# Research Papers — 2026-04 · bundle page 51 of 233 > Full-text markdown of papers #2501–2550 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-04/page/51 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/50.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/52.md) ### Mapping the Political Discourse in the Brazilian Chamber of Deputies: A Multi-Faceted Computational Approach Authors: Flávio Soriano, Victoria F. Mello, Pedro B. Rigueira, Gisele L. Pappa, Wagner Meira, Ana Paula Couto da Silva, Jussara M. Almeida Published: 2026-04-23 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2604.21897v1 Analyses of legislative behavior often rely on voting records, overlooking the rich semantic and rhetorical content of political speech. In this paper, we ask three complementary questions about parliamentary discourse: how things are said, what is being said, and who is speaking in discursively similar ways. To answer these questions, we introduce a scalable and generalizable computational framework that combines diachronic stylometric analysis, contextual topic modeling, and semantic clustering of deputies' speeches. We apply this framework to a large-scale case study of the Brazilian Chamber of Deputies, using a corpus of over 450,000 speeches from 2003 to 2025. Our results show a long-term stylistic shift toward shorter and more direct speeches, a legislative agenda that reorients sharply in response to national crises, and a granular map of discursive alignments in which regional and gender identities often prove more salient than formal party affiliation. More broadly, this work offers a robust methodology for analyzing parliamentary discourse as a multidimensional phenomenon that complements traditional vote-based approaches. --- ### Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models Authors: Chee Wei Tan, Yuchen Wang, Shangxin Guo Published: 2026-04-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.21896v1 This paper introduces a new paradigm for AI game programming, leveraging large language models (LLMs) to extend and operationalize Claude Shannon's taxonomy of game-playing machines. Central to this paradigm is Nemobot, an interactive agentic engineering environment that enables users to create, customize, and deploy LLM-powered game agents while actively engaging with AI-driven strategies. The LLM-based chatbot, integrated within Nemobot, demonstrates its capabilities across four distinct classes of games. For dictionary-based games, it compresses state-action mappings into efficient, generalized models for rapid adaptability. In rigorously solvable games, it employs mathematical reasoning to compute optimal strategies and generates human-readable explanations for its decisions. For heuristic-based games, it synthesizes strategies by combining insights from classical minimax algorithms (see, e.g., shannon1950chess) with crowd-sourced data. Finally, in learning-based games, it utilizes reinforcement learning with human feedback and self-critique to iteratively refine strategies through trial-and-error and imitation learning. Nemobot amplifies this framework by offering a programmable environment where users can experiment with tool-augmented generation and fine-tuning of strategic game agents. From strategic games to role-playing games, Nemobot demonstrates how AI agents can achieve a form of self-programming by integrating crowdsourced learning and human creativity to iteratively refine their own logic. This represents a step toward the long-term goal of self-programming AI. --- ### Revealing Geography-Driven Signals in Zone-Level Claim Frequency Models: An Empirical Study using Environmental and Visual Predictors Authors: Sherly Alfonso-Sánchez, Cristián Bravo, Kristina G. Stankova Published: 2026-04-23 Categories: stat.ML, cs.LG, q-fin.RM arXiv: https://arxiv.org/abs/2604.21893v1 Geographic context is often consider relevant to motor insurance risk, yet public actuarial datasets provide limited location identifiers, constraining how this information can be incorporated and evaluated in claim-frequency models. This study examines how geographic information from alternative data sources can be incorporated into actuarial models for Motor Third Party Liability (MTPL) claim prediction under such constraints. Using the BeMTPL97 dataset, we adopt a zone-level modeling framework and evaluate predictive performance on unseen postcodes. Geographic information is introduced through two channels: environmental indicators from OpenStreetMap and CORINE Land Cover, and orthoimagery released by the Belgian National Geographic Institute for academic use. We evaluate the predictive contribution of coordinates, environmental features, and image embeddings across three baseline models: generalized linear models (GLMs), regularized GLMs, and gradient-boosted trees, while raw imagery is modeled using convolutional neural networks. Our results show that augmenting actuarial variables with constructed geographic information improves accuracy. Across experiments, both linear and tree-based models benefit most from combining coordinates with environmental features extracted at 5 km scale, while smaller neighborhoods also improve baseline specifications. Generally, image embeddings do not improve performance when environmental features are available; however, when such features are absent, pretrained vision-transformer embeddings enhance accuracy and stability for regularized GLMs. Our results show that the predictive value of geographic information in zone-level MTPL frequency models depends less on model complexity than on how geography is represented, and illustrate that geographic context can be incorporated despite limited individual-level spatial information. --- ### A Multi-Stage Warm-Start Deep Learning Framework for Unit Commitment Authors: Muhy Eddin Za'ter, Anna Van Boven, Bri-Mathias Hodge, Kyri Baker Published: 2026-04-23 Categories: eess.SY, cs.AI arXiv: https://arxiv.org/abs/2604.21891v1 Maintaining instantaneous balance between electricity supply and demand is critical for reliability and grid instability. System operators achieve this through solving the task of Unit Commitment (UC),ca high dimensional large-scale Mixed-integer Linear Programming (MILP) problem that is strictly and heavily governed by the grid physical constraints. As grid integrate variable renewable sources, and new technologies such as long duration storage in the grid, UC must be optimally solved for multi-day horizons and potentially with greater frequency. Therefore, traditional MILP solvers increasingly struggle to compute solutions within these tightening operational time limits. To bypass these computational bottlenecks, this paper proposes a novel framework utilizing a transformer-based architecture to predict generator commitment schedules over a 72-hour horizon. Also, because raw predictions in highly dimensional spaces often yield physically infeasible results, the pipeline integrates the self-attention network with deterministic post-processing heuristics that systematically enforce minimum up/down times and minimize excess capacity. Finally, these refined predictions are utilized as a warm start for a downstream MILP solver, while employing a confidence-based variable fixation strategy to drastically reduce the combinatorial search space. Validated on a single-bus test system, the complete multi-stage pipeline achieves 100\% feasibility and significantly accelerates computation times. Notably, in approximately 20\% of test instances, the proposed model reached a feasible operational schedule with a lower overall system cost than relying solely on the solver. --- ### EVENT5Ws: A Large Dataset for Open-Domain Event Extraction from Documents Authors: Praval Sharma, Ashok Samal, Leen-Kiat Soh, Deepti Joshi Published: 2026-04-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.21890v1 Event extraction identifies the central aspects of events from text. It supports event understanding and analysis, which is crucial for tasks such as informed decision-making in emergencies. Therefore, it is necessary to develop automated event extraction approaches. However, existing datasets for algorithm development have limitations, including limited coverage of event types in closed-domain settings and a lack of large, manually verified dataset in open-domain settings. To address these limitations, we create EVENT5Ws , a large, manually annotated, and statistically verified open-domain event extraction dataset. We design a systematic annotation pipeline to create the dataset and provide empirical insights into annotation complexity. Using EVENT5Ws, we evaluate state-of-the-art pre-trained large language models and establish a benchmark for future research. We further show that models trained on EVENT5Ws generalize effectively to datasets from different geographical contexts, which demonstrates its potential for developing generalizable algorithms. Finally, we summarize the lessons learned during the dataset development and provide recommendations to support future large-scale dataset development. --- ### TingIS: Real-time Risk Event Discovery from Noisy Customer Incidents at Enterprise Scale Authors: Jun Wang, Ziyin Zhang, Rui Wang, Hang Yu, Peng Di, Rui Wang Published: 2026-04-23 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.21889v3 Real-time detection and mitigation of technical anomalies are critical for large-scale cloud-native services, where even minutes of downtime can result in massive financial losses and diminished user trust. While customer incidents serve as a vital signal for discovering risks missed by monitoring, extracting actionable intelligence from this data remains challenging due to extreme noise, high throughput, and semantic complexity of diverse business lines. In this paper, we present TingIS, an end-to-end system designed for enterprise-grade incident discovery. At the core of TingIS is a multi-stage event linking engine that synergizes efficient indexing techniques with Large Language Models (LLMs) to make informed decisions on event merging, enabling the stable extraction of actionable incidents from just a handful of diverse user descriptions. This engine is complemented by a cascaded routing mechanism for precise business attribution and a multi-dimensional noise reduction pipeline that integrates domain knowledge, statistical patterns, and behavioral filtering. Deployed in a production environment handling a peak throughput of over 2,000 messages per minute and 300,000 messages per day, TingIS achieves a P90 alert latency of 3.5 minutes and a 95\% discovery rate for high-priority incidents. Benchmarks constructed from real-world data demonstrate that TingIS significantly outperforms baseline methods in routing accuracy, clustering quality, and Signal-to-Noise Ratio. --- ### A Multimodal Text- and Graph-Based Approach for Open-Domain Event Extraction from Documents Authors: Praval Sharma Published: 2026-04-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.21885v1 Event extraction is essential for event understanding and analysis. It supports tasks such as document summarization and decision-making in emergency scenarios. However, existing event extraction approaches have limitations: (1) closed-domain algorithms are restricted to predefined event types and thus rarely generalize to unseen types and (2) open-domain event extraction algorithms, capable of handling unconstrained event types, have largely overlooked the potential of large language models (LLMs) despite their advanced abilities. Additionally, they do not explicitly model document-level contextual, structural, and semantic reasoning, which are crucial for effective event extraction but remain challenging for LLMs due to lost-in-the-middle phenomenon and attention dilution. To address these limitations, we propose multimodal open-domain event extraction, MODEE , a novel approach for open-domain event extraction that combines graph-based learning with text-based representation from LLMs to model document-level reasoning. Empirical evaluations on large datasets demonstrate that MODEE outperforms state-of-the-art open-domain event extraction approaches and can be generalized to closed-domain event extraction, where it outperforms existing algorithms. --- ### Revisiting Non-Verbatim Memorization in Large Language Models: The Role of Entity Surface Forms Authors: Yuto Nishida, Naoki Shikoda, Yosuke Kishinami, Ryo Fujii, Makoto Morishita, Hidetaka Kamigaito, Taro Watanabe Published: 2026-04-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.21882v1 Understanding what kinds of factual knowledge large language models (LLMs) memorize is essential for evaluating their reliability and limitations. Entity-based QA is a common framework for analyzing non-verbatim memorization, but typical evaluations query each entity using a single canonical surface form, making it difficult to disentangle fact memorization from access through a particular name. We introduce RedirectQA, an entity-based QA dataset that uses Wikipedia redirect information to associate Wikidata factual triples with categorized surface forms for each entity, including alternative names, abbreviations, spelling variants, and common erroneous forms. Across 13 LLMs, we examine surface-conditioned factual memorization and find that prediction outcomes often change when only the entity surface form changes. This inconsistency is category-dependent: models are more robust to minor orthographic variations than to larger lexical variations such as aliases and abbreviations. Frequency analyses further suggest that both entity- and surface-level frequencies are associated with accuracy, and that entity frequency often contributes beyond surface frequency. Overall, factual memorization appears neither purely surface-specific nor fully surface-invariant, highlighting the importance of surface-form diversity in evaluating non-verbatim memorization. --- ### Addressing Image Authenticity When Cameras Use Generative AI Authors: Umar Masud, Abhijith Punnappurath, Luxi Zhao, David B. Lindell, Michael S. Brown Published: 2026-04-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.21879v1 The ability of generative AI (GenAI) methods to photorealistically alter camera images has raised awareness about the authenticity of images shared online. Interestingly, images captured directly by our cameras are considered authentic and faithful. However, with the increasing integration of deep-learning modules into cameras' capture-time hardware -- namely, the image signal processor (ISP) -- there is now a potential for hallucinated content in images directly output by our cameras. Hallucinated capture-time image content is typically benign, such as enhanced edges or texture, but in certain operations, such as AI-based digital zoom or low-light image enhancement, hallucinations can potentially alter the semantics and interpretation of the image content. As a result, users may not realize that the content in their camera images is not authentic. This paper addresses this issue by enabling users to recover the 'unhallucinated' version of the camera image to avoid misinterpretation of the image content. Our approach works by optimizing an image-specific multi-layer perceptron (MLP) decoder together with a modality-specific encoder so that, given the camera image, we can recover the image before hallucinated content was added. The encoder and MLP are self-contained and can be applied post-capture to the image without requiring access to the camera ISP. Moreover, the encoder and MLP decoder require only 180 KB of storage and can be readily saved as metadata within standard image formats such as JPEG and HEIC. --- ### Grounding Video Reasoning in Physical Signals Authors: Alibay Osmanli, Zixu Cheng, Shaogang Gong Published: 2026-04-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.21873v1 Physical video understanding requires more than naming an event correctly. A model can answer a question about pouring, sliding, or collision from textual regularities while still failing to localize the event in time or space. We introduce a grounded benchmark for physical video understanding that extends the what--when--where evaluation structure of V-STaR to four video sources, six physics domains, three prompt families (physics, vstar_like, and neutral_rstr), and four input conditions (original, shuffled, ablated, and frame-masked). The benchmark contains 1,560 base video clips from SSV2, YouCook2, HoloAssist, and Roundabout-TAU. Each clip is first converted into a shared grounded event record, and the three query families are derived from that record. Temporal and spatial targets are shared across prompt families, while the non-physics families use deterministic family-appropriate semantic a_what targets derived from the same record. Across models and prompt families, physics remains the strongest regime overall, vstar_like is the clearest non-physics semantic comparison, and neutral_rstr behaves as a harder templated control. Prompt-family robustness is selective rather than universal, perturbation gains cluster in weak original cases, and spatial grounding is the weakest across settings. These results suggest that video Q&A reasoning benchmarks shall report physically grounded, prompt-aware, and perturbation-aware diagnostics alongside aggregate accuracy. --- ### Machine Behavior in Relational Moral Dilemmas: Moral Rightness, Predicted Human Behavior, and Model Decisions Authors: Jiseon Kim, Jea Kwon, Luiz Felipe Vecchietti, Wenchao Dong, Jaehong Kim, Meeyoung Cha Published: 2026-04-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.21871v1 Human moral judgment is context-dependent and modulated by interpersonal relationships. As large language models (LLMs) increasingly function as decision-support systems, determining whether they encode these social nuances is critical. We characterize machine behavior using the Whistleblower's Dilemma by varying two experimental dimensions: crime severity and relational closeness. Our study evaluates three distinct perspectives: (1) moral rightness (prescriptive norms), (2) predicted human behavior (descriptive social expectations), and (3) autonomous model decision-making. By analyzing the reasoning processes, we identify a clear cross-perspective divergence: while moral rightness remains consistently fairness-oriented, predicted human behavior shifts significantly toward loyalty as relational closeness increases. Crucially, model decisions align with moral rightness judgments rather than their own behavioral predictions. This inconsistency suggests that LLM decision-making prioritizes rigid, prescriptive rules over the social sensitivity present in their internal world-modeling, which poses a gap that may lead to significant misalignments in real-world deployments. --- ### Locating acts of mechanistic reasoning in student team conversations with mechanistic machine learning Authors: Kaitlin Gili, Mainak Nistala, Kristen Wendell, Michael C. Hughes Published: 2026-04-23 Categories: physics.ed-ph, cs.LG arXiv: https://arxiv.org/abs/2604.21870v1 STEM education researchers are often interested in identifying moments of students' mechanistic reasoning for deeper analysis, but have limited capacity to search through many team conversation transcripts to find segments with a high concentration of such reasoning. We offer a solution in the form of an interpretable machine learning model that outputs time-varying probabilities that individual students are engaging in acts of mechanistic reasoning, leveraging evidence from their own utterances as well as contributions from the rest of the group. Using the toolkit of intentionally-designed probabilistic models, we introduce a specific inductive bias that steers the probabilistic dynamics toward desired, domain-aligned behavior. Experiments compare trained models with and without the inductive bias components, investigating whether their presence improves the desired model behavior on transcripts involving never-before-seen students and a novel discussion context. Our results show that the inductive bias improves generalization -- supporting the claim that interpretability is built into the model for this task rather than imposed post hoc. We conclude with practical recommendations for STEM education researchers seeking to adopt the tool and for ML researchers aiming to extend the model's design. Overall, we hope this work encourages the development of mechanistically interpretable models that are understandable and controllable for both end users and model designers in STEM education research. --- ### Replay-buffer engineering for noise-robust quantum circuit optimization Authors: Akash Kundu, Sebastian Feld Published: 2026-04-23 Categories: quant-ph, cs.AI, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2604.21863v1 Deep reinforcement learning (RL) for quantum circuit optimization faces three fundamental bottlenecks: replay buffers that ignore the reliability of temporal-difference (TD) targets, curriculum-based architecture search that triggers a full quantum-classical evaluation at every environment step, and the routine discard of noiseless trajectories when retraining under hardware noise. We address all three by treating the replay buffer as a primary algorithmic lever for quantum optimization. We introduce ReaPER$+$, an annealed replay rule that transitions from TD error-driven prioritization early in training to reliability-aware sampling as value estimates mature, achieving $4-32\times$ gains in sample efficiency over fixed PER, ReaPER, and uniform replay while consistently discovering more compact circuits across quantum compilation and QAS benchmarks; validation on LunarLander-v3 confirms the principle is domain-agnostic. Furthermore we eliminate the quantum-classical evaluation bottleneck in curriculum RL by introducing OptCRLQAS which amortizes expensive evaluations over multiple architectural edits, cutting wall-clock time per episode by up to $67.5\%$ on a 12-qubit optimization problem without degrading solution quality. Finally we introduce a lightweight replay-buffer transfer scheme that warm-starts noisy-setting learning by reusing noiseless trajectories, without network-weight transfer or $ε$-greedy pretraining. This reduces steps to chemical accuracy by up to $85-90\%$ and final energy error by up to $90\%$ over from-scratch baselines on 6-, 8-, and 12-qubit molecular tasks. Together, these results establish that experience storage, sampling, and transfer are decisive levers for scalable, noise-robust quantum circuit optimization. --- ### Neuromorphic Computing Based on Parametrically-Driven Oscillators and Frequency Combs Authors: Mahadev Sunil Kumar, Adarsh Ganesan Published: 2026-04-23 Categories: cs.NE, nlin.PS arXiv: https://arxiv.org/abs/2604.21861v1 Parametrically driven oscillators provide a natural platform for neuromorphic computation, where nonlinear mode coupling and intrinsic dynamics enable both memory and high-dimensional transformation. Here, we investigate a two-mode system exhibiting 2:1 parametric resonance and demonstrate its operation as a reservoir computer across distinct dynamical regimes, including sub-threshold, parametric resonance, and frequency-comb states. By encoding input signals into the drive amplitude and sampling the resulting temporal and spectral responses, we perform one step-ahead prediction of benchmark chaotic systems, including Mackey-Glass, Rossler, and Lorenz dynamics. We find that optimal computational performance is achieved within the parametric resonance regime, where nonlinear interactions are activated while temporal coherence is preserved. In contrast, although frequency-comb states introduce increased spectral dimensionality, their performance is not consistently good across their existence band and also degrades in the chaotic comb regime due to loss of phase coherence. Mapping prediction error over parameter space reveals a direct correspondence between computational capability and the underlying bifurcation structure, with low-error regions aligned with the parametric resonance boundary. We further show that the input modulation, the detuning from the frequency matching condition, damping ratio, and input data rate systematically control the accessible dynamical regimes and thereby the computational performance. These results establish parametric resonance as a robust operating regime for oscillator-based reservoir computing and provide design principles for tuning physical systems toward optimal neuromorphic functionality. --- ### Transient Turn Injection: Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models Authors: Naheed Rayhan, Sohely Jahan Published: 2026-04-23 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.21860v1 Large language models (LLMs) are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This paper introduces Transient Turn Injection(TTI), a new multi-turn attack technique that systematically exploits stateless moderation by distributing adversarial intent across isolated interactions. TTI leverages automated attacker agents powered by large language models to iteratively test and evade policy enforcement in both commercial and open-source LLMs, marking a departure from conventional jailbreak approaches that typically depend on maintaining persistent conversational context. Our extensive evaluation across state-of-the-art models-including those from OpenAI, Anthropic, Google Gemini, Meta, and prominent open-source alternatives-uncovers significant variations in resilience to TTI attacks, with only select architectures exhibiting substantial inherent robustness. Our automated blackbox evaluation framework also uncovers previously unknown model specific vulnerabilities and attack surface patterns, especially within medical and high stakes domains. We further compare TTI against established adversarial prompting methods and detail practical mitigation strategies, such as session level context aggregation and deep alignment approaches. Our study underscores the urgent need for holistic, context aware defenses and continuous adversarial testing to future proof LLM deployments against evolving multi-turn threats. --- ### Bounding the Black Box: A Statistical Certification Framework for AI Risk Regulation Authors: Natan Levy, Gadi Perl Published: 2026-04-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.21854v1 Artificial intelligence now decides who receives a loan, who is flagged for criminal investigation, and whether an autonomous vehicle brakes in time. Governments have responded: the EU AI Act, the NIST Risk Management Framework, and the Council of Europe Convention all demand that high-risk systems demonstrate safety before deployment. Yet beneath this regulatory consensus lies a critical vacuum: none specifies what ``acceptable risk'' means in quantitative terms, and none provides a technical method for verifying that a deployed system actually meets such a threshold. The regulatory architecture is in place; the verification instrument is not. This gap is not theoretical. As the EU AI Act moves into full enforcement, developers face mandatory conformity assessments without established methodologies for producing quantitative safety evidence - and the systems most in need of oversight are opaque statistical inference engines that resist white-box scrutiny. This paper provides the missing instrument. Drawing on the aviation certification paradigm, we propose a two-stage framework that transforms AI risk regulation into engineering practice. In Stage One, a competent authority formally fixes an acceptable failure probability $δ$ and an operational input domain $\varepsilon$ - a normative act with direct civil liability implications. In Stage Two, the RoMA and gRoMA statistical verification tools compute a definitive, auditable upper bound on the system's true failure rate, requiring no access to model internals and scaling to arbitrary architectures. We demonstrate how this certificate satisfies existing regulatory obligations, shifts accountability upstream to developers, and integrates with the legal frameworks that exist today. --- ### Beyond Expected Information Gain: Stable Bayesian Optimal Experimental Design with Integral Probability Metrics and Plug-and-Play Extensions Authors: Di Wu, Ling Liang, Haizhao Yang Published: 2026-04-23 Categories: stat.ML, cs.LG, math.NA, stat.CO arXiv: https://arxiv.org/abs/2604.21849v1 Bayesian Optimal Experimental Design (BOED) provides a rigorous framework for decision-making tasks in which data acquisition is often the critical bottleneck, especially in resource-constrained settings. Traditionally, BOED typically selects designs by maximizing expected information gain (EIG), commonly defined through the Kullback-Leibler (KL) divergence. However, classical evaluation of EIG often involves challenging nested expectations, and even advanced variational methods leave the underlying log-density-ratio objective unchanged. As a result, support mismatch, tail underestimation, and rare-event sensitivity remain intrinsic concerns for KL-based BOED. To address these fundamental bottlenecks, we introduce an IPM-based BOED framework that replaces density-based divergences with integral probability metrics (IPMs), including the Wasserstein distance, Maximum Mean Discrepancy, and Energy Distance, resulting in a highly flexible plug-and-play BOED framework. We establish theoretical guarantees showing that IPM-based utilities provide stronger geometry-aware stability under surrogate-model error and prior misspecification than classical EIG-based utilities. We also validate the proposed framework empirically, demonstrating that IPM-based designs yield highly concentrated credible sets. Furthermore, by extending the same sample-based BOED template in a plug-and-play manner to geometry-aware discrepancies beyond the IPM class, illustrated by a neural optimal transport estimator, we achieve accurate optimal designs in high-dimensional settings where conventional nested Monte Carlo estimators and advanced variational methods fail. --- ### Causality-Encoded Diffusion Models for Interventional Sampling and Edge Inference Authors: Li Chen, Xiaotong Shen, Wei Pan Published: 2026-04-23 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2604.21843v1 Standard diffusion models are flexible estimators of complex distributions, but they do not encode causal structures and therefore do not by themselves support causal analysis. We propose a causality-encoded diffusion framework that incorporates a known directed acyclic graph by training conditional diffusion models consistent with the graph factorisation. The resulting sampler approximately recovers the observational distribution and enables interventional sampling by fixing intervened variables while propagating effects through the graph during reverse diffusion. Building on this interventional simulator, we develop a resampling-based test for directed edges that generates null replicates under a candidate graph. We establish convergence guarantees for observational and interventional distribution estimation, with rates governed by the maximum local dimension rather than the ambient dimension, and prove asymptotic control of type I error for the edge test. Simulations show improved interventional distribution recovery relative to baselines, with near-nominal size and favourable power in inference. An application to flow cytometry data demonstrates practical utility of the proposed method in assessing disputed signalling linkages. --- ### TraceScope: Interactive URL Triage via Decoupled Checklist Adjudication Authors: Haolin Zhang, William Reber, Yuxuan Zhang, Guofei Gu, Jeff Huang Published: 2026-04-23 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.21840v1 Modern phishing campaigns increasingly evade snapshot-based URL classifiers using interaction gates (e.g., checkbox/slider challenges), delayed content rendering, and logo-less credential harvesters. This shifts URL triage from static classification toward an interactive forensics task: an analyst must actively navigate the page while isolating themselves from potential runtime exploits. We present TraceScope, a decoupled triage pipeline that operationalizes this workflow at scale. To prevent the observer effect and ensure safety, a sandboxed operator agent drives a real GUI browser guided by visual motivation to elicit page behavior, freezing the session into an immutable evidence bundle. Separately, an adjudicator agent circumvents LLM context limitations by querying evidence on demand to verify a MITRE ATT&CK checklist, and generates an audit-ready report with extracted indicators of compromise (IOCs) and a final verdict. Evaluated on 708 reachable URLs from existing dataset (241 verified phishing from PhishTank and 467 benign from Tranco-derived crawling), TraceScope achieves 0.94 precision and 0.78 recall, substantially improving recall over three prior visual/reference-based classifiers while producing reproducible, analyst-grade evidence suitable for review. More importantly, we manually curated a dataset of real-world phishing emails to evaluate our system in a practical setting. Our evaluation reveals that TraceScope demonstrates superior performance in a real-world scenario as well, successfully detecting sophisticated phishing attempts that current state-of-the-art defenses fail to identify. --- ### Modulating Cross-Modal Convergence with Single-Stimulus, Intra-Modal Dispersion Authors: Eghbal A. Hosseini, Brian Cheung, Evelina Fedorenko, Alex H. Williams Published: 2026-04-23 Categories: q-bio.NC, cs.AI arXiv: https://arxiv.org/abs/2604.21836v1 Neural networks exhibit a remarkable degree of representational convergence across diverse architectures, training objectives, and even data modalities. This convergence is predictive of alignment with brain representation. A recent hypothesis suggests this arises from learning the underlying structure in the environment in similar ways. However, it is unclear how individual stimuli elicit convergent representations across networks. An image can be perceived in multiple ways and expressed differently using words. Here, we introduce a methodology based on the Generalized Procrustes Algorithm to measure intra-modal representational convergence at the single-stimulus level. We applied this to vision models with distinct training objectives, selecting stimuli based on their degree of alignment (intra-modal dispersion). Crucially, we found that this intra-modal dispersion strongly modulates alignment between vision and language models (cross-modal convergence). Specifically, stimuli with low intra-modal dispersion (high agreement among vision models) elicited significantly higher cross-modal alignment than those with high dispersion, by up to a factor of two (e.g., in pairings of DINOv2 with language models). This effect was robust to stimulus selection criteria and generalized across different pairings of vision and language models. Measuring convergence at the single-stimulus level provides a path toward understanding the sources of convergence and divergence across modalities, and between neural networks and human neural representations. --- ### GFlowState: Visualizing the Training of Generative Flow Networks Beyond the Reward Authors: Florian Holeczek, Andreas Hinterreiter, Alex Hernandez-Garcia, Marc Streit, Christina Humer Published: 2026-04-23 Categories: cs.LG, cs.HC arXiv: https://arxiv.org/abs/2604.21830v1 We present GFlowState, a visual analytics system designed to illuminate the training process of Generative Flow Networks (GFlowNets or GFNs). GFlowNets are a probabilistic framework for generating samples proportionally to a reward function. While GFlowNets have proved to be powerful tools in applications such as molecule and material discovery, their training dynamics remain difficult to interpret. Standard machine learning tools allow metric tracking but do not reveal how models explore the sample space, construct sample trajectories, or shift sampling probabilities during training. Our solution, GFlowState, allows users to analyze sampling trajectories, compare the sample space relative to reference datasets, and analyze the training dynamics. To this end, we introduce multiple views, including a chart of candidate rankings, a state projection, a node-link diagram of the trajectory network, and a transition heatmap. These visualizations enable GFlowNet developers and users to investigate sampling behavior and policy evolution, and to identify underexplored regions and sources of training failure. Case studies demonstrate how the system supports debugging and assessing the quality of GFlowNets across application domains. By making the structural dynamics of GFlowNets observable, our work enhances their interpretability and can accelerate GFlowNet development in practice. --- ### Alignment has a Fantasia Problem Authors: Nathanael Jo, Zoe De Simone, Mitchell Gordon, Ashia Wilson Published: 2026-04-23 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2604.21827v3 In accomplishing complex tasks, human cognition typically progresses from abstract to concrete (e.g., from brainstorming ideas to writing an essay). With the advent of highly capable AI assistants, people now offload various parts of their task to the system. However, instruction-tuned AI systems, even when designed to infer implicit intent, lack an understanding of humans' cognitive processes. When a user approaches AI while their goals and intentions are abstract, AI systems often short circuit their cognitive process through which those goals would be refined by jumping toward a final output (e.g., writing the essay entirely). Doing so takes away the user's agency in achieving the task: they may need to spend more time revising or, worse, settle on a suboptimal outcome. We call these failures Fantasia interactions after the famous Disney scene. We argue that Fantasia interactions demand a rethinking of alignment research, where AI systems optimize how cognitive responsibility is allocated within an interaction. We highlight gaps in state-of-the-art alignment methods, and outline a research agenda for training and evaluating models to achieve this vision. --- ### Alignment has a Fantasia Problem Authors: Nathanael Jo, Zoe De Simone, Mitchell Gordon, Ashia Wilson Published: 2026-04-23 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2604.21827v1 Modern AI assistants are trained to follow instructions, implicitly assuming that users can clearly articulate their goals and the kind of assistance they need. Decades of behavioral research, however, show that people often engage with AI systems before their goals are fully formed. When AI systems treat prompts as complete expressions of intent, they can appear to be useful or convenient, but not necessarily aligned with the users' needs. We call these failures Fantasia interactions. We argue that Fantasia interactions demand a rethinking of alignment research: rather than treating users as rational oracles, AI should provide cognitive support by actively helping users form and refine their intent through time. This requires an interdisciplinary approach that bridges machine learning, interface design, and behavioral science. We synthesize insights from these fields to characterize the mechanisms and failures of Fantasia interactions. We then show why existing interventions are insufficient, and propose a research agenda for designing and evaluating AI systems that better help humans navigate uncertainty in their tasks. --- ### On the algebra of Koopman eigenfunctions and on some of their infinities Authors: Zahra Monfared, Saksham Malhotra, Sekiya Hajime, Ioannis Kevrekidis, Felix Dietrich Published: 2026-04-23 Categories: math.DS, cs.LG, math.NA arXiv: https://arxiv.org/abs/2604.21825v1 For continuous-time dynamical systems with reversible trajectories, the nowhere-vanishing eigenfunctions of the Koopman operator of the system form a multiplicative group. Here, we exploit this property to accelerate the systematic numerical computation of the eigenspaces of the operator. Given a small set of (so-called ``principal'') eigenfunctions that are approximated conventionally, we can obtain a much larger set by constructing polynomials of the principal eigenfunctions. This enriches the set, and thus allows us to more accurately represent application-specific observables. Often, eigenfunctions exhibit localized singularities (e.g. in simple, one-dimensional problems with multiple steady states) or extended ones (e.g. in simple, two-dimensional problems possessing a limit cycle, or a separatrix); we discuss eigenfunction matching/continuation across such singularities. By handling eigenfunction singularities and enabling their continuation, our approach supports learning consistent global representations from locally sampled data. This is particularly relevant for multistable systems and applications with sparse or fragmented measurements. --- ### Tool Attention Is All You Need: Dynamic Tool Gating and Lazy Schema Loading for Eliminating the MCP/Tools Tax in Scalable Agentic Workflows Authors: Anuj Sadani, Deepak Kumar Published: 2026-04-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.21816v1 The Model Context Protocol (MCP) has become a common interface for connecting large language model (LLM) agents to external tools, but its reliance on stateless, eager schema injection imposes a hidden per-turn overhead the MCP Tax or Tools Tax that practitioner reports place between roughly 10k and 60k tokens in typical multi-server deployments. This payload inflates the key-value cache, is associated with reasoning degradation as context utilization approaches published fracture points around 70%, and turns token budgets into a recurring operational cost. We introduce Tool Attention, a middleware-layer mechanism that generalizes the "Attention Is All You Need" paradigm from self-attention over tokens to gated attention over tools. Tool Attention combines (i) an Intent Schema Overlap (ISO) score from sentence embeddings, (ii) a state-aware gating function enforcing preconditions and access scopes, and (iii) a two-phase lazy schema loader that keeps a compact summary pool in context and promotes full JSON schemas only for top-k gated tools. We evaluate on a simulated 120-tool, six-server benchmark whose per-server token counts are calibrated to public audits of real MCP deployments. In this simulation, Tool Attention directly reduces measured per-turn tool tokens by 95.0% (47.3k -> 2.4k) and raises effective context utilization (a token-ratio quantity) from 24% to 91%. End-to-end figures for task success, latency, cost, and reasoning quality are reported as projections derived from the measured token counts combined with published deployment telemetry; they are not measured on live LLM agents, and we mark projected values explicitly throughout. Taken together, the results support a simple thesis: protocol-level efficiency, not raw context length, is a binding constraint on scalable gentic systems. The code for this work is accessible at https://github.com/asadani/tool-attention --- ### Divide-then-Diagnose: Weaving Clinician-Inspired Contexts for Ultra-Long Capsule Endoscopy Videos Authors: Bowen Liu, Li Yang, Shanshan Song, Mingyu Tang, Zhifang Gao, Qifeng Chen, Yangqiu Song, Huimin Chen, Xiaomeng Li Published: 2026-04-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.21814v1 Capsule endoscopy (CE) enables non-invasive gastrointestinal screening, but current CE research remains largely limited to frame-level classification and detection, leaving video-level analysis underexplored. To bridge this gap, we introduce and formally define a new task, diagnosis-driven CE video summarization, which requires extracting key evidence frames that covers clinically meaningful findings and making accurate diagnoses from those evidence frames. This setting is challenging because diagnostically relevant events are extremely sparse and can be overwhelmed by tens of thousands of redundant normal frames, while individual observations are often ambiguous due to motion blur, debris, specular highlights, and rapid viewpoint changes. To facilitate research in this direction, we introduce VideoCAP, the first CE dataset with diagnosis-driven annotations derived from real clinical reports. VideoCAP comprises 240 full-length videos and provides realistic supervision for both key evidence frame extraction and diagnosis. To address this task, we further propose DiCE, a clinician-inspired framework that mirrors the standard CE reading workflow. DiCE first performs efficient candidate screening over the raw video, then uses a Context Weaver to organize candidates into coherent diagnostic contexts that preserve distinct lesion events, and an Evidence Converger to aggregate multi-frame evidence within each context into robust clip-level judgments. Experiments show that DiCE consistently outperforms state-of-the-art methods, producing concise and clinically reliable diagnostic summaries. These results highlight diagnosis-driven contextual reasoning as a promising paradigm for ultra-long CE video summarization. --- ### Probably Approximately Consensus: On the Learning Theory of Finding Common Ground Authors: Carter Blair, Ben Armstrong, Shiri Alouf-Heffetz, Nimrod Talmon, Davide Grossi Published: 2026-04-23 Categories: cs.LG, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2604.21811v1 A primary goal of online deliberation platforms is to identify ideas that are broadly agreeable to a community of users through their expressed preferences. Yet, consensus elicitation should ideally extend beyond the specific statements provided by users and should incorporate the relative salience of particular topics. We address this issue by modelling consensus as an interval in a one-dimensional opinion space derived from potentially high-dimensional data via embedding and dimensionality reduction. We define an objective that maximizes expected agreement within a hypothesis interval where the expectation is over an underlying distribution of issues, implicitly taking into account their salience. We propose an efficient Empirical Risk Minimization (ERM) algorithm and establish PAC-learning guarantees. Our initial experiments demonstrate the performance of our algorithm and examine more efficient approaches to identifying optimal consensus regions. We find that through selectively querying users on an existing sample of statements, we can reduce the number of queries needed to a practical number. --- ### Multiscale Super Resolution without Image Priors Authors: Daniel Fu, Gabby Litterio, Pedro Felzenszwalb, Rashid Zia Published: 2026-04-23 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2604.21810v1 We address the ambiguities in the super-resolution problem under translation. We demonstrate that combinations of low-resolution images at different scales can be used to make the super-resolution problem well posed. Such differences in scale can be achieved using sensors with different pixel sizes (as demonstrated here) or by varying the effective pixel size through changes in optical magnification (e.g., using a zoom lens). We show that images acquired with pairwise coprime pixel sizes lead to a system with a stable inverse, and furthermore, that super-resolution images can be reconstructed efficiently using Fourier domain techniques or iterative least squares methods. Our mathematical analysis provides an expression for the expected error of the least squares reconstruction for large signals assuming i.i.d. noise that elucidates the noise-resolution tradeoff. These results are validated through both one- and two-dimensional experiments that leverage charge-coupled device (CCD) hardware binning to explore reconstructions over a large range of effective pixel sizes. Finally, two-dimensional reconstructions for a series of targets are used to demonstrate the advantages of multiscale super-resolution, and implications of these results for common imaging systems are discussed. --- ### Quotient-Space Diffusion Models Authors: Yixian Xu, Yusong Wang, Shengjie Luo, Kaiyuan Gao, Tianyu He, Di He, Chang Liu Published: 2026-04-23 Categories: cs.LG, cs.AI, q-bio.QM, stat.ML arXiv: https://arxiv.org/abs/2604.21809v2 Diffusion-based generative models have reformed generative AI, and also enabled new capabilities in the science domain, e.g., fast generation of 3D structures of molecules. In such tasks, there is often a symmetry in the system, identifying elements that can be converted by certain transformations as equivalent. Equivariant diffusion models guarantee a symmetric distribution, but miss the opportunity to make learning easier, while alignment-based simplification attempts fail to preserve the target distribution. In this work, we develop quotient-space diffusion models, a principled generative framework to fully handle and leverage symmetry. By viewing the intrinsic generation process on the quotient space, the exact construction that removes symmetry redundancy, the framework simplifies learning by allowing model output to have an arbitrary intra-equivalence-class movement, while generating the correct symmetric target distribution with guarantee. We instantiate the framework for molecular structure generation which follows $\mathrm{SE}(3)$ (rigid-body movement) symmetry. It improves the performance over equivariant diffusion models and outperforms alignment-based methods universally for small molecules and proteins, representing a new framework that surpasses previous symmetry treatments in generative models. --- ### TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval Authors: Zixu Li, Yupeng Hu, Zhiheng Fu, Zhiwei Chen, Yongqi Li, Liqiang Nie Published: 2026-04-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.21806v2 Composed Image Retrieval (CIR) is an important image retrieval paradigm that enables users to retrieve a target image using a multimodal query that consists of a reference image and modification text. Although research on CIR has made significant progress, prevailing setups still rely simple modification texts that typically cover only a limited range of salient changes, which induces two limitations highly relevant to practical applications, namely Insufficient Entity Coverage and Clause-Entity Misalignment. In order to address these issues and bring CIR closer to real-world use, we construct two instruction-rich multi-modification datasets, M-FashionIQ and M-CIRR. In addition, we propose TEMA, the Text-oriented Entity Mapping Architecture, which is the first CIR framework designed for multi-modification while also accommodating simple modifications. Extensive experiments on four benchmark datasets demonstrate that TEMA's superiority in both original and multi-modification scenarios, while maintaining an optimal balance between retrieval accuracy and computational efficiency. Our codes and constructed multi-modification dataset (M-FashionIQ and M-CIRR) are available at https://github.com/lee-zixu/ACL26-TEMA/. --- ### SyMTRS: Benchmark Multi-Task Synthetic Dataset for Depth, Domain Adaptation and Super-Resolution in Aerial Imagery Authors: Safouane El Ghazouali, Nicola Venturi, Michael Rueegsegger, Umberto Michelucci Published: 2026-04-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.21801v1 Recent advances in deep learning for remote sensing rely heavily on large annotated datasets, yet acquiring high-quality ground truth for geometric, radiometric, and multi-domain tasks remains costly and often infeasible. In particular, the lack of accurate depth annotations, controlled illumination variations, and multi-scale paired imagery limits progress in monocular depth estimation, domain adaptation, and super-resolution for aerial scenes. We present SyMTRS, a large-scale synthetic dataset generated using a high-fidelity urban simulation pipeline. The dataset provides high-resolution RGB aerial imagery (2048 x 2048), pixel-perfect depth maps, night-time counterparts for domain adaptation, and aligned low-resolution variants for super-resolution at x2, x4, and x8 scales. Unlike existing remote sensing datasets that focus on a single task or modality, SyMTRS is designed as a unified multi-task benchmark enabling joint research in geometric understanding, cross-domain robustness, and resolution enhancement. We describe the dataset generation process, its statistical properties, and its positioning relative to existing benchmarks. SyMTRS aims to bridge critical gaps in remote sensing research by enabling controlled experiments with perfect geometric ground truth and consistent multi-domain supervision. The results obtained in this work can be reproduced from this Github repository: https://github.com/safouaneelg/SyMTRS. --- ### An effective variant of the Hartigan $k$-means algorithm Authors: François Clément, Stefan Steinerberger Published: 2026-04-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.21798v1 The k-means problem is perhaps the classical clustering problem and often synonymous with Lloyd's algorithm (1957). It has become clear that Hartigan's algorithm (1975) gives better results in almost all cases, Telgarsky-Vattani note a typical improvement of $5\%$ -- $10\%$. We point out that a very minor variation of Hartigan's method leads to another $2\%$ -- $5\%$ improvement; the improvement tends to become larger when either dimension or $k$ increase. --- ### Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems Authors: Ye Yu, Heming Liu, Haibo Jin, Xiaopeng Yuan, Peng Kuang, Haohan Wang Published: 2026-04-23 Categories: cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2604.21794v1 Multi-agent systems built on large language models have shown strong performance on complex reasoning tasks, yet most work focuses on agent roles and orchestration while treating inter-agent communication as a fixed interface. Latent communication through internal representations such as key-value caches offers a promising alternative to text-based protocols, but existing approaches do not jointly optimize communication with multi-agent reasoning. Therefore we propose DiffMAS, a training framework that treats latent communication as a learnable component of multi-agent systems. DiffMAS performs parameter-efficient supervised training over multi-agent latent trajectories, enabling agents to jointly learn how information should be encoded and interpreted across interactions. Experiments on mathematical reasoning, scientific QA, code generation, and commonsense benchmarks show that DiffMAS consistently improves reasoning accuracy and decoding stability over single-agent inference, text-based multi-agent systems, and prior latent communication methods, achieving 26.7% on AIME24, 20.2% on GPQA-Diamond, and consistent gains across reasoning benchmarks. --- ### Inferring High-Level Events from Timestamped Data: Complexity and Medical Applications Authors: Yvon K. Awuklu, Meghyn Bienvenu, Katsumi Inoue, Vianney Jouhet, Fleur Mougin Published: 2026-04-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.21793v1 In this paper, we develop a novel logic-based approach to detecting high-level temporally extended events from timestamped data and background knowledge. Our framework employs logical rules to capture existence and termination conditions for simple temporal events and to combine these into meta-events. In the medical domain, for example, disease episodes and therapies are inferred from timestamped clinical observations, such as diagnoses and drug administrations stored in patient records, and can be further combined into higher-level disease events. As some incorrect events might be inferred, we use constraints to identify incompatible combinations of events and propose a repair mechanism to select preferred consistent sets of events. While reasoning in the full framework is intractable, we identify relevant restrictions that ensure polynomial-time data complexity. Our prototype system implements core components of the approach using answer set programming. An evaluation on a lung cancer use case supports the interest of the approach, both in terms of computational feasibility and positive alignment of our results with medical expert opinions. While strongly motivated by the needs of the healthcare domain, our framework is purposely generic, enabling its reuse in other areas. --- ### Mechanism Design for Decentralized Risk Detection: Strict Propriety, Network Coalitions, and the Backfiring Mandat Authors: Jian Ni, Lecheng Zheng, John R Birge Published: 2026-04-23 Categories: cs.GT, cs.LG arXiv: https://arxiv.org/abs/2604.21789v4 Competing firms that share a population of risky customers face a decentralized risk detection problem in which each firm holds fragmentary information whose aggregation would generate social value, but private incentives impede truthful sharing. We develop a dynamic mechanism design framework for this setting and identify three strategic frictions that distinguish it from classical mechanism design with decentralized information: compliance moral hazard, adversarial adaptation, and information destruction through intervention. A temporal value assignment (TVA) mechanism credits firms using a strictly proper scoring rule applied to discounted verified outcomes; under stated assumptions, TVA implements truthful posterior reporting as a Bayes--Nash equilibrium (uniquely optimal at each edge in large federations, with $O(1/m)$ shading in finite systems). A network Shapley characterization shows that under edge-additive coalition value, each firm's marginal contribution is proportional to its weighted cross-firm interaction degree, yielding a sharp prescription for coalition design that prioritizes inter-firm volume over firm size. Embedding TVA in a model of competition among firms, we establish a welfare ordering across four regulatory regimes (autarky, voluntary federation, mandated full sharing, TVA) and identify conditions under which information-sharing mandates without compatible incentive design reduce welfare below autarky: a ``backfiring mandate.'' We illustrate the framework on a 1.4M-transaction synthetic anti-money-laundering benchmark; the same machinery extends to platform fraud, cybersecurity threat intelligence, and supply chain risk detection. --- ### From Codebooks to VLMs: Evaluating Automated Visual Discourse Analysis for Climate Change on Social Media Authors: Katharina Prasse, Steffen Jung, Isaac Bravo, Stefanie Walter, Patrick Knab, Christian Bartelt, Margret Keuper Published: 2026-04-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.21786v1 Social media platforms have become primary arenas for climate communication, generating millions of images and posts that - if systematically analysed - can reveal which communication strategies mobilise public concern and which fall flat. We aim to facilitate such research by analysing how computer vision methods can be used for social media discourse analysis. This analysis includes application-based taxonomy design, model selection, prompt engineering, and validation. We benchmark six promptable vision-language models and 15 zero-shot CLIP-like models on two datasets from X (formerly Twitter) - a 1,038-image expert-annotated set and a larger corpus of over 1.2 million images, with 50,000 labels manually validated - spanning five annotation dimensions: animal content, climate change consequences, climate action, image setting, and image type. Among the models benchmarked, Gemini-3.1-flash-lite outperforms all others across all super-categories and both datasets, while the gap to open-weight models of moderate size remains relatively small. Beyond instance-level metrics, we advocate for distributional evaluation: VLM predictions can reliably recover population level trends even when per-image accuracy is moderate, making them a viable starting point for discourse analysis at scale. We find that chain-of-thought reasoning reduces rather than improves performance, and that annotation dimension specific prompt design improves performance. We release tweet IDs and labels along with our code at https://github.com/KathPra/Codebooks2VLMs.git. --- ### SemEval-2026 Task 4: Narrative Story Similarity and Narrative Representation Learning Authors: Hans Ole Hatzel, Ekaterina Artemova, Haimo Paul Stiemer, Evelyn Gius, Chris Biemann Published: 2026-04-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.21782v1 We present the shared task on narrative similarity and narrative representation learning - NSNRL (pronounced "nass-na-rel"). The task operationalizes narrative similarity as a binary classification problem: determining which of two stories is more similar to an anchor story. We introduce a novel definition of narrative similarity, compatible with both narrative theory and intuitive judgment. Based on the similarity judgments collected under this concept, we also evaluate narrative embedding representations. We collected at least two annotations each for more than 1,000 story summary triples, with each annotation being backed by at least two annotators in agreement. This paper describes the sampling and annotation process for the dataset; further, we give an overview of the submitted systems and the techniques they employ. We received a total of 71 final submissions from 46 teams across our two tracks. In our triple-based classification setup, LLM ensembles make up many of the top-scoring systems, while in the embedding setup, systems with pre- and post-processing on pretrained embedding models perform about on par with custom fine-tuned solutions. Our analysis identifies potential headroom for improvement of automated systems in both tracks. The task website includes visualizations of embeddings alongside instance-level classification results for all teams. --- ### Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshooting Authors: Avinash Paliwal, Adithya Iyer, Shivin Yadav, Muhammad Ali Afridi, Midhun Harikumar Published: 2026-04-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.21776v2 Precise camera control for reshooting dynamic videos is bottlenecked by the severe scarcity of paired multi-view data for non-rigid scenes. We overcome this limitation with a highly scalable self-supervised framework capable of leveraging internet-scale monocular videos. Our core contribution is the generation of pseudo multi-view training triplets, consisting of a source video, a geometric anchor, and a target video. We achieve this by extracting distinct smooth random-walk crop trajectories from a single input video to serve as the source and target views. The anchor is synthetically generated by forward-warping the first frame of the source with a dense tracking field, which effectively simulates the distorted point-cloud inputs expected at inference. Because our independent cropping strategy introduces spatial misalignment and artificial occlusions, the model cannot simply copy information from the current source frame. Instead, it is forced to implicitly learn 4D spatiotemporal structures by actively routing and re-projecting missing high-fidelity textures across distinct times and viewpoints from the source video to reconstruct the target. At inference, our minimally adapted diffusion transformer utilizes a 4D point-cloud derived anchor to achieve state-of-the-art temporal consistency, robust camera control, and high-fidelity novel view synthesis on complex dynamic scenes. --- ### Back to Source: Open-Set Continual Test-Time Adaptation via Domain Compensation Authors: Yingkai Yang, Chaoqi Chen, Hui Huang Published: 2026-04-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.21772v1 Test-Time Adaptation (TTA) aims to mitigate distributional shifts between training and test domains during inference time. However, existing TTA methods fall short in the realistic scenario where models face both continually changing domains and the simultaneous emergence of unknown semantic classes, a challenging setting we term Open-set Continual Test-Time Adaptation (OCTTA). The coupling of domain and semantic shifts often collapses the feature space, severely degrading both classification and out-of-distribution detection. To tackle this, we propose DOmain COmpensation (DOCO), a lightweight and effective framework that robustly performs domain adaptation and OOD detection in a synergistic, closed loop. DOCO first performs dynamic, adaptation-conditioned sample splitting to separate likely ID from OOD samples. Then, using only the ID samples, it learns a domain compensation prompt by aligning feature statistics with the source domain, guided by a structural preservation regularizer that prevents semantic distortion. This learned prompt is then propagated to the OOD samples within the same batch, effectively isolating their semantic novelty for more reliable detection. Extensive experiments on multiple challenging benchmarks demonstrate that DOCO outperforms prior CTTA and OSTTA methods, establishing a new state-of-the-art for the demanding OCTTA setting. --- ### Who Defines "Best"? Towards Interactive, User-Defined Evaluation of LLM Leaderboards Authors: Minji Jung, Minjae Lee, Yejin Kim, Sarang Choi, Minsuk Kahng Published: 2026-04-23 Categories: cs.AI, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2604.21769v1 LLM leaderboards are widely used to compare models and guide deployment decisions. However, leaderboard rankings are shaped by evaluation priorities set by benchmark designers, rather than by the diverse goals and constraints of actual users and organizations. A single aggregate score often obscures how models behave across different prompt types and compositions. In this work, we conduct an in-depth analysis of the dataset used in the LMArena (formerly Chatbot Arena) benchmark and investigate this evaluation challenge by designing an interactive visualization interface as a design probe. Our analysis reveals that the dataset is heavily skewed toward certain topics, that model rankings vary across prompt slices, and that preference-based judgments are used in ways that blur their intended scope. Building on this analysis, we introduce a visualization interface that allows users to define their own evaluation priorities by selecting and weighting prompt slices and to explore how rankings change accordingly. A qualitative study suggests that this interactive approach improves transparency and supports more context-specific model evaluation, pointing toward alternative ways to design and use LLM leaderboards. --- ### Misinformation Span Detection in Videos via Audio Transcripts Authors: Breno Matos, Rennan C. Lima, Savvas Zannettou, Fabricio Benevenuto, Rodrygo L. T. Santos Published: 2026-04-23 Categories: cs.CL, cs.SI arXiv: https://arxiv.org/abs/2604.21767v1 Online misinformation is one of the most challenging issues lately, yielding severe consequences, including political polarization, attacks on democracy, and public health risks. Misinformation manifests in any platform with a large user base, including online social networks and messaging apps. It permeates all media and content forms, including images, text, audio, and video. Distinctly, video-based misinformation represents a multifaceted challenge for fact-checkers, given the ease with which individuals can record and upload videos on various video-sharing platforms. Previous research efforts investigated detecting video-based misinformation, focusing on whether a video shares misinformation or not on a video level. While this approach is useful, it only provides a limited and non-easily interpretable view of the problem given that it does not provide an additional context of when misinformation occurs within videos and what content (i.e., claims) are responsible for the video's misinformation nature. In this work, we attempt to bridge this research gap by creating two novel datasets that allow us to explore misinformation detection on videos via audio transcripts, focusing on identifying the span of videos that are responsible for the video's misinformation claim (misinformation span detection). We present two new datasets for this task. We transcribe each video's audio to text, identifying the video segment in which the misinformation claims appears, resulting in two datasets of more than 500 videos with over 2,400 segments containing annotated fact-checked claims. Then, we employ classifiers built with state-of-the-art language models, and our results show that we can identify in which part of a video there is misinformation with an F1 score of 0.68. We make publicly available our annotated datasets. We also release all transcripts, audio and videos. --- ### AUDITA: A New Dataset to Audit Humans vs. AI Skill at Audio QA Authors: Tasnim Kabir, Dmytro Kurdydyk, Aadi Palnitkar, Liam Dorn, Ahmed Haj Ahmed, Jordan Lee Boyd-Graber Published: 2026-04-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.21766v1 Existing audio question answering benchmarks largely emphasize sound event classification or caption-grounded queries, often enabling models to succeed through shortcut strategies, short-duration cues, lexical priors, dataset-specific biases, or even bypassing audio via metadata and captions rather than genuine reasoning Thus, we present AUDITA (Audio Understanding from Diverse Internet Trivia Authors), a large-scale, real-world benchmark to rigorously evaluate audio reasoning beyond surface-level acoustic recognition. AUDITA comprises carefully curated, human-authored trivia questions grounded in real-world audio, designed to stress robust auditory reasoning through challenging distractors and long-range temporal dependencies, using probing queries that cannot be answered from isolated text or sound cues alone. Human average accuracy of 32.13% shows both the challenge of the task while demonstrating meaningful comprehension of the audio. In stark contrast, state of-the-art audio question answering models perform poorly, with average accuracy below 8.86%. Beyond raw accuracy, we apply Item Response Theory (IRT) to estimate latent proficiency, question difficulty, and expose systematic deficiencies of the models and data. --- ### PrismaDV: Automated Task-Aware Data Unit Test Generation Authors: Hao Chen, Arnab Phani, Sebastian Schelter Published: 2026-04-23 Categories: cs.LG, cs.SE arXiv: https://arxiv.org/abs/2604.21765v1 Data is a central resource for modern enterprises, and data validation is essential for ensuring the reliability of downstream applications. However, existing automated data unit testing frameworks are largely task-agnostic: they validate datasets without considering the semantics and requirements of the code that consumes the data. We present PrismaDV, a compound AI system that analyzes downstream task code together with dataset profiles to identify data access patterns, infer implicit data assumptions, and generate task-aware executable data unit tests. To further adapt the data unit tests over time to specific datasets and downstream tasks, we propose "Selective Informative Feedback for Task Adaptation" (SIFTA), a prompt-optimization framework that leverages the scarce outcomes from the execution of data unit tests and downstream tasks. We evaluate PrismaDV on two new benchmarks spanning 60 tasks across five datasets, where it consistently outperforms both task-agnostic and task-aware baselines in generating unit tests that reflect the end-to-end impact of data errors. Furthermore, we show that with SIFTA, we can automatically learn prompts for PrismaDV's modules that outperform prompts written by hand or generated from a generic prompt optimizer. We publicly release our benchmarks and prototype implementation. --- ### Thinking with Reasoning Skills: Fewer Tokens, More Accuracy Authors: Guangxiang Zhao, Qilong Shi, Xusen Xiao, Xiangzheng Zhang, Tong Yang, Lin Sun Published: 2026-04-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.21764v2 Reasoning LLMs often spend substantial tokens on long intermediate reasoning traces (e.g., chain-of-thought) when solving new problems. We propose to summarize and store reusable reasoning skills distilled from extensive deliberation and trial-and-error exploration, and to retrieve these skills at inference time to guide future reasoning. Unlike the prevailing \emph{reasoning from scratch} paradigm, our approach first recalls relevant skills for each query, helping the model avoid redundant detours and focus on effective solution paths. We evaluate our method on coding and mathematical reasoning tasks, and find that it significantly reduces reasoning tokens while improving overall performance. The resulting lower per-request cost indicates strong practical and economic potential for real-world deployment. --- ### Transferable Physics-Informed Representations via Closed-Form Head Adaptation Authors: Jian Cheng Wong, Isaac Yin Chung Lai, Pao-Hsiung Chiu, Chin Chun Ooi, Abhishek Gupta, Yew-Soon Ong Published: 2026-04-23 Categories: cs.LG, cs.CE, physics.comp-ph arXiv: https://arxiv.org/abs/2604.21761v1 Physics-informed neural networks (PINNs) have garnered significant interest for their potential in solving partial differential equations (PDEs) that govern a wide range of physical phenomena. By incorporating physical laws into the learning process, PINN models have demonstrated the ability to learn physical outcomes reasonably well. However, current PINN approaches struggle to predict or solve new PDEs effectively when there is a lack of training examples, indicating they do not generalize well to unseen problem instances. In this paper, we present a transferable learning approach for PINNs premised on a fast Pseudoinverse PINN framework (Pi-PINN). Pi-PINN learns a transferable physics-informed representation in a shared embedding space and enables rapid solving of both known and unknown PDE instances via closed-form head adaptation using a least-squares-optimal pseudoinverse under PDE constraints. We further investigate the synergies between data-driven multi-task learning loss and physics-informed loss, providing insights into the design of more performant PINNs. We demonstrate the effectiveness of Pi-PINN on various PDE problems, including Poisson's equation, Helmholtz equation, and Burgers' equation, achieving fast and accurate physics-informed solutions without requiring any data for unseen instances. Pi-PINN can produce predictions 100-1000 times faster than a typical PINN, while producing predictions with 10-100 times lower relative error than a typical data-driven model even with only two training samples. Overall, our findings highlight the potential of transferable representations with closed-form head adaptation to enhance the efficiency and generalization of PINNs across PDE families and scientific and engineering applications. --- ### Interpretable facial dynamics as behavioral and perceptual traces of deepfakes Authors: Timothy Joseph Murphy, Jennifer Cook, Hélio Clemente José Cuve Published: 2026-04-23 Categories: cs.CV, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2604.21760v1 Deepfake detection research has largely converged on deep learning approaches that, despite strong benchmark performance, offer limited insight into what distinguishes real from manipulated facial behavior. This study presents an interpretable alternative grounded in bio-behavioral features of facial dynamics and evaluates how computational detection strategies relate to human perceptual judgments. We identify core low-dimensional patterns of facial movement, from which temporal features characterizing spatiotemporal structure were derived. Traditional machine learning classifiers trained on these features achieved modest but significant above-chance deepfake classification, driven by higher-order temporal irregularities that were more pronounced in manipulated than real facial dynamics. Notably, detection was substantially more accurate for videos containing emotive expressions than those without. An emotional valence classification analysis further indicated that emotive signals are systematically degraded in deepfakes, explaining the differential impact of emotive dynamics on detection. Furthermore, we provide an additional and often overlooked dimension of explainability by assessing the relationship between model decisions and human perceptual detection. Model and human judgments converged for emotive but diverged for non-emotive videos, and even where outputs aligned, underlying detection strategies differed. These findings demonstrate that face-swapped deepfakes carry a measurable behavioral fingerprint, most salient during emotional expression. Additionally, model-human comparisons suggest that interpretable computational features and human perception may offer complementary rather than redundant routes to detection. --- ### Neural surrogates for crystal growth dynamics with variable supersaturation: explicit vs. implicit conditioning Authors: Matteo Rigoni, Daniele Lanzoni, Francesco Montalenti, Roberto Bergamaschini Published: 2026-04-23 Categories: cond-mat.mtrl-sci, cond-mat.mes-hall, cs.CE, cs.LG arXiv: https://arxiv.org/abs/2604.21753v1 Simulations of crystal growth are performed by using Convolutional Recurrent Neural Network surrogate models, trained on a dataset of time sequences computed by numerical integration of Allen-Cahn dynamics including faceting via kinetic anisotropy. Two network architectures are developed to take into account the effects of a variable supersaturation value. The first infers it implicitly by processing an input mini-sequence of a few evolution frames and then returns a consistent continuation of the evolution. The second takes the supersaturation parameter as an explicit input along with a single initial frame and predicts the entire sequence. The two models are systematically tested to establish strengths and weaknesses, comparing the prediction performance for models trained on datasets of different size and, in the first architecture, different lengths of input mini-sequence. The analysis of point-wise and mean absolute errors shows how the explicit parameter conditioning guarantees the best results, reproducing with high-fidelity the ground-truth profiles. Comparable results are achievable by the mini-sequence approach only when using larger training datasets. The trained models show strong conditioning by the supersaturation parameter, consistently reproducing its overall impact on growth rates as well as its local effect on the faceted morphology. Moreover, they are perfectly scalable even on 256 times larger domains and can be successfully extended to more than 10 times longer sequences with limited error accumulation. The analysis highlights the potential and limits of these approaches in view of their general exploitation for crystal growth simulations. --- ### Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs Authors: Joseba Fernandez de Landa, Carla Perez-Almendros, Jose Camacho-Collados Published: 2026-04-23 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2604.21751v2 LLMs have limitations when it comes to cultural coverage and competence, and in some cases, show specific cultural biases. Although prior studies have examined the cultural capabilities of LLMs, none have specifically investigated their regional preferences in generic culture-related questions. In this work, we propose a new dataset based on a comprehensive taxonomy of Culture-Related Open Questions (CROQ), with questions available in 24 languages. We evaluate LLMs by prompting them to answer questions from CROQ and provide a sample location. The results show that, contrary to previous cultural bias work, LLMs show a clear tendency towards countries such as Japan in their answers. Moreover, our results show that when prompting in languages such as English or other high-resource ones, LLMs tend to provide more diverse outputs. Low-resource languages, on the other hand, show more inclinations towards answering questions highlighting countries for which the input language is an official language. Finally, we also investigate at which point of LLM training this cultural bias emerges, with our results suggesting that the first clear signs appear after supervised fine-tuning, and not during pre-training. Dataset available at https://huggingface.co/datasets/HiTZ/CROQ --- ### Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs Authors: Joseba Fernandez de Landa, Carla Perez-Almendros, Jose Camacho-Collados Published: 2026-04-23 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2604.21751v1 LLMs have been showing limitations when it comes to cultural coverage and competence, and in some cases show regional biases such as amplifying Western and Anglocentric viewpoints. While there have been works analysing the cultural capabilities of LLMs, there has not been specific work on highlighting LLM regional preferences when it comes to cultural-related questions. In this work, we propose a new dataset based on a comprehensive taxonomy of Culture-Related Open Questions (CROQ). The results show that, contrary to previous cultural bias work, LLMs show a clear tendency towards countries such as Japan. Moveover, our results show that when prompting in languages such as English or other high-resource ones, LLMs tend to provide more diverse outputs and show less inclinations towards answering questions highlighting countries for which the input language is an official language. Finally, we also investigate at which point of LLM training this cultural bias emerges, with our results suggesting that the first clear signs appear after supervised fine-tuning, and not during pre-training. --- ### StructMem: Structured Memory for Long-Horizon Behavior in LLMs Authors: Buqiang Xu, Yijun Chen, Jizhan Fang, Ruobin Zhong, Yunzhi Yao, Yuqi Zhu, Lun Du, Shumin Deng Published: 2026-04-23 Categories: cs.CL, cs.AI, cs.IR, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2604.21748v1 Long-term conversational agents need memory systems that capture relationships between events, not merely isolated facts, to support temporal reasoning and multi-hop question answering. Current approaches face a fundamental trade-off: flat memory is efficient but fails to model relational structure, while graph-based memory enables structured reasoning at the cost of expensive and fragile construction. To address these issues, we propose \textbf{StructMem}, a structure-enriched hierarchical memory framework that preserves event-level bindings and induces cross-event connections. By temporally anchoring dual perspectives and performing periodic semantic consolidation, StructMem improves temporal reasoning and multi-hop performance on \texttt{LoCoMo}, while substantially reducing token usage, API calls, and runtime compared to prior memory systems, see https://github.com/zjunlp/LightMem . ---