# Research Papers — 2026-05 · bundle page 95 of 326 > Full-text markdown of papers #4701–4750 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/95 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/94.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/96.md) ### From One-Pass SGD to Data Reuse: Mini-Batch Scaling Laws in Sketched Linear Regression Authors: Ziyan Chen, Zhongzhu Zhou, Ding-Xuan Zhou Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24316v2 Scaling laws provide compact descriptions of how prediction error varies with compute, model size, and data, but existing theory mainly treats single-sample SGD or full data reuse, leaving the role of mini-batching unclear. We study batch scaling laws for sketched linear regression under a power-law covariance spectrum and a source condition on the target parameter. We analyze one-pass batch SGD, multi-pass batch SGD with replacement, and multi-pass batch SGD without replacement. Our first result is a risk decomposition: all three procedures share the same irreducible and approximation terms, while their stochastic terms depend on the sampling protocol. One-pass batch SGD splits into bias and variance, whereas the two multi-pass methods split into GD bias, GD variance, and a fluctuation term around a common GD reference trajectory. We then prove source-condition scaling laws for one-pass and multi-pass mini-batch methods. For one-pass batch SGD, mini-batching preserves the approximation and optimization-bias exponents, while the variance scales as $O(\min(M,(T_{\mathrm{eff}}γ)^{1/a})/(B T_{\mathrm{eff}}))$. Thus the usual $1/B$ covariance reduction holds at fixed update count $T$, but in the one-pass regime $T=N/B$ it is partly offset by the shorter optimization horizon. For multi-pass batch SGD, with- and without-replacement sampling have identical approximation and GD bias/variance terms; they differ only in the fluctuation covariance prefactor, which is $1/B$ with replacement and $ρ_{N,B}=(N-B)/(B(N-1))$ without replacement. Hence without-replacement sampling is less noisy for $B>1$, and when $B=N$ the fluctuation vanishes, recovering deterministic gradient descent. These results place batch size on the same theoretical footing as compute, data, and model dimension in sketched linear regression. --- ### End-to-End Intracortical Speech Decoding from Neural Activity Authors: Owais Mujtaba Khanday, Jose A. Gonzalez-Lopez, Marc Ouellet, Alberto Galdon, Gonzalo Olivares Granados Published: 2026-05-23 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2605.24313v1 Current high-performing intracortical speech neuroprostheses achieve low word error rates but typically rely on external language models during inference, increasing memory, computation, and latency. In this work, we investigate whether meaningful character-level decoding is achievable without such models. We propose an end-to-end Conformer-based neural decoder trained directly on intracortical recordings from a participant with amyotrophic lateral sclerosis (ALS). Without any external language model, the system achieves a character error rate (CER) of 23.80\% on held-out validation data. Analysis shows that performance variability is driven by inter-session signal degradation, while dominant errors arise from incorrect word boundary segmentation. These results demonstrate that effective character-level decoding is possible in a fully end-to-end framework, providing a strong neural signal for downstream linguistic processing. --- ### Discovering Lexical Gaps Using Embeddings from Multilingual LLMs Authors: Yoonwon Jung, Aaron S. Cohen, Benjamin K. Bergen Published: 2026-05-23 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.24310v1 Lexical gaps are words that do not exist in certain languages. They pose challenges for building multilingual lexical resources, for machine translation, and for cross-lingual transfer. Existing lexical gap detection relies on human judgments or fixed conceptual taxonomies. We propose a data-driven framework for identifying cross-lingual lexical gaps. We extracted contextualized embeddings from Korean-English bilingual LLMs for Korean-to-English and English-to-Korean translation pairs. Combinations of LLMs, embedding types, dimensionality, and orthogonal transformations across 100 train-test splits yielded 4000 distinct embedding spaces in each source language. In each space, we computed the semantic similarity between each source word and its nearest neighbor in the target language, and compared their distribution for gap words versus non-gap words. In 94% (Korean-to-English) and 97% (English-to-Korean) of embedding spaces, gap words showed weaker cross-lingual semantic alignment than non-gap words. Logistic classifiers trained on unaligned embedding spaces can reliably separate gap words from non-gap words, achieving AUCs of 0.81 (Korean-to-English) and 0.76 (English-to-Korean) and retrieving 18/19 Korean and 26/27 English gap words. This approach provides a language-agnostic and taxonomy-free method for scalable lexical gap identification. --- ### CoDA: Color Distribution Probing for Efficient and Generalizable AI-Generated Image Detection Authors: Zexi Jia, Zhiqiang Yuan, Xiaoyue Duan, Jinchao Zhang, Jie Zhou, Anil K. Jain Published: 2026-05-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24306v1 AI-generated image detection faces a persistent trade-off between generalization and efficiency: lightweight artifact-based methods often degrade on unseen generators or domains, whereas more robust large-scale models are computationally expensive. Meanwhile, existing benchmarks mainly focus on cross-model evaluation in photorealistic settings, leaving cross-domain robustness underexplored. To address this gap, we introduce FakeForm, a large-scale benchmark with approximately 370,000 images across 62 diverse domains for both cross-model and cross-domain evaluation. Motivated by this broader setting, we revisit color-distribution probing as an efficient complementary cue for AI-generated image detection. We observe that, especially for photographic content, real photographs tend to exhibit smoother and more stable color patterns, whereas synthetic images often show characteristic color imbalances introduced by neural generation. Based on this observation, we propose CoDA, a compact 1.48M-parameter detector built on a Noise-Quantization Probe, together with a theoretical analysis linking probe responses to color non-uniformity. Experiments show that CoDA achieves state-of-the-art performance on standard benchmarks and the best results on the challenging cross-domain evaluation of FakeForm, while remaining highly competitive in cross-model photorealistic settings. These results suggest that persistent generative artifacts can provide a practical foundation for efficient and robust AI-generated image detection. The models and FakeForm benchmark will be made publicly available. --- ### ChaosBench-Logic v2: Evaluating LLM Logical Reasoning over Dynamical Systems at Scale Authors: Noel Thomas Published: 2026-05-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.24305v1 Standard accuracy on binary reasoning benchmarks hides critical failure modes: prior collapse, inconsistency under paraphrase, and inability to reason about parameter-dependent dynamics. We present ChaosBench-Logic v2, a 40,886-question benchmark over 165 dynamical systems with 27 FOL predicates and 78 axiom edges, together with CARE (Calibration- and Adversarial-Robust Evaluation), a protocol that surfaces these pathologies. Evaluating 14 models, we find that regime-transition reasoning remains near random (MCC = 0.05) even for frontier models, whereas FOL deduction with given premises reaches MCC = 0.52. Per-family decomposition shows that the proprietary-model advantage concentrates on cross-indicator (+0.40) and consistency tasks, while open-source Qwen 2.5-32B dominates indicator diagnostics (0.91 vs. 0.45). Two models exhibit negative MCC on bifurcation questions, confirmed as systematic anti-correlation via confusion-matrix analysis. --- ### ArtSplat: Feed-Forward Articulated 3D Gaussian Splatting from Sparse Multi-State Uncalibrated Views Authors: Inseo Lee, Yoonji Kim, Eugene Sohn, Jiwoong Lee, Jungmin You, Joonseok Lee, Jin-Hwa Kim Published: 2026-05-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.24304v1 Articulated object reconstruction from sparse-view images is an ill-posed problem that requires simultaneous inference of geometry and underlying articulation structure. Existing methods for articulated object reconstruction based on NeRF and 3D Gaussian Splatting (3DGS) typically rely on dense views or strong priors (e.g., depth maps, joint types, predefined number of joints) and require costly per-object optimization. In this paper, we propose ArtSplat, the first feed-forward framework for articulated 3D Gaussian Splatting. It reconstructs both geometry and joint parameters from sparse multi-view images across multiple articulation states in a single forward pass. To address the challenges of single-pass articulated reconstruction, we introduce a per-pixel joint map representation that enables the integration of joint parameter estimation into the feed-forward pipeline. We further propose a Cross-State Attention (CSA) mechanism with state tokens, which effectively captures discrete motion across input states. Experiments on 68 articulated objects from PartNet-Mobility, including both single- and multi-joint configurations, demonstrate that ArtSplat achieves competitive performance in both geometry and joint estimation, while being over 400 times faster than baselines. --- ### Cross-Modal Action Recognition in Egocentric Video Using Mamba: Integrating RGB and Hand Skeleton Streams via CLS Token Fusion Strategies Authors: Juan Ignacio Bustos Gorostegui, Maria Elena Buemi Published: 2026-05-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24302v2 Egocentric action recognition is a challenging task due to erratic camera motion, frequent hand occlusion, and the difficulty of maintaining consistent visual representations over time. In this work, we propose a cross-modal architecture that combines RGB video and temporal hand skeleton data within a unified Mamba-based framework, exploiting the linear time complexity of State Space Models (SSMs). Our architecture consists of three components: a VideoMamba module for visual feature extraction, a skeleton encoder built on a stack of Mamba blocks, and a fusion module that integrates both modalities into a single representation. A central contribution of this work is the design and evaluation of four Class (CLS) token mixing strategies for multimodal fusion: Naive, Average, Weighted and Context-based. These strategies differ in how the pretrained unimodal CLS tokens, which role is to act as information sinks concentrating learned representations, are leveraged to initialize the mixed CLS token used for final classification. We evaluate all strategies on the H2O dataset. Experimental results show that the Average strategy achieves the best performance, yielding gains of over 10% Top-1 accuracy in the Tiny configuration and 2% in the Small configuration over the VideoMamba baseline. --- ### Scaffold-Mediated Post-Training: Co-Evolving Model Parameters and Procedural Scaffold Graphs Authors: Fei Ding, Yongkang Zhang, Runhao Liu, Yuhao Liao, Zijian Zeng, Huiming Yang Published: 2026-05-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.05156v1 Post-training of large language models optimizes only parameters, while inference-time procedural scaffolds are typically designed independently of parameter training. This disconnect makes it difficult to automatically acquire and internalize complex strategies. We propose scaffold-mediated post-training: procedural scaffolds are organized into an evolvable graph structure that co-evolves with model parameters through discovery, distillation, and dynamic recompilation. We instantiate this paradigm as Skill Training. On FeatureBench, automatically discovered skills improve the passed rate by 8.1pp, and after progressive distillation the model still achieves a 27.7% passed rate without any external scaffold (distillation retention rate 85.2%, defined as post-distillation / with-skill passed rate), significantly outperforming standard SFT on the same data. --- ### Beyond Sentiment: Comparing Traditional NLP and LLM-Based Multi-Dimensional Analysis for Political News Evaluation Authors: Maryam Fooladi, Federico Bottino Published: 2026-05-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.05155v1 Traditional sentiment analysis (SA) models, while effective for polarity classification, provide limited insight into the rhetorical, ideological, and framing dimensions of political discourse -- dimensions that are central to research in the social sciences and humanities (SSH). In this paper, we present a comparative study of RoBERTa-based sentiment analysis and an LLM-based multi-dimensional framing analysis platform applied to a corpus of 50 political news articles from 17 international media outlets. The results reveal a critical limitation we term neutral collapse: RoBERTa classifies 70% of articles as neutral, effectively flattening substantively rich political content into an analytically uninformative category. We find that 23% of neutral-classified articles exhibit negative probability scores above 0.30. By contrast, the LLM-based approach captures political bias direction and intensity, sensationalism, emotional appeal, and political framing -- yielding multi-dimensional analytical outputs aligned with SSH epistemologies. We argue that for political media analysis, traditional SA alone is insufficient, and that LLM-based multi-dimensional frameworks offer a more epistemologically adequate computational lens for SSH research needs. --- ### AutoFOAM: The Self-Refining Autonomous OpenFOAM Agent Authors: Arun Govind Neelan, A Seshaditya Published: 2026-05-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.00003v1 Computational Fluid Dynamics (CFD) plays an important role in modern engineering, but using open-source solvers such as OpenFOAM requires considerable knowledge and skills, as well as time-consuming configuration file setup. To reduce this burden, we propose AutoFOAM - a self-evolving large language model (LLM) agent that creates, evaluates, runs, and evolves its own OpenFOAM simulations based solely on natural-language instructions. Our model is pre-trained on the Qwen-coder 2.5-14B, which is then fine-tuned on 252 text prompts targeting 7 OpenFOAM solvers, 13 parametrized mesh templates, and a y plus-aware numerical policy. The crucial element of the algorithm is a sophisticated evolution loop composed of 7 stages. To prevent model degeneration under repeated self-training, the agent employs three complementary anti-collapse streams: RAG-augmented retry context, surgical dictionary-level patching, and prompt-diversity paraphrasing. By bridging generative artificial intelligence with rigorous fluid simulations, AutoFOAM accelerates rapid prototyping and democratizes advanced CFD workflows. --- ### TimeCapsule: Generative Hallucination as a Method for Historical Sensemaking Authors: Hayk Grigorian, Hamed Yaghoobian Published: 2026-05-22 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2607.24750v1 Large Language Models (LLMs) are temporally overexposed: trained on vast contemporary corpora, they encode present-day concepts that make them unreliable narrators of the past. We present TimeCapsule, a 1.2B-parameter LLaMA-style causal model trained exclusively on Victorian texts (1800-1875) as an epistemologically isolated generative archive. Quantitative evaluation shows a 45.4% perplexity reduction over a GPT-2 baseline on held-out Victorian prose, while larger contemporary causal models achieve lower raw perplexity through broader pretraining but lack temporal isolation. TimeCapsule exhibits computational sensemaking, generating historically plausible analogical explanations for unfamiliar modern concepts (e.g., describing a computer as a "hypertrophied lung"). A qualitative hermeneutic probe with two humanities scholars revealed a crisis of authenticity, as both misclassified approximately 40% of genuine Victorian excerpts as machine-produced. We argue that structural ignorance of the future transforms hallucinations into interpretive probes of nineteenth-century ontologies. --- ### Game AI Not Fun? A Scoping Review and Meta-Analysis on the Differences in Enjoyment between Human and Computer Opponents Authors: Ray Ito Published: 2026-05-22 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2607.24749v1 Although advancements in game character AI aim to enhance player engagement, evidence suggests that perceiving an opponent as artificial can diminish the psychological experience. This paper presents a scoping review and meta-analysis of empirical studies focusing on player enjoyment when competing against human versus computer opponents. First, the scoping review was conducted to map the landscape of 20 included studies, detailing their study designs, outcome measures, and research foci. Second, a three-level meta-analysis synthesizing baseline comparisons from nine studies quantitatively assesses the differences in enjoyment. The results demonstrate a statistically significant, medium-to-large pooled effect size, indicating a psychological penalty in computer-opponent conditions. This paper provides a comprehensive overview of the extant knowledge on this topic, and underscores the necessity for further research in order to fully understand and resolve the penalty of the computer opponent context. --- ### A Systematic Survey on Image Description Techniques for STEM Domains Authors: Marco Cardia, Letizia Angileri, Marina Buzzi, Giulio Galesi, Barbara Leporini Published: 2026-05-22 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2607.21611v1 The proliferation of visual data in Science, Technology, Engineering, and Mathematics (STEM) fields presents accessibility barrier for individuals with blindness or visual impairments. While recent advances in Artificial Intelligence (AI) offer new opportunities to generate textual descriptions of STEM images, the research landscape is fragmented and its impact on real users remains limited. This systematic survey examines 20 peer-reviewed studies on AI-based techniques for describing STEM visuals, with a specific focus on accessibility and human-computer interaction. Following the PRISMA methodology and a ROBIS-based risk-of-bias assessment, the review analyzes (i) the types of STEM visuals targeted, (ii) the AI and machine learning architectures employed, (iii) the datasets and evaluation metrics adopted, and (iv) the interaction modalities through which descriptions are delivered. The analysis reveals a shift from static, one-shot alt text toward interactive and multimodal systems that integrate conversational interfaces, keyboard navigation, and audio or haptic feedback. However, critical challenges persist, including factual inaccuracies and hallucinations, the scarcity of accessibility-first datasets co-designed with blind and low-vision users, and a heavy reliance on automatic text-overlap metrics that poorly capture perceived usefulness and trust. The survey concludes by outlining key research directions for HCI, emphasizing user-controlled verbosity, explainable and verifiable AI pipelines, and the integration of accessible description tools into mainstream STEM authoring and learning environments. --- ### PlanE: Meta Planning of Data, Tuning, and Inference for Extractive-based LLMs Authors: Jiacheng Wang, Weiyan Zhang, Guangya Yu Published: 2026-05-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.20470v1 Enhancing the task-specific capabilities of Large Language Models (LLMs) primarily requires substantial instruction-tuning datasets. However, the sheer volume of such data imposes a considerable annotation cost, and a lack of optimization methods for tailoring LLMs to specific tasks. To address the above issues, we propose a \textbf{Plan}ning framework for constructing \textbf{E}xtractive-based LLMs called \textbf{PlanE}, which includes data decomposition, instruction tuning, and prompt inference. Additionally, we introduce a Data-Tuning-Inference (DTI) planner, aimed at selecting the optimal base-LLM and its DTI combinations for specific datasets to improve construction efficiency. The experimental results demonstrate the effectiveness of our PlanE from two views: (1) across different datasets using the same base-LLM, and (2) on the same dataset using different base-LLMs. Furthermore, we validate the generalizability of the proposed DTI planner under different optimization objectives. The codes are publicly available at https://github.com/gugugu-469/PlanE. --- ### Information Discernment in Large Language Models Authors: Joshua Ashkinaze, Laura Kurek, Alina Faisal, Tongyuan Miao, Mariam Joseph, Ceren Budak, Eric Gilbert Published: 2026-05-22 Categories: cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2607.19355v1 LLMs are increasingly used with external knowledge sources like the internet. Do they weigh information appropriately -- updating more for reliable sources (source discernment) and more when claims bring priors closer to the truth (truth discernment)? We formalize this as information discernment and introduce Learn2Discern (L2D), an experimental framework and benchmark grounded in three normative axioms with interpretable metrics. To establish external validity, a pre-registered, quota-matched user study (n=299) confirms that real LLM users endorse all three axioms and report that violations reduce their trust and usage intent. Across 13 models and nearly 670K trials, we find consistent failures across both dimensions: models perform near chance on source and truth discernment, rely on source popularity twice as much as source reliability, and update roughly equally whether a claim improves or worsens their position relative to the ground truth. Models integrate external knowledge most effectively on datasets where their priors are already the most accurate. Newer and larger models improve truth discernment but not source discernment, a blind spot that model complexity does not address. We identify simple inference-time interventions that improve both forms of discernment. We release our dataset and survey as a testbed for a core alignment property that scales in importance as LLMs replace traditional search. --- ### Fence: Specialized SLM Guardrails for LLM Applications Authors: Kumud Lakara, Ruibo Shi, Fran Silavong Published: 2026-05-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.18268v1 Real-world applications that use closed-source large language models (LLMs) need advanced safety measures that go beyond the basic content filters. Content moderation filters such as toxicity and bias have relatively standard definitions where as application specific guardrails like hallucination, topic drift and behaviour deviation are more difficult to model and can vary by use case. Additionally, data scarcity and annotation costs, make the process of creating and testing specialized guardrails challenging. In this work, we propose using Small Language Models (SLMs) trained on synthetic data as specialized guardrails for LLM applications. We introduce a novel synthetic data generation method inspired by the design of Generative Adversarial Networks (GANs) to generate high quality synthetic data samples which can be used to train SLMs to encode use case specific guardrail information and hence function as specialized guardrails. Our experiments demonstrate that SLM guardrails trained on high quality synthetic data show performance gains over prompt based LLM guardrails. --- ### The Economics of Autonomy: Real-Time Risk Indexing for Insurable AI-Driven 6G Systems Authors: Anthony Kiggundu, Michael Zentarra, Christoph Lipps, Hans D. Schotten Published: 2026-05-22 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2607.18267v1 The transition to sixth-generation (6G) networks transforms wireless infrastructure into a cognitive substrate supporting Vehicle-to-Everything (V2X), Industrial IoT (IIoT), and Integrated Sensing and Communication (ISAC). In this paradigm, autonomous agentic AI performs orchestration at millisecond scales, rendering traditional static governance frameworks fundamentally inadequate for risk management. This paper introduces GIRAF(Governance-Integrated Risk and Assurance Framework), a Governance-as-Code (GaC) framework for real-time risk quantification and trust modulation in agentic 6G systems. GIRAF derives a continuous Aggregate Risk Index ($R_{t}$) from machine-readable runtime signals, including epistemic confidence, network jitter, and verification latency. A core contribution is the formalization of the verification staleness trade-off, where safety mechanisms induce risk if computational latency exceeds 6G deadlines. We demonstrate that GIRAF identifies 'Confidence Gaps' discrepancies between agent reported certainty and environmental ground truth, triggering automated safety envelopes when conditions deteriorate. Crucially, GIRAF serves as the foundational governance groundwork and conceptual 'glue' that externalizes these technical risks into machine-readable telemetry. Through simulations with fine-tuned Large Language Models (LLMs), we validate that the framework preserves operational integrity while providing the essential actuarial baseline required for multi-stakeholder liability attribution and dynamic premium quantification in the 6G ecosystem. --- ### What Makes Linguistic Representations Good Models of High-Level Visual Perception in the Human Brain? Authors: Anna Bavaresco, Ina Klarić, Raquel Fernández, Marie-Francine Moens Published: 2026-05-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.16214v1 Image descriptions represented with language models (LMs) predict human brain responses to naturalistic images in high-level visual regions, but the factors driving this predictivity remain unclear. To investigate this, we systematically studied how images are described and which language models are used to embed those descriptions. For a common set of images, we considered six caption types -- including human-annotated and multiple machine-generated captions -- differing along several dimensions. Each caption was represented with five LMs, spanning autoregressive LMs trained to predict upcoming words and text embedders, i.e., LMs fine-tuned on semantic tasks requiring sentence/document-level representations. Machine-generated captions yielded significant brain predictivity and alignment, often surpassing human-annotated captions used in previous work. Across caption types, text embedders consistently outperformed autoregressive LMs, a pattern replicated when measuring behavioural alignment with image-similarity judgments. Analyses of caption representations from different model layers further revealed that both brain predictivity and behavioural alignment peak at intermediate network depth, shortly after a point thought to mark the emergence of syntactic and semantic structure. Altogether, our results demonstrate that both the content of image captions and the LM used to represent them influence brain- and behaviour-modelling performance, establishing caption embeddings as a useful tool for studying high-level visual perception. --- ### Divergent Recommendations, Convergent Diagnoses: Cross-Provider Failure-Mode Convergence in AI Commercial Recommendation Authors: Will Jack, Noah Lehman, Keller Maloney, Sarah Xu Published: 2026-05-22 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.26116v1 A brand whose customers use both ChatGPT and Claude for product recommendations faces a strategic choice: a single optimization playbook, or one per provider? Across 215 commercially-framed prompts in four measurement batches, the two providers disagree on which brands they recommend roughly two-thirds of the time (cross-provider recommendation Jaccard 0.35, below the 0.50-0.61 same-prompt rerun baseline). The picks diverge. But when neither provider recommends a brand, we classify the failure into one of three modes -- discoverability (the brand never reaches the model), compellingness (it reaches the model but isn't mentioned), or positioning (it's mentioned but not recommended) -- and on 7,763 such joint failures, both providers diagnose the same failure mode 95.1% of the time (clustered 95% CI (94.3%, 95.7%)). Agreement rises monotonically with falling brand prominence, from 81% (78.2%, 84.0%) on category leaders to 99.6% (99.3%, 99.9%) on long-tail regional brands. The two providers reach their picks by measurably different generative routes -- Anthropic recommends from priors 43-52% of the time, OpenAI 8-29% -- but they converge on the failure diagnosis where it matters most for the long tail. Work that addresses the diagnosed failure mode lifts visibility on both providers; positioning - and content-level work for category leaders is more provider-specific. --- ### A Multi-Layer AI Framework for Information Landscape Analysis Authors: Maryam Fooladi, Federico Bottino Published: 2026-05-22 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.26115v1 This paper proposes a multi-layer AI framework for information landscape analysis in the context of information disorder. Rather than treating misinformation detection as a binary fact-checking task, the framework analyzes political and media content across multiple dimensions, including source reliability, factual structure, framing, bias, emotional activation, manipulation patterns, and propagation dynamics. The goal is to move beyond isolated claim verification toward a structured representation of the informational environment surrounding an event, entity, or narrative. We argue that AI systems for media analysis should support epistemic mapping: a transparent, multi-dimensional account of how facts, interpretations, actors, and narratives interact over time. The paper presents the conceptual architecture, analytical layers, and methodological rationale of the framework, with the aim of supporting more nuanced, explainable, and critically useful tools for information disorder research. --- ### Estimating Learners' Skill Acquisition Without Temporal Information Authors: Ryosuke Nagai, Kyohei Atarashi, Koh Takeuchi, Jill-Jênn Vie, Hisashi Kashima Published: 2026-05-22 Categories: cs.CY, cs.LG arXiv: https://arxiv.org/abs/2606.20611v1 Recent research in educational data mining, especially knowledge tracing, has focused on predicting learners' future knowledge states to support adaptive instruction. However, in many real-world educational settings, learning data are often available only as single-time-point assessments without temporal information, making existing time-series-based approaches difficult to apply. In this paper, we propose a novel framework for predicting future skill acquisition using only snapshot data. Specifically, we address the problem of predicting the next skill to be acquired from skill mastery patterns estimated by cognitive diagnostic models (CDMs). In the absence of temporal information, we exploit inclusion relations among learners' skill sets to induce a pseudo-temporal ordering, interpreting expanding skill sets as a proxy for learning progression. To efficiently approximate unobserved acquisition paths, we introduce a neural model that captures latent skill acquisition dynamics through expected skill increments. Experiments on both synthetic and real-world datasets demonstrate that the proposed method consistently outperforms baseline approaches, with particularly strong advantages as the skill space becomes larger. These results indicate that meaningful skill acquisition patterns can be inferred from snapshot data alone, providing a practical framework for adaptive learning support in data-constrained educational environments. --- ### Signals in the Noise: Open Source Intelligence (OSINT) for AI Loss of Control Detection Authors: Sarah Bollinger, Nada Aboserie, Amanda Coakley, Chih-Hsuan Lee, Taysir Mathlouthi Published: 2026-05-22 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.20610v1 This paper applies open-source intelligence (OSINT) and cyber threat intelligence (CTI) methodologies to the problem of detecting AI systems operating outside human control. Drawing on a cross-disciplinary literature review and 14 semi-structured expert interviews conducted under Chatham House Rule, the paper develops two threat models, identifies a range of observable traces, and proposes an institutional architecture for monitoring. The research finds that OSINT-based detection of loss of control is partially feasible and worth building now. Three detection vectors emerge as highest priority: transcript-based collection of user-reported AI behaviour; infrastructure correlation for unexpected external connections or replication; and output analysis for capability concealment. The paper argues for a dedicated, federated international monitoring capability anchored in OSINT methods and independent of frontier AI developers, and identifies sustained non-industry funding as the highest-leverage structural intervention available. --- ### Understanding Privacy by Formalizing It Authors: Réka Markovich, Truls Pedersen, Marija Slavkovik Published: 2026-05-22 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.20609v1 In most of the modern societies, there is a broad consensus regarding the need for promoting privacy and thus placing restrictions on technological-including AI-developments to protect people's right to privacy. In order to meet these expectations on the algorithmic level, first we need to make the concept of privacy and the related or derived rights formally specified. However, the notion of (the right to) privacy is subject to different interpretations. In this paper, we use a multi-modal logic to provide an initial formalization of different theories, basic principles and their implications investigating the right to privacy as an epistemic right within the theory of normative positions. --- ### CourseBlueprint: A Structured Pipeline for Adaptive Pedagogical Video Generation Grounded in Course Corpora Authors: Md Zabirul Islam, Md Motaleb Hossen Manik, Ge Wang Published: 2026-05-22 Categories: cs.CY, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2606.20608v1 Generative text-to-video systems can produce visually fluent educational clips, but they rarely encode the pedagogical content knowledge (PCK) needed for effective instruction, including prerequisite-aware sequencing, learner-adaptive depth, and sustained cognitive engagement. We present CourseBlueprint, a course-grounded pipeline for adaptive pedagogical video generation. Given a topic and learner persona, the system generates a structured teaching blueprint in a single forward pass over an undergraduate biomedical-imaging corpus (BMED 2300; twenty-three lectures, 1,116 slides). Instead of ad-hoc prompt chaining, the pipeline uses typed intermediate representations with validation: a scaffolding module builds a stage-labeled prerequisite concept graph with deterministic cycle removal, an adaptive controller assigns per-concept style specifications, and an engagement generator produces narration following a fixed hook->retrieval->core->analogy->forward contract. A deterministic slide-image override further grounds the rendered video by reusing instructor slides whenever retrieval confidence is high. We also release a reusable benchmark corpus and an evaluation harness combining repeated LLM-judge scoring with regex-grounded objective metrics. In a five-topic ablation, removing the engagement contract reduces the engagement score from 5.00 to 1.20, the adaptive score from 4.80 to 3.40, Flesch readability from 38.0 to 19.8, and analogy and retrieval-prompt counts to near zero. The slide-image override converts a 0/9 corpus-grounding failure into 9/10 successful slide matches on the same topic. These results show that pedagogical video quality depends less on surface fluency than on explicit, typed instructional contracts that make scaffolding, adaptation, engagement, and grounding auditable. --- ### Synthetic Resonance: A Framework for Growth-Oriented Human-AI Relationships Authors: Richard A. Fabes Published: 2026-05-22 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2606.18265v2 As human relationships with artificial intelligence systems become increasingly frequent and sustained, existing language and theory fail to accurately capture the nature of these affiliations. Common descriptors such as mutual understanding, connection, or friendship risk anthropomorphizing systems that lack subjective experience, while dominant frameworks tend to reduce AI to either a tool or a threat. In this paper, I introduce the concept of synthetic resonance as an integrative framework for understanding human-AI relationships. Synthetic resonance describes how relationships humans define as meaningful can emerge between a human and an AI system without the need to attribute shared feelings or mutual awareness. I argue that synthetic resonance is best understood as a structured, dynamic pattern of interaction that can produce a sense of relationship without the presence of a second experiencing subject. By clarifying this distinction, the concept of synthetic resonance offers a more precise way of conceptualizing human-AI relationships and highlights their potential value and ethical implications. I also call for more research that tests the processes and outcomes of synthetic resonance. --- ### Limited Marginal Benefit of Reasoning-Heavy LLM Deployment in ESG Narrative Scoring: A 4-Model Consensus Study on Japanese Listed Firms Authors: Hiroyuki Kokubu Published: 2026-05-22 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.13693v1 Automated scoring of ESG narrative disclosures with large language models (LLMs) is gaining traction, yet whether reasoning-heavy frontier models add value commensurate with their cost remains empirically unsettled. We evaluate this question on a corpus of ten Japanese listed firms across three rubric axes -- quantitative targets, progress-tracking infrastructure, and external-standard alignment -- using a four-model consensus design that combines a reasoning-on frontier model with three reasoning-off contemporaries. Across 120 firm x axis x model scores, the pooled mean absolute deviation between the reasoning-on model and each reasoning-off counterpart is 0.38 on a 5-point scale; only 2% of pairwise comparisons reach a two-point deviation, and none exceeds two points. Per-firm cost accounting shows the reasoning-on arm alone costs roughly 5.6x as much as the three-provider reasoning-off ensemble, for outcomes that differ only within small margins. We conclude that in span-based ESG narrative scoring, reasoning-heavy deployment does not materially improve outcomes relative to reasoning-off consensus, while substantially increasing operational cost. We discuss implications for cost-effective ESG auto-scoring pipelines and LLM deployment governance in applied accountability settings. An earlier version of this work is available on SSRN (Abstract ID 6683303). --- ### Symbolic Reasoning Frameworks Trigger Memory-Mediated Ecosystem Dynamics in Multi-Agent LLM Systems Authors: Augustin Chan Published: 2026-05-22 Categories: cs.MA, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.07552v2 Large language models exhibit a risk-averse "turtle" bias as strategic agents. We show that injecting a symbolic reasoning framework as a per-round reflective prompt into one agent acts as a small perturbation whose consequences are not per-decision but emergent: the agent's risk posture is unchanged in isolation, yet over a campaign of accumulating memory and multi-agent interaction the conditions settle into distinct, condition-associated winner ecosystems. In a 7-player Warring States Diplomacy variant (61 games, 6 conditions), the winner distribution differs sharply across the four primary conditions (41 games; permutation omnibus p approximately 0.001): control -> Yan (7/11); I-Ching yarrow -> Yan/Chu co-dominance with Qin fully suppressed (0/10); Tarot -> Qin (5/10); scrambled-text ablation -> Qi (5/10). The scrambled->Qi attractor is robust (vs. pooled and control alone, p = 0.006 and 0.012); tarot->Qin is denominator-dependent (0.006 pooled, 0.064 vs. control). Han never wins and shows no survival difference (Fisher p = 1.0); neither framework's content predicts actions (chi-squared p = 0.95 hexagram, 0.69 Tarot). A memory-free decision-isolation probe (960 calls) shows the process does not change the agent's risk posture in isolation (Friedman p = 0.45; I-Ching p = 0.60; Tarot perturbs move content but not risk, p = 0.021). A 2x2 factorial separating yarrow's decision-time and learning-time components reveals a non-additive interaction: each alone freezes the board (50-60% stalemates), combined they produce zero (permutation p ~ 5e-5). Testing relocates Qin suppression to rival (Chu) expansion governed by campaign memory depth, not the oracle (p = 0.55). We present this as an observation paper: agent-level framework choice produces distinctive, non-additive system-level consequences, transmitted through emergent memory and multi-agent dynamics, not per-decision effects. --- ### Multi-Fidelity Learning with Shallow Recurrent Decoders for Multi-Physics Applications Authors: Stefano Riva, Carolina Introini, J. Nathan Kutz, Antonio Cammi Published: 2026-05-22 Categories: physics.comp-ph, cs.LG arXiv: https://arxiv.org/abs/2606.05202v2 In reactor physics, neutronics and multi-physics phenomena can be modelled at different fidelity levels. High-fidelity models based on the Boltzmann transport equation, multi-group diffusion, or computational fluid dynamics are computationally demanding, whereas simplified models, such as zero-dimensional lumped formulations, can be evaluated efficiently at the cost of neglecting spatial details. The computational intractability of detailed models translates into a scarcity of high-fidelity data and an abundance of low-fidelity data, motivating the development of multi-fidelity (MF) learning strategies able to map between the two. This work extends Shallow Recurrent Decoders (SHRED), a machine learning architecture that reconstructs high-dimensional fields from time-series measurements, to multi-fidelity reduced-order modelling, in which the input trajectories are provided by a low-fidelity model. The resulting MF-SHRED is assessed on three benchmark problems: (i) a two-group point-kinetics-to-diffusion; (ii) a non-linear reaction-advection-diffusion system of six chemical species; and (iii) the coupled neutronics-thermal-hydraulics multi-physics model of the Molten Salt Fast Reactor (MSFR). Across all three cases, MF-SHRED reconstructs the high-fidelity fields with relative errors below a few percent, closely approaching the truncation error of the underlying proper orthogonal decomposition, while reducing the computational cost by three orders of magnitude relative to the corresponding high-fidelity solver. MF-SHRED performs comparably to the original sparse-sensor SHRED formulation. These results support the use of MF-SHRED as a non-intrusive reduced-order modelling strategy for reactor physics and multi-physics applications, particularly for design and safety analysis tasks that must be carried out before a facility is even built. --- ### State commitment learning: training language models to distinguish computation from memory Authors: Fei Ding, Yongkang Zhang, Runhao Liu, Yuhao Liao, Zijian Zeng, Huiming Yang Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.05201v1 Reasoning language models do not distinguish tokens used for computation from tokens that constitute persistent state: once generated, all hidden thoughts remain in context and influence future predictions. As a result, downstream reasoning may depend on failed attempts, dead ends, and private scratch work that should not be safely relied on later. We recast this phenomenon as a new training objective, state commitment learning: training models to explicitly distinguish information that should be committed as persistent state from temporary computation that can be discarded. We define a counterfactual criterion, persistent-state sufficiency, which makes it trainable and measurable whether an answer remains usable after hidden thoughts are erased. We then propose Counterfactual Erasure RL (CERL), which evaluates, under the same prefix, both a path that keeps hidden thoughts and a path that erases them, and gives reward only when the erasure path remains correct. We also introduce the Erasure Dependence Protocol and show across mathematics, long-chain logic, scientific QA, and multi-turn tool-use evaluation that CERL substantially reduces answer dependence on hidden thoughts without sacrificing accuracy, consistently outperforming correctness-only RL and long-answer SFT baselines. --- ### A differentiable machine learning small-angle X-ray scattering analysis framework for structure elucidation of lipid nanoparticles Authors: Maria Bånkestad, Sandra Barman, Magnus Röding, Erik Kaunisto, Viktoriia Meklesh, Audrey Gallud, Marco Mendez, Marianna Yanez Arteta, Stefan Norberg, Ann Terry, Smita Chakraborty, Shun Yu et al. Published: 2026-05-22 Categories: physics.comp-ph, cs.LG arXiv: https://arxiv.org/abs/2606.05200v1 Lipid nanoparticles (LNPs) are efficient delivery systems for negatively charged nucleic acids. Their multi-component architecture yields a core-shell structure. Small-angle X-ray scattering (SAXS) is an important characterization technique for LNPs, but recovering internal structure and size distribution from SAXS is an inverse problem with non-unique solutions. Realistic models are often too expensive for systematic exploration. We introduce a machine-learning-accelerated, differentiable framework for SAXS analysis of heterogeneous, polydisperse LNPs. The forward model combines a core-shell particle with a Gaussian random-field interior, a neural surrogate for the monodisperse SAXS map, and a differentiable layer integrating over particle-size distributions. The surrogate reduces prediction cost by four orders of magnitude, while differentiability enables large-scale multi-start fitting and ensemble identifiability analysis. Applied to synthetic and experimental MC3 LNP data, the framework shows that near-identical SAXS fits can arise from distinct parameter modes, with the experimental fits dominated by a trade-off between size-distribution and interior-structure parameters. --- ### Finite Element-Based Material Learning via Automatic Differentiation: Learning constitutive neural network models from full-field deformation data Authors: Matthias Knipper, Chenyi Ji, Malte Brand, Kevin Linka Published: 2026-05-22 Categories: physics.comp-ph, cs.AI arXiv: https://arxiv.org/abs/2606.05199v1 The identification of constitutive neural network models from heterogeneous full-field deformation data provides a robust alternative to traditional calibration methods based on homogeneous stress-strain experiments, particularly given the high dimensionality of trainable parameters. Existing approaches must balance generality, robustness, and computational efficiency: Conventional finite element model updating is broadly applicable but computationally demanding; weak-form methods offer efficiency but are sensitive to noise and data scarcity; neural operator models are highly expressive but require extensive training datasets. This work presents FE-MAD (Finite Element-Based Material learning via Automatic Differentiation), an end-to-end differentiable framework that integrates a constitutive neural network model within a JAX-FEM nonlinear solver and identifies its parameters through gradient-based minimization of a measurement-mismatch loss. Newton tangent stiffness and loss gradients are computed automatically using forward- and reverse-mode automatic differentiation throughout the entire pipeline, thereby removing the need for analytic adjoints or offline surrogate models. FE-MAD is demonstrated for two architectures: a grey-box Constitutive Artificial Neural Network (CANN), a polyconvex, fully connected model with high flexibility, and a white-box CANN, an expert-system network with phenomenologically interpretable strain-energy terms. Focusing on incompressible isotropic hyperelasticity, FE-MAD is evaluated on three open experimental datasets: (1) full digital image correlation (DIC) of a perforated tensile specimen, (2) a reduced-data scenario with a one-dimensional stretch profile and global force-displacement curve, and (3) a heterogeneous matrix-inclusion system in which both phases constitutive laws are identified and generalized to twenty-two previously unseen samples. --- ### An accurate nucleic acid-small molecule docking framework via geometric deep learning with large-scale pretraining Authors: Shi Li, Xujun Zhang, Mingquan Liu, Hui Zhang, Shuoying Jia, Yu Kang, Tingjun Hou, Peichen Pan Published: 2026-05-22 Categories: q-bio.BM, cs.LG arXiv: https://arxiv.org/abs/2606.05198v1 Nucleic acids are increasingly recognized as therapeutic targets beyond conventional protein-centered drug discovery, yet accurate and efficient docking of small molecules to nucleic acid structures remains challenging. Physics-based docking methods often show limited accuracy and efficiency, whereas deep learning approaches are constrained by the scarcity of experimentally resolved nucleic acid-ligand complexes. Here, we present NucleoDock, a deep learning framework for nucleic acid-small molecule docking. To address data scarcity, NucleoDock combines physics-guided large-scale pretraining on millions of docking-generated synthetic complexes with fine-tuning on curated experimental co-crystal structures. It further integrates sequence- and structure-informed nucleotide representations with atomistic three-dimensional features to capture both biological context and binding-site geometry. A mixture density network-based geometric scoring head is used to model conditional interaction-distance distributions for pose ranking. On an external benchmark of 125 nucleic acid-ligand complexes, NucleoDock achieved a top-1 success rate of 56 percent at an RMSD cutoff of 2.0 Angstrom, outperforming rDock with 29 percent, while generating 100 poses in approximately 5 seconds per complex. Retrospective virtual screening on the ROBIN benchmark further showed improved early enrichment. NucleoDock represents a step toward bridging the methodological gap between protein- and nucleic acid-directed computational drug discovery. --- ### TGSD: Topology-Guided State-Space Diffusion Framework for EEG Spatial Super-Resolution Authors: Zijian Kang, Weiming Zeng, Yueyang Li, Shengyu Gong, Hongjie Yan, Wai Ting Siok, Nizhuan Wang Published: 2026-05-22 Categories: eess.SP, cs.CV arXiv: https://arxiv.org/abs/2606.03998v2 Low-density EEG is more suitable for wearable and IoT-based brain sensing, but sparse electrode sampling often lacks sufficient spatial information to characterize cross-regional neural activity. EEG spatial super-resolution aims to recover dense-channel EEG from sparse recordings, yet remains challenging because channel missingness typically occurs at the whole-channel level, spatiotemporal dependencies over the full electrode layout are often underexplored, and the mapping from sparse to dense signals is inherently ambiguous. To address these issues, we propose TGSD, a topology-guided state-space diffusion framework for EEG spatial super-resolution. TGSD first employs a Hierarchical Spatial Prior Encoder to learn topology-aware priors over the complete electrode layout by integrating local geometric relationships with region-level contextual information. Based on these priors and sparse observations, a Conditional State-Space Diffusion Reconstructor progressively generates missing-channel signals through reverse diffusion, while alternating temporal and channel-wise state-space modeling captures long-range temporal dynamics and inter-channel dependencies in a unified framework. Experiments on the SEED and PhysioNet MM/I datasets show that TGSD consistently outperforms representative baselines under different super-resolution factors in both reconstruction fidelity and downstream classification performance. These results demonstrate the effectiveness of combining topology-aware spatial priors with conditional diffusion for enhancing practical low-density EEG sensing in wearable and IoT scenarios. The official implementation code is available at https://github.com/jtggz/TGSD. --- ### Making Brain-Computer Interfaces More Secure Authors: Md Fahimul Kabir Chowdhury, Gahangir Hossain Published: 2026-05-22 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2606.02597v1 The development of brain-computer interfaces (BCIs) based on electroencephalograms (EEGs) has advanced significantly mainly to machine learning. Although the majority of earlier research has been on increasing classification accuracy, relatively little focus has been placed on security and robustness. According to recent research, EEG-based BCIs are susceptible to adversarial attacks, which can cause misdiagnosis due to minute, well-crafted disturbances. Evaluating model robustness against such perturbations is therefore critical for ensuring reliable deployment. In this study, we propose a lightweight custom Convolutional Neural Network (CNN) architecture to investigate adversarial robustness in EEG-based BCIs. The suggested method is assessed using two EEG datasets and contrasted with three novel CNN models tailored to EEG, namely EEGNet, DeepConvNet, and SleepEEGNet, under gradient-based adversarial attack scenarios. According to experimental findings, the suggested model continuously performs better in classification under adversarial perturbations compared to baseline models, indicating improved robustness. These findings highlight the potential of lightweight architectures for enhancing the reliability of EEG-based BCI systems under adversarial conditions. --- ### Spectral Asymptotics of Neural Network Loss Landscapes: An Exact Decomposition of the Curvature Exponent Authors: Anherutowa Calvo Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.02596v1 The curvature exponent $α$ in $h_k \propto σ_k^α$ -- governing how Hessian eigenvalues scale with gradient singular values -- varies systematically across layer types ($α\approx 2$ for convolutions, $\approx 1$ for transformer attention, $< 1$ for MLP up-projections). Why? We prove the Spectral Alignment Decomposition: $α= 2 + d\logΦ_k / d\logσ_k$, where $Φ_k$ measures alignment between Kronecker factor eigenbases and gradient singular directions. This reduces "why does $α$ vary?" to a geometric question we answer for LayerNorm, residual connections, and softmax heads. The decomposition implies a spectral transfer identity $s = αγ$ linking curvature exponent, effective gradient rank-decay $γ$, and Hessian decay exponent $s$. The identity is algebraic; its empirical content is that $α$ and $γ$, fit on independent data (HVPs vs. SVD), recover $s$ to ~2% median error across 93 layers, five architectures, and three datasets -- with no free parameters. A zeta-function bound on participation ratio shows curvature concentrates onto effectively one direction per layer. As a proof of concept, we derive the architecture-adaptive preconditioner $T(σ;α)$ and show that Spectral Newton -- implementing $T$ in the gradient singular basis -- outperforms AdamW on vision benchmarks where $α\approx 2$. --- ### Human-in-the-Loop Contextual Bandits for Short-Term Rental Dynamic Pricing: Structural Equivalence of Historical Warm-Up and Approval-Gated Live Learning Authors: Oleg Miroshnichenko Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.02595v1 Dynamic pricing in short-term rental (STR) markets presents a distinctive challenge for online learning algorithms: pricing decisions carry significant financial risk, operators require explainability, and market feedback is sparse (one booking outcome per listed night). We introduce the Human-in-the-Loop Gated Bandit (HITL-GB) framework, in which a contextual bandit algorithm generates price recommendations but a human agent retains authority to accept, modify, or reject each recommendation before it is applied. We show that under this approval constraint, historical pricing data -- collected under a prior deterministic policy -- is structurally equivalent to on-policy warm-up data for initialising the bandit's posterior, bypassing the weeks-to-months cold-start period that renders pure online bandit learning impractical in sparse-feedback markets. We formalise the approval-gated reward signal, derive a regularised ridge-regression warm-up procedure from historical episodes, and validate the approach on real STR production data (anonymised urban market, 2 rooms, April 2022 -- April 2026, 1,461 nightly pricing episodes). Our warm-up procedure compresses effective cold-start from ~150 episodes to ~30 episodes when initialising agents from the Hierarchical Factored Thompson Sampling (HF-TS) family. We further argue that the structural equivalence result is domain-agnostic: any high-stakes domain where human approval is legally or operationally required -- including clinical drug dosing, credit origination, content moderation, and radiological diagnosis -- satisfies the same conditions and benefits from the same warm-up strategy. In regulated industries, mandatory human oversight is thus a statistical asset rather than a deployment constraint. --- ### SentimentLens: Reconciling Sentiment and Ratings via Dual-Modality in the Hospitality Sector Authors: Dineth Jayakody, Pasindu Thenahandi, Sampath Jayarathna Published: 2026-05-22 Categories: cs.IR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.00084v1 Online travel platforms generate vast volumes of user-generated hotel reviews, offering rich opportunities to understand traveler experiences at scale. However, transforming unstructured textual feedback into structured, actionable insights remains a challenging task. This paper presents SentimentLens, a scalable analysis system based on Aspect-Based Sentiment Analysis that performs knowledge extraction from unstructured hotel reviews and organizes them into interpretable service categories. SentimentLens integrates aspect term extraction, aspect sentiment classification, semantic category assignment, and multi-level analytical modules to support region-level, hotel-level, and category-level evaluation. The system is designed to operate across different geographic contexts and hospitality settings. To demonstrate its practical utility, we apply SentimentLens to a large real-world dataset of over 10,000 publicly available hotel reviews. Through extensive analysis, the framework reveals how traveler sentiment varies across regions, service categories, and hotel archetypes. We further implement a cross-modal reconciliation of textual sentiment and numerical ratings to identify latent operational conflicts, structural inconsistencies in service quality, and high-impact improvement opportunities using importance--performance and entropy-based analyses. The results show that SentimentLens effectively transforms large-scale unstructured reviews into actionable intelligence, supporting data-driven decision-making for hospitality management and tourism policy. While demonstrated using a national case study, the proposed system is generalizable to other destinations and review-driven service domains. --- ### From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models Authors: Christian Gumbsch, Leonardo Barcellona, Lennard Schünemann, Platon Karageorgis, Andrii Zadaianchuk, Zehao Wang, Sergey Zakharov, Fabien Despinoy, Rahaf Aljundi, Efstratios Gavves Published: 2026-05-22 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2606.00083v1 Reinforcement learning relies on accurate reward functions, which are often hand-crafted or even unavailable in real-world applications, such as robotics. Recent work has explored the zero-shot reasoning capabilities of pre-trained Vision-Language Models (VLMs) as reward models. However, without careful prompt engineering, these approaches tend to produce suboptimal rewards, where false positive predictions can severely degrade downstream policy learning. In robotics, limited datasets comprising expert demonstrations are often collected to bootstrap policy learning. This scenario provides an opportunity to optimize a reward model prior policy training. We propose Demo2Reward a test-time adaptation technique to optimize the language instruction of a reward model based on a few demonstrations (3-10 trajectories) to reduce false positives while preserving true positives. Crucially, this requires no additional model training or computation resources during policy learning. We show that Demo2Reward consistently outperforms existing zero- and few-shot VLM reward models across a range of simulated robotic tasks and policy backbones. Finally, we demonstrate that Demo2Reward effectively transfers to a real-world robotic learning scenario, enabling policy learning without manually engineering a reward function. --- ### Hoeffding Concept Bottleneck Models with Applications to Overhead Images Authors: Clément Bénard, Manon Arfib, Christophe Labreuche, Victor Quétu Published: 2026-05-22 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2606.00082v1 Explainability of deep learning algorithms is critical for computer-vision applications with high-stake decisions. Concept bottleneck models (CBM) have recently shown promising performance to provide explainable and accurate predictions for classification problems, based on a bottleneck of high-level concepts. Existing CBM methods rely on a linear aggregation of the concept scores to compute predictions. However, a large number of concepts is often used in this linear approach, which undermines explainability and favors information leakage. In general, the underlying relation between concepts and output logits is not linear. Therefore, we introduce Hoeffding Concept Bottleneck Models (HCBM), which build on the Hoeffding functional decomposition of gradient-boosted trees to provide non-linear and sparse aggregations of concept scores, and generate compact predictions using prime implicants. HCBM are proved to be robust to interconcept leakage, and outperform standard linear CBM in practice, as shown in extensive experiments. Beyond classification, HCBM can be adapted to object detection, and we focus on a challenging case with overhead images to show the high performance of HCBM in these settings. --- ### DAStatFormer: A Hybrid Multibranch Transformer with Statistical Feature Integration for DAS-Based Pattern Recognitions Authors: Michel Dione, Jerry Lonlac, Hélène Louis, Anthony Fleury, Stephane Lecoeuche Published: 2026-05-22 Categories: cs.LG, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2606.00081v1 Distributed Acoustic Sensing (DAS) enables large-scale monitoring through optical fibers, but its high dimensionality and complex spatio-temporal patterns make event classification demanding. Existing deep learning approaches-CNNs, recurrent models, and Transformer variants-either fail to capture long-range dependencies or require processing raw DAS matrices at prohibitive cost. We propose DAStatFormer, a hybrid multibranch Transformer that combines compact multidomain statistical features with Gated Transformer Networks. Instead of raw signals, we extract 24 ANOVA-selected attributes per channel from the temporal, waveform, and spectral domains, reducing data size by orders of magnitude while preserving discriminative information. Each domain is processed via dedicated step-wise and channel-wise attention branches, fused by an adaptive gating mechanism. Experiments on the open $Φ$-OTDR benchmark and a real-scenario DAS dataset show that DAS-tatFormer achieves up to 99.4% accuracy and near-perfect real-world performance, while using significantly fewer parameters and lower inference cost than models such as DASFormer and DeepViT. These results demonstrate its suitability for scalable, real-time DAS-based monitoring. We release our code at https://github.com/MichelD-git/DAStatFormer --- ### Planktonzilla: Multimodal dataset and models for understanding plankton ecosystems Authors: Alan Gerson Contreras Montanares, Luis Valenzuela, Luis Martí, Nayat Sanchez-Pi Published: 2026-05-22 Categories: cs.CV, cs.AI, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2606.00080v1 Marine plankton underpin aquatic food webs and play a key role in global CO2 sequestration, making reliable species identification critical for understanding ocean health and climate feedbacks. Existing classification models perform well on individual collections but fail to generalize across instruments and environments due to isolated training datasets and inconsistent labels. To address this, we introduce Planktonzilla-17M, a unified dataset consolidating publicly available plankton image collections spanning thirteen imaging systems. It comprises 17.4 million images with standardized taxonomy and geo-environmental metadata, including 3.74 million plankton images spanning over 602 taxonomic classes, of which 201 are identified at the species level, making it the largest and most comprehensive plankton image dataset to date. Using this large-scale dataset, we perform a controlled comparison between supervised and CLIP-style image--text training on a shared ViT backbone. We find that a supervised classifier matches or exceeds CLIP-style training when trained using taxonomic lineage as text. We further observe that BioCLIP and BioCLIP2 perform poorly on plankton in zero-shot and few-shot settings. Leveraging Planktonzilla-17M improves plankton classification performance, highlighting the limitations of current biological foundation models in marine imaging domains. --- ### BitsMoE: Cost-Aware Bit Allocation in Spectral Space for MoE LLM Quantization Authors: Jiayu Zhao, Zihan Teng, Minhao Fan, Tianrui Ma, Wentao Ren, Song Chen, Weichen Liu Published: 2026-05-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.00079v2 Mixture-of-Experts (MoE) large language models incur substantial memory costs due to their large expert parameter counts. Mixed-precision quantization reduces these costs by allocating different bit-widths to experts or linear blocks according to their importance. However, assigning a single precision within each expert or linear block overlooks its internal structural heterogeneity. This limitation motivates two key questions: (1) how to define a fine-grained unit for quantization within a linear transformation; and (2) how to characterize the quantization cost of each unit under actual activation patterns and different bit-widths. To address these two questions, we propose BitsMoE, a cost-aware mixed-precision quantization framework built on two complementary techniques: (1) Shared-basis Spectral Decomposition (SSD) separates expert weights into a shared basis and expert-specific spectral components, defining structural quantization units while exploiting cross-expert redundancy. (2) Factorized Quantization Cost Modeling (FQCM) estimates component-wise costs from output reconstruction loss by combining intrinsic spectral importance, activation-dependent importance, and bit-width-dependent distortion. Using these component-wise costs, we formulate bit allocation as an integer linear program (ILP) that minimizes total modeled quantization cost under a fixed memory budget. On Qwen3-30B-A3B at 2-bit, BitsMoE achieves 64.29% average accuracy over seven downstream tasks, outperforming the evaluated MoE-specific methods, including those using ILP-based bit allocation, and exceeding GEMQ by 2.80 percentage points. Under the same setting, it achieves a $16.47\times$ end-to-end offline quantization speedup over GEMQ. It also achieves up to $6.46\times$ the decode throughput of GPTQ. --- ### BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization Authors: Jiayu Zhao, Zihan Teng, Minhao Fan, Tianrui Ma, Wentao Ren, Song Chen, Weichen Liu Published: 2026-05-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.00079v1 Mixture-of-Experts (MoE) large language models reduce per-token computation through sparse expert activation, but their deployment remains memory-intensive because all expert weights must be kept resident in memory. Existing MoE compression methods struggle in the ultra-low-bit regime: pruning irreversibly removes model capacity, while coarse-grained quantization fails to allocate bits according to heterogeneous expert and weight-direction importance. We propose BitsMoE, a spectral-energy-guided bit-allocation framework for MoE LLM quantization. BitsMoE decomposes each MoE layer by SVD into a shared basis and expert-specific spectral factors, retaining the shared basis without quantization to preserve common cross-expert structure and using the expert-specific factors as fine-grained quantization units. To determine the bit-width of each unit, BitsMoE formulates spectrum-wise mixed-precision quantization as an activation-aware reconstruction surrogate and solves an integer linear program that minimizes estimated reconstruction loss under a fixed bit budget. Experiments across multiple MoE LLMs show that BitsMoE substantially reduces downstream task accuracy degradation in ultra-low-bit regimes. Under 2-bit quantization on Qwen3-30B-A3B-Base, BitsMoE accelerates quantization by 12.3$\times$, improves average accuracy by 27.83 percentage points, and increases decoding speed by 1.76$\times$ over GPTQ. Our model and code are publicly available at https://github.com/zjiayu064/BitsMoE. --- ### Flow-Based Generative Modeling for Optimizing Sampling Policies in Compressed Sensing Applications Authors: Roman Pavelkin, Luis A. Zavala-Mondragon, Christiaan G. A. Viviers, Fons van der Sommen Published: 2026-05-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.00078v2 Numerous modern applications in signal processing and medical imaging necessitate acquiring high-dimensional signals under tight resource constraints. Traditional sampling theory suggests that accurate signal reconstruction requires a number of measurements proportional to the signal's ambient dimension, a requirement often too expensive or impractical. Compressed sensing challenges this notion by demonstrating that sparse signals can be recovered with fewer measurements, provided the measurement operator meets certain conditions. This proof-of-concept study presents a task-aware flow-based generative framework -- a reformulation of the conventional Flow Matching training paradigm with a flow model trained to optimize subsampling in compressed sensing applications. We establish the fundamental feasibility of the proposed framework of learning subsampling masks that substantially enhance the performance of compressed sensing for image classification, image reconstruction, and MRI acceleration. For the image reconstruction task, our method demonstrated state-of-the-art performance, achieving Peak Signal-to-Noise Ratio of 25.17 dB at the subsampling rate of 5\% on the CelebA dataset and 29.24 dB when reconstructing $8\times$ accelerated MRI measurements (fastMRI dataset) with the minimal computational overhead. These results highlight the effectiveness of task-conditioning within generative flow models and reveal a promising direction for representation learning strategies. Overall, the proposed framework offers a unified, flexible approach to designing data- and task-driven sensing schemes that can be potentially adapted to a broad range of inverse problems. --- ### Flow-Based Generative Modeling for Optimizing Sampling Policies in Compressed Sensing Applications Authors: Roman Pavelkin, Luis A. Zavala-Mondragon, Christiaan G. A. Viviers, Fons van der Sommen Published: 2026-05-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.00078v1 Numerous modern applications in signal processing and medical imaging necessitate acquiring high-dimensional signals under tight resource constraints. Traditional sampling theory suggests that accurate signal reconstruction requires a number of measurements proportional to the signal's ambient dimension, a requirement often too expensive or impractical. Compressed sensing challenges this notion by demonstrating that sparse signals can be recovered with fewer measurements, provided the measurement operator meets certain conditions. This proof-of-concept study presents a task-aware flow-based generative framework -- a reformulation of the conventional Flow Matching training paradigm with a flow model trained to optimize subsampling in compressed sensing applications. We establish the fundamental feasibility of the proposed framework of learning subsampling masks that substantially enhance the performance of compressed sensing for image classification, image reconstruction, and MRI acceleration. For the image reconstruction task, our method demonstrated state-of-the-art performance, achieving Peak Signal-to-Noise Ratio of 25.17 dB at the subsampling rate of 5\% on the CelebA dataset and 29.24 dB when reconstructing $8\times$ accelerated MRI measurements (fastMRI dataset) with the minimal computational overhead. These results highlight the effectiveness of task-conditioning within generative flow models and reveal a promising direction for representation learning strategies. Overall, the proposed framework offers a unified, flexible approach to designing data- and task-driven sensing schemes that can be potentially adapted to a broad range of inverse problems. --- ### Improved Belief-Attention in Vision Task Authors: Guoqiang Zhang Published: 2026-05-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.00077v1 Recently, Belief-Attention \cite{Guoqiang25BeliefAttention} has been proposed by first performing an orthogonal projection of the softmax-based weighted summation of $V$ vectors with respect to the original $V$ vectors and then taking the perpendicular component as the residual signal in Transformer for performance improvement. In this paper, we first conduct an ablation study showing the projected component also carries information about the token correlation, which should not be ignored. We then propose to extend Belief-Attention by making use of both the perpendicular and projected components. In particular, the projected component goes through certain activation function and then a linear mapping before merging with the considered token. Conceptually speaking, the neural block for the projected component can be viewed as a two-layer feedforward network (FFN) within the new attention block. It is also noted that standard attention captures the token correlation via the inner-product matrix $QK^T$. We propose to introduce an additional inner-product matrix $ZZ^T$ to $QK^T$ to capture richer token correlation. We refer to the new module as Belief2-Attention. It can be easily shown that Belief2-Attention is more expressive than standard Attention. We then verify the effectiveness of Belief2-Attention for vision tasks of image classification and segmentation. --- ### DefocusTrackerAI -- A Generalized Framework for the Automatic Detection of Defocused Particle Images Authors: Gonçalo Coutinho, Ana S. Moita, António L. N. Moreira, Massimiliano Rossi Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.00076v1 The present work introduces DefocusTrackerAI, a generalized deep-learning framework for the automatic detection and position estimation of defocused particle images from any kind of optical configuration without compromising uncertainty and recall, intended as a follow-up of the open-source project DefocusTracker. We selected the deep neural network architecture from the direct comparison of two well-known object detection models, Faster R-CNN and YOLOv9, trained on a diverse and feature-rich synthetic image set containing astigmatic and non-astigmatic defocused particle images of varying diameters. The model evaluation on synthetic data showed that, first, YOLOv9 outperforms Faster R-CNN, achieving higher recall and lower uncertainty, particularly at high particle image densities; and second, that YOLOv9 provides enhanced spatial resolution, with uncertainty values between 0.1 and 0.4 pixels for particle image densities N_s up to 0.5, outperforming state-of-the-art algorithms. We demonstrated that our models are able to detect astigmatic and non-astigmatic defocused particle images in multiple optical setups with varying lighting conditions. In addition, we successfully applied our models on real DPT experiments, including fluorescence and shadowgraph data, showing that they can be used beyond conventional DPT applications, including the tracking of sprays and droplets. A pre-trained, ready-to-use version of DefocusTrackerAI based on YOLOv9 is available at https://gitlab.com/goncalo.coutinho/defocustrackerAI-main/-/tree/7e0f11f649ebad50e20dca5b9545f26ca303ebe0 and can be used for automatic detection of defocused particle images of any kind with high accuracy. In combination with a suitable calibration approach for the depth position, it can be used as an effective first step for three-dimensional defocusing particle tracking. --- ### Representation Alignment Rests on Linear Structure Authors: Kiril Bangachev, Guy Bresler, Yury Polyanskiy Published: 2026-05-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.28870v1 We investigate the Platonic Representation Hypothesis (PRH) through a tripartite statistical framework of representations: signal, bias, and noise. {1) Signal:} We propose that Platonic alignment arises from the universal relationship between objects and attributes, which is encoded linearly in representations according to the Linear Representation Hypothesis (LRH). We provide evidence that LRH helps explain PRH by extracting linear object-attribute features with sparse autoencoders and showing that these sparse representations often exhibit stronger cross-modal alignment than their dense counterparts. {2) Bias:} Models have different implicit biases due to the diverse architectures and training procedures used. We show that this difference can be partially mitigated. Centering and normalization consistently improve cross-model alignment. {3) Noise:} Finite-sample training leads to noise in representations. We provide evidence that representational noise is driven by data scarcity by revealing a strong and consistent positive correlation between word frequency and alignment in LLMs and text embedding models. Synthesizing signal, bias, and noise, we propose a statistical model that refines the Linear Representation Hypothesis and explains further phenomena related to the alignment of representations emerging from diverse modern AI architectures. --- ### Balancing Multimodal Learning through Label Space Reshaping Authors: Xiaoyu Ma, Weijie Zhang, Yuanhao Gao, Han Miao, Yongjian Deng, Hao Chen Published: 2026-05-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.28869v1 Multimodal learning often suffers from modality imbalance, where modalities that converge faster dominate optimization while others remain undertrained. Existing approaches typically mitigate this issue by strengthening the weak modality or adjusting optimization gradients. However, such strategies mainly compensate for optimization rate discrepancies, often at the expense of the strong modality's optimization capacity, without analyzing how these discrepancies arise at the modality level. Based on theoretical insights and empirical observations, we argue that the discrepancy of learning pace arises from differences in the mapping difficulty between modality-specific feature space and the shared label space. To address this issue, we propose Balanced Multimodal Label Reshaping (BMLR), the first method that promotes multimodal balance from the label-side design. BMLR reshapes the cross-modal label space to equalize mapping difficulty across modalities, thereby facilitating modality interaction and injecting richer inter-class information into each modality. Extensive experiments across multiple architectures demonstrate that BMLR consistently improves multimodal performance and exhibits strong compatibility with diverse model designs. The source code will be released soon. --- ### TaxDistill: Improving Metagenomic Taxonomic Annotation via Distilled Genomic Foundation Models Authors: Rongye Ye, Lun Li, Zheng Luo, Yiran Zhan, Shuhui Song Published: 2026-05-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.28868v1 Metagenomic taxonomic annotation aims to identify the microbial origins of DNA fragments in environmental samples. Traditional methods that rely on sequence similarity are often constrained by the high microbial diversity and the incompleteness of reference databases, which has motivated the development of learning approaches such as Taxometer that perform post hoc correction to learn more informative metagenomic sequence representations. However, these methods typically rely on labels derived from similarity search tools during training, which inevitably introduces noise that can impair representation learning and degrade classification performance. To address this issue, we propose TaxDistill, a knowledge distillation framework for metagenomic classification. We introduce GenomeOcean, a 500M parameter genomic foundation model, as the teacher network to extract deep semantic features and generate soft labels based on confidence. By distilling this soft label information into a lightweight student network, TaxDistill effectively reduces the label noise introduced by initial retrieval tools. Comprehensive experiments on seven diverse CAMI2 datasets demonstrate that TaxDistill outperforms existing baselines in most scenarios. For instance, on the Gastrointestinal dataset, it improves the F1 score of MMseqs2 from 0.763 to 0.941, outperforming the Taxometer baseline. Overall, TaxDistill provides a reliable method for label correction in complex metagenomic analysis. ---