# Research Papers — 2026-03 · bundle page 58 of 243 > Full-text markdown of papers #2851–2900 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/58 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/57.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/59.md) ### SpecXMaster Technical Report Authors: Yutang Ge, Yaning Cui, Hanzheng Li, Jun-Jie Wang, Fanjie Xu, Jinhan Dong, Yongqi Jin, Dongxu Cui, Peng Jin, Guojiang Zhao, Hengxing Cai, Tianci Yangfeng et al. Published: 2026-03-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.23101v3 Intelligent spectroscopy serves as a pivotal element in AI-driven closed-loop scientific discovery, functioning as the critical bridge between matter structure and artificial intelligence. However, conventional expert-dependent spectral interpretation encounters substantial hurdles, including susceptibility to human bias and error, dependence on limited specialized expertise, and variability across interpreters. To address these challenges, we propose SpecXMaster, an intelligent framework leveraging Agentic Reinforcement Learning (RL) for NMR molecular spectral interpretation. SpecXMaster enables automated extraction of multiplicity information from both 1H and 13C spectra directly from raw FID (free induction decay) data. This end-to-end pipeline enables fully automated interpretation of NMR spectra into chemical structures. It demonstrates superior performance across multiple public NMR interpretation benchmarks and has been refined through iterative evaluations by professional chemical spectroscopists. We believe that SpecXMaster, as a novel methodological paradigm for spectral interpretation, will have a profound impact on the organic chemistry community. --- ### When Language Models Lose Their Mind: The Consequences of Brain Misalignment Authors: Gabriele Merlin, Mariya Toneva Published: 2026-03-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.23091v1 While brain-aligned large language models (LLMs) have garnered attention for their potential as cognitive models and for potential for enhanced safety and trustworthiness in AI, the role of this brain alignment for linguistic competence remains uncertain. In this work, we investigate the functional implications of brain alignment by introducing brain-misaligned models--LLMs intentionally trained to predict brain activity poorly while maintaining high language modeling performance. We evaluate these models on over 200 downstream tasks encompassing diverse linguistic domains, including semantics, syntax, discourse, reasoning, and morphology. By comparing brain-misaligned models with well-matched brain-aligned counterparts, we isolate the specific impact of brain alignment on language understanding. Our experiments reveal that brain misalignment substantially impairs downstream performance, highlighting the critical role of brain alignment in achieving robust linguistic competence. These findings underscore the importance of brain alignment in LLMs and offer novel insights into the relationship between neural representations and linguistic processing. --- ### A Synchronized Audio-Visual Multi-View Capture System Authors: Xiangwei Shi, Gara Dorta, Ruud de Jong, Ojas Shirekar, Chirag Raman Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23089v2 Multi-view capture systems have been an important tool in research for recording human motion under controlling conditions. Most existing systems are specified around video streams and provide little or no support for audio acquisition and rigorous audio-video alignment, despite both being essential for studying conversational interaction where timing at the level of turn-taking, overlap, and prosody matters. In this technical report, we describe an audio-visual multi-view capture system that addresses this gap by treating synchronized audio and synchronized video as first-class signals. The system combines a multi-camera pipeline with multi-channel microphone recording under a unified timing architecture and provides a practical workflow for calibration, acquisition, and quality control that supports repeatable recordings at scale. We quantify synchronization performance in deployment and show that the resulting recordings are temporally consistent enough to support fine-grained analysis and data-driven modeling of conversation behavior. --- ### Policy-based Tuning of Autoregressive Image Models with Instance- and Distribution-Level Rewards Authors: Orhun Bugra Baran, Melih Kandemir, Ramazan Gokberk Cinbis Published: 2026-03-24 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2603.23086v2 Autoregressive (AR) models are highly effective for image generation, yet their standard maximum-likelihood estimation training lacks direct optimization for sample quality and diversity. While reinforcement learning (RL) has been used to align diffusion models, these methods typically suffer from output diversity collapse. Similarly, concurrent RL methods for AR models rely strictly on instance-level rewards, often trading off distributional coverage for quality. To address these limitations, we propose a lightweight RL framework that casts token-based AR synthesis as a Markov Decision Process, optimized via Group Relative Policy Optimization (GRPO). Our core contribution is the introduction of a novel distribution-level Leave-One-Out FID (LOO-FID) reward; by leveraging an exponential moving average of feature moments, it explicitly encourages sample diversity and prevents mode collapse during policy updates. We integrate this with composite instance-level rewards (CLIP and HPSv2) for strict semantic and perceptual fidelity, and stabilize the multi-objective learning with an adaptive entropy regularization term. Extensive experiments on LlamaGen and VQGAN architectures demonstrate clear improvements across standard quality and diversity metrics within only a few hundred tuning iterations. The results also show that the model can be updated to produce competitive samples even without Classifier-Free Guidance, and bypass its 2x inference cost. --- ### When Models Learn to Ask Why: Adaptive Causal Reasoning for Trustworthy Medical Vision-Language Models Authors: Jianxin Lin, Chunzheng Zhu, Peter J. Kneuertz, Yunfei Bai, Yuan Xue Published: 2026-03-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.23085v2 Vision-Language Models (VLMs) have enabled interpretable medical diagnosis by integrating visual perception with linguistic reasoning. Yet, existing medical chain-of-thought (CoT) models lack explicit mechanisms to represent and enforce causal reasoning, leaving them vulnerable to spurious correlations and limiting their clinical reliability. We pinpoint three core challenges in medical CoT reasoning: how to adaptively trigger causal correction, construct high-quality causal-spurious contrastive samples, and maintain causal consistency across reasoning trajectories. To address these challenges, we propose MedCausalX, an end-to-end framework explicitly models causal reasoning chains in medical VLMs. We first introduce the CRMed dataset providing fine-grained anatomical annotations, structured causal reasoning chains, and counterfactual variants that guide the learning of causal relationships beyond superficial correlations. Building upon CRMed, MedCausalX employs a two-stage adaptive reflection architecture equipped with $\langle$causal$\rangle$ and $\langle$verify$\rangle$ tokens, enabling the model to autonomously determine when and how to perform causal analysis and verification. Finally, a trajectory-level causal correction objective optimized through error-attributed reinforcement learning refines the reasoning chain, allowing the model to distinguish genuine causal dependencies from shortcut associations. Extensive experiments on multiple benchmarks show that MedCausalX consistently outperforms state-of-the-art methods, improving diagnostic consistency by +5.4 points, reducing hallucination by over 10 points, and attaining top spatial grounding IoU, thereby setting a new standard for causally grounded medical reasoning. The code and dataset are available at https://github.com/zhcz328/MedCausalX. --- ### MsFormer: Enabling Robust Predictive Maintenance Services for Industrial Devices Authors: Jiahui Zhou, Dan Li, Ruibing Jin, Jian Lou, Yanran Zhao, Zhenghua Chen, Zigui Jiang, See-Kiong Ng Published: 2026-03-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.23076v1 Providing reliable predictive maintenance is a critical industrial AI service essential for ensuring the high availability of manufacturing devices. Existing deep-learning methods present competitive results on such tasks but lack a general service-oriented framework to capture complex dependencies in industrial IoT sensor data. While Transformer-based models show strong sequence modeling capabilities, their direct deployment as robust AI services faces significant bottlenecks. Specifically, streaming sensor data collected in real-world service environments often exhibits multi-scale temporal correlations driven by machine working principles. Besides, the datasets available for training time-to-failure predictive services are typically limited in size. These issues pose significant challenges for directly applying existing models as robust predictive services. To address these challenges, we propose MsFormer, a lightweight Multi-scale Transformer designed as a unified AI service model for reliable industrial predictive maintenance. MsFormer incorporates a Multi-scale Sampling (MS) module and a tailored position encoding mechanism to capture sequential correlations across multi-streaming service data. Additionally, to accommodate data-scarce service environments, MsFormer adopts a lightweight attention mechanism with straightforward pooling operations instead of self-attention. Extensive experiments on real-world datasets demonstrate that the proposed framework achieves significant performance improvements over state-of-the-art methods. Furthermore, MsFormer outperforms across industrial devices and operating conditions, demonstrating strong generalizability while maintaining a highly reliable Quality of Service (QoS). --- ### Can an LLM Detect Instances of Microservice Infrastructure Patterns? Authors: Carlos Eduardo Duarte, Neil B. Harrison, Filipe Figueiredo Correia, Ademar Aguiar, Pavlína Gonçalves Published: 2026-03-24 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.23073v1 Architectural patterns are frequently found in various software artifacts. The wide variety of patterns and their implementations makes detection challenging with current tools, especially since they often only support detecting patterns in artifacts written in a single language. Large Language Models (LLMs), trained on a diverse range of software artifacts and knowledge, might overcome the limitations of existing approaches. However, their true effectiveness and the factors influencing their performance have not yet been thoroughly examined. To better understand this, we developed MicroPAD. This tool utilizes GPT 5 nano to identify architectural patterns in software artifacts written in any language, based on natural-language pattern descriptions. We used MicroPAD to evaluate an LLM's ability to detect instances of architectural patterns, particularly infrastructure-related microservice patterns. To accomplish this, we selected a set of GitHub repositories and contacted their top contributors to create a new, human-annotated dataset of 190 repositories containing microservice architectural patterns. The results show that MicroPAD was capable of detecting pattern instances across multiple languages and artifact types. The detection performance varied across patterns (F1 scores ranging from 0.09 to 0.70), specifically in relation to their prevalence and the distinctiveness of the artifacts through which they manifest. We also found that patterns associated with recognizable, dominant artifacts were detected more reliably. Whether these findings generalize to other LLMs and tools is a promising direction for future research. --- ### Generalization Bounds for Physics-Informed Neural Networks for the Incompressible Navier-Stokes Equations Authors: Sebastien Andre-Sloan, Dibyakanti Kumar, Alejandro F Frangi, Anirbit Mukherjee Published: 2026-03-24 Categories: cs.LG, math.AP, math.NA arXiv: https://arxiv.org/abs/2603.23072v1 This work establishes rigorous first-of-its-kind upper bounds on the generalization error for the method of approximating solutions to the (d+1)-dimensional incompressible Navier-Stokes equations by training depth-2 neural networks trained via the unsupervised Physics-Informed Neural Network (PINN) framework. This is achieved by bounding the Rademacher complexity of the PINN risk. For appropriately weight bounded net classes our derived generalization bounds do not explicitly depend on the network width and our framework characterizes the generalization gap in terms of the fluid's kinematic viscosity and loss regularization parameters. In particular, the resulting sample complexity bounds are dimension-independent. Our generalization bounds suggest using novel activation functions for solving fluid dynamics. We provide empirical validation of the suggested activation functions and the corresponding bounds on a PINN setup solving the Taylor-Green vortex benchmark. --- ### PolarAPP: Beyond Polarization Demosaicking for Polarimetric Applications Authors: Yidong Luo, Chenggong Li, Yunfeng Song, Ping Wang, Boxin Shi, Junchao Zhang, Xin Yuan Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23071v2 Polarimetric imaging enables advanced vision applications such as normal estimation and de-reflection by capturing unique surface-material interactions. However, existing applications (alternatively called downstream tasks) rely on datasets constructed by naively regrouping raw measurements from division-of-focal-plane sensors, where pixels of the same polarization angle are extracted and aligned into sparse images without proper demosaicking. This reconstruction strategy results in suboptimal, incomplete targets that limit downstream performance. Moreover, current demosaicking methods are task-agnostic, optimizing only for photometric fidelity rather than utility in downstream tasks. Towards this end, we propose PolarAPP, the first framework to jointly optimize demosaicking and its downstream tasks. PolarAPP introduces a feature alignment mechanism that semantically aligns the representations of demosaicking and downstream networks via meta-learning, guiding the reconstruction to be task-aware. It further employs an equivalent imaging constraint for demosaicking training, enabling direct regression to physically meaningful outputs without relying on rearranged data. Finally, a task-refinement stage fine-tunes the task network using the stable demosaicking front-end to further enhance accuracy. Extensive experimental results demonstrate that PolarAPP outperforms existing methods in both demosaicking quality and downstream performance. Code is available upon acceptance. --- ### AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing Authors: Sarubi Thillainathan, Ji-Ung Lee, Michael Sullivan, Alexander Koller Published: 2026-03-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.23069v4 The task of authorship style transfer involves rewriting text in the style of a target author while preserving the meaning of the original text. Existing style transfer methods train a single model on large corpora to model all target styles at once: this high-cost approach offers limited flexibility for target-specific adaptation, and often sacrifices meaning preservation for style transfer. In this paper, we propose AuthorMix: a lightweight, modular, and interpretable style transfer framework. We first train individual, style-specific LoRA adapters on a small set of high-resource authors: this allows for the rapid training of specialized adaptation models for each new target using layer-wise adapter mixing via reinforcement learning, necessitating only a handful of target-style training examples. AuthorMix ranks first on the combined style-meaning score among all baselines, including GPT-5.1, and substantially improves meaning preservation over the trained baselines; under human evaluation it is the only method best-or-tied on every dimension. --- ### AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing Authors: Sarubi Thillainathan, Ji-Ung Lee, Michael Sullivan, Alexander Koller Published: 2026-03-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.23069v3 The task of authorship style transfer involves rewriting text in the style of a target author while preserving the meaning of the original text. Existing style transfer methods train a single model on large corpora to model all target styles at once: this high-cost approach offers limited flexibility for target-specific adaptation, and often sacrifices meaning preservation for style transfer. In this paper, we propose AuthorMix: a lightweight, modular, and interpretable style transfer framework. We train individual, style-specific LoRA adapters on a small set of high-resource authors, allowing the rapid training of specialized adaptation models for each new target via learned, layer-wise adapter mixing, using only a handful of target-style training examples. AuthorMix outperforms existing, SoTA style-transfer baselines-as well as GPT-5.1-for low-resource targets, achieving the highest overall score and substantially improving meaning preservation in both automatic and human evaluations. --- ### MLLM-HWSI: A Multimodal Large Language Model for Hierarchical Whole Slide Image Understanding Authors: Basit Alawode, Arif Mahmood, Muaz Khalifa Al-Radi, Shahad Albastaki, Asim Khan, Muhammad Bilal, Moshira Ali Abdalla, Mohammed Bennamoun, Sajid Javed Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23067v2 Whole Slide Images (WSIs) exhibit hierarchical structure, where diagnostic information emerges from cellular morphology, regional tissue organization, and global context. Existing Computational Pathology (CPath) Multimodal Large Language Models (MLLMs) typically compress an entire WSI into a single embedding, which hinders fine-grained grounding and ignores how pathologists synthesize evidence across different scales. We introduce \textbf{MLLM-HWSI}, a Hierarchical WSI-level MLLM that aligns visual features with pathology language at four distinct scales, cell as word, patch as phrase, region as sentence, and WSI as paragraph to support interpretable evidence-grounded reasoning. MLLM-HWSI decomposes each WSI into multi-scale embeddings with scale-specific projectors and jointly enforces (i) a hierarchical contrastive objective and (ii) a cross-scale consistency loss, preserving semantic coherence from cells to the WSI. We compute diagnostically relevant patches and aggregate segmented cell embeddings into a compact cellular token per-patch using a lightweight \textit{Cell-Cell Attention Fusion (CCAF)} transformer. The projected multi-scale tokens are fused with text tokens and fed to an instruction-tuned LLM for open-ended reasoning, VQA, report, and caption generation tasks. Trained in three stages, MLLM-HWSI achieves new SOTA results on 13 WSI-level benchmarks across six CPath tasks. By aligning language with multi-scale visual evidence, MLLM-HWSI provides accurate, interpretable outputs that mirror diagnostic workflows and advance holistic WSI understanding. Code is available at: \href{https://github.com/BasitAlawode/HWSI-MLLM}{GitHub}. --- ### Mind Your HEARTBEAT! Claw Background Execution Inherently Enables Silent Memory Pollution Authors: Yechao Zhang, Shiqian Zhao, Jie Zhang, Gelei Deng, Jiawen Zhang, Xiaogeng Liu, Chaowei Xiao, Tianwei Zhang Published: 2026-03-24 Categories: cs.CR, cs.AI, cs.SI arXiv: https://arxiv.org/abs/2603.23064v3 We identify a critical security vulnerability in mainstream Claw personal AI agents: untrusted content encountered during heartbeat-driven background execution can silently pollute agent memory and subsequently influence user-facing behavior without the user's awareness. This vulnerability arises from an architectural design shared across the Claw ecosystem: heartbeat background execution runs in the same session as user-facing conversation, so content ingested from any external source monitored in the background (including email, message channels, news feeds, code repositories, and social platforms) can enter the same memory context used for foreground interaction, often with limited user visibility and without clear source provenance. We formalize this process as an Exposure (E) $\rightarrow$ Memory (M) $\rightarrow$ Behavior (B) pathway: misinformation encountered during heartbeat execution enters the agent's short-term session context, potentially gets written into long-term memory, and later shapes downstream user-facing behavior. We instantiate this pathway in an agent-native social setting using MissClaw, a controlled research replica of Moltbook. We find that (1) social credibility cues, especially perceived consensus, are the dominant driver of short-term behavioral influence, with misleading rates up to 61%; (2) routine memory-saving behavior can promote short-term pollution into durable long-term memory at rates up to 91%, with cross-session behavioral influence reaching 76%; (3) under naturalistic browsing with content dilution and context pruning, pollution still crosses session boundaries. Overall, prompt injection is not required: ordinary social misinformation is sufficient to silently shape agent memory and behavior under heartbeat-driven background execution. --- ### Machine Learning Models for the Early Detection of Burnout in Software Engineering: a Systematic Literature Review Authors: Tien Rahayu Tulili, Ayushi Rastogi, Andrea Capiluppi Published: 2026-03-24 Categories: cs.SE, cs.AI, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2603.23063v1 Burnout is an occupational syndrome that, like many other professions, affects the majority of software engineers. Past research studies showed important trends, including an increasing use of machine learning techniques to allow for an early detection of burnout. This paper is a systematic literature review (SLR) of the research papers that proposed machine learning (ML) approaches, and focused on detecting burnout in software developers and IT professionals. Our objective is to review the accuracy and precision of the proposed ML techniques, and to formulate recommendations for future researchers interested to replicate or extend those studies. From our SLR we observed that a majority of primary studies focuses on detecting emotions or utilise emotional dimensions to detect or predict the presence of burnout. We also performed a cross-sectional study to detect which ML approach shows a better performance at detecting emotions; and which dataset has more potential and expressivity to capture emotions. We believe that, by identifying which ML tools and datasets show a better performance at detecting emotions, and indirectly at identifying burnout, our paper can be a valuable asset to progress in this important research direction. --- ### Minibal: Balanced Game-Playing Without Opponent Modeling Authors: Quentin Cohen-Solal, Tristan Cazenave Published: 2026-03-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.23059v1 Recent advances in game AI, such as AlphaZero and Athénan, have achieved superhuman performance across a wide range of board games. While highly powerful, these agents are ill-suited for human-AI interaction, as they consistently overwhelm human players, offering little enjoyment and limited educational value. This paper addresses the problem of balanced play, in which an agent challenges its opponent without either dominating or conceding. We introduce Minibal (Minimize & Balance), a variant of Minimax specifically designed for balanced play. Building on this concept, we propose several modifications of the Unbounded Minimax algorithm explicitly aimed at discovering balanced strategies. Experiments conducted across seven board games demonstrate that one variant consistently achieves the most balanced play, with average outcomes close to perfect balance. These results establish Minibal as a promising foundation for designing AI agents that are both challenging and engaging, suitable for both entertainment and serious games. --- ### Prompt Amplification and Zero-Shot Late Fusion in Audio-Language Models for Speech Emotion Recognition Authors: Saurabh Kataria, Xiao Hu Published: 2026-03-24 Categories: eess.AS, cs.LG arXiv: https://arxiv.org/abs/2603.23057v1 Audio-Language Models (ALMs) are making strides in understanding speech and non-speech audio. However, domain-specialist Foundation Models (FMs) remain the best for closed-ended speech processing tasks such as Speech Emotion Recognition (SER). Using ALMs for Zero-shot SER is a popular choice, but their potential to work with specialists to achieve state-of-the-art (SOTA) performance remains unexplored. We propose ZS-Fuse, a late-fusion method that combines zero-shot emotion estimates from a dual-encoder ALM with specialist FMs. To handle ambiguity in emotions and sensitivity to prompt choice, 1) we use a simple prompt ensemble and 2) suggest a novel technique called prompt amplification, which repeats audio and text queries to discover stronger zero-shot capabilities. We demonstrate the efficacy of our technique by evaluating ZS-Fuse with three dual-encoder ALMs and two FMs, and report improvements over SOTA baselines, such as WavLM-Large, on three speech emotion recognition datasets. --- ### Post-Selection Distributional Model Evaluation Authors: Amirmohammad Farzaneh, Osvaldo Simeone Published: 2026-03-24 Categories: stat.ML, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2603.23055v3 Formal model evaluation methods typically certify that a model satisfies a prescribed target key performance indicator (KPI) level. However, in many applications, the relevant target KPI level may not be known a priori, and the user may instead wish to compare candidate models by analyzing the full trade-offs between performance and reliability achievable at test time by the models. This task, requiring the reliable estimate of the test-time KPI distributions, is made more complicated by the fact that the same data must often be used both to pre-select a subset of candidate models and to estimate their KPI distributions, causing a potential post-selection bias. In this work, we introduce post-selection distributional model evaluation (PS-DME), a general framework for statistically valid distributional model assessment after arbitrary data-dependent model pre-selection. Building on e-values, PS-DME controls post-selection false coverage rate (FCR) for the distributional KPI estimates and we establish explicit conditions under which it is provably more sample efficient than a baseline method based on sample splitting. Experiments on synthetic data, text-to-SQL decoding with large language models, and telecom network performance evaluation demonstrate that PS-DME enables reliable comparison of candidate configurations across a range of reliability levels, supporting the statistically reliable exploration of performance--reliability trade-offs. --- ### DBAutoDoc: Automated Discovery and Documentation of Undocumented Database Schemas via Statistical Analysis and Iterative LLM Refinement Authors: Amith Nagarajan, Thomas Altman Published: 2026-03-24 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2603.23050v1 A tremendous number of critical database systems lack adequate documentation. Declared primary keys are absent, foreign key constraints have been dropped for performance, column names are cryptic abbreviations, and no entity-relationship diagrams exist. We present DBAutoDoc, a system that automates the discovery and documentation of undocumented relational database schemas by combining statistical data analysis with iterative large language model (LLM) refinement. DBAutoDoc's central insight is that schema understanding is fundamentally an iterative, graph-structured problem. Drawing structural inspiration from backpropagation in neural networks, DBAutoDoc propagates semantic corrections through schema dependency graphs across multiple refinement iterations until descriptions converge. This propagation is discrete and semantic rather than mathematical, but the structural analogy is precise: early iterations produce rough descriptions akin to random initialization, and successive passes sharpen the global picture as context flows through the graph. The system makes four concrete contributions detailed in the paper. On a suite of benchmark databases, DBAutoDoc achieved overall weighted scores of 96.1% across two model families (Google's Gemini and Anthropic's Claude) using a composite metric. Ablation analysis demonstrates that the deterministic pipeline contributes a 23-point F1 improvement over LLM-only FK detection, confirming that the system's contribution is substantial and independent of LLM pre-training knowledge. DBAutoDoc is released as open-source software with all evaluation configurations and prompt templates included for full reproducibility. --- ### MSR-HuBERT: Self-supervised Pre-training for Adaptation to Multiple Sampling Rates Authors: Zikang Huang, Meng Ge, Tianrui Wang, Xuanchen Li, Xiaobao Wang, Longbiao Wang, Jianwu Dang Published: 2026-03-24 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2603.23048v1 Self-supervised learning (SSL) has advanced speech processing. However, existing speech SSL methods typically assume a single sampling rate and struggle with mixed-rate data due to temporal resolution mismatch. To address this limitation, we propose MSRHuBERT, a multi-sampling-rate adaptive pre-training method. Building on HuBERT, we replace its single-rate downsampling CNN with a multi-sampling-rate adaptive downsampling CNN that maps raw waveforms from different sampling rates to a shared temporal resolution without resampling. This design enables unified mixed-rate pre-training and fine-tuning. In experiments spanning 16 to 48 kHz, MSRHuBERT outperforms HuBERT on speech recognition and full-band speech reconstruction, preserving high-frequency detail while modeling low-frequency semantic structure. Moreover, MSRHuBERT retains HuBERT's mask-prediction objective and Transformer encoder, so existing analyses and improvements that were developed for HuBERT can apply directly. --- ### Parametric Knowledge in RAG-SFT for Domain-Specific Document Generation Authors: Julian Oestreich, Maximilian Bley, Frank Binder, Lydia Müller, André Alcalde, Maksym Sydorenkoq Published: 2026-03-24 Categories: cs.CL, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2603.23047v2 Retrieval-Augmented Generation (RAG) fine-tuning has shown substantial improvements over vanilla RAG, yet most studies target document question answering, leaving open whether these gains transfer to specialized tasks. We study supervised RAG fine-tuning (RAG-SFT) for requirements document generation in the electronics engineering domain, adapting two 7B models under two different training data strategies. Because Rouge and BertScore poorly capture factuality on long technical text, we introduce C-FEX, a claim-based evaluation pipeline that attributes each response claim to its origin (augmented prompt or reference response), and propose Parametric Knowledge Precision (PKP), which isolates claims originating from the model's weights and measures their correctness. We show that a prior metric to assess parametric knowledge decomposes as PKP $\times$ PR, separating the rate of parametric output (PR) from its quality (PKP). Empirically, fine-tuned 7B models match or exceed a 72B baseline; standard metrics disagree with claim-based factuality and can mislead about fine-tuning gains; and, fine-tuning does not reinforce correct parametric knowledge but suppresses hallucination---models speak from their weights less often but far more reliably. --- ### Parametric Knowledge and Retrieval Behavior in RAG Fine-Tuning for Electronic Design Automation Authors: Julian Oestreich, Maximilian Bley, Frank Binder, Lydia Müller, Maksym Sydorenko, André Alcalde Published: 2026-03-24 Categories: cs.CL, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2603.23047v1 Retrieval-Augmented Generation (RAG) fine-tuning has shown substantial improvements over vanilla RAG, yet most studies target document question answering and often rely on standard NLP metrics that can obscure factual differences. We evaluate RAG fine-tuning for long-form text generation in electronic design automation, adapting a 7B model under five context augmentation strategies with varying retrieval conditions. We introduce TriFEX, a human-validated, triple-based evaluation pipeline that attributes generated claims to their origin-user query, context and reference-and propose Parametric Knowledge Precision (PKP), which isolates internalized knowledge by filtering out claims leaked in the prompt. We show that ROUGE and BERTScore fail to detect factual differences that our triple-based evaluation reveals. Additionally, we demonstrate that an existing metric for knowledge internalization is retrieva-sensitive, with about 75% of its cross-condition variance driven by changes in the rate at which internal knowledge is expressed (PR), rather than by changes in its actual correctness (PKP). The fine-tuned 7B variants outperform a 72B baseline on most metrics, further showing generalization across conditions and on a related benchmark. These results underscore the limitations of available metrics in RAG evaluation and show that smaller models could be reasonably well adapted to specialized tasks for cost-efficient, on-premises deployment. --- ### Assessing the Robustness of Climate Foundation Models under No-Analog Distribution Shifts Authors: Maria Conchita Agana Navarro, Geng Li, Theo Wolf, Maria Perez-Ortiz Published: 2026-03-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.23043v2 The accelerating pace of climate change introduces profound non-stationarities that challenge the ability of Machine Learning based climate emulators to generalize beyond their training distributions. While these emulators offer computationally efficient alternatives to traditional Earth System Models, their reliability remains a potential bottleneck under "no-analog" future climate states, which we define here as regimes where external forcing drives the system into conditions outside the empirical range of the historical training data. A fundamental challenge in evaluating this reliability is data contamination; because many models are trained on simulations that already encompass future scenarios, true out-of-distribution (OOD) performance is often masked. To address this, we benchmark the OOD robustness of three state-of-the-art architectures: U-Net, ConvLSTM, and the ClimaX foundation model specifically restricted to a historical-only training regime (1850-2014). We evaluate these models using two complementary strategies: (i) temporal extrapolation to the recent climate (2015-2023) and (ii) cross-scenario forcing shifts across divergent emission pathways. Our analysis within this experimental setup reveals an accuracy vs. stability trade-off: while the ClimaX foundation model achieves the lowest absolute error, it exhibits higher relative performance changes under distribution shifts, with precipitation errors increasing by up to 8.44% under extreme forcing scenarios. These findings suggest that when restricted to historical training dynamics, even high-capacity foundation models are sensitive to external forcing trajectories. Our results underscore the necessity of scenario-aware training and rigorous OOD evaluation protocols to ensure the robustness of climate emulators under a changing climate. --- ### HUydra: Full-Range Lung CT Synthesis via Multiple HU Interval Generative Modelling Authors: António Cardoso, Pedro Sousa, Tania Pereira, Hélder P. Oliveira Published: 2026-03-24 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.23041v1 Currently, a central challenge and bottleneck in the deployment and validation of computer-aided diagnosis (CAD) models within the field of medical imaging is data scarcity. For lung cancer, one of the most prevalent types worldwide, limited datasets can delay diagnosis and have an impact on patient outcome. Generative AI offers a promising solution for this issue, but dealing with the complex distribution of full Hounsfield Unit (HU) range lung CT scans is challenging and remains as a highly computationally demanding task. This paper introduces a novel decomposition strategy that synthesizes CT images one HU interval at a time, rather than modelling the entire HU domain at once. This framework focuses on training generative architectures on individual tissue-focused HU windows, then merges their output into a full-range scan via a learned reconstruction network that effectively reverses the HU-windowing process. We further propose multi-head and multi-decoder models to better capture textures while preserving anatomical consistency, with a multi-head VQVAE achieving the best performance for the generative task. Quantitative evaluation shows this approach significantly outperforms conventional 2D full-range baselines, achieving a 6.2% improvement in FID and superior MMD, Precision, and Recall across all HU intervals. The best performance is achieved by a multi-head VQVAE variant, demonstrating that it is possible to enhance visual fidelity and variability while also reducing model complexity and computational cost. This work establishes a new paradigm for structure-aware medical image synthesis, aligning generative modelling with clinical interpretation. --- ### YOLO with Kolmogorov-Arnold networks and vision-language foundation models for interpretable object detection with trustworthy multimodal AI in computer vision perception Authors: Marios Impraimakis, Daniel Vazquez, Feiyu Zhou Published: 2026-03-24 Categories: cs.CV, cs.AI, cs.CL, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.23037v2 The trustworthy object detection capabilities of a novel Kolmogorov-Arnold network framework are examined here. The approach addresses a key limitation in computer vision for vehicle detection perception, and beyond. These systems offer limited transparency regarding the reliability of their confidence scores in visually degraded or ambiguous scenes. To this end, a Kolmogorov-Arnold network is employed as an interpretable post-hoc surrogate to model the trustworthiness of the You Only Look Once (Yolov10) detections using seven geometric and semantic features. The additive spline-based structure of the Kolmogorov-Arnold network enables direct visualisation of each feature's influence. This produces smooth and transparent functional mappings that reveal when the model's confidence is well supported and when it is unreliable. Furthermore, a bootstrapped language-image (BLIP) foundation model generates descriptive captions of each scene. This tool enables a lightweight multimodal interface without affecting the interpretability layer. Experiments on both Common Objects in Context (COCO), and images from the University of Bath campus demonstrate that the framework accurately identifies low-trust predictions under blur, occlusion, or low texture. This provides actionable insights for acceptance, review, or downstream risk mitigation. The resulting system delivers interpretable object detection with trustworthy confidence estimates. It offers a powerful tool for transparent and practical perception component for autonomous and multimodal artificial intelligence applications. --- ### YOLOv10 with Kolmogorov-Arnold networks and vision-language foundation models for interpretable object detection and trustworthy multimodal AI in computer vision perception Authors: Marios Impraimakis, Daniel Vazquez, Feiyu Zhou Published: 2026-03-24 Categories: cs.CV, cs.AI, cs.CL, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.23037v1 The interpretable object detection capabilities of a novel Kolmogorov-Arnold network framework are examined here. The approach refers to a key limitation in computer vision for autonomous vehicles perception, and beyond. These systems offer limited transparency regarding the reliability of their confidence scores in visually degraded or ambiguous scenes. To address this limitation, a Kolmogorov-Arnold network is employed as an interpretable post-hoc surrogate to model the trustworthiness of the You Only Look Once (Yolov10) detections using seven geometric and semantic features. The additive spline-based structure of the Kolmogorov-Arnold network enables direct visualisation of each feature's influence. This produces smooth and transparent functional mappings that reveal when the model's confidence is well supported and when it is unreliable. Experiments on both Common Objects in Context (COCO), and images from the University of Bath campus demonstrate that the framework accurately identifies low-trust predictions under blur, occlusion, or low texture. This provides actionable insights for filtering, review, or downstream risk mitigation. Furthermore, a bootstrapped language-image (BLIP) foundation model generates descriptive captions of each scene. This tool enables a lightweight multimodal interface without affecting the interpretability layer. The resulting system delivers interpretable object detection with trustworthy confidence estimates. It offers a powerful tool for transparent and practical perception component for autonomous and multimodal artificial intelligence applications. --- ### Traffic Sign Recognition in Autonomous Driving: Dataset, Benchmark, and Field Experiment Authors: Guoyang Zhao, Weiqing Qi, Kai Zhang, Chenguang Zhang, Zeying Gong, Zhihai Bi, Kai Chen, Benshan Ma, Ming Liu, Jun Ma Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23034v1 Traffic Sign Recognition (TSR) is a core perception capability for autonomous driving, where robustness to cross-region variation, long-tailed categories, and semantic ambiguity is essential for reliable real-world deployment. Despite steady progress in recognition accuracy, existing traffic sign datasets and benchmarks offer limited diagnostic insight into how different modeling paradigms behave under these practical challenges. We present TS-1M, a large-scale and globally diverse traffic sign dataset comprising over one million real-world images across 454 standardized categories, together with a diagnostic benchmark designed to analyze model capability boundaries. Beyond standard train-test evaluation, we provide a suite of challenge-oriented settings, including cross-region recognition, rare-class identification, low-clarity robustness, and semantic text understanding, enabling systematic and fine-grained assessment of modern TSR models. Using TS-1M, we conduct a unified benchmark across three representative learning paradigms: classical supervised models, self-supervised pretrained models, and multimodal vision-language models (VLMs). Our analysis reveals consistent paradigm-dependent behaviors, showing that semantic alignment is a key factor for cross-region generalization and rare-category recognition, while purely visual models remain sensitive to appearance shift and data imbalance. Finally, we validate the practical relevance of TS-1M through real-scene autonomous driving experiments, where traffic sign recognition is integrated with semantic reasoning and spatial localization to support map-level decision constraints. Overall, TS-1M establishes a reference-level diagnostic benchmark for TSR and provides principled insights into robust and semantic-aware traffic sign perception. Project page: https://guoyangzhao.github.io/projects/ts1m. --- ### Generative Event Pretraining with Foundation Model Alignment Authors: Jianwen Cao, Jiaxu Xing, Nico Messikommer, Davide Scaramuzza Published: 2026-03-24 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.23032v1 Event cameras provide robust visual signals under fast motion and challenging illumination conditions thanks to their microsecond latency and high dynamic range. However, their unique sensing characteristics and limited labeled data make it challenging to train event-based visual foundation models (VFMs), which are crucial for learning visual features transferable across tasks. To tackle this problem, we propose GEP (Generative Event Pretraining), a two-stage framework that transfers semantic knowledge learned from internet-scale image datasets to event data while learning event-specific temporal dynamics. First, an event encoder is aligned to a frozen VFM through a joint regression-contrastive objective, grounding event features in image semantics. Second, a transformer backbone is autoregressively pretrained on mixed event-image sequences to capture the temporal structure unique to events. Our approach outperforms state-of-the-art event pretraining methods on a diverse range of downstream tasks, including object recognition, segmentation, and depth estimation. Together, VFM-guided alignment and generative sequence modeling yield a semantically rich, temporally aware event model that generalizes robustly across domains. --- ### Looking Beyond the Window: Global-Local Aligned CLIP for Training-free Open-Vocabulary Semantic Segmentation Authors: ByeongCheol Lee, Hyun Seok Seong, Sangeek Hyun, Gilhan Park, WonJun Moon, Jae-Pil Heo Published: 2026-03-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.23030v1 A sliding-window inference strategy is commonly adopted in recent training-free open-vocabulary semantic segmentation methods to overcome limitation of the CLIP in processing high-resolution images. However, this approach introduces a new challenge: each window is processed independently, leading to semantic discrepancy across windows. To address this issue, we propose Global-Local Aligned CLIP~(GLA-CLIP), a framework that facilitates comprehensive information exchange across windows. Rather than limiting attention to tokens within individual windows, GLA-CLIP extends key-value tokens to incorporate contextual cues from all windows. Nevertheless, we observe a window bias: outer-window tokens are less likely to be attended, since query features are produced through interactions within the inner window patches, thereby lacking semantic grounding beyond their local context. To mitigate this, we introduce a proxy anchor, constructed by aggregating tokens highly similar to the given query from all windows, which provides a unified semantic reference for measuring similarity across both inner- and outer-window patches. Furthermore, we propose a dynamic normalization scheme that adjusts attention strength according to object scale by dynamically scaling and thresholding the attention map to cope with small-object scenarios. Moreover, GLA-CLIP can be equipped on existing methods and broad their receptive field. Extensive experiments validate the effectiveness of GLA-CLIP in enhancing training-free open-vocabulary semantic segmentation performance. Code is available at https://github.com/2btlFe/GLA-CLIP. --- ### Cog3DMap: Multi-View Vision-Language Reasoning with 3D Cognitive Maps Authors: Chanyoung Gwak, Yoonwoo Jeong, Byungwoo Jeon, Hyunseok Lee, Jinwoo Shin, Minsu Cho Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23023v1 Precise spatial understanding from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs), as their visual representations are predominantly semantic and lack explicit geometric grounding. While existing approaches augment visual tokens with geometric cues from visual geometry models, their MLLM is still required to implicitly infer the underlying 3D structure of the scene from these augmented tokens, limiting its spatial reasoning capability. To address this issue, we introduce Cog3DMap, a framework that recurrently constructs an explicit 3D memory from multi-view images, where each token is grounded in 3D space and possesses both semantic and geometric information. By feeding these tokens into the MLLM, our framework enables direct reasoning over a spatially structured 3D map, achieving state-of-the-art performance on various spatial reasoning benchmarks. Code will be made publicly available. --- ### Concept-based explanations of Segmentation and Detection models in Natural Disaster Management Authors: Samar Heydari, Jawher Said, Galip Ümit Yolcu, Evgenii Kortukov, Elena Golimblevskaia, Evgenios Vlachos, Vasileios Mygdalis, Ioannis Pitas, Sebastian Lapuschkin, Leila Arras Published: 2026-03-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.23020v1 Deep learning models for flood and wildfire segmentation and object detection enable precise, real-time disaster localization when deployed on embedded drone platforms. However, in natural disaster management, the lack of transparency in their decision-making process hinders human trust required for emergency response. To address this, we present an explainability framework for understanding flood segmentation and car detection predictions on the widely used PIDNet and YOLO architectures. More specifically, we introduce a novel redistribution strategy that extends Layer-wise Relevance Propagation (LRP) explanations for sigmoid-gated element-wise fusion layers. This extension allows LRP relevances to flow through the fusion modules of PIDNet, covering the entire computation graph back to the input image. Furthermore, we apply Prototypical Concept-based Explanations (PCX) to provide both local and global explanations at the concept level, revealing which learned features drive the segmentation and detection of specific disaster semantic classes. Experiments on a publicly available flood dataset show that our framework provides reliable and interpretable explanations while maintaining near real-time inference capabilities, rendering it suitable for deployment on resource-constrained platforms, such as Unmanned Aerial Vehicles (UAVs). --- ### A Sobering Look at Tabular Data Generation via Probabilistic Circuits Authors: Davide Scassola, Dylan Ponsford, Adrián Javaloy, Sebastiano Saccani, Luca Bortolussi, Henry Gouk, Antonio Vergari Published: 2026-03-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.23016v2 Tabular data is more challenging to generate than text and images, due to its heterogeneous features and much lower sample sizes. On this task, diffusion-based models are the current state-of-the-art (SotA) model class, achieving almost perfect performance on commonly used benchmarks. In this paper, we question the perception of progress for tabular data generation. First, we highlight the limitations of current protocols to evaluate the fidelity of generated data, and advocate for alternative ones. Next, we revisit a simple baseline -- hierarchical mixture models in the form of deep probabilistic circuits (PCs) -- which delivers competitive or superior performance to SotA models for a fraction of the cost. PCs are the generative counterpart of decision forests, and as such can natively handle heterogeneous data as well as deliver tractable probabilistic generation and inference. Finally, in a rigorous empirical analysis we show that the apparent saturation of progress for SotA models is largely due to the use of inadequate metrics. As such, we highlight that there is still much to be done to generate realistic tabular data. Code available at https://github.com/april-tools/tabpc. --- ### A Sobering Look at Tabular Data Generation via Probabilistic Circuits Authors: Davide Scassola, Dylan Ponsford, Adrián Javaloy, Sebastiano Saccani, Luca Bortolussi, Henry Gouk, Antonio Vergari Published: 2026-03-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.23016v1 Tabular data is more challenging to generate than text and images, due to its heterogeneous features and much lower sample sizes. On this task, diffusion-based models are the current state-of-the-art (SotA) model class, achieving almost perfect performance on commonly used benchmarks. In this paper, we question the perception of progress for tabular data generation. First, we highlight the limitations of current protocols to evaluate the fidelity of generated data, and advocate for alternative ones. Next, we revisit a simple baseline -- hierarchical mixture models in the form of deep probabilistic circuits (PCs) -- which delivers competitive or superior performance to SotA models for a fraction of the cost. PCs are the generative counterpart of decision forests, and as such can natively handle heterogeneous data as well as deliver tractable probabilistic generation and inference. Finally, in a rigorous empirical analysis we show that the apparent saturation of progress for SotA models is largely due to the use of inadequate metrics. As such, we highlight that there is still much to be done to generate realistic tabular data. Code available at https://github.com/april-tools/tabpc. --- ### Knowledge Access Beats Model Size: Memory Augmented Routing for Persistent AI Agents Authors: Xunzhuo Liu, Bowei He, Xue Liu, Andy Luo, Haichen Zhang, Huamin Chen Published: 2026-03-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.23013v1 Production AI agents frequently receive user-specific queries that are highly repetitive, with up to 47\% being semantically similar to prior interactions, yet each query is typically processed with the same computational cost. We argue that this redundancy can be exploited through conversational memory, transforming repetition from a cost burden into an efficiency advantage. We propose a memory-augmented inference framework in which a lightweight 8B-parameter model leverages retrieved conversational context to answer all queries via a low-cost inference path. Without any additional training or labeled data, this approach achieves 30.5\% F1, recovering 69\% of the performance of a full-context 235B model while reducing effective cost by 96\%. Notably, a 235B model without memory (13.7\% F1) underperforms even the standalone 8B model (15.4\% F1), indicating that for user-specific queries, access to relevant knowledge outweighs model scale. We further analyze the role of routing and confidence. At practical confidence thresholds, routing alone already directs 96\% of queries to the small model, but yields poor accuracy (13.0\% F1) due to confident hallucinations. Memory does not substantially alter routing decisions; instead, it improves correctness by grounding responses in retrieved user-specific information. As conversational memory accumulates over time, coverage of recurring topics increases, further narrowing the performance gap. We evaluate on 152 LoCoMo questions (Qwen3-8B/235B) and 500 LongMemEval questions. Incorporating hybrid retrieval (BM25 + cosine similarity) improves performance by an additional +7.7 F1, demonstrating that retrieval quality directly enhances end-to-end system performance. Overall, our results highlight that memory, rather than model size, is the primary driver of accuracy and efficiency in persistent AI agents. --- ### Zero-Shot Personalization of Objects via Textual Inversion Authors: Aniket Roy, Maitreya Suin, Rama Chellappa Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23010v1 Recent advances in text-to-image diffusion models have substantially improved the quality of image customization, enabling the synthesis of highly realistic images. Despite this progress, achieving fast and efficient personalization remains a key challenge, particularly for real-world applications. Existing approaches primarily accelerate customization for human subjects by injecting identity-specific embeddings into diffusion models, but these strategies do not generalize well to arbitrary object categories, limiting their applicability. To address this limitation, we propose a novel framework that employs a learned network to predict object-specific textual inversion embeddings, which are subsequently integrated into the UNet timesteps of a diffusion model for text-conditional customization. This design enables rapid, zero-shot personalization of a wide range of objects in a single forward pass, offering both flexibility and scalability. Extensive experiments across multiple tasks and settings demonstrate the effectiveness of our approach, highlighting its potential to support fast, versatile, and inclusive image customization. To the best of our knowledge, this work represents the first attempt to achieve such general-purpose, training-free personalization within diffusion models, paving the way for future research in personalized image generation. --- ### AgentRAE: Remote Action Execution through Notification-based Visual Backdoors against Screenshots-based Mobile GUI Agents Authors: Yutao Luo, Haotian Zhu, Shuchao Pang, Zhigang Lu, Tian Dong, Yongbin Zhou, Minhui Xue Published: 2026-03-24 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.23007v1 The rapid adoption of mobile graphical user interface (GUI) agents, which autonomously control applications and operating systems (OS), exposes new system-level attack surfaces. Existing backdoors against web GUI agents and general GenAI models rely on environmental injection or deceptive pop-ups to mislead the agent operation. However, these techniques do not work on screenshots-based mobile GUI agents due to the challenges of restricted trigger design spaces, OS background interference, and conflicts in multiple trigger-action mappings. We propose AgentRAE, a novel backdoor attack capable of inducing Remote Action Execution in mobile GUI agents using visually natural triggers (e.g., benign app icons in notifications). To address the underfitting caused by natural triggers and achieve accurate multi-target action redirection, we design a novel two-stage pipeline that first enhances the agent's sensitivity to subtle iconographic differences via contrastive learning, and then associates each trigger with a specific mobile GUI agent action through a backdoor post-training. Our extensive evaluation reveals that the proposed backdoor preserves clean performance with an attack success rate of over 90% across ten mobile operations. Furthermore, it is hard to visibly detect the benign-looking triggers and circumvents eight representative state-of-the-art defenses. These results expose an overlooked backdoor vector in mobile GUI agents, underscoring the need for defenses that scrutinize notification-conditioned behaviors and internal agent representations. --- ### Can Large Language Models Reason and Optimize Under Constraints? Authors: Fabien Bernier, Salah Ghamizi, Pantelis Dogoulis, Maxime Cordy Published: 2026-03-24 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.23004v1 Large Language Models (LLMs) have demonstrated great capabilities across diverse natural language tasks; yet their ability to solve abstraction and optimization problems with constraints remains scarcely explored. In this paper, we investigate whether LLMs can reason and optimize under the physical and operational constraints of Optimal Power Flow (OPF) problem. We introduce a challenging evaluation setup that requires a set of fundamental skills such as reasoning, structured input handling, arithmetic, and constrained optimization. Our evaluation reveals that SoTA LLMs fail in most of the tasks, and that reasoning LLMs still fail in the most complex settings. Our findings highlight critical gaps in LLMs' ability to handle structured reasoning under constraints, and this work provides a rigorous testing environment for developing more capable LLM assistants that can tackle real-world power grid optimization problems. --- ### On the use of Aggregation Operators to improve Human Identification using Dental Records Authors: Antonio D. Villegas-Yeguas, Guillermo R-García, Tzipi Kahana, Jorge Pinares Toledo, Esi Sharon, Oscar Ibañez, Oscar Cordón Published: 2026-03-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.23003v1 The comparison of dental records is a standardized technique in forensic dentistry used to speed up the identification of individuals in multiple-comparison scenarios. Specifically, the odontogram comparison is a procedure to compute criteria that will be used to perform a ranking. State-of-the-art automatic methods either make use of simple techniques, without utilizing the full potential of the information obtained from a comparison, or their internal behavior is not known due to the lack of peer-reviewed publications. This work aims to design aggregation mechanisms to automatically compare pairs of dental records that can be understood and validated by experts, improving the current methods. To do so, we introduce different aggregation approaches using the state-of-the-art codification, based on seven different criteria. In particular, we study the performance of i) data-driven lexicographical order-based aggregations, ii) well-known fuzzy logic aggregation methods and iii) machine learning techniques as aggregation mechanisms. To validate our proposals, 215 forensic cases from two different populations have been used. The results obtained show how the use of white-box machine learning techniques as aggregation models (average ranking from 2.02 to 2.21) are able to improve the state-of-the-art (average ranking of 3.91) without compromising the explainability and interpretability of the method. --- ### PaperVoyager : Building Interactive Web with Visual Language Models Authors: Dasen Dai, Biao Wu, Meng Fang, Wenhao Wang Published: 2026-03-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.22999v3 Recent advances in visual language models have enabled autonomous agents for complex reasoning, tool use, and document understanding. However, existing document agents mainly transform papers into static artifacts such as summaries, webpages, or slides, which are insufficient for technical papers involving dynamic mechanisms and state transitions. In this work, we propose a Paper-to-Interactive-System Agent that converts research papers into executable interactive web systems. Given a PDF paper, the agent performs end-to-end processing without human intervention, including paper understanding, system modeling, and interactive webpage synthesis, enabling users to manipulate inputs and observe dynamic behaviors. To evaluate this task, we introduce a benchmark of 19 research papers paired with expert-built interactive systems as ground truth. We further propose PaperVoyager, a structured generation framework that explicitly models mechanisms and interaction logic during synthesis. Experiments show that PaperVoyager significantly improves the quality of generated interactive systems, offering a new paradigm for interactive scientific paper understanding. --- ### VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thought Authors: Xuanyu Zhang, Weiqi Li, Qunliang Xing, Jingfen Xie, Bin Chen, Junlin Li, Li Zhang, Jian Zhang, Shijie Zhao Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22998v1 Video restoration in real-world scenarios is challenged by heterogeneous degradations, where static architectures and fixed inference pipelines often fail to generalize. Recent agent-based approaches offer dynamic decision making, yet existing video restoration agents remain limited by insufficient quality perception and inefficient search strategies. We propose VQ-Jarvis, a retrieval-augmented, all-in-one intelligent video restoration agent with sharper vision and faster thought. VQ-Jarvis is designed to accurately perceive degradations and subtle differences among paired restoration results, while efficiently discovering optimal restoration trajectories. To enable sharp vision, we construct VSR-Compare, the first large-scale video paired enhancement dataset with 20K comparison pairs covering 7 degradation types, 11 enhancement operators, and diverse content domains. Based on this dataset, we train a multiple operator judge model and a degradation perception model to guide agent decisions. To achieve fast thought, we introduce a hierarchical operator scheduling strategy that adapts to video difficulty: for easy cases, optimal restoration trajectories are retrieved in a one-step manner from a retrieval-augmented generation (RAG) library; for harder cases, a step-by-step greedy search is performed to balance efficiency and accuracy. Extensive experiments demonstrate that VQ-Jarvis consistently outperforms existing methods on complex degraded videos. --- ### Training-Free Interaction-Aligned Visual Token Pruning for Efficient Embodied Manipulation Authors: Jintao Cheng, Weibin Li, Haozhe Wang, Gang Wang, Yipu Zhang, Xiaoyu Tang, Jin Wu, Xieyuanli Chen, Yunhui Liu, Wei Zhang Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22991v2 Efficient visual representation is a central image-processing challenge in embodied manipulation, where policies repeatedly process dense visual-token sequences during closed-loop control. Existing methods rank or prune tokens using semantic relevance, VLM attention, cross-frame redundancy, or motion in the action space. These signals may discard task-relevant regions when instruction-related appearance and observed image motion are not yet spatially aligned. We introduce Interaction-Aligned Pruning (IAprune), a training-free method that treats per-frame budget setting and within-budget token selection as two linked decisions. Semantic--motion spatial agreement guides the choice between Conservative and Aggressive coverage, and the resulting region size is mapped to a calibrated dynamic budget. Continuous semantic and motion responses rank the existing tokens, while geometric residual correction redirects fixed selection slots toward under-represented boundaries without increasing the sequence length. Across four embodied manipulation policies, three simulation benchmarks, and a real-robot platform, IAprune provides a favorable accuracy--efficiency trade-off, matching the unpruned policy on LIBERO with a \(1.54\times\) speedup and reaching \(1.48\times\) acceleration on a real robot. Phase-wise analysis shows that retention gains are largest under tight budgets early in an episode, while fixed-budget analysis confirms that geometry replaces low-priority tokens with boundary and contact-region evidence rather than retaining more tokens. Our project website is: \href{https://chengjt1999.github.io/VLA-IAP.github.io/}{IAprune.com}. --- ### VLA-IAP: Training-Free Visual Token Pruning via Interaction Alignment for Vision-Language-Action Models Authors: Jintao Cheng, Haozhe Wang, Weibin Li, Gang Wang, Yipu Zhang, Xiaoyu Tang, Jin Wu, Xieyuanli Chen, Yunhui Liu, Wei Zhang Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22991v1 Vision-Language-Action (VLA) models have rapidly advanced embodied intelligence, enabling robots to execute complex, instruction-driven tasks. However, as model capacity and visual context length grow, the inference cost of VLA systems becomes a major bottleneck for real-world deployment on resource-constrained platforms. Existing visual token pruning methods mainly rely on semantic saliency or simple temporal cues, overlooking the continuous physical interaction, a fundamental property of VLA tasks. Consequently, current approaches often prune visually sparse yet structurally critical regions that support manipulation, leading to unstable behavior during early task phases. To overcome this, we propose a shift toward an explicit Interaction-First paradigm. Our proposed \textbf{training-free} method, VLA-IAP (Interaction-Aligned Pruning), introduces a geometric prior mechanism to preserve structural anchors and a dynamic scheduling strategy that adapts pruning intensity based on semantic-motion alignment. This enables a conservative-to-aggressive transition, ensuring robustness during early uncertainty and efficiency once interaction is locked. Extensive experiments show that VLA-IAP achieves a \textbf{97.8\% success rate} with a \textbf{$1.25\times$ speedup} on the LIBERO benchmark, and up to \textbf{$1.54\times$ speedup} while maintaining performance \textbf{comparable to the unpruned backbone}. Moreover, the method demonstrates superior and consistent performance across multiple model architectures and three different simulation environments, as well as a real robot platform, validating its strong generalization capability and practical applicability. Our project website is: \href{https://chengjt1999.github.io/VLA-IAP.github.io/}{VLA-IAP.com}. --- ### Robustness Quantification and Uncertainty Quantification: Comparing Two Methods for Assessing the Reliability of Classifier Predictions Authors: Adrián Detavernier, Jasper De Bock Published: 2026-03-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.22988v1 We consider two approaches for assessing the reliability of the individual predictions of a classifier: Robustness Quantification (RQ) and Uncertainty Quantification (UQ). We explain the conceptual differences between the two approaches, compare both approaches on a number of benchmark datasets and show that RQ is capable of outperforming UQ, both in a standard setting and in the presence of distribution shift. Beside showing that RQ can be competitive with UQ, we also demonstrate the complementarity of RQ and UQ by showing that a combination of both approaches can lead to even better reliability assessments. --- ### A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attacks Authors: Najeeb Jebreel, David Sánchez, Josep Domingo-Ferrer Published: 2026-03-24 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2603.22987v1 Membership inference attacks (MIAs) aim to determine whether a data sample was included in a machine learning (ML) model's training set and have become the de facto standard for measuring privacy leakages in ML. We propose an evaluation framework that defines the conditions under which MIAs constitute a genuine privacy threat, and review representative MIAs against it. We find that, under the realistic conditions defined in our framework, MIAs represent weak privacy threats. Thus, relying on them as a privacy metric in ML can lead to an overestimation of risk and to unnecessary sacrifices in model utility as a consequence of employing too strong defenses. --- ### Beyond Hate: Differentiating Uncivil and Intolerant Speech in Multimodal Content Moderation Authors: Nils A. Herrmann, Tobias Eder, Jingyi He, Georg Groh Published: 2026-03-24 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2603.22985v1 Current multimodal toxicity benchmarks typically use a single binary hatefulness label. This coarse approach conflates two fundamentally different characteristics of expression: tone and content. Drawing on communication science theory, we introduce a fine-grained annotation scheme that distinguishes two separable dimensions: incivility (rude or dismissive tone) and intolerance (content that attacks pluralism and targets groups or identities) and apply it to 2,030 memes from the Hateful Memes dataset. We evaluate different vision-language models under coarse-label training, transfer learning across label schemes and a joint learning approach that combines the coarse hatefulness label with our fine-grained annotations. Our results show that fine-grained annotations complement existing coarse labels and, when used jointly, improve overall model performance. Moreover, models trained with the fine-grained scheme exhibit more balanced moderation-relevant error profiles and are less prone to under-detection of harmful content than models trained on hatefulness labels alone (FNR-FPR, the difference between false negative and false positive rates: 0.74 to 0.42 for LLaVA-1.6-Mistral-7B; 0.54 to 0.28 for Qwen2.5-VL-7B). This work contributes to data-centric approaches in content moderation by improving the reliability and accuracy of moderation systems through enhanced data quality. Overall, combining both coarse and fine-grained labels provides a practical route to more reliable multimodal moderation. --- ### Can Graph Foundation Models Generalize Over Architecture? Authors: Benjamin Gutteridge, Michael Bronstein, Xiaowen Dong Published: 2026-03-24 Categories: cs.LG, cs.AI, cs.SI arXiv: https://arxiv.org/abs/2603.22984v1 Graph foundation models (GFMs) have recently attracted interest due to the promise of graph neural network (GNN) architectures that generalize zero-shot across graphs of arbitrary scales, feature dimensions, and domains. While existing work has demonstrated this ability empirically across diverse real-world benchmarks, these tasks share a crucial hidden limitation: they admit a narrow set of effective GNN architectures. In particular, current domain-agnostic GFMs rely on fixed architectural backbones, implicitly assuming that a single message-passing regime suffices across tasks. In this paper, we argue that architecture adaptivity is a necessary requirement for true GFMs. We show that existing approaches are non-robust to task-dependent architectural attributes and, as a case study, use range as a minimal and measurable axis along which this limitation becomes explicit. With theoretical analysis and controlled synthetic experiments, we demonstrate that fixed-backbone GFMs provably under-reach on tasks whose architectural requirements differ from those seen at training time. To address this issue, we introduce a framework that adapts effective GNN architecture at inference time by discovering and mixing task-specific linear graph operators, enabling zero-shot generalization across tasks with heterogeneous architectural requirements, without retraining. We validate our approach on arbitrary-range synthetic tasks and a suite of real-world benchmarks, demonstrating improved performance and robustness over existing domain-agnostic GFMs. --- ### JFTA-Bench: Evaluate LLM's Ability of Tracking and Analyzing Malfunctions Using Fault Trees Authors: Yuhui Wang, Zhixiong Yang, Ming Zhang, Shihan Dou, Zhiheng Xi, Enyu Zhou, Senjie Jin, Yujiong Shen, Dingwei Zhu, Yi Dong, Tao Gui, Qi Zhang et al. Published: 2026-03-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.22978v2 In the maintenance of complex systems, fault trees are used to locate problems and provide targeted solutions. To enable fault trees stored as images to be directly processed by large language models, which can assist in tracking and analyzing malfunctions, we propose a novel textual representation of fault trees. Building on it, we construct a benchmark for multi-turn dialogue systems that emphasizes robust interaction in complex environments, evaluating a model's ability to assist in malfunction localization, which contains $3130$ entries and $40.75$ turns per entry on average. We train an end-to-end model to generate vague information to reflect user behavior and introduce long-range rollback and recovery procedures to simulate user error scenarios, enabling assessment of a model's integrated capabilities in task tracking and error recovery, and Gemini 2.5 pro archives the best performance. --- ### JFTA-Bench: Evaluate LLM's Ability of Tracking and Analyzing Malfunctions Using Fault Trees Authors: Yuhui Wang, Zhixiong Yang, Ming Zhang, Shihan Dou, Zhiheng Xi, Enyu Zhou, Senjie Jin, Yujiong Shen, Dingwei Zhu, Yi Dong, Tao Gui, Qi Zhang et al. Published: 2026-03-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.22978v1 In the maintenance of complex systems, fault trees are used to locate problems and provide targeted solutions. To enable fault trees stored as images to be directly processed by large language models, which can assist in tracking and analyzing malfunctions, we propose a novel textual representation of fault trees. Building on it, we construct a benchmark for multi-turn dialogue systems that emphasizes robust interaction in complex environments, evaluating a model's ability to assist in malfunction localization, which contains $3130$ entries and $40.75$ turns per entry on average. We train an end-to-end model to generate vague information to reflect user behavior and introduce long-range rollback and recovery procedures to simulate user error scenarios, enabling assessment of a model's integrated capabilities in task tracking and error recovery, and Gemini 2.5 pro archives the best performance. --- ### DariMis: Harm-Aware Modeling for Dari Misinformation Detection on YouTube Authors: Jawid Ahmad Baktash, Mosa Ebrahimi, Mohammad Zarif Joya, Mursal Dawodi Published: 2026-03-24 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.22977v1 Dari, the primary language of Afghanistan, is spoken by tens of millions of people yet remains largely absent from the misinformation detection literature. We address this gap with DariMis, the first manually annotated dataset of 9,224 Dari-language YouTube videos, labeled across two dimensions: Information Type (Misinformation, Partly True, True) and Harm Level (Low, Medium, High). A central empirical finding is that these dimensions are structurally coupled, not independent: 55.9 percent of Misinformation carries at least Medium harm potential, compared with only 1.0 percent of True content. This enables Information Type classifiers to function as implicit harm-triage filters in content moderation pipelines. We further propose a pair-input encoding strategy that represents the video title and description as separate BERT segment inputs, explicitly modeling the semantic relationship between headline claims and body content, a key signal of misleading information. An ablation study against single-field concatenation shows that pair-input encoding yields a 7.0 percentage point gain in Misinformation recall (60.1 percent to 67.1 percent), the safety-critical minority class, despite modest overall macro F1 differences (0.09 percentage points). We benchmark a Dari/Farsi-specialized model (ParsBERT) against XLM-RoBERTa-base; ParsBERT achieves the best test performance with accuracy of 76.60 percent and macro F1 of 72.77 percent. Bootstrap 95 percent confidence intervals are reported for all metrics, and we discuss both the practical significance and statistical limitations of the results. --- ### Where Experts Disagree, Models Fail: Detecting Implicit Legal Citations in French Court Decisions Authors: Avrile Floro, Tamara Dhorasoo, Soline Pellez, Nils Holzenberger Published: 2026-03-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.22973v2 Applying computational methods to law at scale requires separating genuine legal reasoning from surface similarity. We study this through a concrete task: detecting implicit citations of the French Civil Code, where a court applies a statutory rule without naming it: a post-hoc question about the reasoning a court actually used. We release a benchmark of 1,015 passage-article pairs annotated by three legal experts. Our central finding is that their disagreement is itself informative: the third of cases the experts dispute are where models fail. Our best ensemble reaches an F1 score of 0.70 overall. Yet, two-thirds of its false positives fall on those disputed cases, a concentration that holds across all ten models we evaluate. Disagreement is a signal of intrinsic difficulty, not annotation noise. This should not block useful tools, however: reframed as top-$k$ ranking with multi-model consensus, the same signals reach 76% precision for the top-200 candidates without supervision. --- ### WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion Authors: Manuel-Andreas Schneider, Angela Dai Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22972v3 Recent progress in image and video synthesis has inspired their use in advancing 3D scene generation. However, we observe that text-to-image and -video approaches struggle to maintain scene- and object-level consistency beyond a limited environment scale without a persistent, explicit geometric representation. We thus present a geometry-first approach that decouples this complex problem of large-scale 3D scene synthesis into its structural composition, represented as a mesh scaffold, and realistic appearance synthesis, which leverages powerful image synthesis models conditioned on the mesh scaffold. From an input text description, we first construct a mesh capturing the environment's geometry (walls, floors, etc.), and then use image synthesis, segmentation and object reconstruction to populate the mesh structure with objects in realistic layouts. This mesh scaffold is then rendered to condition image synthesis, providing a structural backbone for consistent appearance generation. This enables scalable, arbitrarily-sized 3D scenes of high object richness and diversity, combining robust 3D consistency with photorealistic detail. We believe this marks a significant step toward generating truly environment-scale, immersive 3D worlds. ---