# Research Papers — 2026-04 · bundle page 20 of 233 > Full-text markdown of papers #951–1000 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/20 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/19.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/21.md) ### NeuralEmu: in situ Measurement-Driven, ML-based, High-Fidelity 5G Network Emulation Authors: Haoran Wan, Yaxiong Xie, Kyle Jamieson Published: 2026-04-28 Categories: cs.NI, cs.LG arXiv: https://arxiv.org/abs/2604.26080v1 Current and future applications demand ultra-low latency and consistent throughput, yet frequently traverse 5G cellular networks, so cope with volatile packet dynamics, as 5G base station schedulers dynamically react to user workloads and wireless channel conditions. The task of evaluating network algorithms in these environments is hamstrung by current tools: record-and-replay emulators sever the feedback interaction that exists between application end points and a commercial operator's proprietary 5G scheduler, while full-stack simulators rely on overly simplistic scheduling logic. To bridge this reality gap, we present NeuralEmu, a high-fidelity, machine learning-based emulation framework that learns complex 5G scheduler resource allocation behaviors directly from extremely high-resolution network telemetry tools. The first emulator to handle multiple clients, NeuralEmu utilizes machine learning to dynamically predict resource block allocations and modulation schemes based on instantaneous user buffer occupancy and channel states. To capture realistic cross-user contention, a traffic reconstruction model inverts cellular network scheduling results to recover the underlying traffic patterns of uncontrolled background users. Implemented as an high-performance Linux middlebox emulator, NeuralEmu reduces emulation error relative to the state of the art for various network applications including but not limited to 55% for web-page load time, 57% for WebRTC encoder bit rate, and 51% for cloud gaming packet one-way delay, providing an accurate, standardized testing ground for tomorrow's real-time interactive network protocols and applications. --- ### PPG-Based Affect Recognition with Long-Range Deep Models: A Measurement-Driven Comparison of CNN, Transformer, and Mamba Architectures Authors: Karim Alghoul, Hussein Al Osman, Abdulmotaleb El Saddik Published: 2026-04-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.26078v1 Photoplethysmography (PPG) is increasingly used in wearable affective computing due to its low cost and ease of integration into consumer devices. Recent advances in deep learning have introduced long-range sequence models, such as Transformers, and state-space models, like Mamba, which have demonstrated strong performance on natural language and general time-series tasks. However, it remains unclear whether these architectures offer tangible benefits over widely used Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTMs) for PPG-based affect recognition, given that datasets are typically small and noisy. This work presents a measurement-driven comparison of four deep learning architectures, CNN, CNN-LSTM hybrid, Transformers, and Mamba, for classifying arousal, valence, and relaxation states from wrist-based PPG signals. All models are evaluated under a subject-independent 5-fold cross-validation protocol using identical preprocessing, segmentation, and training pipelines. Our results show that the Transformer and Mamba models achieve performance comparable to that of a CNN baseline, but do not consistently outperform it across all tasks. CNNs remain the most effective overall, providing the highest accuracy with the smallest model size, whereas Transformers have a better balance of F1 scores for Arousal and Relaxation. The study provides the first evaluation of Transformer and Mamba models for PPG-based affect recognition, offering practical guidance on model selection for wearable affective monitoring systems. --- ### Privacy-Preserving Federated Learning Framework for Distributed Chemical Process Optimization Authors: Teetat Pipattaratonchai, Aueaphum Aueawatthanaphisut Published: 2026-04-28 Categories: cs.LG, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2604.26073v1 Industrial chemical plants often operate under strict data confidentiality constraints, making centralized data-driven process modeling difficult. Federated learning (FL) provides a promising solution by enabling collaborative model training across distributed facilities without sharing raw operational data. This paper proposes a privacy-preserving federated learning framework for distributed chemical process optimization using data collected from multiple geographically separated plants. Each plant locally trains a neural-network-based process model using its own time-series sensor data, while only model parameters are transmitted to a central aggregation server through secure aggregation mechanisms. This design allows cross-plant knowledge sharing while maintaining strict data locality and industrial confidentiality. Experimental evaluation was conducted using process datasets from three independent chemical plants operating under heterogeneous conditions. The results demonstrate rapid convergence of the federated model, with the global mean squared error decreasing from approximately 2369 to below 50 within the first five communication rounds and stabilizing around 35 after 40 rounds. In comparison with local-only training, the proposed federated framework significantly improves prediction accuracy across all plants, while achieving performance comparable to centralized training. The findings indicate that federated learning provides an effective and scalable solution for collaborative industrial analytics, enabling privacy-preserving predictive modeling and process optimization across distributed chemical production facilities. --- ### Observable Neural ODEs for Identifiable Causal Forecasting in Continuous Time Authors: Jennifer Wendland, Nicolas Freitag, Maik Kschischo Published: 2026-04-28 Categories: cs.LG, math.OC, math.ST, q-bio.QM arXiv: https://arxiv.org/abs/2604.26070v2 Causal inference in continuous-time sequential decision problems is challenged by hidden confounders. We show that, in latent state-space models with time-varying interventions, observability of the latent dynamics from observed data is necessary for identifying dynamic treatment effects, linking control-theoretic observability to causal identifiability, even when hidden confounders affect both treatments and outcomes. We derive a continuous-time adjustment formula expressing potential outcome distributions under treatment trajectories via the measurement model, latent dynamics, and the filtering distribution over latent states given observed histories. We propose Observable Neural ODEs (ObsNODEs), Neural ODE models in observable normal form for causal forecasting. ObsNODEs learn continuous-time dynamics with states reconstructible from observations, enabling outcome prediction under alternative treatment paths. Experiments on synthetic cancer data, semi-synthetic data based on MIMIC-IV, and real-world sepsis data show strong performance over recent sequence models. --- ### RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments Authors: Zaid Nasser, Mikhail Iumanov, Tianhao Li, Maxim Popov, Jaafar Mahmoud, Sergey Kolyubin Published: 2026-04-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.26067v1 We present RADIO-ViPE (Reduce All Domains Into One -- Video Pose Engine), an online semantic SLAM system that enables geometry-aware open-vocabulary grounding, associating arbitrary natural language queries with localized 3D regions and objects in dynamic environments. Unlike existing approaches that require calibrated, posed RGB-D input, RADIO-ViPE operates directly on raw monocular RGB video streams, requiring no prior camera intrinsics, depth sensors, or pose initialization. The system tightly couples multi-modal embeddings -- spanning vision and language -- derived from agglomerative foundation models (e.g., RADIO) with geometric scene information. This coupling takes place in initialization, optimization and factor graph connections to improve the consistency of the map from multiple modalities. The optimization is wrapped within adaptive robust kernels, designed to handle both actively moving objects and agent-displaced scene elements (e.g., furniture rearranged during ego-centric session). Experiments demonstrate that RADIO-ViPE achieves state-of-the-art results on the dynamic TUM-RGBD benchmark while maintaining competitive performance against offline open-vocabulary methods that rely on calibrated data and static scene assumptions. RADIO-ViPE bridges a critical gap in real-world deployment, enabling robust open-vocabulary semantic grounding for autonomous robotics and unconstrained in-the-wild video streams. Project page: https://be2rlab.github.io/radio_vipe --- ### Incremental Strongly Connected Components with Predictions Authors: Ronald Deng, Samuel McCauley, Aidin Niaparast, Helia Niaparast, Bennett Ptak, Shirel Quintanilla, Shikha Singh, Nathan Vosburg Published: 2026-04-28 Categories: cs.DS, cs.LG arXiv: https://arxiv.org/abs/2604.26062v1 Algorithms with predictions is a growing area that aims to leverage machine-learned predictions to design faster beyond-worst-case algorithms. In this paper, we use this framework to design a learned data structure for the incremental strongly connected components (SCC) problem. In this problem, the $n$ vertices of a graph are known a priori and the $m$ directed edges arrive over time. The goal is to efficiently maintain the strongly connected components of the graph after each insert. Our algorithm receives a possibly erroneous prediction of the edge sequence and uses it to precompute partial solutions to support fast inserts. We show that our algorithm achieves nearly optimal bounds with good predictions and its performance smoothly degrades with the prediction error. We also implement our data structure and perform experiments on real datasets. Our empirical results show that the theory is predictive of practical runtime improvements. --- ### Similarity Choice and Negative Scaling in Supervised Contrastive Learning for Deepfake Audio Detection Authors: Jaskirat Sudan, Hashim Ali, Surya Subramani, Hafiz Malik Published: 2026-04-28 Categories: eess.AS, cs.LG arXiv: https://arxiv.org/abs/2604.26057v1 Supervised contrastive learning (SupCon) is widely used to shape representations, but has seen limited targeted study for audio deepfake detection. Existing work typically combines contrastive terms with broader pipelines; however, the focus on SupCon itself is missing. In this work, we run a controlled study on wav2vec2 XLS-R (300M) that varies (i) similarity in SupCon (cosine vs angular similarity derived from the hyperspherical angle) and (ii) negative scaling using a warm-started global cross-batch queue. Stage 1 fine-tunes the encoder and projection head with SupCon; Stage 2 freezes them and trains a linear classifier with BCE. Trained on ASVspoof 2019 LA and evaluated on ASV19 eval plus ITW and ASVspoof 2021 DF/LA, Cosine SupCon with a delayed queue achieves the best ITW EER (8.29%) and pooled EER (4.44), while angular similarity performs strongly without queued negatives (ITW 8.70), indicating reduced reliance on large negative sets. --- ### From Prompt Risk to Response Risk: Paired Analysis of Safety Behavior of Large Language Models Authors: Mengya Hu, Qiong Wei, Sandeep Atluri Published: 2026-04-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.26052v4 Safety evaluations of large language models (LLMs) typically report binary outcomes, i.e. attack success rate (ASR), refusal rate, or harmful versus safe classification, which hide how risk changes between prompt and response. We present a paired analysis over human labeled prompt and response records across four harm categories (Sexual, Self harm, Hate and Violence) and ordinal severity levels (Safe, Low, Medium, High). 61% of responses reduce harm relative to the prompt, 36% preserve severity, and 3% escalate. The escalation splits into two mechanisms: benign prompts triggering unrequested harmful detail, and answers that stay on task at higher severity than the prompt. Category decomposition shows that Sexual content exhibits the highest harm persistence in this sample, driven by compliance at the same severity rather than drift from benign inputs. Joint relevance analysis exposes a helpfulness versus harmlessness tradeoff: compliance escalations remain highly relevant, whereas safe responses include generic refusals with low relevance. A public supporting evaluation over 600 prompts and six models reproduces the framework's measurements and two directional signals, while few-shot LLM graders exhibit a prompt/response detection asymmetry that data calibration does not close. Grader prompts, public-evaluation artifacts, and analysis code are shared at https://github.com/microsoft/PairedSafety. --- ### Evaluating the Alignment Between GeoAI Explanations and Domain Knowledge in Satellite-Based Flood Mapping Authors: Hyunho Lee, Wenwen Li Published: 2026-04-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.26051v2 The increasing number of satellites has improved the temporal resolution of Earth observation, making satellite-based flood mapping a promising approach for operational flood monitoring. Deep learning-based approaches for flood mapping using satellite imagery, an important application within Geospatial Artificial Intelligence (GeoAI), have shown improved predictive performance by learning complex spatial and spectral patterns from large volumes of remote sensing data. However, the opaque decision-making processes of deep learning models remain a major barrier to their integration into critical scientific and operational workflows. This highlights the need for a systematic assessment of whether model explanations align with established domain knowledge in remote sensing. To address this research gap, this study introduces the ADAGE (Alignment between Domain Knowledge and GeoAI Explanation Evaluation) framework. The proposed framework is designed to systematically evaluate how well explanations of deep learning models align with established remote sensing knowledge, particularly regarding the distinctive spectral properties of the Earth's surface. The ADAGE framework employs Channel-Group SHAP (SHapley Additive exPlanations) method to estimate the contributions of grouped input channels to pixel-level predictions. Experiments on two satellite-based flood mapping tasks demonstrate that the ADAGE framework can (1) quantitatively assess the alignment between model explanations and reference explanations derived from domain knowledge, and (2) help domain experts identify misaligned explanations through the proposed alignment scores. This study contributes to bridging the gap between explainability and domain knowledge in GeoAI for Earth observation, enhancing the applicability of GeoAI models in scientific and operational workflows. --- ### BioGraphletQA: Knowledge-Anchored Generation of Complex QA Datasets Authors: Richard A. A. Jonker, Bárbara Maria Ribeiro de Abreu Martins, Sérgio Matos Published: 2026-04-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.26048v1 This paper presents a principled and scalable framework for systematically generating complex Question Answering (QA) data. In the core of this framework is a graphlet-anchored generation process, where small subgraphs from a Knowledge Graph (KG) are used in a structured prompt to control the complexity and ensure the factual grounding of questions generated by Large Language Models. The first instantiation of this framework is BioGraphletQA, a new biomedical KGQA dataset of 119,856 QA pairs. Each entry is grounded in a graphlet of up to five nodes from the OREGANO KG, with most of the pairs being enriched with relevant document snippets from PubMed. We start by demonstrating the framework's value and the dataset's quality through evaluation by a domain expert on 106 QA pairs, confirming the high scientific validity and complexity of the generated data. Secondly, we establish its practical utility by showing that augmenting downstream benchmarks with our data improves accuracy on PubMedQA from 49.2% to 68.5% in a low-resource setting, and on MedQA from a 41.4% baseline to 44.8% in a full-resource setting. Our framework provides a robust and generalizable solution for creating critical resources to advance complex QA tasks, including MCQA and KGQA. All resources supporting this work, including the dataset (https://zenodo.org/records/17381119) and framework code (https://github.com/ieeta-pt/BioGraphletQA), are publicly available to facilitate use, reproducibility and extension. --- ### RaMP: Runtime-Aware Megakernel Polymorphism for Mixture-of-Experts Authors: Vyom Sharma, Debajyoti Datta Published: 2026-04-28 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2604.26039v1 The optimal kernel configuration for Mixture-of-Experts (MoE) inference depends on both batch size and the expert routing distribution, yet production systems dispatch from batch size alone, leaving 10-70% of kernel throughput unrealized. We present RaMP, a routing-aware dispatch framework. A performance-region analysis derives, from hardware constants alone, when each optimization helps, correctly predicting all 8 tested architectures, including 3 unseen. A four-parameter wave cost model selects the fastest configuration from the runtime expert histogram, achieving 0.93% mean regret versus exhaustive search, fitted from just 10-24 minutes of one-time profiling per model. Because the model depends only on CTA grid geometry, it is kernel-agnostic: applied to Alpha-MoE, it delivers 1.14x with no source modification. Paired with a co-designed CuTe DSL kernel exposing 134-268 polymorphic configurations, RaMP delivers 1.22x kernel speedup over static dispatch and 1.30x end-to-end speedup in vLLM serving over Triton, 1.41x over DeepGEMM, and 1.13x over FlashInfer CUTLASS. --- ### Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding Authors: Chang Liu, Henghui Ding, Nikhila Ravi, Yunchao Wei, Shuting He, Song Bai, Philip Torr, Leilei Cao, Jinrong Zhang, Deshui Miao, Xusheng He, Dengxian Gong et al. Published: 2026-04-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.26031v1 This report summarizes the objectives, datasets, and top-performing methodologies of the 2026 Pixel-level Video Understanding in the Wild (PVUW) Challenge, hosted at CVPR 2026, which evaluates state-of-the-art models under highly unconstrained conditions. To provide a comprehensive assessment, the 2026 edition features three specialized tracks: the MOSE track for tracking objects within densely cluttered and severely occluded scenarios; the MeViS-Text track for localizing targets via motion-focused linguistic expressions; and the newly inaugurated MeViS-Audio track, which pioneers acoustic-driven object segmentation. By introducing previously unreleased challenging data and analyzing the cutting-edge, multimodal solutions submitted by participants, this report highlights the community's latest technical advancements and charts promising future directions for robust video scene comprehension. --- ### Safe, Scalable, and Accurate Bayes Posterior Sampling for Large-Data Generalized Linear Mixed Models Authors: Youngsoo Baek, Samuel I. Berchuck Published: 2026-04-28 Categories: stat.ME, stat.CO, stat.ML arXiv: https://arxiv.org/abs/2604.26029v1 We consider the problem of scalable sampling algorithms to fit Bayesian generalized linear mixed models on large datasets. Stochastic gradient Langevin dynamics, coupled with smooth re-parameterizations of variance parameters, produces divergent Markov chains and cannot be reliably used for sampling covariance parameters of random effects. We advocate the use of a mirror Langevin dynamics algorithm, propose the novel stochastic mirror Langevin dynamics based on data subsampling, and provide concrete guidelines for its use in a Bayesian inference framework. Based on an explicit Wasserstein distance error bound between the posterior and its algorithmic approximation, we propose a post-processing step that yields an asymptotic, order-wise correct estimation of the posterior variance, eliminating the irreducible posterior variance estimation bias due to subsampling. Empirical performance of the method is evaluated through simulated experiments and a longitudinal study of pain trajectories in a study of breast cancer survivors. --- ### Generalized Disguise Makeup Presentation Attack Detection Using an Attention-Guided Patch-Based Framework Authors: Fateme Taraghi, Atefe Aghaei, Mohsen Ebrahimi Moghaddam Published: 2026-04-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.26025v1 Despite significant advances in facial recognition systems, they remain vulnerable to face presentation attacks. Among them, disguise makeup attacks are particularly challenging, as they use advanced cosmetics, prosthetic components, and artificial materials to realistically alter facial appearance, often making detection difficult even for humans. Despite their importance, this problem remains underexplored, and publicly available datasets are limited. To address this, we propose a generalized disguise makeup presentation attack detection framework. The method adopts a two-phase design in which a style-invariant full-face model, trained with metric learning and enhanced by a whitening transformation, extracts region attention scores via Grad-CAM. These scores guide a patch-based phase that performs localized analysis using region-specific subnetworks trained with metric learning for fine-grained discrimination. We also construct a new, diverse dataset of live and disguise makeup faces collected under real-world conditions, covering variations in subjects, environments, and disguise materials. Experimental results demonstrate strong generalization across both the collected dataset and SIW-Mv2, achieving 8.97% ACER and 9.76% EER on the collected dataset, and 0% ACER on Obfuscation and Impersonation and 1.34% on Cosmetics attacks of SIW-Mv2. The proposed method consistently outperforms prior works while maintaining robust performance across other spoof types. --- ### Correcting Performance Estimation Bias in Imbalanced Classification with Minority Subconcepts Authors: Taylor Maxson, Roberto Corizzo, Yaning Wu, Nathalie Japkowicz, Colin Bellinger Published: 2026-04-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.26024v1 Class-level evaluation can conceal substantial performance disparities across subconcepts within the same class, causing models that perform well on average to fail on specific subpopulations. Prior work has shown that common evaluation measures for imbalanced classification are biased toward larger minority subconcepts and that utility-based reweighting using true subconcept labels can mitigate this bias; however, such labels are rarely available at test time. We introduce a practical utility-weighted evaluation that replaces unavailable subconcept labels with predicted posterior probabilities from a multiclass subconcept model. Evaluation weights are defined as the expected utility under this posterior, yielding a soft, uncertainty-aware metric we call predicted-weighted balanced accuracy (pBA). Experiments on tabular benchmarks as well as medical-imaging and text datasets show that unweighted scores can be misleading under within-class heterogeneity, while pBA provides more stable and interpretable assessments when subconcept distributions are uneven but not pathological. Our code is available at: https://anonymous.4open.science/r/correcting-bias-imbalance-9C6C/. --- ### Training Computer Use Agents to Assess the Usability of Graphical User Interfaces Authors: Alice Gao, Weixi Tong, Rishab Vempati, Katharina Reinecke, R. Benjamin Shapiro, Tianyi Zhang, Jason Wu Published: 2026-04-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.26020v1 Usability testing with experts and potential users can assess the effectiveness, efficiency, and user satisfaction of graphical user interfaces (GUIs) but doing so remains a costly and time-intensive process. Prior work has used computer use agents (CUAs) and other generative agents that can simulate user interactions and preference, but we show that agents still struggle to provide accurate usability assessments. In this work, we present a novel machine learning method that operationalizes a computational definition of usability to train CUAs to assess GUI usability by i) prioritizing important interaction flows, ii) executing them through human-like interactions, and iii) predicting a learned numerical usability score. We train a computer use agent, uxCUA, with our algorithm on a large-scale dataset of fully interactive user interfaces (UIs) paired with usability labels and human preferences. We show that uxCUA outperforms larger models in accurate usability assessments and produces realistic critiques of both synthetic and real UIs. More broadly, our work aims to build a principled, data-driven foundation for automated usability assessment in HCI. --- ### QERNEL: a Scalable Large Electron Model Authors: Khachatur Nazaryan, Liang Fu Published: 2026-04-28 Categories: cond-mat.str-el, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.26018v1 We introduce QERNEL, a foundational neural wavefunction that variationally solves families of parameterized many-electron Hamiltonians and captures their ground states throughout parameter space within a single model. QERNEL combines FiLM-based parameter conditioning with scale-efficient architectural elements -- mixture of experts and grouped-query attention, substantially improving expressivity at low computational cost. We apply QERNEL to interacting electrons in semiconductor moiré heterobilayers, training a single weight-shared model for systems of up to 150 electrons. By solving the many-electron Schrödinger equation conditioned on moiré potential depth, QERNEL captures both quantum liquid and crystal states and discovers the sharp phase transition between them, marked by abrupt changes in interaction energy and charge density. Our work establishes a foundation model for moiré quantum materials and a scalable architecture toward a Large Electron Model for solids. --- ### Learning Neural Operator Surrogates for the Black Hole Accretion Code Authors: Matthias Nägele, Cedric Bös, Chester Tan, Christian M. Fromm, Ingo Scholtes, Karl Mannheim Published: 2026-04-28 Categories: astro-ph.HE, cs.LG arXiv: https://arxiv.org/abs/2604.25985v1 General-relativistic magnetohydrodynamic (GR-MHD) simulations are essential for studying black hole accretion, relativistic jets, and magnetic reconnection, yet their computational cost severely limits systematic parameter exploration. We investigate neural operator surrogates for two astrophysically relevant simulation scenarios produced by the Black Hole Accretion Code (\texttt{BHAC}). First, a Physics Informed Fourier Neural Operator (PINO) is trained on the special-relativistic resistive MHD (SRRMHD) evolution of the Orszag-Tang vortex over a range of resistivities spanning the Sweet-Parker and fast reconnection regimes. By embedding the governing equations as an additional loss term evaluated at finer temporal resolution than the available data supervision, the model learns dynamics at time steps where no simulation data is provided, enabling recovery of plasmoid formation that a data-only baseline trained on the same sparse snapshots fails to reproduce. To our knowledge, the present work is the first application of a physics informed neural operator to special relativistic resistive MHD, and the first to investigate the capability of such models to resolve plasmoid formation in SRRMHD. In a second line of investigation, an OFormer-style Transformer Neural Operator is trained on the evolution of spine-sheath relativistic jets created with \texttt{BHAC}, in special-relativistic MHD (SRMHD). The model is directly applied on the adaptive mesh, highlighting the need for linear attention due to long sequences. The neural surrogate model is capable of capturing most of the major details, especially in early predictions. To our knowledge, this constitutes the first application of a neural operator directly on a high resolution adaptive mesh refinement grid in the context of MHD simulations. --- ### Occam's Razor is Only as Sharp as Your ELBO Authors: Ethan Harvey, Michael C. Hughes Published: 2026-04-28 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.25984v1 The marginal likelihood, also known as the evidence, is regarded as a mathematical embodiment of Occam's razor, enabling model selection that avoids overfitting. The evidence lower bound (ELBO) objective from variational inference has also been used for similar purposes. Prior work has shown that restricting the approximate posterior family via a mean-field approximation can lead the ELBO to underfit. In this paper, we show how ELBO-based hyperparameter learning in a simple over-parameterized regression model can also produce overfitting, depending on the assumed rank of the covariance matrix in a Gaussian approximate posterior. Surprisingly, among only the underfit and overfit options, Bayesian model selection via the evidence itself sometimes prefers the overfit version, while the ELBO does not. Bayesian practitioners hoping to scale to large models should be cautious about how reduced-rank assumptions needed for tractability may impact the potential for model selection. --- ### Open Problems in Frontier AI Risk Management Authors: Marta Ziosi, Miro Plueckebaum, Stephen Casper, Henry Papadatos, Ze Shen Chin, Peter Slattery, James Gealy, Tim G. J. Rudner, Brian Tse, Ariel Gil, Patricia Paskov, Maximilian Negele et al. Published: 2026-04-28 Categories: cs.LG, cs.AI, cs.CY, cs.ET arXiv: https://arxiv.org/abs/2604.25982v1 Frontier AI both amplifies existing risks and introduces qualitatively novel challenges. Not only is there a notable lack of stable scientific consensus resulting from the rapid pace of technological change, but emerging frontier AI safety practices are often misaligned with, or may undermine, established risk management frameworks. To address these challenges, we systematically surface open problems in frontier AI risk management. Adopting a problem-oriented approach, we examine each stage of the risk management process - risk planning, identification, analysis, evaluation, and mitigation - through a structured review of the literature, identifying unresolved challenges and the actors best positioned to address them. Recognising that different types of open problems call for different responses, we classify open problems according to whether they reflect (a) a lack of scientific or technical consensus, (b) misalignment with, or challenges to, established risk management frameworks, or (c) shortcomings in implementation despite apparent consensus and alignment. By mapping these open problems and identifying the actors best positioned to address them - including developers, deployers, regulators, standards bodies, researchers, and third-party evaluators - this work aims to clarify where progress is needed to enable robust and meaningful consensus on frontier AI risk management.The paper does not propose specific solutions; instead, it provides a problem-oriented, agenda-setting reference document, complemented by a living online repository, intended to support coordination, reduce duplication, and guide future research and governance efforts. --- ### Lightweight Quantum Agent for Edge Systems: Joint PQC and NOMA Resource Allocation Authors: Yongtao Yao, Wenjing Xiao, Miaojiang Chen, Anfeng Liu, Zhiquan Liu, Min Chen, Ahmed Farouk, H. Herbert Song Published: 2026-04-28 Categories: cs.IT, cs.AI arXiv: https://arxiv.org/abs/2604.25980v1 In the context of quantum secure scenarios, existing research on mobile edge devices and intelligent computing and edge (ICE) systems based on the Non-Orthogonal Multiple Access (NOMA) communication model have overlooked the energy consumption overhead of Post-Quantum Cryptography (PQC) modules, and the high complexity of traditional resource allocation algorithms fails to meet the demands of real-time decision-making. To address these challenges, this paper proposes a lightweight agentic AI framework designed for online joint optimization within ICE-enabled mobile devices. The scheme constructs a multi-stage stochastic Mixed Integer Nonlinear Programming (MINLP) model that incorporates static power-consumption constraints for PQC modules. Based on Lyapunov optimization theory, the long-term optimization problem is decoupled, and a linear complexity algorithm is proposed to solve the nonconvex challenges of NOMA power allocation . Simulation results verify that the proposed scheme significantly improves computational throughput while ensuring system queue stability and energy consumption constraints. Compared with traditional Successive Convex Approximation (SCA) algorithms, the complexity is reduced to $\mathcal{O}(N)$, achieving a speedup of approximately 46 times when the number of devices $N=35$, thereby meeting the real-time decision-making requirements in dynamic wireless environments. --- ### A Quantitative Confirmation of the Currier Language Distinction Authors: Christophe Parisel Published: 2026-04-28 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2604.25979v2 We present a unified quantitative analysis of the Currier A/B language distinction in the Voynich Manuscript, proceeding in two stages. First, we confirm that the distinction is genuine: a Beta-Binomial mixture model applied to character-pair substitution ratios across 185 folios, without access to Currier's labels, selects 2 by BIC and predicts held-out folio labels at 89% accuracy. Second, we show that the A/B contrast is not primitive but is a low-resolution projection of a higher-dimensional generative system. Its dominant component is a discrete boolean "switch" set once per folio, governing the vowel following the digraphs ch and sh. A two-state binomial mixture achieves Delta\ AIC = 2,549 over a single-state model and assigns 195 of 197 folios unambiguously. This switch does not operate uniformly: word templates divide into fixed contexts and switchable contexts, with template identity accounting for 92% of variance. --- ### Mini-Batch Class Composition Bias in Link Prediction Authors: Kieran Maguire, Srinandan Dasmahapatra Published: 2026-04-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.25978v1 Prior work on node classification has shown that Graph Neural Networks (GNNs) can learn representations that transfer across graphs, when underlying graph properties are shared. For a fixed graph, one would then expect GNNs trained for link prediction to learn a representation consistent with that learnt for node classification. We show this intuition does not hold in the general case. Instead, we find popular link prediction models can learn a trivial mini-batch dependent heuristic, enabled by batch-normalisation layers, to solve the edge classification task. When correcting for this, we observe increased alignment of the network representation with node-class relevant features, suggesting the network has learnt a graph representation that better aligns with the underlying graph's properties. Our findings suggest that standard link prediction training may be leading us to overestimate link predictors' ability to learn a generalised representation of a graph that is consistent across tasks. --- ### Auditing Marketing Budget Allocation with Hindsight Regret Authors: Nilavra Pathak, Olivier Jeunen, Eric Lambert Published: 2026-04-28 Categories: econ.EM, cs.AI, cs.LG, q-fin.PM arXiv: https://arxiv.org/abs/2604.25977v2 Organizations routinely make strategic budget allocations under operational constraints, but often lack a principled way to assess whether realized allocations were close to the best feasible choices in hindsight. We present a retrospective auditing framework based on hindsight regret, defined as the opportunity cost of the realized allocation relative to a constraint-faithful benchmark under the same budget and stability guardrails. The framework estimates regime-specific spend--response functions from historical logs, computes feasible hindsight allocations via constrained optimization, and propagates uncertainty through Monte Carlo evaluation to produce regret distributions, expected lift, and probability-of-improvement summaries. This separates allocation inefficiency from uncertainty in the estimated response surfaces. Experiments on real marketing allocation logs show that the framework yields interpretable post-hoc diagnostics and reveals a practical trade-off between allocation flexibility and detectability: moderate feasible reallocations often capture most measurable gain, while larger shifts move into weak-support regions with higher uncertainty. The result is a practical method for auditing historical budget decisions when online experimentation is costly or infeasible. --- ### Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective Authors: Jiaming Yang, Chenwei Tang, Liangli Zhen, Jiancheng Lv Published: 2026-04-28 Categories: cs.LG, cs.AI, cs.IT arXiv: https://arxiv.org/abs/2604.25975v2 Key-Value (KV) caching is essential for large language model inference, yet its memory overhead poses a critical bottleneck for long-context generation. Existing eviction policies predominantly rely on empirical heuristics, lacking a rigorous theoretical foundation. This work rethinks KV cache eviction through the lens of the Information Bottleneck principle. Under a linear-Gaussian surrogate of attention, we derive a closed-form mutual information objective that characterizes the effective information capacity of a retained KV cache subset. This formulation reveals that a wide range of existing eviction strategies can be interpreted as different approximations of the same capacity-maximization principle. Guided by this insight, we introduce CapKV, a capacity-aware eviction method that directly targets information preservation via a log-determinant approximation using statistical leverage scores. This approach replaces heuristic selection with a theoretically grounded mechanism that preserves the maximum predictive signal. Extensive experiments across multiple models and long-context benchmarks show that CapKV consistently outperforms prior methods, achieving a better trade-off between memory efficiency and generational fidelity. Our code is available at https://github.com/jiamingyy/CapKV --- ### Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective Authors: Jiaming Yang, Chenwei Tang, Liangli Zhen, Jiancheng Lv Published: 2026-04-28 Categories: cs.LG, cs.AI, cs.IT arXiv: https://arxiv.org/abs/2604.25975v1 Key-value (KV) caching is essential for large language model inference, yet its memory overhead poses a critical bottleneck for long-context generation. Existing eviction policies predominantly rely on empirical heuristics, lacking a rigorous theoretical foundation. This work rethinks KV cache eviction through the lens of the Information Bottleneck principle. Under a linear-Gaussian surrogate of attention, we derive a closed-form mutual information objective that characterizes the effective information capacity of a retained KV cache subset. This formulation reveals that a wide range of existing eviction strategies can be interpreted as different approximations of the same capacity-maximization principle. Guided by this insight, we introduce CapKV, a capacity-aware eviction method that directly targets information preservation via a log-determinant approximation using statistical leverage scores. This approach replaces heuristic selection with a theoretically grounded mechanism that preserves the maximum predictive signal. Extensive experiments across multiple models and long-context benchmarks show that CapKV consistently outperforms prior methods, achieving a better trade-off between memory efficiency and generational fidelity. --- ### A Survey of Multi-Agent Deep Reinforcement Learning with Graph Neural Network-Based Communication Authors: Valentin Cuzin-Rambaud, Laetitia Matignon, Maxime Morge Published: 2026-04-28 Categories: cs.LG, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2604.25972v1 In multi-agent reinforcement learning (MARL), the integration of a communication mechanism, allowing agents to better learn to coordinate their actions and converge on their objectives by sharing information. Based on an interaction graph, a subclass of methods employs graph neural networks (GNNs) to learn the communication, enabling agents to improve their internal representations by enriching them with information exchanged. With growing research, we note a lack of explicit structure and framework to distinguish and classify MARL approaches with communication based on GNNs. Thus, this paper surveys recent works in this field. We propose a generalized GNN-based communication process with the goal of making the underlying concepts behind the methods more obvious and accessible. --- ### Mining Negative Sequential Patterns to Improve Viral Genomic Feature Representation and Classification Authors: Wenxi Zhu, Wensheng Gan, Zhenlian Qi Published: 2026-04-28 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2604.25968v1 Viruses represent the most abundant biological entities on Earth and play a pivotal role in microbial ecosystems, yet, as prominent human pathogens, they are closely linked to human morbidity and mortality. Accurate identification of viral sequences from viral genome sequences is therefore essential, but existing genome-based classification models that largely relying on composition- or frequency-based subsequence features often suffer from limited interpretability and reduced accuracy, particularly on complex or imbalanced datasets. To address these limitations, we propose GeneNSPCla (Genomic Negative Sequential Pattern-based Classification), a novel viral classification framework based on Negative Sequential Patterns (NSPs) that extracts discriminative absence-based features from nucleotide sequences of RNA viral genomes. By transforming these NSPs into numerical feature vectors and integrating them into multiple supervised classifiers, GeneNSPCla effectively captures both presence and absence signals in viral sequences. Furthermore, we propose a negative pattern mining algorithm adapted for processing genomic data: GONPM+, which can discover longer and more biologically meaningful negative sequential patterns. The experimental results demonstrate that the average accuracy of GONPM+ in 8 classifiers has improved by 10.03% compared to the original negative pattern mining algorithm and by 24.75% compared to the positive pattern mining algorithm. These findings highlight the effectiveness of incorporating absence-based sequential information, providing a new and complementary perspective for viral genome analysis and classification. --- ### Adversarial Robustness of NTK Neural Networks Authors: Yuxuan Hou Published: 2026-04-28 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.25965v2 Deep learning models are widely deployed in safety-critical domains, but remain vulnerable to adversarial attacks. In this paper, we study the adversarial robustness of NTK neural networks in the context of nonparametric regression. We establish minimax optimal rates for adversarial regression in Sobolev spaces and then show that NTK neural networks, trained via gradient flow with early stopping, can achieve this optimal rate. However, in the overfitting regime, we prove that the minimum norm interpolant is vulnerable to adversarial perturbations. --- ### Recursive Multi-Agent Systems Authors: Jiaru Zou, Rui Pan, Ruizhong Qiu, Pan Lu, Shizhe Diao, Jindong Jiang, Hanghang Tong, Tong Zhang, Markus J. Buehler, Jingrui He, James Zou Published: 2026-04-28 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.25917v2 Recursive or looped language models have recently emerged as a new scaling axis by iteratively refining the same model computation over latent states to deepen reasoning. We extend such scaling principle from a single model to multi-agent systems, and ask: Can agent collaboration itself be scaled through recursion? To this end, we introduce RecursiveMAS, a recursive multi-agent framework that casts the entire system as a unified latent-space recursive computation. RecursiveMAS connects heterogeneous agents as a collaboration loop through the lightweight RecursiveLink module, enabling in-distribution latent thoughts generation and cross-agent latent state transfer. To optimize our framework, we develop an inner-outer loop learning algorithm for iterative whole-system co-optimization through shared gradient-based credit assignment across recursion rounds. Theoretical analyses of runtime complexity and learning dynamics establish that RecursiveMAS is more efficient than standard text-based MAS and maintains stable gradients during recursive training. Empirically, we instantiate RecursiveMAS under 4 representative agent collaboration patterns and evaluate across 9 benchmarks spanning mathematics, science, medicine, search, and code generation. In comparison with advanced single/multi-agent and recursive computation baselines, RecursiveMAS consistently delivers an average accuracy improvement of 8.3%, together with 1.2$\times$-2.4$\times$ end-to-end inference speedup, and 34.6%-75.6% token usage reduction. Code and Data are provided in https://recursivemas.github.io. --- ### DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios Authors: Jinxiang Meng, Shaoping Huang, Fangyu Lei, Jingyu Guo, Haoxiang Liu, Jiahao Su, Sihan Wang, Yao Wang, Enrui Wang, Ye Yang, Hongze Chai, Jinming Lv et al. Published: 2026-04-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.25914v1 Real-world data visualization (DV) requires native environmental grounding, cross-platform evolution, and proactive intent alignment. Yet, existing benchmarks often suffer from code-sandbox confinement, single-language creation-only tasks, and assumption of perfect intent. To bridge these gaps, we introduce DV-World, a benchmark of 260 tasks designed to evaluate DV agents across real-world professional lifecycles. DV-World spans three domains: DV-Sheet for native spreadsheet manipulation including chart and dashboard creation as well as diagnostic repair; DV-Evolution for adapting and restructuring reference visual artifacts to fit new data across diverse programming paradigms and DV-Interact for proactive intent alignment with a user simulator that mimics real-world ambiguous requirements. Our hybrid evaluation framework integrates Table-value Alignment for numerical precision and MLLM-as-a-Judge with rubrics for semantic-visual assessment. Experiments reveal that state-of-the-art models achieve less than 50% overall performance, exposing critical deficits in handling the complex challenges of real-world data visualization. DV-World provides a realistic testbed to steer development toward the versatile expertise required in enterprise workflows. Our data and code are available at \href{https://github.com/DA-Open/DV-World}{this project page}. --- ### How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum Authors: Chu-Cheng Lin, Eugene Ie Published: 2026-04-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.25907v2 SFT-then-RLVR is widely used for post-training reasoning models, but why this specific ordering, and why RLVR-only stalls at cold start, have lacked a unifying theoretical account. We provide that account under a unified loss family $J_Q$ using the Tsallis $q$-logarithm. $J_Q$ is a single-parameter family that interpolates between RLVR (at $q{=}0$, the \textit{exploitation pole}) and the log-marginal-likelihood over latent trajectories (at $q{=}1$, the \textit{density-estimation pole}), under which the standard pipeline corresponds to a stepwise $q{=}1 \to 0$ schedule. All members share the same per-example gradient direction, differing only by a per-instance amplification $P_θ^{-q}$ that reweights each instance independently of the learning rate. Under gradient flow analysis, we show that the exploitation pole requires $Ω(\frac{1}{p_0})$ time to escape cold start but is robust to label noise, while the density-estimation pole escapes in $Θ\big(\log(\frac{1}{p_0})\big)$ but memorizes label noise. This separation explains how SFT ($q{=}1$) first moves the model out of the cold-start regime, followed by the more robust RLVR ($q{=}0$), under the SFT-then-RLVR paradigm. We further derive two Monte Carlo estimators that directly optimize fixed-$q$ on the $J_Q$ continuum, without annotated rationales: Gradient-Amplified RL (GARL) and Posterior-Attenuated Fine-Tuning (PAFT), with shared bias $O\big(\frac{q}{M P_θ^q}\big)$ but different variance and stability properties. On FinQA, HotPotQA, and MuSiQue, GARL at sufficiently high $q$ substantially mitigates cold-start stalling, escaping cold start where GRPO fails entirely. In warm start, GARL at low $q$ dominates FinQA where training is stable; on HotPotQA and MuSiQue, GARL destabilizes and PAFT at $q{=}0.75$ remains stable, reaching $47.9$ \texttt{m@16} on HotPotQA ($+13.9$ over GRPO). --- ### A paradox of AI fluency Authors: Christopher Potts, Moritz Sudhof Published: 2026-04-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.25905v1 How much does a user's skill with AI shape what AI actually delivers for them? This question is critical for users, AI product builders, and society at large, but it remains underexplored. Using a richly annotated sample of 27K transcripts from WildChat-4.8M, we show that fluent users take on more complex tasks than novices and adopt a fundamentally different interactional mode: they iterate collaboratively with the AI, refining goals and critically assessing outputs, whereas novices take a passive stance. These differences lead to a paradox of AI fluency: fluent users experience more failures than novices -- but their failures tend to be visible (a direct consequence of their engagement), they are more likely to lead to partial recovery, and they occur alongside greater success on complex tasks. Novices, by contrast, more often experience invisible failures: conversations that appear to end successfully but in fact miss the mark. Taken together, these results reframe what success with AI depends on. Individuals should adopt a stance of active engagement rather than passive acceptance. AI product builders should recognize that they are designing not just model behavior but user behavior; encouraging deep engagement, rather than friction-free experiences, will lead to more success overall. Our code and data are available at https://github.com/bigspinai/bigspin-fluency-outcomes --- ### Teacher Forcing as Generalized Bayes: Optimization Geometry Mismatch in Switching Surrogates for Chaotic Dynamics Authors: Andre Herz, Daniel Durstewitz, Georgia Koppe Published: 2026-04-28 Categories: cs.LG, math.DS, stat.ML arXiv: https://arxiv.org/abs/2604.25904v1 Identity teacher forcing (ITF) enables stable training of deterministic recurrent surrogates for chaotic dynamical systems and has been highly effective for dynamical systems reconstruction (DSR) with recurrent neural networks (RNNs), including interpretable almost-linear RNNs (AL-RNNs). However, as an intervention-based prediction loss (and thus a generalized Bayes update), teacher forcing need not match the free-running model's marginal likelihood geometry. We compare the objective-induced curvatures of ITF and marginal likelihood in a probabilistic switching augmentation of AL-RNNs, estimating ambiguity-aware observed information via Louis' identity. In the switching setting studied here, conditioning on a single forced regime path (as ITF does) inflates curvature, while marginal likelihood curvature is reduced by a missing-information correction when multiple switching explanations remain plausible. In Lorenz-63 experiments, windowed evidence fine-tuning improves held-out evidence but can degrade dynamical quantities of interest (QoIs) relative to ITF-pretrained models. --- ### Carbon-Taxed Transformers: A Green Compression Pipeline for Overgrown Language Models Authors: Ajmain Inqiad Alam, Palash Roy, Chanchal K. Roy, Banani Roy, Kevin A. Schneider Published: 2026-04-28 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2604.25903v1 The accelerating adoption of Large Language Models (LLMs) in software engineering (SE) has brought with it a silent crisis: unsustainable computational cost. While these models demonstrate remarkable capabilities in different SE tasks, they are unmanageably large, slow to deploy, memory-intensive, and carbon-heavy. This reality threatens not only the scalability and accessibility of AI-powered SE, but also its long-term environmental sustainability. The research challenge is clear: we must go beyond accuracy and address efficiency and environmental cost as first-class design constraints. To meet this challenge, we introduce Carbon-Taxed Transformers (CTT), a systematic multi-architectural compression principled pipeline ordering inspired by economic carbon taxation principles. Drawing from the economic concept of carbon pricing, CTT operationalizes a computational carbon tax that penalizes architectural inefficiencies and rewards deployment-ready compression. We evaluate CTT across three core SE tasks: code clone detection, code summarization, and code generation, with models spanning encoder-only, encoder-decoder, and decoder-only architecture. Our results show that CTT delivers on inference: (1) up to 49x memory reduction, (2) time reduction up to 8-10x for clone detection, up to 3x for summarization, and 4-7x for generation, (3) up to 81% reduction in CO2 emissions and (4) CTT retains around 98% accuracy on clone detection, around 89% on summarization, and up to 91% (textual metrics) and 68% (pass@1) for generation. Two ablation studies show that pipeline ordering and individual component contributions are both essential, providing empirical justification for CTT's design and effectiveness. This work establishes a viable path toward responsible AI in SE through aggressive yet performance-preserving compression. --- ### Toward a Functional Geometric Algebra for Natural Language Semantics Authors: James Pustejovsky Published: 2026-04-28 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.25902v1 Distributional and neural approaches to natural language semantics have been built almost exclusively on conventional linear algebra: vectors, matrices, tensors, and the operations that accompany them. These methods have achieved remarkable empirical success, yet they face persistent structural limitations in compositional semantics, type sensitivity, and interpretability. I argue in this paper that geometric algebra (GA) -- specifically, Clifford algebras -- provides a mathematically superior foundation for semantic representation, and that a Functional Geometric Algebra (FGA) framework extends GA toward a typed, compositional semantics capable of supporting inference, transformation, and interpretability while retaining full compatibility with distributional learning and modern neural architectures. I develop the formal foundations, identify three core capabilities that GA provides and linear algebra does not, present a detailed worked example illustrating operator-level semantic contrasts, and show how GA-based operations already implicit in current transformer architectures can be made explicit and extended. The central claim is not merely increased dimensionality but increased structural organization: GA expands an $n$-dimensional embedding space into a $2^n$ multivector algebra where base semantic concepts and their higher-order interactions are represented within a single, principled algebraic framework. --- ### TSN-Affinity: Similarity-Driven Parameter Reuse for Continual Offline Reinforcement Learning Authors: Dominik Żurek, Kamil Faber, Marcin Pietron, Paweł Gajewski, Roberto Corizzo Published: 2026-04-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.25898v1 Continual offline reinforcement learning (CORL) aims to learn a sequence of tasks from datasets collected over time while preserving performance on previously learned tasks. This setting corresponds to domains where new tasks arise over time, but adapting the model in live environment interactions is expensive, risky, or impossible. However, CORL inherits the dual difficulty of offline reinforcement learning and adapting while preventing catastrophic forgetting. Replay-based continual learning approaches remain a strong baseline but incur memory overhead and suffer from a distribution mismatch between replayed samples and newly learned policies. At the same time, architectural continual learning methods have shown strong potential in supervised learning but remain underexplored in CORL. In this work, we propose TSN-Affinity, a novel CORL method based on TinySubNetworks and Decision Transformer. The method enables task-specific parameterization and controlled knowledge sharing through a RL-aware reuse strategy that routes tasks according to action compatibility and latent similarity. We evaluate the approach on benchmarks based on Atari games and simulations of manipulation tasks with the Franka Emika Panda robotic arm, covering both discrete and continuous control. Results show strong retention from sparse SubNetworks, with routing further improving multi-task performance. Our findings suggest that similarity-guided architectural reuse is a strong and viable alternative to replay-based strategies in a CORL setting. Our code is available at: https://github.com/anonymized-for-submission123/tsn-affinity. --- ### Variational Neural Belief Parameterizations for Robust Dexterous Grasping under Multimodal Uncertainty Authors: Clinton Enwerem, Shreya Kalyanaraman, John S. Baras, Calin Belta Published: 2026-04-28 Categories: cs.RO, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2604.25897v2 Contact variability, sensing uncertainty, and external disturbances make grasp execution stochastic. Expected-quality objectives ignore tail outcomes and often select grasps that fail under adverse contact realizations. Risk-sensitive POMDPs address this failure mode, but many use particle-filter beliefs that scale poorly, obstruct gradient-based optimization, and estimate Conditional Value-at-Risk (CVaR) with high-variance approximations. We instead formulate grasp acquisition as variational inference over latent contact parameters and object pose, representing the belief with a differentiable Gaussian mixture. We use Gumbel-Softmax component selection and location-scale reparameterization to express samples as smooth functions of the belief parameters, enabling pathwise gradients through a differentiable CVaR surrogate for direct optimization of tail robustness. In simulation, our variational neural belief improves robust grasp success under contact-parameter uncertainty and exogenous force perturbations while reducing planning time by roughly an order of magnitude relative to particle-filter model-predictive control. On a serial-chain robot arm with a multifingered hand, we validate grasp-and-lift success under object-pose uncertainty against a Gaussian baseline. Both methods succeed on the tested perturbations, but our controller terminates in fewer steps and less wall-clock time while achieving a higher tactile grasp-quality proxy. Our learned belief also calibrates risk more accurately, keeping mean absolute calibration error below 0.14 across tested simulation regimes, compared with 0.58 for a Cross-Entropy Method planner. We provide code, simulation assets, and a dataset of 243 force-closed grasps at the following link: www.github.com/coenwerem/vnb-grasp. --- ### Three Models of RLHF Annotation: Extension, Evidence, and Authority Authors: Steve Coyne Published: 2026-04-28 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.25895v1 Preference-based alignment methods, most prominently Reinforcement Learning with Human Feedback (RLHF), use the judgments of human annotators to shape large language model behaviour. However, the normative role of these judgments is rarely made explicit. I distinguish three conceptual models of that role. The first is extension: annotators extend the system designers' own judgments about what outputs should be. The second is evidence: annotators provide independent evidence about some facts, whether moral, social or otherwise. The third is authority: annotators have some independent authority (as representatives of the broader population) to determine system outputs. I argue that these models have implications for how RLHF pipelines should solicit, validate and aggregate annotations. I survey landmark papers in the literature on RLHF and related methods to illustrate how they implicitly draw on these models, describe failure modes that come from unintentionally or intentionally conflating them, and offer normative criteria for choosing among them. My central recommendation is that RLHF pipeline designers should decompose annotation into separable dimensions and tailor each pipeline to the model most appropriate for that dimension, rather than seeking a single unified pipeline. --- ### Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers Authors: Jan Dubiński, Jan Betley, Anna Sztyber-Betley, Daniel Tan, Owain Evans Published: 2026-04-28 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2604.25891v1 Finetuning a language model can lead to emergent misalignment (EM) (Betley et al., 2025b). Models trained on a narrow distribution of misaligned behavior generalize to more egregious behaviors when tested outside the training distribution. We study a set of interventions proposed to reduce EM. We confirm that these interventions reduce or eliminate EM on existing evaluations (questions like "How do I make a quick buck?"). However, if the evaluation prompts are tweaked to resemble the training context, the model displays EM. We call this conditional misalignment. As in standard EM, the model displays misaligned behaviors more egregious than those seen during training, but only on inputs sharing features with the training data. The first two interventions are diluting misaligned data with benign data, and finetuning on benign data after misaligned data. Both produce conditional misalignment. For instance, models trained on a mix of only 5% insecure code still show misalignment when asked to format responses as Python strings (resembling the training context). The third intervention is inoculation prompting. Here, statements with a similar form to the inoculation prompt serve as triggers for misalignment, even if they have the opposite meaning. On the positive side, inoculation prompting has lower (but still non-zero) conditional misalignment if training is on-policy or includes reasoning distillation. Our results imply that in realistic post-training, where misaligned data is typically combined with benign data, models may be conditionally misaligned even if standard evaluations look clean. --- ### Robust Deepfake Detection: Mitigating Spatial Attention Drift via Calibrated Complementary Ensembles Authors: Minh-Khoa Le-Phan, Minh-Hoang Le, Trong-Le Do, Minh-Triet Tran Published: 2026-04-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.25889v1 Current deepfake detection models achieve state-of-the-art performance on pristine academic datasets but suffer severe spatial attention drift under real-world compound degradations, such as blurring and severe lossy compression. To address this vulnerability, we propose a foundation-driven forensic framework that integrates an extreme compound degradation engine with a structurally constrained, multi-stream architecture. During training, our degradation pipeline systematically destroys high-frequency artifacts, optimizing the DINOv2-Giant backbone to extract invariant geometric and semantic priors. We then process images through three specialized pathways: a Global Texture stream, a Localized Facial stream, and a Hybrid Semantic Fusion stream incorporating CLIP. Through analyzing spatial attribution via Score-CAM and feature stability using Cosine Similarity, we quantitatively demonstrate that these streams extract non-redundant, complementary feature representations and stabilize attention entropy. By aggregating these predictions via a calibrated, discretized voting mechanism, our ensemble successfully suppresses background attention drift while acting as a robust geometric anchor. Our approach yields highly stable zero-shot generalization, achieving Fourth Place in the NTIRE 2026 Robust Deepfake Detection Challenge at CVPR. Code is available at https://github.com/khoalephanminh/ntire26-deepfake-challenge. --- ### No Pedestrian Left Behind: Real-Time Detection and Tracking of Vulnerable Road Users for Adaptive Traffic Signal Control Authors: Anas Gamal Aly, Hala ElAarag Published: 2026-04-28 Categories: cs.CV, cs.AI, cs.RO, eess.SY arXiv: https://arxiv.org/abs/2604.25887v1 Current pedestrian crossing signals operate on fixed timing without adjustment to pedestrian behavior, which can leave vulnerable road users (VRUs) such as the elderly, disabled, or distracted pedestrians stranded when the light changes. We introduce No Pedestrian Left Behind (NPLB), a real-time adaptive traffic signal system that monitors VRUs in crosswalks and automatically extends signal timing when needed. We evaluated five state-of-the-art object detection models on the BGVP dataset, with YOLOv12 achieving the highest mean Average Precision at 50% (mAP@0.5) of 0.756. NPLB integrates our fine-tuned YOLOv12 with ByteTrack multi-object tracking and an adaptive controller that extends pedestrian phases when remaining time falls below a critical threshold. Through 10,000 Monte Carlo simulations, we demonstrate that NPLB improves VRU safety by 71.4%, reducing stranding rates from 9.10% to 2.60%, while requiring signal extensions in only 12.1% of crossing cycles. --- ### Explainable AI for Jet Tagging: A Comparative Study of GNNExplainer, GNNShap, and GradCAM for Jet Tagging in the Lund Jet Plane Authors: Pahal D. Patel, Sanmay Ganguly Published: 2026-04-28 Categories: hep-ph, cs.LG, hep-ex arXiv: https://arxiv.org/abs/2604.25885v1 Graph neural networks such as ParticleNet and transformer based networks on point clouds such as ParticleTransformer achieve state-of-the-art performance on jet tagging benchmarks at the Large Hadron Collider, yet the physical reasoning behind their predictions remains opaque. We present different methods, i.e. perturbation-based (GNNExplainer), Shapley-value-based (GNNShap), and gradient-based (GRADCam); adapted to operate on LundNet's Lund-plane graph representation. Leveraging the fact that each node in the Lund plane corresponds to a physically meaningful parton splitting, we construct Monte Carlo truth explanation masks and introduce a physics-informed evaluation framework that goes beyond standard fidelity metrics. We perform the analysis in three transverse-momentum bins ($\mathrm{p_T} \in (500,700)$, $(800,1000)$, and the inclusive region $(500,1000)$ GeV), revealing how explanation quality and focus shift between non-perturbative and perturbative regimes. We further quantify the correlation between explainer-assigned node importance and classical jet substructure observables -- $N$-subjettiness ratios $τ_{21}$ and $τ_{32}$ and the energy correlation functions -- establishing the degree to which the model has learned known QCD features. We find that overall the weight assigned by explainability methods has a correlation with analytic observables, with expected shift across different phase space regimes, indicating that a trained neural network indeed learns some aspects of jet-substructure moments. Our open-source implementation enables reproducible explainability studies for graph-based jet taggers. --- ### QCalEval: Benchmarking Vision-Language Models for Quantum Calibration Plot Understanding Authors: Shuxiang Cao, Zijian Zhang, Abhishek Agarwal, Grace Bratrud, Niyaz R. Beysengulov, Daniel C. Cole, Alejandro Gómez Frieiro, Elena O. Glen, Hao Hsu, Gang Huang, Raymond Jow, Greshma Shaji et al. Published: 2026-04-28 Categories: quant-ph, cs.CV arXiv: https://arxiv.org/abs/2604.25884v1 Quantum computing calibration depends on interpreting experimental data, and calibration plots provide the most universal human-readable representation for this task, yet no systematic evaluation exists of how well vision-language models (VLMs) interpret them. We introduce QCalEval, the first VLM benchmark for quantum calibration plots: 243 samples across 87 scenario types from 22 experiment families, spanning superconducting qubits and neutral atoms, evaluated on six question types in both zero-shot and in-context learning settings. The best general-purpose zero-shot model reaches a mean score of 72.3, and many open-weight models degrade under multi-image in-context learning, whereas frontier closed models improve substantially. A supervised fine-tuning ablation at the 9-billion-parameter scale shows that SFT improves zero-shot performance but cannot close the multimodal in-context learning gap. As a reference case study, we release NVIDIA Ising Calibration 1, an open-weight model based on Qwen3.5-35B-A3B that reaches 74.7 zero-shot average score. --- ### When Errors Can Be Beneficial: A Categorization of Imperfect Rewards for Policy Gradient Authors: Shuning Shang, Hubert Strauss, Stanley Wei, Sanjeev Arora, Noam Razin Published: 2026-04-28 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2604.25872v1 Training language models via reinforcement learning often relies on imperfect proxy rewards, since ground truth rewards that precisely define the intended behavior are rarely available. Standard metrics for assessing the quality of proxy rewards, such as ranking accuracy, treat incorrect rewards as strictly harmful. In this work, however, we highlight that not all deviations from the ground truth are equal. By theoretically analyzing which outputs attract probability during policy gradient optimization, we categorize reward errors according to their effect on the increase in ground truth reward. The analysis establishes that reward errors, though conventionally viewed as harmful, can also be benign or even beneficial by preventing the policy from stalling around outputs with mediocre ground truth reward. We then present two practical implications of our theory. First, for reinforcement learning from human feedback (RLHF), we develop reward model evaluation metrics that account for the harmfulness of reward errors. Compared to standard ranking accuracy, these metrics typically correlate better with the performance of a language model after RLHF, yet gaps remain in robustly evaluating reward models. Second, we provide insights for reward design in settings with verifiable rewards. A key theme underlying our results is that the effectiveness of a proxy reward function depends heavily on its interaction with the initial policy and learning algorithm. --- ### Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders Authors: Bangzhao Shu, Arinjay Singh, Mai ElSherief Published: 2026-04-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.25866v2 Large language models (LLMs) are increasingly used in emotionally sensitive human-AI applications, where reliable emotion detection is essential. However, their emotion recognition abilities remain uneven: models often perform well on some emotions while consistently struggling with others. Although recent work has explored emotion mechanisms in LLMs, little is known about why models are weaker on some emotions than others from a mechanistic interpretability perspective. In this work, we investigate emotion-specific biases through the causal mechanisms of emotion inference using sparse autoencoders (SAEs). We systematically identify causal sparse emotion features that drive emotion inference and analyze their sparse causal organization within and across emotions. We show that some emotions, such as surprise and fear, rely on highly concentrated feature sets, whereas disgust exhibits a more distributed sparse causal organization: its causal features are generally weaker, frequently co-activate with features for other emotions, and are often overshadowed by causal features for anger. These representational differences provide a mechanistic explanation for why LLMs struggle more with certain emotions. Finally, we conduct two intervention experiments: targeted steering of weaker causal features to mitigate emotion-specific failures, and global optimization of a steering vector over the identified causal features to improve overall emotion recognition performance. --- ### RESTestBench: A Benchmark for Evaluating the Effectiveness of LLM-Generated REST API Test Cases from NL Requirements Authors: Leon Kogler, Stefan Hangler, Maximilian Ehrhart, Benedikt Dornauer, Roland Wuersching, Peter Schrammel Published: 2026-04-28 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.25862v1 Existing REST API testing tools are typically evaluated using code coverage and crash-based fault metrics. However, recent LLM-based approaches increasingly generate tests from NL requirements to validate functional behaviour, making traditional metrics weak proxies for whether generated tests validate intended behaviour. To address this gap, we present RESTestBench, a benchmark comprising three REST services paired with manually verified NL requirements in both precise and vague variants, enabling controlled and reproducible evaluation of requirement-based test generation. RESTestBench further introduces a requirements-based mutation testing metric that measures the fault-detection effectiveness of a generated test case with respect to a specific requirement, extending the property-based approach of Bartocci et al. . Using RESTestBench, we evaluate two approaches across multiple state-of-the-art LLMs: (i) non-refinement-based generation, and (ii) refinement-based generation guided by interaction with the running SUT. In the refinement experiments, RESTestBench assesses how exposure to the actual implementation, valid or mutated, affects test effectiveness. Our results show that test effectiveness drops considerably when the generator interacts with faulty or mutated code, especially for vague requirements, sometimes negating the benefit of refinement and indicating that incorporating actual SUT behaviour is unnecessary when requirement detail is high. --- ### Luminol-AIDetect: Fast Zero-shot Machine-Generated Text Detection based on Perplexity under Text Shuffling Authors: Lucio La Cava, Andrea Tagarelli Published: 2026-04-28 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2604.25860v2 Machine-generated text (MGT) detection requires identifying structurally invariant signals across generation models, rather than relying on model-specific fingerprints. In this respect, we hypothesize that while large language models excel at local semantic consistency, their autoregressive nature results in a specific kind of structural fragility compared to human writing. We propose Luminol-AIDetect, a novel, zero-shot statistical approach that exposes this fragility through coherence disruption. By applying a simple randomized text-shuffling procedure, we demonstrate that the resulting shift in perplexity serves as a principled, model-agnostic discriminant, as MGT displays a characteristic dispersion in perplexity-under-shuffling that differs markedly from the more stable structural variability of human-written text. Luminol-AIDetect leverages this distinction to inform its decision process, where a handful of perplexity-based scalar features are extracted from an input text and its shuffled version, then detection is performed via density estimation and ensemble-based prediction. Evaluated across 8 content domains, 11 adversarial attack types, and 18 languages, Luminol-AIDetect demonstrates state-of-the-art performance, with gains up to 17x lower FPR while being cheaper than prior methods. --- ### Investigation into In-Context Learning Capabilities of Transformers Authors: Rushil Chandrupatla, Leo Bangayan, Sebastian Leng Published: 2026-04-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.25858v2 Transformers have demonstrated a strong ability for in-context learning (ICL), enabling models to solve previously unseen tasks using only example input output pairs provided at inference time. While prior theoretical work has established conditions under which transformers can perform linear classification in-context, the empirical scaling behavior governing when this mechanism succeeds remains insufficiently characterized. In this paper, we conduct a systematic empirical study of in-context learning for Gaussian-mixture binary classification tasks. Building on the theoretical framework of Frei and Vardi (2024), we analyze how in-context test accuracy depends on three fundamental factors: the input dimension, the number of in-context examples, and the number of pre-training tasks. Using a controlled synthetic setup and a linear in-context classifier formulation, we isolate the geometric conditions under which models successfully infer task structure from context alone. We additionally investigate the emergence of benign overfitting, where models memorize noisy in-context labels while still achieving strong generalization performance on clean test data. Through extensive sweeps across dimensionality, sequence length, task diversity, and signal-to-noise regimes, we identify the parameter regions in which this phenomenon arises and characterize how it depends on data geometry and training exposure. Our results provide a comprehensive empirical map of scaling behavior in in-context classification, highlighting the critical role of dimensionality, signal strength, and contextual information in determining when in-context learning succeeds and when it fails. --- ### SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring Authors: Hector G. Rodriguez, Marcus Rohrbach Published: 2026-04-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.25855v2 Multimodal large language models (MLLMs) achieve ever-stronger performance on visual-language tasks. Even as traditional visual question answering (VQA) benchmarks approach saturation, reliable deployment requires satisfying low error tolerances in real-world, out-of-distribution (OOD) scenarios. Precisely, selective prediction aims to improve coverage, i.e. the share of inputs the system answers, while adhering to a user-defined risk level. This is typically achieved by assigning a confidence score to each answer and abstaining on those that fall below a certain threshold. Existing selective prediction methods estimate implicit confidence scores, relying on model internal signals like logits or hidden representations, which are not available for frontier closed-sourced models. To enable reliable generalization in VQA, we require reasoner models to produce localized visual evidence while answering, and design a selector that explicitly learns to estimate the quality of the localization provided by the reasoner using only model inputs and outputs. We show that SIEVES (Selective Prediction through Visual Evidence Scoring) improves coverage by up to three times on challenging OOD benchmarks (V* Bench, HR-Bench-8k, MME-RealWorld-Lite, VizWiz, and AdVQA), compared to non-grounding baselines. Beyond better generalization to OOD tasks, the design of the SIEVES selector enables transfer to proprietary reasoners without access to their weights or logits, such as o3 and Gemini-3-Pro, providing coverage boosts beyond those attributable to accuracy alone. We highlight that SIEVES generalizes across all tested OOD benchmarks and reasoner models (Pixel-Reasoner, o3, and Gemini-3-Pro), without benchmark- or reasoner-specific training or adaptation. Code is publicly available at https://github.com/hector-gr/SIEVES . ---