# Research Papers — 2026-03 · bundle page 49 of 243 > Full-text markdown of papers #2401–2450 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/49 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/48.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/50.md) ### C-STEP: Continuous Space-Time Empowerment for Physics-informed Safe Reinforcement Learning of Mobile Agents Authors: Guihlerme Daubt, Adrian Redder Published: 2026-03-25 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2603.24241v1 Safe navigation in complex environments remains a central challenge for reinforcement learning (RL) in robotics. This paper introduces Continuous Space-Time Empowerment for Physics-informed (C-STEP) safe RL, a novel measure of agent-centric safety tailored to deterministic, continuous domains. This measure can be used to design physics-informed intrinsic rewards by augmenting positive navigation reward functions. The reward incorporates the agents internal states (e.g., initial velocity) and forward dynamics to differentiate safe from risky behavior. By integrating C-STEP with navigation rewards, we obtain an intrinsic reward function that jointly optimizes task completion and collision avoidance. Numerical results demonstrate fewer collisions, reduced proximity to obstacles, and only marginal increases in travel time. Overall, C-STEP offers an interpretable, physics-informed approach to reward shaping in RL, contributing to safety for agentic mobile robotic systems. --- ### InstanceRSR: Real-World Super-Resolution via Instance-Aware Representation Alignment Authors: Zixin Guo, Kai Zhao, Luyan Zhang Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24240v1 Existing real-world super-resolution (RSR) methods based on generative priors have achieved remarkable progress in producing high-quality and globally consistent reconstructions. However, they often struggle to recover fine-grained details of diverse object instances in complex real-world scenes. This limitation primarily arises because commonly adopted denoising losses (e.g., MSE) inherently favor global consistency while neglecting instance-level perception and restoration. To address this issue, we propose InstanceRSR, a novel RSR framework that jointly models semantic information and introduces instance-level feature alignment. Specifically, we employ low-resolution (LR) images as global consistency guidance while jointly modeling image data and semantic segmentation maps to enforce semantic relevance during sampling. Moreover, we design an instance representation learning module to align the diffusion latent space with the instance latent space, enabling instance-aware feature alignment, and further incorporate a scale alignment mechanism to enhance fine-grained perception and detail recovery. Benefiting from these designs, our approach not only generates photorealistic details but also preserves semantic consistency at the instance level. Extensive experiments on multiple real-world benchmarks demonstrate that InstanceRSR significantly outperforms existing methods in both quantitative metrics and visual quality, achieving new state-of-the-art (SOTA) performance. --- ### DVM: A Bytecode Virtual Machine Approach for Dynamic Tensor Computation Authors: Jingzhi Fang, Xiong Gao, Renwei Zhang, Zichun Ye, Lei Chen, Jie Zhao, Chengnuo Huang, Hui Xu, Xuefeng Jin Published: 2026-03-25 Categories: cs.PL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.24239v2 Dynamism is common in AI computation, e.g., the dynamic tensor shapes and the dynamic control flows in models. Due to the long compilation time, existing runtime compilation damages the model efficiency, while the offline compilers either suffer from the long compilation time and device memory footprint to cover all the possible execution instances of a dynamic model, or sacrifice optimization opportunities for usability. In this paper, we rethink the feasibility of runtime compilation for dynamic models and identify that the key for it to work is to speed up the compilation or hide the compilation overhead. To do this, we propose a real-time compiler, DVM. In DVM, we design a runtime operator compiler based on a bytecode virtual machine to perform effective and efficient compilation for each dynamic operator instance given its input. Specifically, instead of compiling programs into machine code, we encode the operator program into bytecode on the CPU and decode the bytecode into virtual instructions for direct execution on the NPU. Based on the runtime operator compiler, we further propose an operator fuser, which performs symbol-deduction-based fusion on static graphs and runtime fusion on dynamic graphs. Both pattern- and stacking-based fusion are supported to increase fusion opportunities. Evaluation on operators, subgraphs, and models shows that, compared with TorchInductor, PyTorch-eager and MindSpore-graph-O0, we are up to 11.77$\times$ better in terms of the operator/model efficiency and up to 5 orders of magnitude faster in terms of the maximum compilation time. --- ### Attack Assessment and Augmented Identity Recognition for Human Skeleton Data Authors: Joseph G. Zalameda, Megan A. Witherow, Alexander M. Glandon, Jose Aguilera, Khan M. Iftekharuddin Published: 2026-03-25 Categories: cs.LG, cs.CR, cs.CV arXiv: https://arxiv.org/abs/2603.24232v1 Machine learning models trained on small data sets for security applications are especially vulnerable to adversarial attacks. Person identification from LiDAR based skeleton data requires time consuming and expensive data acquisition for each subject identity. Recently, Assessment and Augmented Identity Recognition for Skeletons (AAIRS) has been used to train Hierarchical Co-occurrence Networks for Person Identification (HCN-ID) with small LiDAR based skeleton data sets. However, AAIRS does not evaluate robustness of HCN-ID to adversarial attacks or inoculate the model to defend against such attacks. Popular perturbation-based approaches to generating adversarial attacks are constrained to targeted perturbations added to real training samples, which is not ideal for inoculating models with small training sets. Thus, we propose Attack-AAIRS, a novel addition to the AAIRS framework. Attack-AAIRS leverages a small real data set and a GAN generated synthetic data set to assess and improve model robustness against unseen adversarial attacks. Rather than being constrained to perturbations of limited real training samples, the GAN learns the distribution of adversarial attack samples that exploit weaknesses in HCN-ID. Attack samples drawn from this distribution augment training for inoculation of the HCN-ID to improve robustness. Ten-fold cross validation of Attack-AAIRS yields increased robustness to unseen attacks- including FGSM, PGD, Additive Gaussian Noise, MI-FGSM, and BIM. The HCN-ID Synthetic Data Quality Score for Attack-AAIRS indicates that generated attack samples are of similar quality to the original benign synthetic samples generated by AAIRS. Furthermore, inoculated models show consistent final test accuracy with the original model trained on real data, demonstrating that our method improves robustness to adversarial attacks without reducing test performance on real data. --- ### When Annotators Agree but Labels Disagree: The Projection Problem in Stance Detection Authors: Bowen Zhang Published: 2026-03-25 Categories: cs.CL, cs.SI arXiv: https://arxiv.org/abs/2603.24231v2 Stance detection is nearly always formulated as classifying text into Favor, Against, or Neutral. This convention was inherited from debate analysis and has been applied without modification to social media since SemEval-2016. However, attitudes toward complex targets are not unitary. A person can accept climate science while opposing carbon taxes, expressing support on one dimension and opposition on another. When annotators must compress such multi-dimensional attitudes into a single label, different annotators may weight different dimensions, producing disagreement that reflects different compression choices rather than confusion. We call this the projection problem. We conduct an annotation study across five targets from three stance benchmarks (SemEval-2016, P-Stance, COVID-19-Stance), with the same three annotators labeling all targets. For each target, annotators assign both a standard stance label and per-dimension judgments along target-specific dimensions discovered through bottom-up analysis, using the same number of categories for both. Across all fifteen target--dimension pairs, dimensional agreement consistently exceeds label agreement. The gap appears to scale with target complexity: modest for a single-entity target like Joe Biden (AC1: 0.87 vs. 0.95), but large for a multi-faceted policy target like school closures (AC1: 0.21 vs. 0.71). --- ### Identification of NMF by choosing maximum-volume basis vectors Authors: Qianqian Qi, Zhongming Chen, Peter G. M. van der Heijden Published: 2026-03-25 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2603.24227v1 In nonnegative matrix factorization (NMF), minimum-volume-constrained NMF is a widely used framework for identifying the solution of NMF by making basis vectors as similar as possible. This typically induces sparsity in the coefficient matrix, with each row containing zero entries. Consequently, minimum-volume-constrained NMF may fail for highly mixed data, where such sparsity does not hold. Moreover, the estimated basis vectors in minimum-volume-constrained NMF may be difficult to interpret as they may be mixtures of the ground truth basis vectors. To address these limitations, in this paper we propose a new NMF framework, called maximum-volume-constrained NMF, which makes the basis vectors as distinct as possible. We further establish an identifiability theorem for maximum-volume-constrained NMF and provide an algorithm to estimate it. Experimental results demonstrate the effectiveness of the proposed method. --- ### UniScale: Synergistic Entire Space Data and Model Scaling for Search Ranking Authors: Liren Yu, Caiyuan Li, Feiyi Dong, Tao Zhang, Zhixuan Zhang, Dan Ou, Haihong Tang, Bo Zheng Published: 2026-03-25 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2603.24226v4 Recent advances in Large Language Models (LLMs) have inspired a surge of scaling research in industrial search, advertising, and recommendation systems. However, existing approaches focus mainly on architectural improvements, overlooking the critical synergy between data and architecture design. We observe that scaling model parameters alone exhibits diminishing returns, and that the performance degradation caused by complex heterogeneous data distributions is often irrecoverable through model design alone. In this paper, we propose UniScale, a novel co-design framework that jointly optimizes data and architecture to unlock the full potential of model scaling. UniScale includes two core parts: (1) ES$^3$ (Entire-Space Sample System), a high-quality data scaling system that expands the training signal beyond conventional sampling strategies through intra-domain expansion with hierarchical label attribution and cross-domain searchification; and (2) HHSFT (Heterogeneous Hierarchical Sample Fusion Transformer), a novel architecture that effectively models the complex heterogeneous distribution of scaled data via Heterogeneous Hierarchical Feature Interaction and Entire Space User Interest Fusion, thereby surpassing the performance ceiling of structure-only model tuning. Extensive experiments on large-scale industrial datasets demonstrate that UniScale achieves significant improvements and exhibits clear scaling trends. Online A/B tests on a real-world E-commerce search platform confirm that UniScale consistently outperforms strong production baselines, achieving 1.70% and 2.04% increases in user purchase and Gross Merchandise Value (GMV). --- ### Joint Model Parameter Scaling and Universal-Domain Data Integration for E-commerce Search Ranking Authors: Liren Yu, Caiyuan Li, Feiyi Dong, Tao Zhang, Zhixuan Zhang, Dan Ou, Haihong Tang, Bo Zheng Published: 2026-03-25 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2603.24226v3 Scaling studies for industrial search, advertising, and recommendation have largely emphasized enlarging model capacity or refining architectures. Yet in real-world systems, performance is constrained not only by model size but also by the quality and distribution of training data. Our empirical analysis shows two key bottlenecks: increasing parameters alone yields progressively smaller gains, and the challenges introduced by heterogeneous, large-scale behavior data cannot be fully resolved by architecture tuning in isolation. To address this issue, we present UniScale, a unified framework that couples data scaling with model design. UniScale consists of two components. First, ES$^3$, an entire-space sample construction system, broadens supervision beyond conventional sampled training data by enriching intra-domain search contexts with globally attributed supervisory signals and introducing cross-domain examples that reflect user decisions under comparable content exposure conditions. Second, HHSFT, a heterogeneous hierarchical fusion transformer, is tailored to exploit the resulting large-scale heterogeneous data through hierarchical feature interaction and user-interest fusion across the entire behavior space. Together, these components enable more effective scaling than structure-centric optimization alone. Experiments show that UniScale consistently improves offline performance and demonstrates favorable scaling behavior. In online A/B tests on a large e-commerce search platform, it delivers a 1.70% increase in purchases and a 2.04% lift in GMV. --- ### RVLM: Recursive Vision-Language Models with Adaptive Depth Authors: Nicanor Mayumu, Zeenath Khan, Melodena Stephens, Patrick Mukala, Farhad Oroumchian Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24224v1 Medical AI systems face two fundamental limitations. First, conventional vision-language models (VLMs) perform single-pass inference, yielding black-box predictions that cannot be audited or explained in clinical terms. Second, iterative reasoning systems that expose intermediate steps rely on fixed iteration budgets wasting compute on simple cases while providing insufficient depth for complex ones. We address both limitations with a unified framework. RVLM replaces single-pass inference with an iterative generate-execute loop: at each step, the model writes Python code, invokes vision sub-agents, manipulates images, and accumulates evidence. Every diagnostic claim is grounded in executable code, satisfying auditability requirements of clinical AI governance frameworks. RRouter makes iteration depth adaptive: a lightweight controller predicts the optimal budget from task-complexity features, then monitors progress and terminates early when reasoning stalls. We evaluate on BraTS 2023 Meningioma (brain MRI) and MIMIC-CXR (chest X-ray) using Gemini 2.5 Flash without fine-tuning. Across repeated runs, RVLM shows high consistency on salient findings (e.g., mass presence and enhancement) and can detect cross-modal discrepancies between Fluid-Attenuated Inversion Recovery (FLAIR) signal characteristics and segmentation boundaries. On MIMIC-CXR, it generates structured reports and correctly recognises view-specific artefacts. Code: https://github.com/nican2018/rvlm. --- ### Variation is the Norm: Embracing Sociolinguistics in NLP Authors: Anne-Marie Lutgen, Alistair Plum, Verena Blaschke, Barbara Plank, Christoph Purschke Published: 2026-03-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.24222v1 In Natural Language Processing (NLP), variation is typically seen as noise and "normalised away" before processing, even though it is an integral part of language. Conversely, studying language variation in social contexts is central to sociolinguistics. We present a framework to combine the sociolinguistic dimension of language with the technical dimension of NLP. We argue that by embracing sociolinguistics, variation can actively be included in a research setup, in turn informing the NLP side. To illustrate this, we provide a case study on Luxembourgish, an evolving language featuring a large amount of orthographic variation, demonstrating how NLP performance is impacted. The results show large discrepancies in the performance of models tested and fine-tuned on data with a large amount of orthographic variation in comparison to data closer to the (orthographic) standard. Furthermore, we provide a possible solution to improve the performance by including variation in the fine-tuning process. This case study highlights the importance of including variation in the research setup, as models are currently not robust to occurring variation. Our framework facilitates the inclusion of variation in the thought-process while also being grounded in the theoretical framework of sociolinguistics. --- ### Environment-Grounded Multi-Agent Workflow for Autonomous Penetration Testing Authors: Michael Somma, Markus Großpointner, Paul Zabalegui, Eppu Heilimo, Branka Stojanović Published: 2026-03-25 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.24221v1 The increasing complexity and interconnectivity of digital infrastructures make scalable and reliable security assessment methods essential. Robotic systems represent a particularly important class of operational technology, as modern robots are highly networked cyber-physical systems deployed in domains such as industrial automation, logistics, and autonomous services. This paper explores the use of large language models for automated penetration testing in robotic environments. We propose an environment-grounded multi-agent architecture tailored to Robotics-based systems. The approach dynamically constructs a shared graph-based memory during execution that captures the observable system state, including network topology, communication channels, vulnerabilities, and attempted exploits. This enables structured automation while maintaining traceability and effective context management throughout the testing process. Evaluated across multiple iterations within a specialized robotics Capture-the-Flag scenario (ROS/ROS2), the system demonstrated high reliability, successfully completing the challenge in 100\% of test runs (n=5). This performance significantly exceeds literature benchmarks while maintaining the traceability and human oversight required by frameworks like the EU AI Act. --- ### Who Benefits from RAG? The Role of Exposure, Utility and Attribution Bias Authors: Mahdi Dehghan, Graham McDonald Published: 2026-03-25 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2603.24218v1 Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have achieved substantial improvements in accuracy by grounding their responses in external documents that are relevant to the user's query. However, relatively little work has investigated the impact of RAG in terms of fairness. Particularly, it is not yet known if queries that are associated with certain groups within a fairness category systematically receive higher accuracy, or accuracy improvements in RAG systems compared to LLM-only, a phenomenon we refer to as query group fairness. In this work, we conduct extensive experiments to investigate the impact of three key factors on query group fairness in RAG, namely: Group exposure, i.e., the proportion of documents from each group appearing in the retrieved set, determined by the retriever; Group utility, i.e., the degree to which documents from each group contribute to improving answer accuracy, capturing retriever-generator interactions; and Group attribution, i.e., the extent to which the generator relies on documents from each group when producing responses. We examine group-level average accuracy and accuracy improvements disparities across four fairness categories using three datasets derived from the TREC 2022 Fair Ranking Track for two tasks: article generation and title generation. Our findings show that RAG systems suffer from the query group fairness problem and amplify disparities in terms of average accuracy across queries from different groups, compared to an LLM-only setting. Moreover, group utility, exposure, and attribution can exhibit strong positive or negative correlations with average accuracy or accuracy improvements of queries from that group, highlighting their important role in fair RAG. Our data and code are publicly available from Github. --- ### Where Do Your Citations Come From? Citation-Constellation: A Free, Open-Source, No-Code, and Auditable Tool for Citation Network Decomposition with Complementary BARON and HEROCON Scores Authors: Mahbub Ul Alam Published: 2026-03-25 Categories: cs.DL, cs.AI, cs.DB, cs.IR arXiv: https://arxiv.org/abs/2603.24216v1 Standard citation metrics treat all citations as equal, obscuring the social and structural pathways through which scholarly influence propagates. I introduce Citation-Constellation, a freely available no-code tool for citation network analysis with two complementary bibliometric scores that decompose a researcher's citation profile by network proximity between citing and cited authors. BARON (Boundary-Anchored Research Outreach Network score) is a strict binary metric counting only citations from outside the detected collaborative network. HEROCON (Holistic Equilibrated Research Outreach CONstellation score) applies graduated weights assigning partial credit to in-group citations based on relationship proximity. The gap between scores serves as a diagnostic of inner-circle dependence. An extended abstract with full details appears in the paper. The tool implements this through a phased architecture: (1) self-citation analysis, (2) co-authorship graph traversal, (3) temporal institutional affiliation matching via ROR, and (4) AI-agent-driven venue governance extraction using a local LLM. Phases 1-3 are fully operational; Phase 4 is under development. Key design choices include ORCID-validated author identity resolution, an UNKNOWN classification for citations with insufficient metadata, and comprehensive audit trails documenting every classification decision. A no-code web interface enables researchers to compute scores without programming, installation, or registration. I present these scores as structural diagnostics, not quality indicators. BARON and HEROCON describe where in the social graph citations originate. They should not be used for hiring, promotion, or funding decisions. HEROCON weights are experimental and require empirical calibration. --- ### Uncovering Memorization in Timeseries Imputation models: LBRM Membership Inference and its link to attribute Leakage Authors: Faiz Taleb, Ivan Gazeau, Maryline Laurent Published: 2026-03-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.24213v1 Deep learning models for time series imputation are now essential in fields such as healthcare, the Internet of Things (IoT), and finance. However, their deployment raises critical privacy concerns. Beyond the well-known issue of unintended memorization, which has been extensively studied in generative models, we demonstrate that time series models are vulnerable to inference attacks in a black-box setting. In this work, we introduce a two-stage attack framework comprising: (1) a novel membership inference attack based on a reference model that improves detection accuracy, even for models robust to overfitting-based attacks, and (2) the first attribute inference attack that predicts sensitive characteristics of the training data for timeseries imputation model. We evaluate these attacks on attention-based and autoencoder architectures in two scenarios: models that are trained from scratch, and fine-tuned models where the adversary has access to the initial weights. Our experimental results demonstrate that the proposed membership attack retrieves a significant portion of the training data with a tpr@top25% score significantly higher than a naive attack baseline. We show that our membership attack also provides a good insight of whether attribute inference will work (with a precision of 90% instead of 78% in the genral case). --- ### HEART-PFL: Stable Personalized Federated Learning under Heterogeneity with Hierarchical Directional Alignment and Adversarial Knowledge Transfer Authors: Minjun Kim, Minje Kim Published: 2026-03-25 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.24209v1 Personalized Federated Learning (PFL) aims to deliver effective client-specific models under heterogeneous distributions, yet existing methods suffer from shallow prototype alignment and brittle server-side distillation. We propose HEART-PFL, a dual-sided framework that (i) performs depth-aware Hierarchical Directional Alignment (HDA) using cosine similarity in the early stage and MSE matching in the deep stage to preserve client specificity, and (ii) stabilizes global updates through Adversarial Knowledge Transfer (AKT) with symmetric KL distillation on clean and adversarial proxy data. Using lightweight adapters with only 1.46M trainable parameters, HEART-PFL achieves state-of-the-art personalized accuracy on CIFAR-100, Flowers-102, and Caltech-101 (63.42%, 84.23%, and 95.67%, respectively) under Dirichlet non-IID partitions, and remains robust to out-of-domain proxy data. Ablation studies further confirm that HDA and AKT provide complementary gains in alignment, robustness, and optimization stability, offering insights into how the two components mutually reinforce effective personalization. Overall, these results demonstrate that HEART-PFL simultaneously enhances personalization and global stability, highlighting its potential as a strong and scalable solution for PFL(code available at https://github.com/danny0628/HEART-PFL). --- ### Powerful Teachers Matter: Text-Guided Multi-view Knowledge Distillation with Visual Prior Enhancement Authors: Xin Zhang, Jianyang Xu, Hao Peng, Dongjing Wang, Jingyuan Zheng, Yu Li, Yuyu Yin, Hongbo Wang Published: 2026-03-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.24208v1 Knowledge distillation transfers knowledge from large teacher models to smaller students for efficient inference. While existing methods primarily focus on distillation strategies, they often overlook the importance of enhancing teacher knowledge quality. In this paper, we propose Text-guided Multi-view Knowledge Distillation (TMKD), which leverages dual-modality teachers, a visual teacher and a text teacher (CLIP), to provide richer supervisory signals. Specifically, we enhance the visual teacher with multi-view inputs incorporating visual priors (edge and high-frequency features), while the text teacher generates semantic weights through prior-aware prompts to guide adaptive feature fusion. Additionally, we introduce vision-language contrastive regularization to strengthen semantic knowledge in the student model. Extensive experiments on five benchmarks demonstrate that TMKD consistently improves knowledge distillation performance by up to 4.49\%, validating the effectiveness of our dual-teacher multi-view enhancement strategy. Code is available at https://anonymous.4open.science/r/TMKD-main-44D1. --- ### IPatch: A Multi-Resolution Transformer Architecture for Robust Time-Series Forecasting Authors: Aymane Harkati, Moncef Garouani, Olivier Teste, Julien Aligon, Mohamed Hamlich Published: 2026-03-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.24207v1 Accurate forecasting of multivariate time series remains challenging due to the need to capture both short-term fluctuations and long-range temporal dependencies. Transformer-based models have emerged as a powerful approach, but their performance depends critically on the representation of temporal data. Traditional point-wise representations preserve individual time-step information, enabling fine-grained modeling, yet they tend to be computationally expensive and less effective at modeling broader contextual dependencies, limiting their scalability to long sequences. Patch-wise representations aggregate consecutive steps into compact tokens to improve efficiency and model local temporal dynamics, but they often discard fine-grained temporal details that are critical for accurate predictions in volatile or complex time series. We propose IPatch, a multi-resolution Transformer architecture that integrates both point-wise and patch-wise tokens, modeling temporal information at multiple resolutions. Experiments on 7 benchmark datasets demonstrate that IPatch consistently improves forecasting accuracy, robustness to noise, and generalization across various prediction horizons compared to single-representation baselines. --- ### Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search Authors: Yulin Shen, Xudong Pan, Geng Hong, Min Yang Published: 2026-03-25 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.24203v1 Recent advances in the Model Context Protocol (MCP) have enabled large language models (LLMs) to invoke external tools with unprecedented ease. This creates a new class of powerful and tool augmented agents. Unfortunately, this capability also introduces an under explored attack surface, specifically the malicious manipulation of tool responses. Existing techniques for indirect prompt injection that target MCP suffer from high deployment costs, weak semantic coherence, or heavy white box requirements. Furthermore, they are often easily detected by recently proposed defenses. In this paper, we propose Tree structured Injection for Payloads (TIP), a novel black-box attack which generates natural payloads to reliably seize control of MCP enabled agents even under defense. Technically, We cast payload generation as a tree structured search problem and guide the search with an attacker LLM operating under our proposed coarse-to-fine optimization framework. To stabilize learning and avoid local optima, we introduce a path-aware feedback mechanism that surfaces only high quality historical trajectories to the attacker model. The framework is further hardened against defensive transformations by explicitly conditioning the search on observable defense signals and dynamically reallocating the exploration budget. Extensive experiments on four mainstream LLMs show that TIP attains over 95% attack success in undefended settings while requiring an order of magnitude fewer queries than prior adaptive attacks. Against four representative defense approaches, TIP preserves more than 50% effectiveness and significantly outperforms the state-of-the-art attacks. By implementing the attack on real world MCP systems, our results expose an invisible but practical threat vector in MCP deployments. We also discuss potential mitigation approaches to address this critical security gap. --- ### A Deep Dive into Scaling RL for Code Generation with Synthetic Data and Curricula Authors: Cansu Sancaktar, David Zhang, Gabriel Synnaeve, Taco Cohen Published: 2026-03-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.24202v1 Reinforcement learning (RL) has emerged as a powerful paradigm for improving large language models beyond supervised fine-tuning, yet sustaining performance gains at scale remains an open challenge, as data diversity and structure, rather than volume alone, become the limiting factor. We address this by introducing a scalable multi-turn synthetic data generation pipeline in which a teacher model iteratively refines problems based on in-context student performance summaries, producing structured difficulty progressions without any teacher fine-tuning. Compared to single-turn generation, this multi-turn approach substantially improves the yield of valid synthetic problems and naturally produces stepping stones, i.e. easier and harder variants of the same core task, that support curriculum-based training. We systematically study how task difficulty, curriculum scheduling, and environment diversity interact during RL training across the Llama3.1-8B Instruct and Qwen3-8B Base model families, with additional scaling experiments on Qwen2.5-32B. Our results show that synthetic augmentation consistently improves in-domain code and in most cases out-of-domain math performance, and we provide empirical insights into how curriculum design and data diversity jointly shape RL training dynamics. --- ### RefReward-SR: LR-Conditioned Reward Modeling for Preference-Aligned Super-Resolution Authors: Yushuai Song, Weize Quan, Weining Wang, Jiahui Sun, Jing Liu, Meng Li, Pengbin Yu, Zhentao Chen, Wei Shen, Lunxi Yuan, Dong-ming Yan Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24198v1 Recent advances in generative super-resolution (SR) have greatly improved visual realism, yet existing evaluation and optimization frameworks remain misaligned with human perception. Full-Reference and No-Reference metrics often fail to reflect perceptual preference, either penalizing semantically plausible details due to pixel misalignment or favoring visually sharp but inconsistent artifacts. Moreover, most SR methods rely on ground-truth (GT)-dependent distribution matching, which does not necessarily correspond to human judgments. In this work, we propose RefReward-SR, a low-resolution (LR) reference-aware reward model for preference-aligned SR. Instead of relying on GT supervision or NR evaluation, RefReward-SR assesses high-resolution (HR) reconstructions conditioned on their LR inputs, treating the LR image as a semantic anchor. Leveraging the visual-linguistic priors of a Multimodal Large Language Models (MLLM), it evaluates semantic consistency and plausibility in a reasoning-aware manner. To support this paradigm, we construct RefSR-18K, the first large-scale LR-conditioned preference dataset for SR, providing pairwise rankings based on LR-HR consistency and HR naturalness. We fine-tune the MLLM with Group Relative Policy Optimization (GRPO) using LR-conditioned ranking rewards, and further integrate GRPO into SR model training with RefReward-SR as the core reward signal for preference-aligned generation. Extensive experiments show that our framework achieves substantially better alignment with human judgments, producing reconstructions that preserve semantic consistency while enhancing perceptual plausibility and visual naturalness. Code, models, and datasets will be released upon paper acceptance. --- ### Quantum Neural Physics: Solving Partial Differential Equations on Quantum Simulators using Quantum Convolutional Neural Networks Authors: Jucai Zhai, Muhammad Abdullah, Boyang Chen, Fazal Chaudry, Paul N. Smith, Claire E. Heaney, Yanghua Wang, Jiansheng Xiang, Christopher C. Pain Published: 2026-03-25 Categories: quant-ph, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2603.24196v2 Neural Physics recasts local discretisations of partial differential equations (PDEs) as fixed convolutional operators, providing a physics-preserving alternative to data-driven surrogate modelling in scientific machine learning. However, existing realizations remain largely confined to classical AI hardware and do not directly connect to quantum structured operator design. To bridge this gap, we introduce a \emph{Quantum Neural Physics} framework and develop a Hybrid Quantum-Classical CNN Multigrid Solver (HQC-CNNMG). The proposed method maps analytically prescribed stencil operators to local quantum convolutional primitives and embeds them within a classical multilevel W-cycle architecture, combining the operator-centric view of scientific ML with the numerical rigor of multigrid solvers. Using amplitude encoding together with the Linear Combination of Unitaries (LCU) and the Quantum Fourier Transform (QFT), the resulting local quantum operators admit logarithmic-depth implementation, with circuit depth scaling as $\mathcal{O}(\log K)$ for an encoded block of size $K$ under the idealized parallel circuit model considered here. Numerical experiments on Poisson, transient diffusion, convection--diffusion, and incompressible Navier--Stokes problems demonstrate numerical consistency, stable multilevel behaviour, and workflow-level feasibility on noiseless simulators. Comparisons with representative quantum linear solver paradigms further show that the main strength of HQC-CNNMG lies in its balanced trade-off among local circuit depth, numerical robustness, and compatibility with PDE structure, rather than in fully quantum global inversion. --- ### TsetlinWiSARD: On-Chip Training of Weightless Neural Networks using Tsetlin Automata on FPGAs Authors: Shengyu Duan, Marcos L. L. Sartori, Rishad Shafik, Alex Yakovlev Published: 2026-03-25 Categories: cs.LG, cs.AR arXiv: https://arxiv.org/abs/2603.24186v1 Increasing demands for adaptability, privacy, and security at the edge have persistently pushed the frontiers for a new generation of machine learning (ML) algorithms with training and inference capabilities on-chip. Weightless Neural Network (WNN) is such an algorithm that is principled on lookup table based simple neuron structures. As a result, it offers architectural benefits, such as low-latency, low-complexity inference, compared to deep neural networks that depend heavily on multiply-accumulate operations. However, traditional WNNs rely on memorization-based one-shot training, which either leads to overfitting and reduced accuracy or requires tedious post-training adjustments, limiting their effectiveness for efficient on chip training. In this work, we propose TsetlinWiSARD, a training approach for WNNs that leverages Tsetlin Automata (TAs) to enable probabilistic, feedback-driven learning. It overcomes the overfitting of WiSARD's one-shot training with iterative optimization, while maintaining simple, continuous binary feedback for efficient on-chip training. Central to our approach is a field programmable gate array (FPGA)-based training architecture that delivers state-of-the-art accuracy while significantly improving hardware efficiency. Our approach provides over 1000x faster training when compared with the traditional WiSARD implementation of WNNs. Further, we demonstrate 22% reduced resource usage, 93.3% lower latency, and 64.2% lower power consumption compared to FPGA-based training accelerators implementing other ML algorithms. --- ### Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection Authors: Adhemar de Senneville, Xavier Bou, Jérémy Anger, Rafael Grompone, Gabriele Facciolo Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24181v1 Current Large Vision Language Models (LVLMs) excel at many zero-shot tasks like image captioning, visual question answering and OCR. However, these same models suffer from poor performance at image classification tasks, underperforming against CLIP-based methods. Notably, this gap is surprising because many LVLMs use CLIP-pretrained vision encoders. Yet LVLMs are not inherently limited by CLIP's architecture with independent vision and text encoders. In CLIP, this separation biases classification toward class-name matching rather than joint visual-text reasoning. In this paper we show that, despite their poor raw performance, LVLMs can improve visual feature class separability at inference using prompt conditioning, and LVLMs' internal representations, especially attention heads, can outperform the model itself at zero-shot and few-shot classification. We introduce Head Ensemble Classifiers (HEC) to bridge the performance gap between CLIP-based and LVLM-based classification methods. Inspired by Gaussian Discriminant Analysis, HEC ranks the most discriminative vision and text heads and combines them into a training-free classifier. We show that HEC achieves state-of-the-art performance in few-shot and zero-shot classification across 12 datasets. --- ### Modeling Spatiotemporal Neural Frames for High Resolution Brain Dynamic Authors: Wanying Qu, Jianxiong Gao, Wei Wang, Yanwei Fu Published: 2026-03-25 Categories: eess.IV, cs.CV, q-bio.NC arXiv: https://arxiv.org/abs/2603.24176v2 Capturing dynamic spatiotemporal neural activity is essential for understanding large-scale brain mechanisms. Functional magnetic resonance imaging (fMRI) provides high-resolution cortical representations that form a strong basis for characterizing fine-grained brain activity patterns. The high acquisition cost of fMRI limits large-scale applications, therefore making high-quality fMRI reconstruction a crucial task. Electroencephalography (EEG) offers millisecond-level temporal cues that complement fMRI. Leveraging this complementarity, we present an EEG-conditioned framework for reconstructing dynamic fMRI as continuous neural sequences with high spatial fidelity and strong temporal coherence at the cortical-vertex level. To address sampling irregularities common in real fMRI acquisitions, we incorporate a null-space intermediate-frame reconstruction, enabling measurement-consistent completion of arbitrary intermediate frames and improving sequence continuity and practical applicability. Experiments on the CineBrain dataset demonstrate superior voxel-wise reconstruction quality and robust temporal consistency across whole-brain and functionally specific regions. The reconstructed fMRI also preserves essential functional information, supporting downstream visual decoding tasks. This work provides a new pathway for estimating high-resolution fMRI dynamics from EEG and advances multimodal neuroimaging toward more dynamic brain activity modeling. --- ### Walma: Learning to See Memory Corruption in WebAssembly Authors: Oussama Draissi, Mark Günzel, Ahmad-Reza Sadeghi, Lucas Davi Published: 2026-03-25 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2603.24167v2 WebAssembly's (Wasm) monolithic linear memory turns a single memory-corruption bug into a bidirectional threat: a compromised module can attack its embedding host, and a malicious host can tamper with a trusted module's state. Existing defenses require custom runtimes or source changes, and none can verify runtime integrity under an adversarial host. We present Walma, a framework for WebAssembly linear memory attestation that renders snapshots of linear memory as grayscale images and classifies them with a convolutional neural network. The network reads the row-aligned structure that compiled code imposes on memory and detects corruption that byte and texture statistics miss. On structured targets this extends to tampering that no program input triggers, such as direct memory writes by a malicious host. On real-world CVE-affected applications, hiding corruption from Walma's verdict requires overwriting a large fraction of memory, hundreds of kilobytes to megabytes on our targets. A Shannon-entropy analysis of benign memory bounds the class of out-of-band edits that the learned prior can detect. Across the 53 binaries of the WABench suite, attestation costs 1.07x--1.69x at the host boundary, making continuous, state-centric memory attestation for Wasm practical. --- ### Heuristic-inspired Reasoning Priors Facilitate Data-Efficient Referring Object Detection Authors: Xu Zhang, Zhe Chen, Jing Zhang, Dacheng Tao Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24166v1 Most referring object detection (ROD) models, especially the modern grounding detectors, are designed for data-rich conditions, yet many practical deployments, such as robotics, augmented reality, and other specialized domains, would face severe label scarcity. In such regimes, end-to-end grounding detectors need to learn spatial and semantic structure from scratch, wasting precious samples. We ask a simple question: Can explicit reasoning priors help models learn more efficiently when data is scarce? To explore this, we first introduce a Data-efficient Referring Object Detection (De-ROD) task, which is a benchmark protocol for measuring ROD performance in low-data and few-shot settings. We then propose the HeROD (Heuristic-inspired ROD), a lightweight, model-agnostic framework that injects explicit, heuristic-inspired spatial and semantic reasoning priors, which are interpretable signals derived based on the referring phrase, into 3 stages of a modern DETR-style pipeline: proposal ranking, prediction fusion, and Hungarian matching. By biasing both training and inference toward plausible candidates, these priors promise to improve label efficiency and convergence performance. On RefCOCO, RefCOCO+, and RefCOCOg, HeROD consistently outperforms strong grounding baselines in scarce-label regimes. More broadly, our results suggest that integrating simple, interpretable reasoning priors provides a practical and extensible path toward better data-efficient vision-language understanding. --- ### CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcare Authors: Akash Ghosh, Tajamul Ashraf, Rishu Kumar Singh, Numan Saeed, Sriparna Saha, Xiuying Chen, Salman Khan Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24157v1 Multimodal agentic pipelines are transforming human-computer interaction by enabling efficient and accessible automation of complex, real-world tasks. However, recent efforts have focused on short-horizon or general-purpose applications (e.g., mobile or desktop interfaces), leaving long-horizon automation for domain-specific systems, particularly in healthcare, largely unexplored. To address this, we introduce CareFlow, a high-quality human-annotated benchmark comprising complex, long-horizon software workflows across medical annotation tools, DICOM viewers, EHR systems, and laboratory information systems. On this benchmark, existing vision-language models (VLMs) perform poorly, struggling with long-horizon reasoning and multi-step interactions in medical contexts. To overcome this, we propose CarePilot, a multi-agent framework based on the actor-critic paradigm. The Actor integrates tool grounding with dual-memory mechanisms (long-term and short-term experience) to predict the next semantic action from the visual interface and system state. The Critic evaluates each action, updates memory based on observed effects, and either executes or provides corrective feedback to refine the workflow. Through iterative agentic simulation, the Actor learns to perform more robust and reasoning-aware predictions during inference. Our experiments show that CarePilot achieves state-of-the-art performance, outperforming strong closed-source and open-source multimodal baselines by approximately 15.26% and 3.38%, respectively, on our benchmark and out-of-distribution dataset. --- ### A convergent Plug-and-Play Majorization-Minimization algorithm for Poisson inverse problems Authors: Thibaut Modrzyk, Ane Etxebeste, Élie Bretin, Voichita Maxim Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24156v1 In this paper, we present a novel variational plug-and-play algorithm for Poisson inverse problems. Our approach minimizes an explicit functional which is the sum of a Kullback-Leibler data fidelity term and a regularization term based on a pre-trained neural network. By combining classical likelihood maximization methods with recent advances in gradient-based denoisers, we allow the use of pre-trained Gaussian denoisers without sacrificing convergence guarantees. The algorithm is formulated in the majorization-minimization framework, which guarantees convergence to a stationary point. Numerical experiments confirm state-of-the-art performance in deconvolution and tomography under moderate noise, and demonstrate clear superiority in high-noise conditions, making this method particularly valuable for nuclear medicine applications. --- ### A visual observation on the geometry of UMAP projections of the difference vectors of antonym and synonym word pair embeddings Authors: Rami Luisto Published: 2026-03-25 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.24150v1 Antonyms, or opposites, are sometimes defined as \emph{word pairs that have all of the same contextually relevant properties but one}. Seeing how transformer models seem to encode concepts as directions, this begs the question if one can detect ``antonymity'' in the geometry of the embedding vectors of word pairs, especially based on their difference vectors. Such geometrical studies are then naturally contrasted by comparing antonymic pairs to their opposites; synonyms. This paper started as an exploratory project on the complexity of the systems needed to detect the geometry of the embedding vectors of antonymic word pairs. What we now report is a curious ``swirl'' that appears across embedding models in a somewhat specific projection configuration. --- ### LightSplat: Fast and Memory-Efficient Open-Vocabulary 3D Scene Understanding in Five Seconds Authors: Jaehun Bang, Jinhyeok Kim, Minji Kim, Seungheon Jeong, Kyungdon Joo Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24146v1 Open-vocabulary 3D scene understanding enables users to segment novel objects in complex 3D environments through natural language. However, existing approaches remain slow, memory-intensive, and overly complex due to iterative optimization and dense per-Gaussian feature assignments. To address this, we propose LightSplat, a fast and memory-efficient training-free framework that injects compact 2-byte semantic indices into 3D representations from multi-view images. By assigning semantic indices only to salient regions and managing them with a lightweight index-feature mapping, LightSplat eliminates costly feature optimization and storage overhead. We further ensure semantic consistency and efficient inference via single-step clustering that links geometrically and semantically related masks in 3D. We evaluate our method on LERF-OVS, ScanNet, and DL3DV-OVS across complex indoor-outdoor scenes. As a result, LightSplat achieves state-of-the-art performance with up to 50-400x speedup and 64x lower memory, enabling scalable language-driven 3D understanding. For more details, visit our project page https://vision3d-lab.github.io/lightsplat/. --- ### Linear-Nonlinear Fusion Neural Operator for Partial Differential Equations Authors: Heng Wu, Junjie Wang, Benzhuo Lu Published: 2026-03-25 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2603.24143v2 Neural operator learning directly constructs the mapping relationship from the equation parameter space to the solution space, enabling efficient direct inference in practical applications without the need for repeated solution of partial differential equations (PDEs) -- an advantage that is difficult to achieve with traditional numerical methods. In this work, we find that explicitly decoupling linear and nonlinear effects within such operator mappings leads to improved learning efficiency. This yields a novel network structure, namely the Linear-Nonlinear Fusion Neural Operator (LNF-NO), which models operator mappings via the multiplicative fusion of a linear component and a nonlinear component, thus achieving a lightweight and interpretable representation. This linear-nonlinear decoupling enables efficient capture of complex solution features at the operator level while maintaining stability and generality. LNF-NO naturally supports multiple functional inputs and is applicable to both regular grids and irregular geometries. Across a diverse suite of PDE operator-learning benchmarks, including nonlinear Poisson-Boltzmann equations and multi-physics coupled systems, LNF-NO is typically substantially faster to train than several representative neural operator baselines, while achieving comparable or improved accuracy across most tested cases. On the tested 3D Poisson-Boltzmann case, LNF-NO achieves strong accuracy while requiring substantially less training time than the three-dimensional Fourier Neural Operator and Transolver baselines. --- ### A Longitudinal Analysis of the CEC Single-Objective Competitions (2010-2024) and Implications for Variational Quantum Optimization Authors: Vojtěch Novák, Tomáš Bezděk, Ivan Zelinka, Swagatam Das, Martin Beseda Published: 2026-03-25 Categories: quant-ph, cs.NE arXiv: https://arxiv.org/abs/2603.24140v1 This paper provides a historical analysis of the IEEE CEC Single Objective Optimization competition results (2010-2024). We analyze how benchmark functions shaped winning algorithms, identifying the 2014 introduction of dense rotation matrices as a key performance filter. This design choice introduced parameter non-separability, reduced effectiveness of coordinate-dependent methods (PSO, GA), and established the dominance of Differential Evolution variants capable of preserving the rotational invariance of their difference vectors, specifically L-SHADE. Post-2020 analysis reveals a shift towards high complexity hybrid optimizers that combine different mechanisms (e.g., Eigenvector Crossover, Societal Sharing, Reinforcement Learning) to maximize ranking stability. We conclude by identifying structural similarities between these modern benchmarks and Variational Quantum Algorithm landscapes, suggesting that evolved CEC solvers possess the specific adaptive capabilities required for quantum control. --- ### Tutor-Student Reinforcement Learning: A Dynamic Curriculum for Robust Deepfake Detection Authors: Zhanhe Lei, Zhongyuan Wang, Jikang Cheng, Baojin Huang, Yuhong Yang, Zhen Han, Chao Liang, Dengpan Ye Published: 2026-03-25 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.24139v2 Standard supervised training for deepfake detection treats all samples with uniform importance, which can be suboptimal for learning robust and generalizable features. In this work, we propose a novel Tutor-Student Reinforcement Learning (TSRL) framework to dynamically optimize the training curriculum. Our method models the training process as a Markov Decision Process where a ``Tutor'' agent learns to guide a ``Student'' (the deepfake detector). The Tutor, implemented as a Proximal Policy Optimization (PPO) agent, observes a rich state representation for each training sample, encapsulating not only its visual features but also its historical learning dynamics, such as EMA loss and forgetting counts. Based on this state, the Tutor takes an action by assigning a continuous weight (0-1) to the sample's loss, thereby dynamically re-weighting the training batch. The Tutor is rewarded based on the Student's immediate performance change, specifically rewarding transitions from incorrect to correct predictions. This strategy encourages the Tutor to learn a curriculum that prioritizes high-value samples, such as hard-but-learnable examples, leading to a more efficient and effective training process. We demonstrate that this adaptive curriculum improves the Student's generalization capabilities against unseen manipulation techniques compared to traditional training methods. Code is available at https://github.com/wannac1/TSRL. --- ### Efficient Controller Learning from Human Preferences and Numerical Data Via Multi-Modal Surrogate Models Authors: Lukas Theiner, Maik Pfefferkorn, Yongpeng Zhao, Sebastian Hirt, Rolf Findeisen Published: 2026-03-25 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2603.24138v1 Tuning control policies manually to meet high-level objectives is often time-consuming. Bayesian optimization provides a data-efficient framework for automating this process using numerical evaluations of an objective function. However, many systems, particularly those involving humans, require optimization based on subjective criteria. Preferential Bayesian optimization addresses this by learning from pairwise comparisons instead of quantitative measurements, but relying solely on preference data can be inefficient. We propose a multi-fidelity, multi-modal Bayesian optimization framework that integrates low-fidelity numerical data with high-fidelity human preferences. Our approach employs Gaussian process surrogate models with both hierarchical, autoregressive and non-hierarchical, coregionalization-based structures, enabling efficient learning from mixed-modality data. We illustrate the framework by tuning an autonomous vehicle's trajectory planner, showing that combining numerical and preference data significantly reduces the need for experiments involving the human decision maker while effectively adapting driving style to individual preferences. --- ### Spectral Scalpel: Amplifying Adjacent Action Discrepancy via Frequency-Selective Filtering for Skeleton-Based Action Segmentation Authors: Haoyu Ji, Bowen Chen, Zhihao Yang, Wenze Huang, Yu Gao, Xueting Liu, Weihong Ren, Zhiyong Wang, Honghai Liu Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24134v1 Skeleton-based Temporal Action Segmentation (STAS) seeks to densely segment and classify diverse actions within long, untrimmed skeletal motion sequences. However, existing STAS methodologies face challenges of limited inter-class discriminability and blurred segmentation boundaries, primarily due to insufficient distinction of spatio-temporal patterns between adjacent actions. To address these limitations, we propose Spectral Scalpel, a frequency-selective filtering framework aimed at suppressing shared frequency components between adjacent distinct actions while amplifying their action-specific frequencies, thereby enhancing inter-action discrepancies and sharpening transition boundaries. Specifically, Spectral Scalpel employs adaptive multi-scale spectral filters as scalpels to edit frequency spectra, coupled with a discrepancy loss between adjacent actions serving as the surgical objective. This design amplifies representational disparities between neighboring actions, effectively mitigating boundary localization ambiguities and inter-class confusion. Furthermore, complementing long-term temporal modeling, we introduce a frequency-aware channel mixer to strengthen channel evolution by aggregating spectra across channels. This work presents a novel paradigm for STAS that extends conventional spatio-temporal modeling by incorporating frequency-domain analysis. Extensive experiments on five public datasets demonstrate that Spectral Scalpel achieves state-of-the-art performance. Code is available at https://github.com/HaoyuJi/SpecScalpel. --- ### MedAidDialog: A Multilingual Multi-Turn Medical Dialogue Dataset for Accessible Healthcare Authors: Shubham Kumar Nigam, Suparnojit Sarkar, Piyush Patel Published: 2026-03-25 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.24132v1 Conversational artificial intelligence has the potential to assist users in preliminary medical consultations, particularly in settings where access to healthcare professionals is limited. However, many existing medical dialogue systems operate in a single-turn question--answering paradigm or rely on template-based datasets, limiting conversational realism and multilingual applicability. In this work, we introduce MedAidDialog, a multilingual multi-turn medical dialogue dataset designed to simulate realistic physician--patient consultations. The dataset extends the MDDial corpus by generating synthetic consultations using large language models and further expands them into a parallel multilingual corpus covering seven languages: English, Hindi, Telugu, Tamil, Bengali, Marathi, and Arabic. Building on this dataset, we develop MedAidLM, a conversational medical model trained using parameter-efficient fine-tuning on quantized small language models, enabling deployment without high-end computational infrastructure. Our framework additionally incorporates optional patient pre-context information (e.g., age, gender, allergies) to personalize the consultation process. Experimental results demonstrate that the proposed system can effectively perform symptom elicitation through multi-turn dialogue and generate diagnostic recommendations. We further conduct medical expert evaluation to assess the plausibility and coherence of the generated consultations. --- ### Reservoir-Based Graph Convolutional Networks Authors: Mayssa Soussia, Gita Ayu Salsabila, Mohamed Ali Mahjoub, Islem Rekik Published: 2026-03-25 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2603.24131v2 Message passing is a core mechanism in Graph Neural Networks (GNNs), enabling the iterative update of node embeddings by aggregating information from neighboring nodes. Graph Convolutional Networks (GCNs) exemplify this approach by adapting convolutional operations for graph structures, allowing features from adjacent nodes to be combined effectively. However, GCNs encounter challenges with complex or dynamic data. Capturing long-range dependencies often requires deeper layers, which not only increase computational costs but also lead to over-smoothing, where node embeddings become indistinguishable. To overcome these challenges, reservoir computing has been integrated into GNNs, leveraging iterative message-passing dynamics for stable information propagation without extensive parameter tuning. Despite its promise, existing reservoir-based models lack structured convolutional mechanisms, limiting their ability to accurately aggregate multi-hop neighborhood information. To address these limitations, we propose RGC-Net (\emph{Reservoir-based Graph Convolutional Network}), which integrates reservoir dynamics with structured graph convolution. Key contributions include: (i) a reimagined convolutional framework with fixed-random reservoir weights and a leaky integrator to enhance feature retention; (ii) a robust, adaptable model for graph classification; and (iii) an RGC-Net-powered transformer for graph generation with application to dynamic brain connectivity. Extensive experiments show RGC-Net achieves state-of-the-art performance in classification and generative tasks, including brain graph evolution, with faster convergence and mitigated over-smoothing. Our source code is available at https://github.com/basiralab/RGC-Net. --- ### Reservoir-Based Graph Convolutional Networks Authors: Mayssa Soussia, Gita Ayu Salsabila, Mohamed Ali Mahjoub, Islem Rekik Published: 2026-03-25 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2603.24131v1 Message passing is a core mechanism in Graph Neural Networks (GNNs), enabling the iterative update of node embeddings by aggregating information from neighboring nodes. Graph Convolutional Networks (GCNs) exemplify this approach by adapting convolutional operations for graph structures, allowing features from adjacent nodes to be combined effectively. However, GCNs encounter challenges with complex or dynamic data. Capturing long-range dependencies often requires deeper layers, which not only increase computational costs but also lead to over-smoothing, where node embeddings become indistinguishable. To overcome these challenges, reservoir computing has been integrated into GNNs, leveraging iterative message-passing dynamics for stable information propagation without extensive parameter tuning. Despite its promise, existing reservoir-based models lack structured convolutional mechanisms, limiting their ability to accurately aggregate multi-hop neighborhood information. To address these limitations, we propose RGC-Net (Reservoir-based Graph Convolutional Network), which integrates reservoir dynamics with structured graph convolution. Key contributions include: (i) a reimagined convolutional framework with fixed random reservoir weights and a leaky integrator to enhance feature retention; (ii) a robust, adaptable model for graph classification; and (iii) an RGC-Net-powered transformer for graph generation with application to dynamic brain connectivity. Extensive experiments show that RGC-Net achieves state-of-the-art performance in classification and generative tasks, including brain graph evolution, with faster convergence and reduced over-smoothing. Source code is available at https://github.com/basiralab/RGC-Net . --- ### On Gossip Algorithms for Machine Learning with Pairwise Objectives Authors: Igor Colin, Aurélien Bellet, Stephan Clémençon, Joseph Salmon Published: 2026-03-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.24128v1 In the IoT era, information is more and more frequently picked up by connected smart sensors with increasing, though limited, storage, communication and computation abilities. Whether due to privacy constraints or to the structure of the distributed system, the development of statistical learning methods dedicated to data that are shared over a network is now a major issue. Gossip-based algorithms have been developed for the purpose of solving a wide variety of statistical learning tasks, ranging from data aggregation over sensor networks to decentralized multi-agent optimization. Whereas the vast majority of contributions consider situations where the function to be estimated or optimized is a basic average of individual observations, it is the goal of this article to investigate the case where the latter is of pairwise nature, taking the form of a U -statistic of degree two. Motivated by various problems such as similarity learning, ranking or clustering for instance, we revisit gossip algorithms specifically designed for pairwise objective functions and provide a comprehensive theoretical framework for their convergence. This analysis fills a gap in the literature by establishing conditions under which these methods succeed, and by identifying the graph properties that critically affect their efficiency. In particular, a refined analysis of the convergence upper and lower bounds is performed. --- ### Likelihood Hacking in Probabilistic Program Synthesis Authors: Jacek Karwowski, Younesse Kaddar, Zihuiwen Ye, Esmeralda S. Whitammer, Sam Staton Published: 2026-03-25 Categories: cs.LG, cs.PL arXiv: https://arxiv.org/abs/2603.24126v2 When language models are trained by reinforcement learning (RL) to write probabilistic programs, they can artificially inflate their marginal-likelihood reward by producing programs whose data distribution fails to normalise instead of fitting the data better. We call this failure likelihood hacking (LH). We formalise LH in a core probabilistic programming language (PPL) and give sufficient syntactic conditions for its prevention, proving that a safe language fragment $\mathcal{L}_{\text{safe}}$ satisfying these conditions cannot produce likelihood-hacking programs. Empirically, we show that GRPO-trained models generating PyMC code discover LH exploits within the first few training steps, driving violation rates well above the untrained-model baseline. We implement $\mathcal{L}_{\text{safe}}$'s conditions as $\texttt{SafeStan}$, a LH-resistant modification of Stan, and show empirically that it suppresses LH under optimisation pressure. These results show that language-level safety constraints are both theoretically grounded and effective in practice for automated Bayesian model discovery. --- ### Likelihood hacking in probabilistic program synthesis Authors: Jacek Karwowski, Younesse Kaddar, Zihuiwen Ye, Nikolay Malkin, Sam Staton Published: 2026-03-25 Categories: cs.LG, cs.PL arXiv: https://arxiv.org/abs/2603.24126v1 When language models are trained by reinforcement learning (RL) to write probabilistic programs, they can artificially inflate their marginal-likelihood reward by producing programs whose data distribution fails to normalise instead of fitting the data better. We call this failure likelihood hacking (LH). We formalise LH in a core probabilistic programming language (PPL) and give sufficient syntactic conditions for its prevention, proving that a safe language fragment $\mathcal{L}_{\text{safe}}$ satisfying these conditions cannot produce likelihood-hacking programs. Empirically, we show that GRPO-trained models generating PyMC code discover LH exploits within the first few training steps, driving violation rates well above the untrained-model baseline. We implement $\mathcal{L}_{\text{safe}}$'s conditions as $\texttt{SafeStan}$, a LH-resistant modification of Stan, and show empirically that it prevents LH under optimisation pressure. These results show that language-level safety constraints are both theoretically grounded and effective in practice for automated Bayesian model discovery. --- ### Alignment Reduces Expressed but Not Encoded Gender Bias: A Unified Framework and Study Authors: Nour Bouchouchi, Thibault Laugel, Xavier Renard, Christophe Marsala, Marie-Jeanne Lesot, Marcin Detyniecki Published: 2026-03-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.24125v3 During training, Large Language Models (LLMs) learn social regularities that can lead to gender bias in downstream applications. Most mitigation efforts focus on reducing bias in generated outputs, typically evaluated on structured benchmarks, which raises two concerns: output-level evaluation does not reveal whether alignment modifies the model's underlying representations, and structured benchmarks may not reflect realistic usage scenarios. We propose a unified framework to jointly analyze intrinsic and extrinsic gender bias in LLMs using identical neutral prompts, enabling direct comparison between gender-related information encoded in internal representations and bias expressed in generated outputs. Contrary to prior work reporting weak or inconsistent correlations, we find a consistent association between latent gender information and expressed bias when measured under the unified protocol. We further examine the effect of alignment through supervised fine-tuning aimed at reducing gender bias. Our results suggest that while the latter indeed reduces expressed bias, measurable gender-related associations are still present in internal representations, and can be reactivated under adversarial prompting. Finally, we consider two realistic settings and show that debiasing effects observed on structured benchmarks do not necessarily generalize, e.g., to the case of story generation. --- ### Alignment Reduces Expressed but Not Encoded Gender Bias: A Unified Framework and Study Authors: Nour Bouchouchi, Thibault Laugel, Xavier Renard, Christophe Marsala, Marie-Jeanne Lesot, Marcin Detyniecki Published: 2026-03-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.24125v2 During training, Large Language Models (LLMs) learn social regularities that can lead to gender bias in downstream applications. Most mitigation efforts focus on reducing bias in generated outputs, typically evaluated on structured benchmarks, which raises two concerns: output-level evaluation does not reveal whether alignment modifies the model's underlying representations, and structured benchmarks may not reflect realistic usage scenarios. We propose a unified framework to jointly analyze intrinsic and extrinsic gender bias in LLMs using identical neutral prompts, enabling direct comparison between gender-related information encoded in internal representations and bias expressed in generated outputs. Contrary to prior work reporting weak or inconsistent correlations, we find a consistent association between latent gender information and expressed bias when measured under the unified protocol. We further examine the effect of alignment through supervised fine-tuning aimed at reducing gender bias. Our results suggest that while the latter indeed reduces expressed bias, measurable gender-related associations are still present in internal representations, and can be reactivated under adversarial prompting. Finally, we consider two realistic settings and show that debiasing effects observed on structured benchmarks do not necessarily generalize, e.g., to the case of story generation. --- ### The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation Authors: Mingyi Liu Published: 2026-03-25 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.24124v2 RLHF-aligned language models exhibit response homogenization: on TruthfulQA (n=790), 40-79% of questions produce a single semantic cluster across 10 i.i.d. samples. On affected questions, sampling-based uncertainty methods have zero discriminative power (AUROC=0.500), while free token entropy retains signal (0.603). This alignment tax is task-dependent: on GSM8K (n=500), token entropy achieves 0.724 (Cohen's d=0.81). A base-vs-instruct ablation confirms the causal role of alignment: the base model shows 1.0% single-cluster rate vs. 28.5% for the instruct model (p < 10^{-6}). A training stage ablation (Base 0.0% -> SFT 1.5% -> DPO 4.0% SCR) localizes the cause to DPO, not SFT. Cross-family replication on four model families reveals alignment tax severity varies by family and scale. We validate across 22 experiments, 5 benchmarks, 4 model families, and 3 model scales (3B-14B), with Jaccard, embedding, and NLI-based baselines at three DeBERTa scales (all ~0.51 AUROC). Cross-embedder validation with two independent embedding families rules out coupling bias. Cross-dataset validation on WebQuestions (58.0% SCR) confirms generalization beyond TruthfulQA. The central finding -- response homogenization -- is implementation-independent and label-free. Motivated by this diagnosis, we explore a cheapest-first cascade (UCBD) over orthogonal uncertainty signals. Selective prediction raises GSM8K accuracy from 84.4% to 93.2% at 50% coverage; weakly dependent boundaries (|r| <= 0.12) enable 57% cost savings. --- ### Combi-CAM: A Novel Multi-Layer Approach for Explainable Image Geolocalization Authors: David Faget, José Luis Lisani, Miguel Colom Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24117v1 Planet-scale photo geolocalization involves the intricate task of estimating the geographic location depicted in an image purely based on its visual features. While deep learning models, particularly convolutional neural networks (CNNs), have significantly advanced this field, understanding the reasoning behind their predictions remains challenging. In this paper, we present Combi-CAM, a novel method that enhances the explainability of CNN-based geolocalization models by combining gradient-weighted class activation maps obtained from several layers of the network architecture, rather than using only information from the deepest layer as is typically done. This approach provides a more detailed understanding of how different image features contribute to the model's decisions, offering deeper insights than the traditional approaches. --- ### Retinal Layer Segmentation in OCT Images With 2.5D Cross-slice Feature Fusion Module for Glaucoma Assessment Authors: Hyunwoo Kim, Heesuk Kim, Wungrak Choi, Jae-Sang Hyun Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24115v1 For accurate glaucoma diagnosis and monitoring, reliable retinal layer segmentation in OCT images is essential. However, existing 2D segmentation methods often suffer from slice-to-slice inconsistencies due to the lack of contextual information across adjacent B-scans. 3D segmentation methods are better for capturing slice-to-slice context, but they require expensive computational resources. To address these limitations, we propose a 2.5D segmentation framework that incorporates a novel cross-slice feature fusion (CFF) module into a U-Net-like architecture. The CFF module fuses inter-slice features to effectively capture contextual information, enabling consistent boundary detection across slices and improved robustness in noisy regions. The framework was validated on both a clinical dataset and the publicly available DUKE DME dataset. Compared to other segmentation methods without the CFF module, the proposed method achieved an 8.56% reduction in mean absolute distance and a 13.92% reduction in root mean square error, demonstrating improved segmentation accuracy and robustness. Overall, the proposed 2.5D framework balances contextual awareness and computational efficiency, enabling anatomically reliable retinal layer delineation for automated glaucoma evaluation and potential clinical applications. --- ### Mixed-signal implementation of feedback-control optimizer for single-layer Spiking Neural Networks Authors: Jonathan Haag, Christian Metzner, Dmitrii Zendrikov, Giacomo Indiveri, Benjamin Grewe, Chiara De Luca, Matteo Saponati Published: 2026-03-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.24113v1 On-chip learning is key to scalable and adaptive neuromorphic systems, yet existing training methods are either difficult to implement in hardware or overly restrictive. However, recent studies show that feedback-control optimizers can enable expressive, on-chip training of neuromorphic devices. In this work, we present a proof-of-concept implementation of such feedback-control optimizers on a mixed-signal neuromorphic processor. We assess the proposed approach in an In-The-Loop(ITL) training setup on both a binary classification task and the nonlinear Yin-Yang problem, demonstrating on-chip training that matches the performance of numerical simulations and gradient-based baselines. Our results highlight the feasibility of feedback-driven, online learning under realistic mixed-signal constraints, and represent a co-design approach toward embedding such rules directly in silicon for autonomous and adaptive neuromorphic computing. --- ### Toward a Multi-Layer ML-Based Security Framework for Industrial IoT Authors: Aymen Bouferroum, Valeria Loscri, Abderrahim Benslimane Published: 2026-03-25 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2603.24111v3 The Industrial Internet of Things (IIoT) introduces significant security challenges as resource-constrained devices become increasingly integrated into critical industrial processes. Existing security approaches typically address threats at a single network layer, often relying on expensive hardware and remaining confined to simulation environments. In this paper, we present the research framework and contributions of our doctoral thesis, which aims to develop a lightweight, Machine Learning (ML)-based security framework for IIoT environments. We first describe our adoption of the Tm-IIoT trust model and the Hybrid IIoT (H-IIoT) architecture as foundational baselines, then introduce the Trust Convergence Acceleration (TCA) approach, our primary contribution that integrates ML to predict and mitigate the impact of degraded network conditions on trust convergence, achieving up to a 28.6% reduction in convergence time while maintaining robustness against adversarial behaviors. We then propose a real-world deployment architecture based on affordable, open-source hardware, designed to implement and extend the security framework. Finally, we outline our ongoing research toward multi-layer attack detection, including physical-layer threat identification and considerations for robustness against adversarial ML attacks. --- ### Comparative analysis of dual-form networks for live land monitoring using multi-modal satellite image time series Authors: Iris Dumeur, Jérémy Anger, Gabriele Facciolo Published: 2026-03-25 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.24109v1 Multi-modal Satellite Image Time Series (SITS) analysis faces significant computational challenges for live land monitoring applications. While Transformer architectures excel at capturing temporal dependencies and fusing multi-modal data, their quadratic computational complexity and the need to reprocess entire sequences for each new acquisition limit their deployment for regular, large-area monitoring. This paper studies various dual-form attention mechanisms for efficient multi-modal SITS analysis, that enable parallel training while supporting recurrent inference for incremental processing. We compare linear attention and retention mechanisms within a multi-modal spectro-temporal encoder. To address SITS-specific challenges of temporal irregularity and unalignment, we develop temporal adaptations of dual-form mechanisms that compute token distances based on actual acquisition dates rather than sequence indices. Our approach is evaluated on two tasks using Sentinel-1 and Sentinel-2 data: multi-modal SITS forecasting as a proxy task, and real-world solar panel construction monitoring. Experimental results demonstrate that dual-form mechanisms achieve performance comparable to standard Transformers while enabling efficient recurrent inference. The multimodal framework consistently outperforms mono-modal approaches across both tasks, demonstrating the effectiveness of dual mechanisms for sensor fusion. The results presented in this work open new opportunities for operational land monitoring systems requiring regular updates over large geographic areas. --- ### Granular Ball Guided Stable Latent Domain Discovery for Domain-General Crowd Counting Authors: Fan Chen, Shuyin Xia, Yi Wang Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24106v2 Single-source domain generalization for crowd counting is highly challenging because a single labeled source domain may contain heterogeneous latent domains, while unseen target domains often exhibit severe distribution shifts. A central issue is stable latent domain discovery: directly performing flat clustering on evolving sample-level latent features is easily disturbed by feature noise, outliers, and representation drift, leading to unreliable pseudo-domain assignments and weakened domain-structured learning. To address this problem, we propose a granular ball guided stable latent domain discovery framework for domain-general crowd counting. The proposed method first groups samples into compact local granular balls and then clusters granular ball centers as representatives to infer pseudo-domains, thereby converting direct sample-level clustering into a hierarchical representative-based clustering process. This design produces more stable and semantically consistent pseudo-domain assignments. On top of the discovered latent domains, we develop a two-branch learning framework that improves transferable semantic representations via semantic codebook re-encoding and captures domain-specific appearance variations through a style branch, thereby alleviating semantic--style entanglement under domain shifts. Extensive experiments on ShanghaiTech A/B, UCF\_QNRF, and NWPU-Crowd under a strict no-adaptation protocol verify the effectiveness of the proposed method and show strong generalization ability, especially in transfer settings with large domain gaps. ---