arXiv:2602.18807v1 Announce Type: cross Abstract: We evaluate GPTutor, an LLM-powered tutoring system for an undergraduate discrete mathematics course. It integrates two LLM-supported tools: a structured proof-review tool that provides embedded feedback on students' written proof attempts, and a chatbot for math questions. In a staggered-access study with 148 students, earlier access was associated with higher homework performance during the interval when only the experimental group could use the system, while we did not observe this performance increase transfer to exam scores. Usage logs show that students with lower self-efficacy and prior exam performance used both components more frequently. Session-level behavioral labels, produced by human coding and scaled using an automated classifier, characterize how students engaged with the chatbot (e.g., answer-seeking or help-seeking). In models controlling for prior performance and self-efficacy, higher chatbot usage and answer-seeking behavior were negatively associated with subsequent midterm performance, whereas proof-review usage showed no detectable independent association. Together, the findings suggest that chatbot-based support alone may not reliably support transfer to independent assessment of math proof-learning outcomes, whereas work-anchored, structured feedback appears less associated with reduced learning.

arXiv:2602.19207v1 Announce Type: cross Abstract: Federated learning (FL) is a privacy-preserving machine learning paradigm that enables multiple parties to collaboratively train models on privately owned data without sharing raw information. While standard FL typically addresses either horizontal or vertical data partitions, many real-world scenarios exhibit a complex hybrid distribution. This paper proposes Hybrid Federated Learning (HybridFL) to address data split both horizontally across disjoint users and vertically across complementary feature sets. We evaluate HybridFL in a financial crime detection context, where a transaction party holds transaction-level attributes and multiple banks maintain private account-level features. By integrating horizontal aggregation and vertical feature fusion, the proposed architecture enables joint learning while strictly preserving data locality. Experiments on AMLSim and SWIFT datasets demonstrate that HybridFL significantly outperforms the transaction-only local model and achieves performance comparable to a centralized benchmark.

arXiv:2602.20028v1 Announce Type: cross Abstract: Accurate taxonomic identification is the cornerstone of biodiversity monitoring and agricultural management, particularly for the hyper-diverse superfamily Ichneumonoidea. Comprising the families Ichneumonidae and Braconidae, these parasitoid wasps are ecologically critical for regulating insect populations, yet they remain one of the most taxonomically challenging groups due to their cryptic morphology and vast number of undescribed species. To address the scarcity of robust digital resources for these key groups, we present a curated image dataset designed to advance automated identification systems. The dataset contains 3,556 high-resolution images, primarily focused on Neotropical Ichneumonidae and Braconidae, while also including supplementary families such as Andrenidae, Apidae, Bethylidae, Chrysididae, Colletidae, Halictidae, Megachilidae, Pompilidae, and Vespidae to improve model robustness. Crucially, a subset of 1,739 images is annotated in COCO format, featuring multi-class bounding boxes for the full insect body, wing venation, and scale bars. This resource provides a foundation for developing computer vision models capable of identifying these families.

arXiv:2404.09877v3 Announce Type: replace Abstract: In the rapidly changing environments of disaster response, planning and decision-making for autonomous agents involve complex and interdependent choices. Although recent advancements have improved traditional artificial intelligence (AI) approaches, they often struggle in such settings, particularly when applied to agents operating outside their well-defined training parameters. To address these challenges, we propose an attention-based cognitive architecture inspired by Dual Process Theory (DPT). This framework integrates, in an online fashion, rapid yet heuristic (human-like) responses (System 1) with the slow but optimized planning capabilities of machine intelligence (System 2). We illustrate how a supervisory controller can dynamically determine in real-time the engagement of either system to optimize mission objectives by assessing their performance across a number of distinct attributes. Evaluated for trajectory planning in dynamic environments, our framework demonstrates that this synergistic integration effectively manages complex tasks by optimizing multiple mission objectives.

arXiv:2602.17385v2 Announce Type: replace Abstract: Task Arithmetic yields a modular, scalable way to adapt foundation models. Combining multiple task vectors, however, can lead to cross-task interference, causing representation drift and degraded performance. Representation drift regularization provides a natural remedy to disentangle task vectors; however, existing approaches typically require external task data, conflicting with modularity and data availability constraints (e.g., privacy requirements). We propose a dataless approach by framing regularization against representation drift as a curvature matrix approximation problem. This allows us to leverage well-established techniques; in particular, we adopt Kronecker-Factored Approximate Curvature and obtain a practical regularizer that achieves state-of-the-art results in task addition and negation. Our method has constant complexity in the number of tasks and promotes robustness to task vector rescaling, eliminating the need for held-out tuning.

arXiv:2507.23465v3 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly deployed in enterprise settings, controlling model behavior based on user roles becomes an essential requirement. Existing safety methods typically assume uniform access and focus on preventing harmful or toxic outputs, without addressing role-specific access constraints. In this work, we investigate whether LLMs can be fine-tuned to generate responses that reflect the access privileges associated with different organizational roles. We explore three modeling strategies: a BERT-based classifier, an LLM-based classifier, and role-conditioned generation. To evaluate these approaches, we construct two complementary datasets. The first is adapted from existing instruction-tuning corpora through clustering and role labeling, while the second is synthetically generated to reflect realistic, role-sensitive enterprise scenarios. We assess model performance across varying organizational structures and analyze robustness to prompt injection, role mismatch, and jailbreak attempts.

arXiv:2509.19405v2 Announce Type: replace-cross Abstract: Accurate outdoor positioning in cellular networks is hindered by sparse, heterogeneous measurement collections and the high cost of exhaustive site surveys. This paper introduces a lightweight, modular mobile data augmentation framework designed to enhance multi-cell fingerprinting-based positioning using operator-collected minimization of drive test (MDT) records. The proposed approach decouples spatial and radio-feature synthesis: kernel density estimation (KDE) models the empirical spatial distribution to generate geographically coherent synthetic locations, while a k-nearest-neighbor (KNN)-based block produces augmented per-cell radio fingerprints. The architecture is intentionally training-free, interpretable, and suitable for distributed or on-premise operator deployments, supporting privacy-aware workflows. We both validate each augmentation module independently and assess its end-to-end impact on fingerprinting-based positioning using a real-world MDT dataset provided by an Italian mobile network operator across diverse urban and peri-urban scenarios. Results show that the proposed KDE-KNN augmentation consistently improves positioning performance with respect to state-of-the-art approaches, reducing the median positioning error by up to 30% in the most sparsely sampled or structurally complex regions. We also observe region-dependent saturation effects, which emerge most rapidly in scenarios with high user density where the information gain from additional synthetic samples quickly diminishes. Overall, the framework offers a practical, low-complexity path to enhance operator positioning services using existing mobile data traces.

arXiv:2510.11390v2 Announce Type: replace-cross Abstract: We present a systematic study of medical-domain interpretability in Large Language Models (LLMs). We study how the LLMs both represent and process medical knowledge through four different interpretability techniques: (1) UMAP projections of intermediate activations, (2) gradient-based saliency with respect to the model weights, (3) layer lesioning/removal and (4) activation patching. We present knowledge maps of five LLMs which show, at a coarse-resolution, where knowledge about patient's ages, medical symptoms, diseases and drugs is stored in the models. In particular for Llama3.3-70B, we find that most medical knowledge is processed in the first half of the model's layers. In addition, we find several interesting phenomena: (i) age is often encoded in a non-linear and sometimes discontinuous manner at intermediate layers in the models, (ii) the disease progression representation is non-monotonic and circular at certain layers of the model, (iii) in Llama3.3-70B, drugs cluster better by medical specialty rather than mechanism of action, especially for Llama3.3-70B and (iv) Gemma3-27B and MedGemma-27B have activations that collapse at intermediate layers but recover by the final layers. These results can guide future research on fine-tuning, un-learning or de-biasing LLMs for medical tasks by suggesting at which layers in the model these techniques should be applied.

arXiv:2602.13427v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used to produce such models. Prior work on backdoor attacks has largely focused on a black-box threat model, with an adversary targeting the model builder's LLM. However, in the bias manipulation setting, the model builder themselves could be the adversary, warranting a white-box threat model where the attacker's ability to poison, and manipulate the poisoned data is substantially increased. Furthermore, despite growing research in semantically-triggered backdoors, most studies have limited themselves to syntactically-triggered attacks. Motivated by these limitations, we conduct an analysis consisting of over 1000 evaluations using higher poisoning ratios and greater data augmentation to gain a better understanding of the potential of syntactically- and semantically-triggered backdoor attacks in a white-box setting. In addition, we study whether two representative defense paradigms, model-intrinsic and model-extrinsic backdoor removal, are able to mitigate these attacks. Our analysis reveals numerous new findings. We discover that while both syntactically- and semantically-triggered attacks can effectively induce the target behaviour, and largely preserve utility, semantically-triggered attacks are generally more effective in inducing negative biases, while both backdoor types struggle with causing positive biases. Furthermore, while both defense types are able to mitigate these backdoors, they either result in a substantial drop in utility, or require high computational overhead.

arXiv:2602.14106v1 Announce Type: cross Abstract: The most valuable asset of any cloud-based organization is data, which is increasingly exposed to sophisticated cyberattacks. Until recently, the implementation of security measures in DevOps environments was often considered optional by many government entities and critical national services operating in the cloud. This includes systems managing sensitive information, such as electoral processes or military operations, which have historically been valuable targets for cybercriminals. Resistance to security implementation is often driven by concerns over losing agility in software development, increasing the risk of accumulated vulnerabilities. Nowadays, patching software is no longer enough; adopting a proactive cyber defense strategy, supported by Artificial Intelligence (AI), is crucial to anticipating and mitigating threats. Thus, this work proposes integrating the Security Chaos Engineering (SCE) methodology with a new LLM-based flow to automate the creation of attack defense trees that represent adversary behavior and facilitate the construction of SCE experiments based on these graphical models, enabling teams to stay one step ahead of attackers and implement previously unconsidered defenses. Further detailed information about the experiment performed, along with the steps to replicate it, can be found in the following repository: https://github.com/mariomc14/devsecops-adversary-llm.git.

arXiv:2602.14365v1 Announce Type: cross Abstract: Rheumatoid arthritis (RA) is an autoimmune disease characterized by systemic joint inflammation. Early diagnosis and tight follow-up are essential to the management of RA, as ongoing inflammation can cause irreversible joint damage. The detection of arthritis is important for diagnosis and assessment of disease activity; however, it often takes a long time for patients to receive appropriate specialist care. Therefore, there is a strong need to develop systems that can detect joint inflammation easily using RGB images captured at home. Consequently, we tackle the task of RA inflammation detection from RGB hand images. This task is highly challenging due to general issues in medical imaging, such as the scarcity of positive samples, data imbalance, and the inherent difficulty of the task itself. However, to the best of our knowledge, no existing work has explicitly addressed these challenges in RGB-based RA inflammation detection. This paper quantitatively demonstrates the difficulty of visually detecting inflammation by constructing a dedicated dataset, and we propose a inflammation detection framework with global local encoder that combines self-supervised pretraining on large-scale healthy hand images with imbalance-aware training to detect RA-related joint inflammation from RGB hand images. Our experiments demonstrated that the proposed approach improves F1-score by 0.2 points and Gmean by 0.25 points compared with the baseline model.

arXiv:2602.14423v1 Announce Type: cross Abstract: Data augmentation is one of the most widely used techniques to improve generalization in modern machine learning, often justified by its ability to promote invariance to label-irrelevant transformations. However, its theoretical role remains only partially understood. In this work, we propose an information-theoretic framework that systematically accounts for the effect of augmentation on generalization and invariance learning. Our approach builds upon mutual information-based bounds, which relate the generalization gap to the amount of information a learning algorithm retains about its training data. We extend this framework by modeling the augmented distribution as a composition of the original data distribution with a distribution over transformations, which naturally induces an orbit-averaged loss function. Under mild sub-Gaussian assumptions on the loss function and the augmentation process, we derive a new generalization bound that decompose the expected generalization gap into three interpretable terms: (1) a distributional divergence between the original and augmented data, (2) a stability term measuring the algorithm dependence on training data, and (3) a sensitivity term capturing the effect of augmentation variability. To connect our bounds to the geometry of the augmentation group, we introduce the notion of group diameter, defined as the maximal perturbation that augmentations can induce in the input space. The group diameter provides a unified control parameter that bounds all three terms and highlights an intrinsic trade-off: small diameters preserve data fidelity but offer limited regularization, while large diameters enhance stability at the cost of increased bias and sensitivity. We validate our theoretical bounds with numerical experiments, demonstrating that it reliably tracks and predicts the behavior of the true generalization gap.

arXiv:2602.14486v1 Announce Type: cross Abstract: The Platonic Representation Hypothesis suggests that representations from neural networks are converging to a common statistical model of reality. We show that the existing metrics used to measure representational similarity are confounded by network scale: increasing model depth or width can systematically inflate representational similarity scores. To correct these effects, we introduce a permutation-based null-calibration framework that transforms any representational similarity metric into a calibrated score with statistical guarantees. We revisit the Platonic Representation Hypothesis with our calibration framework, which reveals a nuanced picture: the apparent convergence reported by global spectral measures largely disappears after calibration, while local neighborhood similarity, but not local distances, retains significant agreement across different modalities. Based on these findings, we propose the Aristotelian Representation Hypothesis: representations in neural networks are converging to shared local neighborhood relationships.

arXiv:2602.06855v3 Announce Type: replace Abstract: LLM agents hold significant promise for advancing scientific research. To accelerate this progress, we introduce AIRS-Bench (the AI Research Science Benchmark), a suite of 20 tasks sourced from state-of-the-art machine learning papers. These tasks span diverse domains, including language modeling, mathematics, bioinformatics, and time series forecasting. AIRS-Bench tasks assess agentic capabilities over the full research lifecycle -- including idea generation, experiment analysis and iterative refinement -- without providing baseline code. The AIRS-Bench task format is versatile, enabling easy integration of new tasks and rigorous comparison across different agentic frameworks. We establish baselines using frontier models paired with both sequential and parallel scaffolds. Our results show that agents exceed human SOTA in four tasks but fail to match it in sixteen others. Even when agents surpass human benchmarks, they do not reach the theoretical performance ceiling for the underlying tasks. These findings indicate that AIRS-Bench is far from saturated and offers substantial room for improvement. We open-source the AIRS-Bench task definitions and evaluation code to catalyze further development in autonomous scientific research.

arXiv:2502.12581v4 Announce Type: replace-cross Abstract: Reliably labelling data typically requires annotations from multiple human workers. However, humans are far from being perfect. Hence, it is a common practice to aggregate labels gathered from multiple annotators to make a more confident estimate of the true label. Among many aggregation methods, the simple and well known Majority Vote (MV) selects the class label polling the highest number of votes. However, despite its importance, the optimality of MV's label aggregation has not been extensively studied. We address this gap in our work by characterising the conditions under which MV achieves the theoretically optimal lower bound on label estimation error. Our results capture the tolerable limits on annotation noise under which MV can optimally recover labels for a given class distribution. This certificate of optimality provides a more principled approach to model selection for label aggregation as an alternative to otherwise inefficient practices that sometimes include higher experts, gold labels, etc., that are all marred by the same human uncertainty despite huge time and monetary costs. Experiments on both synthetic and real world data corroborate our theoretical findings.

arXiv:2507.04704v2 Announce Type: replace-cross Abstract: Understanding how cellular morphology, gene expression, and spatial context jointly shape tissue function is a central challenge in biology. Image-based spatial transcriptomics technologies now provide high-resolution measurements of cell images and gene expression profiles, but existing methods typically analyze these modalities in isolation or at limited resolution. We address the problem by introducing SPATIA, a multi-level generative and predictive model that learns unified, spatially aware representations by fusing morphology, gene expression, and spatial context from the cell to the tissue level. SPATIA also incorporates a novel spatially conditioned generative framework for predicting cell morphologies under perturbations. Specifically, we propose a confidence-aware flow matching objective that reweights weak optimal-transport pairs based on uncertainty. We further apply morphology-profile alignment to encourage biologically meaningful image generation, enabling the modeling of microenvironment-dependent phenotypic transitions. We assembled a multi-scale dataset consisting of 25.9 million cell-gene pairs across 17 tissues. We benchmark SPATIA against 18 models across 12 tasks, spanning categories such as phenotype generation, annotation, clustering, gene imputation, and cross-modal prediction. SPATIA achieves improved performance over state-of-the-art models, improving generative fidelity by 8% and predictive accuracy by up to 3%.

arXiv:2508.19278v2 Announce Type: replace-cross Abstract: Simulated environments have proven invaluable in Autonomous Cyber Operations (ACO) where Reinforcement Learning (RL) agents can be trained without the computational overhead of emulation. These environments must accurately represent cybersecurity scenarios while producing the necessary signals to support RL training. In this study, we present a framework where we first extend CybORG's Cage Challenge 2 environment by implementing three new actions: Patch, Isolate, and Unisolate, to better represent the capabilities available to human operators in real-world settings. We then propose a design for agent development where we modify the reward signals and the agent's feature space to enhance training performance. To validate these modifications, we train DQN and PPO agents in the updated environment. Our study demonstrates that CybORG can be extended with additional realistic functionality, while maintaining its ability to generate informative training signals for RL agents.

arXiv:2509.05311v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has shown great potential for autonomous decision-making in the cybersecurity domain, enabling agents to learn through direct environment interaction. However, RL agents in Autonomous Cyber Operations (ACO) typically learn from scratch, requiring them to execute undesirable actions to learn their consequences. In this study, we integrate external knowledge in the form of a Large Language Model (LLM) pretrained on cybersecurity data that our RL agent can directly leverage to make informed decisions. By guiding initial training with an LLM, we improve baseline performance and reduce the need for exploratory actions with obviously negative outcomes. We evaluate our LLM-integrated approach in a simulated cybersecurity environment, and demonstrate that our guided agent achieves over 2x higher rewards during early training and converges to a favorable policy approximately 4,500 episodes faster than the baseline.