data rather than the IPC for finite-length data. However, a method for estimating it has not been established. We evaluated the IPC for infinitely long data using the asymptotic expansion of the IPC and weighted least-squares fitting. Then, we showed the validity of our method by numerical simulations. This work makes the performance evaluation of RC more evident.
Authors: O. Duranthon, L. Zdeborov\'a
Abstract: Graph neural networks (GNNs) are designed to process data associated with graphs. They are finding an increasing range of applications; however, as with other modern machine learning techniques, their theoretical understanding is limited. GNNs can encounter difficulties in gathering information from nodes that are far apart by iterated aggregation steps. This situation is partly caused by so-called oversmoothing; and overcoming it is one of the practically motivated challenges. We consider the situation where information is aggregated by multiple steps of convolution, leading to graph convolutional networks (GCNs). We analyze the generalization performance of a basic GCN, trained for node classification on data generated by the contextual stochastic block model. We predict its asymptotic performance by deriving the free energy of the problem, using the replica method, in the high-dimensional limit. Calling depth the number of convolutional steps, we show the importance of going to large depth to approach the Bayes-optimality. We detail how the architecture of the GCN has to scale with the depth to avoid oversmoothing. The resulting large depth limit can be close to the Bayes-optimality and leads to a continuous GCN. Technically, we tackle this continuous limit via an approach that resembles dynamical mean-field theory (DMFT) with constraints at the initial and final times. An expansion around large regularization allows us to solve the corresponding equations for the performance of the deep GCN. This promising tool may contribute to the analysis of further deep neural networks.
Authors: Caifeng Zou, Zachary E. Ross, Robert W. Clayton, Fan-Chi Lin, Kamyar Azizzadenesheli
Abstract: Numerical simulations of seismic wave propagation are crucial for investigating velocity structures and improving seismic hazard assessment. However, standard methods such as finite difference or finite element are computationally expensive. Recent studies have shown that a new class of machine learning models, called neural operators, can solve the elastodynamic wave equation orders of magnitude faster than conventional methods. Full waveform inversion is a prime beneficiary of the accelerated simulations. Neural operators, as end-to-end differentiable operators, combined with automatic differentiation, provide an alternative approach to the adjoint-state method. State-of-the-art optimization techniques built into PyTorch provide neural operators with greater flexibility to improve the optimization dynamics of full waveform inversion, thereby mitigating cycle-skipping problems. In this study, we demonstrate the first application of neural operators for full waveform inversion on a real seismic dataset, which consists of several nodal transects collected across the San Gabriel, Chino, and San Bernardino basins in the Los Angeles metropolitan area.
Authors: Reginald McLean, Evangelos Chatzaroulas, Luc McCutcheon, Frank R\"oder, Tianhe Yu, Zhanpeng He, K. R. Zentner, Ryan Julian, J K Terry, Isaac Woungang, Nariman Farsad, Pablo Samuel Castro
Abstract: Meta-World is widely used for evaluating multi-task and meta-reinforcement learning agents, which are challenged to master diverse skills simultaneously. Since its introduction however, there have been numerous undocumented changes which inhibit a fair comparison of algorithms. This work strives to disambiguate these results from the literature, while also leveraging the past versions of Meta-World to provide insights into multi-task and meta-reinforcement learning benchmark design. Through this process we release a new open-source version of Meta-World (https://github.com/Farama-Foundation/Metaworld/) that has full reproducibility of past results, is more technically ergonomic, and gives users more control over the tasks that are included in a task set.
Authors: Zechen Li, Lanqing Yang, Yiheng Bian, Hao Pan, Yongjian Fu, Yezhou Wang, Zhuxi Chen, Yi-Chao Chen, Guangtao Xue
Abstract: Indoor environments typically contain diverse RF signals distributed across multiple frequency bands, including NB-IoT, Wi-Fi, and millimeter-wave. Consequently, wideband RF modeling is essential for practical applications such as joint deployment of heterogeneous RF systems, cross-band communication, and distributed RF sensing. Although 3D Gaussian Splatting (3DGS) techniques effectively reconstruct RF radiance fields at a single frequency, they cannot model fields at arbitrary or unknown frequencies across a wide range. In this paper, we present a novel 3DGS algorithm for unified wideband RF radiance field modeling. RF wave propagation depends on signal frequency and the 3D spatial environment, including geometry and material electromagnetic (EM) properties. To address these factors, we introduce a frequency-embedded EM feature network that utilizes 3D Gaussian spheres at each spatial location to learn the relationship between frequency and transmission characteristics, such as attenuation and radiance intensity. With a dataset containing sparse frequency samples in a specific 3D environment, our model can efficiently reconstruct RF radiance fields at arbitrary and unseen frequencies. To assess our approach, we introduce a large-scale power angular spectrum (PAS) dataset with 50,000 samples spanning 1 to 94 GHz across six indoor environments. Experimental results show that the proposed model trained on multiple frequencies achieves a Structural Similarity Index Measure (SSIM) of 0.922 for PAS reconstruction, surpassing state-of-the-art single-frequency 3DGS models with SSIM of 0.863.
Authors: Yuxin Ren, Maxwell D Collins, Miao Hu, Huanrui Yang
Abstract: While transformers dominate modern vision and language models, their attention mechanism remains poorly suited for in-memory computing (IMC) devices due to intensive activation-to-activation multiplications and non-local memory access, leading to substantial latency and bandwidth overhead on ReRAM-based accelerators. To address this mismatch, we propose FAR, a Function-preserving Attention Replacement framework that substitutes all attention in pretrained DeiTs with sequential modules inherently compatible with IMC dataflows. Specifically, FAR replaces self-attention with a multi-head bidirectional LSTM architecture via block-wise distillation to retain functional equivalence while enabling linear-time computation and localized weight reuse. We further incorporate structured pruning on FAR models, enabling flexible adaptation to resource-constrained IMC arrays while maintaining functional fidelity. Evaluations on the DeiT family demonstrate that FAR maintains comparable accuracy to the original attention-based models on ImageNet and multiple downstream tasks with reduced parameters and latency. Further analysis shows that FAR preserves the semantic token relationships learned by attention while improving computational efficiency, highlighting its potential for energy-efficient transformer inference on IMC-based edge accelerators.
Authors: Mohammadhossein Homaei, Mehran Tarif, Agustin Di Bartolo, Victor Gonzalez Morales, Mar Avila Vegas
Abstract: The Internet of Underwater Things (IoUT) has a lot of problems, like low bandwidth, high latency, mobility, and not enough energy. Routing protocols that were made for land-based networks, like RPL, don't work well in these underwater settings. This paper talks about RL-RPL-UA, a new routing protocol that uses reinforcement learning to make things work better in underwater situations. Each node has a small RL agent that picks the best parent node depending on local data such the link quality, buffer level, packet delivery ratio, and remaining energy. RL-RPL-UA works with all standard RPL messages and adds a dynamic objective function to help people make decisions in real time. Aqua-Sim simulations demonstrate that RL-RPL-UA boosts packet delivery by up to 9.2%, uses 14.8% less energy per packet, and adds 80 seconds to the network's lifetime compared to previous approaches. These results show that RL-RPL-UA is a potential and energy-efficient way to route data in underwater networks.
Authors: Zihan Zhang, Lei Shi, Ding-Xuan Zhou
Abstract: In this paper, we study the binary classification problem on $[0,1]^d$ under the Tsybakov noise condition (with exponent $s \in [0,\infty]$) and the compositional assumption. This assumption requires the conditional class probability function of the data distribution to be the composition of $q+1$ vector-valued multivariate functions, where each component function is either a maximum value function or a H\"{o}lder-$\beta$ smooth function that depends only on $d_*$ of its input variables. Notably, $d_*$ can be significantly smaller than the input dimension $d$. We prove that, under these conditions, the optimal convergence rate for the excess 0-1 risk of classifiers is $\left( \frac{1}{n} \right)^{\frac{\beta\cdot(1\wedge\beta)^q}{{\frac{d_*}{s+1}+(1+\frac{1}{s+1})\cdot\beta\cdot(1\wedge\beta)^q}}}$, which is independent of the input dimension $d$. Additionally, we demonstrate that ReLU deep neural networks (DNNs) trained with hinge loss can achieve this optimal convergence rate up to a logarithmic factor. This result provides theoretical justification for the excellent performance of ReLU DNNs in practical classification tasks, particularly in high-dimensional settings. The generalized approach is of independent interest.
Authors: Daniel Daza, Alberto Bernardi, Luca Costabello, Christophe Gueret, Masoud Mansoury, Michael Cochez, Martijn Schut
Abstract: Methods for query answering over incomplete knowledge graphs retrieve entities that are \emph{likely} to be answers, which is particularly useful when such answers cannot be reached by direct graph traversal due to missing edges. However, existing approaches have focused on queries formalized using first-order-logic. In practice, many real-world queries involve constraints that are inherently vague or context-dependent, such as preferences for attributes or related categories. Addressing this gap, we introduce the problem of query answering with soft constraints. We formalize the problem and introduce two efficient methods designed to adjust query answer scores by incorporating soft constraints without disrupting the original answers to a query. These methods are lightweight, requiring tuning only two parameters or a small neural network trained to capture soft constraints while maintaining the original ranking structure. To evaluate the task, we extend existing QA benchmarks by generating datasets with soft constraints. Our experiments demonstrate that our methods can capture soft constraints while maintaining robust query answering performance and adding very little overhead.
Authors: Elena Camuffo, Francesco Barbato, Mete Ozay, Simone Milani, Umberto Michieli
Abstract: Personalized object detection aims to adapt a general-purpose detector to recognize user-specific instances from only a few examples. Lightweight models often struggle in this setting due to their weak semantic priors, while large vision-language models (VLMs) offer strong object-level understanding but are too computationally demanding for real-time or on-device applications. We introduce MOCHA (Multi-modal Objects-aware Cross-arcHitecture Alignment), a distillation framework that transfers multimodal region-level knowledge from a frozen VLM teacher into a lightweight vision-only detector. MOCHA extracts fused visual and textual teacher's embeddings and uses them to guide student training through a dual-objective loss that enforces accurate local alignment and global relational consistency across regions. This process enables efficient transfer of semantics without the need for teacher modifications or textual input at inference. MOCHA consistently outperforms prior baselines across four personalized detection benchmarks under strict few-shot regimes, yielding a +10.1 average improvement, with minimal inference cost.
Authors: Adrien Goldszal, Diego Calanzone, Vincent Taboga, Pierre-Luc Bacon
Abstract: Most refrigerants currently used in air-conditioning systems, such as hydrofluorocarbons, are potent greenhouse gases and are being phased down. Large-scale molecular screening has been applied to the search for alternatives, but in practice only about 300 refrigerants are known, and only a few additional candidates have been suggested without experimental validation. This scarcity of reliable data limits the effectiveness of purely data-driven methods. We present Refgen, a generative pipeline that integrates machine learning with physics-grounded inductive biases. Alongside fine-tuning for valid molecular generation, Refgen incorporates predictive models for critical properties, equations of state, thermochemical polynomials, and full vapor compression cycle simulations. These models enable reinforcement learning fine-tuning under thermodynamic constraints, enforcing consistency and guiding discovery toward molecules that balance efficiency, safety, and environmental impact. By embedding physics into the learning process, Refgen leverages scarce data effectively and enables de novo refrigerant discovery beyond the known set of compounds.
Authors: Sihan Hu, Xiansheng Cai, Yuan Huang, Zhiyuan Yao, Linfeng Zhang, Pan Zhang, Youjin Deng, Kun Chen
Abstract: Training large language models with Reinforcement Learning with Verifiable Rewards (RLVR) exhibits a set of distinctive and puzzling behaviors that remain poorly understood, including a two-stage learning curve, a V-shaped response-length trajectory, and a pronounced vulnerability to catastrophic forgetting. In this work, we propose that these behaviors are emergent collective phenomena governed not by neural implementation details, but by the topological evolution of the latent reasoning graph in semantic space. By demonstrating a dynamical isomorphism between a 1.5B-parameter LLM and a minimal Concept Network Model (CoNet), we trace the causal source to the self-organization of a sparse concept web pinned to an average degree of two. This geometric perspective provides a unified physical explanation for the observed anomalies: the V-shaped trajectory tracks the evolution from parallel local skill optimization to global network integration; catastrophic forgetting stems from the topological disconnection of critical ``trunk'' edges; and policy collapse arises from the accumulation of sequential transitions at the web's leaf nodes, where broad exploration abruptly freezes into rigid, high-reward trajectories. Identifying a ``maximally frustrated state'' at the transition between learning stages, we propose Annealed-RLVR, a principled algorithm that injects a targeted SFT ``heating'' step to resolve this topological bottleneck. Experiments confirm that this theory-driven intervention outperforms standard RLVR on both in-distribution and out-of-distribution benchmarks (including Minerva and AIME). By recasting RLVR from black-box optimization into a predictable process of structural self-organization, our work provides a new physical intuition for engineering the emergent reasoning capabilities of future AI systems.
Authors: Ali Farki, Elaheh Moradi, Deepika Koundal, Jussi Tohka
Abstract: Predicting future brain state from a baseline magnetic resonance image (MRI) is a central challenge in neuroimaging and has important implications for studying neurodegenerative diseases such as Alzheimer's disease (AD). Most existing approaches predict future cognitive scores or clinical outcomes, such as conversion from mild cognitive impairment to dementia. Instead, here we investigate longitudinal MRI image-to-image prediction that forecasts a participant's entire brain MRI several years into the future, intrinsically modeling complex, spatially distributed neurodegenerative patterns. We implement and evaluate five deep learning architectures (UNet, U2-Net, UNETR, Time-Embedding UNet, and ODE-UNet) on two longitudinal cohorts (ADNI and AIBL). Predicted follow-up MRIs are directly compared with the actual follow-up scans using metrics that capture global similarity and local differences. The best performing models achieve high-fidelity predictions, and all models generalize well to an independent external dataset, demonstrating robust cross-cohort performance. Our results indicate that deep learning can reliably predict participant-specific brain MRI at the voxel level, offering new opportunities for individualized prognosis.
Authors: Masahiro Tanaka
Abstract: In this study, a scalable online kernel learning framework is proposed for estimating bidirectional causal effects in systems characterized by mutual dependence and heteroskedasticity. Traditional causal inference often focuses on unidirectional effects, overlooking the common bidirectional relationships in real-world phenomena. Building on heteroskedasticity-based identification, the proposed method integrates a quasi-maximum likelihood estimator for simultaneous equation models with large scale online kernel learning. It employs random Fourier feature approximations to flexibly model nonlinear conditional means and variances, while an adaptive online gradient descent algorithm ensures computational efficiency for streaming and high-dimensional data. Results from extensive simulations demonstrate that the proposed method achieves superior accuracy and stability than single equation and polynomial approximation baselines, exhibiting lower bias and root mean squared error across various data-generating processes. These results confirm that the proposed approach effectively captures complex bidirectional causal effects with near-linear computational scaling. By combining econometric identification with modern machine learning techniques, the proposed framework offers a practical, scalable, and theoretically grounded solution for large scale causal inference in natural/social science, policy making, business, and industrial applications.
Authors: Shaowen Wang, Yiqi Dong, Ruinian Chang, Tansheng Zhu, Yuebo Sun, Kaifeng Lyu, Jian Li
Abstract: Despite substantial advances, large language models (LLMs) continue to exhibit hallucinations, generating plausible yet incorrect responses. In this paper, we highlight a critical yet previously underexplored class of hallucinations driven by spurious correlations -- superficial but statistically prominent associations between features (e.g., surnames) and attributes (e.g., nationality) present in the training data. We demonstrate that these spurious correlations induce hallucinations that are confidently generated, immune to model scaling, evade current detection methods, and persist even after refusal fine-tuning. Through systematically controlled synthetic experiments and empirical evaluations on state-of-the-art open-source and proprietary LLMs (including GPT-5), we show that existing hallucination detection methods, such as confidence-based filtering and inner-state probing, fundamentally fail in the presence of spurious correlations. Our theoretical analysis further elucidates why these statistical biases intrinsically undermine confidence-based detection techniques. Our findings thus emphasize the urgent need for new approaches explicitly designed to address hallucinations caused by spurious correlations.
Authors: Shourya Batra, Pierce Tillman, Samarth Gaggar, Shashank Kesineni, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Vasu Sharma, Maheep Chaudhary
Abstract: As Large Language Models (LLMs) evolve into personal assistants with access to sensitive user data, they face a critical privacy challenge: while prior work has addressed output-level privacy, recent findings reveal that LLMs often leak private information through their internal reasoning processes, violating contextual privacy expectations. These leaky thoughts occur when models inadvertently expose sensitive details in their reasoning traces, even when final outputs appear safe. The challenge lies in preventing such leakage without compromising the model's reasoning capabilities, requiring a delicate balance between privacy and utility. We introduce Steering Activations towards Leakage-free Thinking (SALT), a lightweight test-time intervention that mitigates privacy leakage in model's Chain of Thought (CoT) by injecting targeted steering vectors into hidden state. We identify the high-leakage layers responsible for this behavior. Through experiments across multiple LLMs, we demonstrate that SALT achieves reductions including $18.2\%$ reduction in CPL on QwQ-32B, $17.9\%$ reduction in CPL on Llama-3.1-8B, and $31.2\%$ reduction in CPL on Deepseek in contextual privacy leakage dataset AirGapAgent-R while maintaining comparable task performance and utility. Our work establishes SALT as a practical approach for test-time privacy protection in reasoning-capable language models, offering a path toward safer deployment of LLM-based personal agents.
Authors: Gioliano de Oliveira Braga, Pedro Henrique dos Santos Rocha, Rafael Pimenta de Mattos Paix\~ao, Giovani Hoff da Costa, Gustavo Cavalcanti Morais, Louren\c{c}o Alves Pereira J\'unior
Abstract: Wi-Fi Channel State Information (CSI) has been repeatedly proposed as a biometric modality, often with reports of high accuracy and operational feasibility. However, the field lacks a consolidated understanding of its security properties, adversarial resilience, and methodological consistency. This Systematization of Knowledge (SoK) examines CSI-based biometric authentication through a security lens, analyzing how existing works diverge in sensing infrastructure, signal representations, feature pipelines, learning models, and evaluation methodologies. Our synthesis reveals systemic inconsistencies: reliance on aggregate accuracy metrics, limited reporting of FAR/FRR/EER, absence of per-user risk analysis, and scarce consideration of threat models or adversarial feasibility. To this end, we construct a unified evaluation framework to expose these issues empirically and demonstrate how security-relevant metrics such as per-class EER, Frequency Count of Scores (FCS), and the Gini Coefficient uncover risk concentration that remains hidden under traditional reporting practices. The resulting analysis highlights concrete attack surfaces--including replay, geometric mimicry, and environmental perturbation--and shows how methodological choices materially influence vulnerability profiles. Based on these findings, we articulate the security boundaries of current CSI biometrics and provide guidelines for rigorous evaluation, reproducible experimentation, and future research directions. This SoK offers the security community a structured, evidence-driven reassessment of Wi-Fi CSI biometrics and their suitability as an authentication primitive.
Authors: Chunqiu Steven Xia, Zhe Wang, Yan Yang, Yuxiang Wei, Lingming Zhang
Abstract: Large Language Models (LLMs) are reshaping almost all industries, including software engineering. In recent years, a number of LLM agents have been proposed to solve real-world software problems. Such software agents are typically equipped with a suite of coding tools and can autonomously decide the next actions to form complete trajectories to solve end-to-end software tasks. While promising, they typically require dedicated design and may still be suboptimal, since it can be extremely challenging and costly to exhaust the entire agent scaffold design space. Recognizing that software agents are inherently software themselves that can be further refined/modified, researchers have proposed a number of self-improving software agents recently, including the Darwin-G\"odel Machine (DGM). Meanwhile, such self-improving agents require costly offline training on specific benchmarks and may not generalize well across different LLMs or benchmarks. In this paper, we propose Live-SWE-agent, the first live software agent that can autonomously and continuously evolve itself on-the-fly during runtime when solving real-world software problems. More specifically, Live-SWE-agent starts with the most basic agent scaffold with only access to bash tools (e.g., mini-SWE-agent), and autonomously evolves its own scaffold implementation while solving real-world software problems. Our evaluation on the widely studied SWE-bench Verified benchmark shows that LIVE-SWE-AGENT can achieve an impressive solve rate of 77.4% without test-time scaling, outperforming all existing software agents, including the best proprietary solution. Moreover, Live-SWE-agent outperforms state-of-the-art manually crafted software agents on the recent SWE-Bench Pro benchmark, achieving the best-known solve rate of 45.8%.